Add submodule dependency filesHEADmaster

Change-Id: Iaf8d18082d3991dec7c0ebbea540f092188eb4ec

1 files changed, 4047 insertions, 0 deletions

diff --git a/capstone/suite/synctools/tablegen/include/llvm/IR/IntrinsicsNVVM.td b/capstone/suite/synctools/tablegen/include/llvm/IR/IntrinsicsNVVM.td
new file mode 100644
index 000000000..7f694f689
--- /dev/null
+++ b/capstone/suite/synctools/tablegen/include/llvm/IR/IntrinsicsNVVM.td
@@ -0,0 +1,4047 @@
+//===- IntrinsicsNVVM.td - Defines NVVM intrinsics ---------*- tablegen -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines all of the NVVM-specific intrinsics for use with NVPTX.
+//
+//===----------------------------------------------------------------------===//
+
+// The following intrinsics were once defined here, but are now auto-upgraded
+// to target-generic LLVM intrinsics.
+//
+//   * llvm.nvvm.brev32  --> llvm.bitreverse.i32
+//   * llvm.nvvm.brev64  --> llvm.bitreverse.i64
+//   * llvm.nvvm.clz.i   --> llvm.ctlz.i32
+//   * llvm.nvvm.clz.ll  --> trunc i64 llvm.ctlz.i64(x) to i32
+//   * llvm.nvvm.popc.i  --> llvm.ctpop.i32
+//   * llvm.nvvm.popc.ll --> trunc i64 llvm.ctpop.i64 to i32
+//   * llvm.nvvm.abs.i   --> select(x >= -x, x, -x)
+//   * llvm.nvvm.abs.ll  --> ibid.
+//   * llvm.nvvm.max.i   --> select(x sge y, x, y)
+//   * llvm.nvvm.max.ll  --> ibid.
+//   * llvm.nvvm.max.ui  --> select(x uge y, x, y)
+//   * llvm.nvvm.max.ull --> ibid.
+//   * llvm.nvvm.max.i   --> select(x sle y, x, y)
+//   * llvm.nvvm.max.ll  --> ibid.
+//   * llvm.nvvm.max.ui  --> select(x ule y, x, y)
+//   * llvm.nvvm.max.ull --> ibid.
+//   * llvm.nvvm.h2f     --> llvm.convert.to.fp16.f32
+
+def llvm_anyi64ptr_ty     : LLVMAnyPointerType<llvm_i64_ty>;     // (space)i64*
+
+//
+// MISC
+//
+
+let TargetPrefix = "nvvm" in {
+  def int_nvvm_prmt : GCCBuiltin<"__nvvm_prmt">,
+      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+        [IntrNoMem, Commutative]>;
+
+//
+// Min Max
+//
+
+  def int_nvvm_fmin_f : GCCBuiltin<"__nvvm_fmin_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_fmin_ftz_f : GCCBuiltin<"__nvvm_fmin_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+
+  def int_nvvm_fmax_f : GCCBuiltin<"__nvvm_fmax_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty]
+        , [IntrNoMem, Commutative]>;
+  def int_nvvm_fmax_ftz_f : GCCBuiltin<"__nvvm_fmax_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+
+  def int_nvvm_fmin_d : GCCBuiltin<"__nvvm_fmin_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_fmax_d : GCCBuiltin<"__nvvm_fmax_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+
+//
+// Multiplication
+//
+
+  def int_nvvm_mulhi_i : GCCBuiltin<"__nvvm_mulhi_i">,
+      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_mulhi_ui : GCCBuiltin<"__nvvm_mulhi_ui">,
+      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty],
+        [IntrNoMem, Commutative]>;
+
+  def int_nvvm_mulhi_ll : GCCBuiltin<"__nvvm_mulhi_ll">,
+      Intrinsic<[llvm_i64_ty], [llvm_i64_ty, llvm_i64_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_mulhi_ull : GCCBuiltin<"__nvvm_mulhi_ull">,
+      Intrinsic<[llvm_i64_ty], [llvm_i64_ty, llvm_i64_ty],
+        [IntrNoMem, Commutative]>;
+
+  def int_nvvm_mul_rn_ftz_f : GCCBuiltin<"__nvvm_mul_rn_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_mul_rn_f : GCCBuiltin<"__nvvm_mul_rn_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_mul_rz_ftz_f : GCCBuiltin<"__nvvm_mul_rz_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_mul_rz_f : GCCBuiltin<"__nvvm_mul_rz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_mul_rm_ftz_f : GCCBuiltin<"__nvvm_mul_rm_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_mul_rm_f : GCCBuiltin<"__nvvm_mul_rm_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_mul_rp_ftz_f : GCCBuiltin<"__nvvm_mul_rp_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_mul_rp_f : GCCBuiltin<"__nvvm_mul_rp_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+
+  def int_nvvm_mul_rn_d : GCCBuiltin<"__nvvm_mul_rn_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_mul_rz_d : GCCBuiltin<"__nvvm_mul_rz_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_mul_rm_d : GCCBuiltin<"__nvvm_mul_rm_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_mul_rp_d : GCCBuiltin<"__nvvm_mul_rp_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+
+  def int_nvvm_mul24_i : GCCBuiltin<"__nvvm_mul24_i">,
+      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_mul24_ui : GCCBuiltin<"__nvvm_mul24_ui">,
+      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty],
+        [IntrNoMem, Commutative]>;
+
+//
+// Div
+//
+
+  def int_nvvm_div_approx_ftz_f : GCCBuiltin<"__nvvm_div_approx_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_div_approx_f : GCCBuiltin<"__nvvm_div_approx_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+
+  def int_nvvm_div_rn_ftz_f : GCCBuiltin<"__nvvm_div_rn_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_div_rn_f : GCCBuiltin<"__nvvm_div_rn_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+
+  def int_nvvm_div_rz_ftz_f : GCCBuiltin<"__nvvm_div_rz_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_div_rz_f : GCCBuiltin<"__nvvm_div_rz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+
+  def int_nvvm_div_rm_ftz_f : GCCBuiltin<"__nvvm_div_rm_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_div_rm_f : GCCBuiltin<"__nvvm_div_rm_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+
+  def int_nvvm_div_rp_ftz_f : GCCBuiltin<"__nvvm_div_rp_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_div_rp_f : GCCBuiltin<"__nvvm_div_rp_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+
+  def int_nvvm_div_rn_d : GCCBuiltin<"__nvvm_div_rn_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_div_rz_d : GCCBuiltin<"__nvvm_div_rz_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_div_rm_d : GCCBuiltin<"__nvvm_div_rm_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_div_rp_d : GCCBuiltin<"__nvvm_div_rp_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+
+//
+// Sad
+//
+
+  def int_nvvm_sad_i : GCCBuiltin<"__nvvm_sad_i">,
+      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_sad_ui : GCCBuiltin<"__nvvm_sad_ui">,
+      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+        [IntrNoMem, Commutative]>;
+
+//
+// Floor  Ceil
+//
+
+  def int_nvvm_floor_ftz_f : GCCBuiltin<"__nvvm_floor_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_floor_f : GCCBuiltin<"__nvvm_floor_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_floor_d : GCCBuiltin<"__nvvm_floor_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+
+  def int_nvvm_ceil_ftz_f : GCCBuiltin<"__nvvm_ceil_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_ceil_f : GCCBuiltin<"__nvvm_ceil_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_ceil_d : GCCBuiltin<"__nvvm_ceil_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+
+//
+// Abs
+//
+
+  def int_nvvm_fabs_ftz_f : GCCBuiltin<"__nvvm_fabs_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_fabs_f : GCCBuiltin<"__nvvm_fabs_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_fabs_d : GCCBuiltin<"__nvvm_fabs_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+
+//
+// Round
+//
+
+  def int_nvvm_round_ftz_f : GCCBuiltin<"__nvvm_round_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_round_f : GCCBuiltin<"__nvvm_round_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+
+  def int_nvvm_round_d : GCCBuiltin<"__nvvm_round_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+
+//
+// Trunc
+//
+
+  def int_nvvm_trunc_ftz_f : GCCBuiltin<"__nvvm_trunc_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_trunc_f : GCCBuiltin<"__nvvm_trunc_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+
+  def int_nvvm_trunc_d : GCCBuiltin<"__nvvm_trunc_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+
+//
+// Saturate
+//
+
+  def int_nvvm_saturate_ftz_f : GCCBuiltin<"__nvvm_saturate_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_saturate_f : GCCBuiltin<"__nvvm_saturate_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+
+  def int_nvvm_saturate_d : GCCBuiltin<"__nvvm_saturate_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+
+//
+// Exp2  Log2
+//
+
+  def int_nvvm_ex2_approx_ftz_f : GCCBuiltin<"__nvvm_ex2_approx_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_ex2_approx_f : GCCBuiltin<"__nvvm_ex2_approx_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_ex2_approx_d : GCCBuiltin<"__nvvm_ex2_approx_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+
+  def int_nvvm_lg2_approx_ftz_f : GCCBuiltin<"__nvvm_lg2_approx_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_lg2_approx_f : GCCBuiltin<"__nvvm_lg2_approx_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_lg2_approx_d : GCCBuiltin<"__nvvm_lg2_approx_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+
+//
+// Sin  Cos
+//
+
+  def int_nvvm_sin_approx_ftz_f : GCCBuiltin<"__nvvm_sin_approx_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_sin_approx_f : GCCBuiltin<"__nvvm_sin_approx_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+
+  def int_nvvm_cos_approx_ftz_f : GCCBuiltin<"__nvvm_cos_approx_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_cos_approx_f : GCCBuiltin<"__nvvm_cos_approx_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+
+//
+// Fma
+//
+
+  def int_nvvm_fma_rn_ftz_f : GCCBuiltin<"__nvvm_fma_rn_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_fma_rn_f : GCCBuiltin<"__nvvm_fma_rn_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_fma_rz_ftz_f : GCCBuiltin<"__nvvm_fma_rz_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_fma_rz_f : GCCBuiltin<"__nvvm_fma_rz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_fma_rm_ftz_f : GCCBuiltin<"__nvvm_fma_rm_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_fma_rm_f : GCCBuiltin<"__nvvm_fma_rm_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_fma_rp_ftz_f : GCCBuiltin<"__nvvm_fma_rp_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_fma_rp_f : GCCBuiltin<"__nvvm_fma_rp_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+
+  def int_nvvm_fma_rn_d : GCCBuiltin<"__nvvm_fma_rn_d">,
+      Intrinsic<[llvm_double_ty],
+        [llvm_double_ty, llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_fma_rz_d : GCCBuiltin<"__nvvm_fma_rz_d">,
+      Intrinsic<[llvm_double_ty],
+        [llvm_double_ty, llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_fma_rm_d : GCCBuiltin<"__nvvm_fma_rm_d">,
+      Intrinsic<[llvm_double_ty],
+        [llvm_double_ty, llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_fma_rp_d : GCCBuiltin<"__nvvm_fma_rp_d">,
+      Intrinsic<[llvm_double_ty],
+        [llvm_double_ty, llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+
+//
+// Rcp
+//
+
+  def int_nvvm_rcp_rn_ftz_f : GCCBuiltin<"__nvvm_rcp_rn_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_rcp_rn_f : GCCBuiltin<"__nvvm_rcp_rn_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_rcp_rz_ftz_f : GCCBuiltin<"__nvvm_rcp_rz_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_rcp_rz_f : GCCBuiltin<"__nvvm_rcp_rz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_rcp_rm_ftz_f : GCCBuiltin<"__nvvm_rcp_rm_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_rcp_rm_f : GCCBuiltin<"__nvvm_rcp_rm_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_rcp_rp_ftz_f : GCCBuiltin<"__nvvm_rcp_rp_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_rcp_rp_f : GCCBuiltin<"__nvvm_rcp_rp_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+
+  def int_nvvm_rcp_rn_d : GCCBuiltin<"__nvvm_rcp_rn_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_rcp_rz_d : GCCBuiltin<"__nvvm_rcp_rz_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_rcp_rm_d : GCCBuiltin<"__nvvm_rcp_rm_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_rcp_rp_d : GCCBuiltin<"__nvvm_rcp_rp_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+
+  def int_nvvm_rcp_approx_ftz_d : GCCBuiltin<"__nvvm_rcp_approx_ftz_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+
+//
+// Sqrt
+//
+
+  def int_nvvm_sqrt_f : GCCBuiltin<"__nvvm_sqrt_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_sqrt_rn_ftz_f : GCCBuiltin<"__nvvm_sqrt_rn_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_sqrt_rn_f : GCCBuiltin<"__nvvm_sqrt_rn_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_sqrt_rz_ftz_f : GCCBuiltin<"__nvvm_sqrt_rz_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_sqrt_rz_f : GCCBuiltin<"__nvvm_sqrt_rz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_sqrt_rm_ftz_f : GCCBuiltin<"__nvvm_sqrt_rm_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_sqrt_rm_f : GCCBuiltin<"__nvvm_sqrt_rm_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_sqrt_rp_ftz_f : GCCBuiltin<"__nvvm_sqrt_rp_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_sqrt_rp_f : GCCBuiltin<"__nvvm_sqrt_rp_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_sqrt_approx_ftz_f : GCCBuiltin<"__nvvm_sqrt_approx_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_sqrt_approx_f : GCCBuiltin<"__nvvm_sqrt_approx_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+
+  def int_nvvm_sqrt_rn_d : GCCBuiltin<"__nvvm_sqrt_rn_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_sqrt_rz_d : GCCBuiltin<"__nvvm_sqrt_rz_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_sqrt_rm_d : GCCBuiltin<"__nvvm_sqrt_rm_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_sqrt_rp_d : GCCBuiltin<"__nvvm_sqrt_rp_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+
+//
+// Rsqrt
+//
+
+  def int_nvvm_rsqrt_approx_ftz_f : GCCBuiltin<"__nvvm_rsqrt_approx_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_rsqrt_approx_f : GCCBuiltin<"__nvvm_rsqrt_approx_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_rsqrt_approx_d : GCCBuiltin<"__nvvm_rsqrt_approx_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+
+//
+// Add
+//
+
+  def int_nvvm_add_rn_ftz_f : GCCBuiltin<"__nvvm_add_rn_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_add_rn_f : GCCBuiltin<"__nvvm_add_rn_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_add_rz_ftz_f : GCCBuiltin<"__nvvm_add_rz_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_add_rz_f : GCCBuiltin<"__nvvm_add_rz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_add_rm_ftz_f : GCCBuiltin<"__nvvm_add_rm_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_add_rm_f : GCCBuiltin<"__nvvm_add_rm_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_add_rp_ftz_f : GCCBuiltin<"__nvvm_add_rp_ftz_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_add_rp_f : GCCBuiltin<"__nvvm_add_rp_f">,
+      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
+        [IntrNoMem, Commutative]>;
+
+  def int_nvvm_add_rn_d : GCCBuiltin<"__nvvm_add_rn_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_add_rz_d : GCCBuiltin<"__nvvm_add_rz_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_add_rm_d : GCCBuiltin<"__nvvm_add_rm_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+  def int_nvvm_add_rp_d : GCCBuiltin<"__nvvm_add_rp_d">,
+      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
+        [IntrNoMem, Commutative]>;
+
+//
+// Convert
+//
+
+  def int_nvvm_d2f_rn_ftz : GCCBuiltin<"__nvvm_d2f_rn_ftz">,
+      Intrinsic<[llvm_float_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2f_rn : GCCBuiltin<"__nvvm_d2f_rn">,
+      Intrinsic<[llvm_float_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2f_rz_ftz : GCCBuiltin<"__nvvm_d2f_rz_ftz">,
+      Intrinsic<[llvm_float_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2f_rz : GCCBuiltin<"__nvvm_d2f_rz">,
+      Intrinsic<[llvm_float_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2f_rm_ftz : GCCBuiltin<"__nvvm_d2f_rm_ftz">,
+      Intrinsic<[llvm_float_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2f_rm : GCCBuiltin<"__nvvm_d2f_rm">,
+      Intrinsic<[llvm_float_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2f_rp_ftz : GCCBuiltin<"__nvvm_d2f_rp_ftz">,
+      Intrinsic<[llvm_float_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2f_rp : GCCBuiltin<"__nvvm_d2f_rp">,
+      Intrinsic<[llvm_float_ty], [llvm_double_ty], [IntrNoMem]>;
+
+  def int_nvvm_d2i_rn : GCCBuiltin<"__nvvm_d2i_rn">,
+      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2i_rz : GCCBuiltin<"__nvvm_d2i_rz">,
+      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2i_rm : GCCBuiltin<"__nvvm_d2i_rm">,
+      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2i_rp : GCCBuiltin<"__nvvm_d2i_rp">,
+      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
+
+  def int_nvvm_d2ui_rn : GCCBuiltin<"__nvvm_d2ui_rn">,
+      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2ui_rz : GCCBuiltin<"__nvvm_d2ui_rz">,
+      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2ui_rm : GCCBuiltin<"__nvvm_d2ui_rm">,
+      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2ui_rp : GCCBuiltin<"__nvvm_d2ui_rp">,
+      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
+
+  def int_nvvm_i2d_rn : GCCBuiltin<"__nvvm_i2d_rn">,
+      Intrinsic<[llvm_double_ty], [llvm_i32_ty], [IntrNoMem]>;
+  def int_nvvm_i2d_rz : GCCBuiltin<"__nvvm_i2d_rz">,
+      Intrinsic<[llvm_double_ty], [llvm_i32_ty], [IntrNoMem]>;
+  def int_nvvm_i2d_rm : GCCBuiltin<"__nvvm_i2d_rm">,
+      Intrinsic<[llvm_double_ty], [llvm_i32_ty], [IntrNoMem]>;
+  def int_nvvm_i2d_rp : GCCBuiltin<"__nvvm_i2d_rp">,
+      Intrinsic<[llvm_double_ty], [llvm_i32_ty], [IntrNoMem]>;
+
+  def int_nvvm_ui2d_rn : GCCBuiltin<"__nvvm_ui2d_rn">,
+      Intrinsic<[llvm_double_ty], [llvm_i32_ty], [IntrNoMem]>;
+  def int_nvvm_ui2d_rz : GCCBuiltin<"__nvvm_ui2d_rz">,
+      Intrinsic<[llvm_double_ty], [llvm_i32_ty], [IntrNoMem]>;
+  def int_nvvm_ui2d_rm : GCCBuiltin<"__nvvm_ui2d_rm">,
+      Intrinsic<[llvm_double_ty], [llvm_i32_ty], [IntrNoMem]>;
+  def int_nvvm_ui2d_rp : GCCBuiltin<"__nvvm_ui2d_rp">,
+      Intrinsic<[llvm_double_ty], [llvm_i32_ty], [IntrNoMem]>;
+
+  def int_nvvm_f2i_rn_ftz : GCCBuiltin<"__nvvm_f2i_rn_ftz">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2i_rn : GCCBuiltin<"__nvvm_f2i_rn">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2i_rz_ftz : GCCBuiltin<"__nvvm_f2i_rz_ftz">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2i_rz : GCCBuiltin<"__nvvm_f2i_rz">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2i_rm_ftz : GCCBuiltin<"__nvvm_f2i_rm_ftz">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2i_rm : GCCBuiltin<"__nvvm_f2i_rm">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2i_rp_ftz : GCCBuiltin<"__nvvm_f2i_rp_ftz">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2i_rp : GCCBuiltin<"__nvvm_f2i_rp">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+
+  def int_nvvm_f2ui_rn_ftz : GCCBuiltin<"__nvvm_f2ui_rn_ftz">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ui_rn : GCCBuiltin<"__nvvm_f2ui_rn">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ui_rz_ftz : GCCBuiltin<"__nvvm_f2ui_rz_ftz">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ui_rz : GCCBuiltin<"__nvvm_f2ui_rz">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ui_rm_ftz : GCCBuiltin<"__nvvm_f2ui_rm_ftz">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ui_rm : GCCBuiltin<"__nvvm_f2ui_rm">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ui_rp_ftz : GCCBuiltin<"__nvvm_f2ui_rp_ftz">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ui_rp : GCCBuiltin<"__nvvm_f2ui_rp">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+
+  def int_nvvm_i2f_rn : GCCBuiltin<"__nvvm_i2f_rn">,
+      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
+  def int_nvvm_i2f_rz : GCCBuiltin<"__nvvm_i2f_rz">,
+      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
+  def int_nvvm_i2f_rm : GCCBuiltin<"__nvvm_i2f_rm">,
+      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
+  def int_nvvm_i2f_rp : GCCBuiltin<"__nvvm_i2f_rp">,
+      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
+
+  def int_nvvm_ui2f_rn : GCCBuiltin<"__nvvm_ui2f_rn">,
+      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
+  def int_nvvm_ui2f_rz : GCCBuiltin<"__nvvm_ui2f_rz">,
+      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
+  def int_nvvm_ui2f_rm : GCCBuiltin<"__nvvm_ui2f_rm">,
+      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
+  def int_nvvm_ui2f_rp : GCCBuiltin<"__nvvm_ui2f_rp">,
+      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
+
+  def int_nvvm_lohi_i2d : GCCBuiltin<"__nvvm_lohi_i2d">,
+      Intrinsic<[llvm_double_ty], [llvm_i32_ty, llvm_i32_ty],
+        [IntrNoMem, Commutative]>;
+
+  def int_nvvm_d2i_lo : GCCBuiltin<"__nvvm_d2i_lo">,
+      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2i_hi : GCCBuiltin<"__nvvm_d2i_hi">,
+      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
+
+  def int_nvvm_f2ll_rn_ftz : GCCBuiltin<"__nvvm_f2ll_rn_ftz">,
+      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ll_rn : GCCBuiltin<"__nvvm_f2ll_rn">,
+      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ll_rz_ftz : GCCBuiltin<"__nvvm_f2ll_rz_ftz">,
+      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ll_rz : GCCBuiltin<"__nvvm_f2ll_rz">,
+      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ll_rm_ftz : GCCBuiltin<"__nvvm_f2ll_rm_ftz">,
+      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ll_rm : GCCBuiltin<"__nvvm_f2ll_rm">,
+      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ll_rp_ftz : GCCBuiltin<"__nvvm_f2ll_rp_ftz">,
+      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ll_rp : GCCBuiltin<"__nvvm_f2ll_rp">,
+      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
+
+  def int_nvvm_f2ull_rn_ftz : GCCBuiltin<"__nvvm_f2ull_rn_ftz">,
+      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ull_rn : GCCBuiltin<"__nvvm_f2ull_rn">,
+      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ull_rz_ftz : GCCBuiltin<"__nvvm_f2ull_rz_ftz">,
+      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ull_rz : GCCBuiltin<"__nvvm_f2ull_rz">,
+      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ull_rm_ftz : GCCBuiltin<"__nvvm_f2ull_rm_ftz">,
+      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ull_rm : GCCBuiltin<"__nvvm_f2ull_rm">,
+      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ull_rp_ftz : GCCBuiltin<"__nvvm_f2ull_rp_ftz">,
+      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2ull_rp : GCCBuiltin<"__nvvm_f2ull_rp">,
+      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
+
+  def int_nvvm_d2ll_rn : GCCBuiltin<"__nvvm_d2ll_rn">,
+      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2ll_rz : GCCBuiltin<"__nvvm_d2ll_rz">,
+      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2ll_rm : GCCBuiltin<"__nvvm_d2ll_rm">,
+      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2ll_rp : GCCBuiltin<"__nvvm_d2ll_rp">,
+      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
+
+  def int_nvvm_d2ull_rn : GCCBuiltin<"__nvvm_d2ull_rn">,
+      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2ull_rz : GCCBuiltin<"__nvvm_d2ull_rz">,
+      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2ull_rm : GCCBuiltin<"__nvvm_d2ull_rm">,
+      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_d2ull_rp : GCCBuiltin<"__nvvm_d2ull_rp">,
+      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
+
+  def int_nvvm_ll2f_rn : GCCBuiltin<"__nvvm_ll2f_rn">,
+      Intrinsic<[llvm_float_ty], [llvm_i64_ty], [IntrNoMem]>;
+  def int_nvvm_ll2f_rz : GCCBuiltin<"__nvvm_ll2f_rz">,
+      Intrinsic<[llvm_float_ty], [llvm_i64_ty], [IntrNoMem]>;
+  def int_nvvm_ll2f_rm : GCCBuiltin<"__nvvm_ll2f_rm">,
+      Intrinsic<[llvm_float_ty], [llvm_i64_ty], [IntrNoMem]>;
+  def int_nvvm_ll2f_rp : GCCBuiltin<"__nvvm_ll2f_rp">,
+      Intrinsic<[llvm_float_ty], [llvm_i64_ty], [IntrNoMem]>;
+  def int_nvvm_ull2f_rn : GCCBuiltin<"__nvvm_ull2f_rn">,
+      Intrinsic<[llvm_float_ty], [llvm_i64_ty], [IntrNoMem]>;
+  def int_nvvm_ull2f_rz : GCCBuiltin<"__nvvm_ull2f_rz">,
+      Intrinsic<[llvm_float_ty], [llvm_i64_ty], [IntrNoMem]>;
+  def int_nvvm_ull2f_rm : GCCBuiltin<"__nvvm_ull2f_rm">,
+      Intrinsic<[llvm_float_ty], [llvm_i64_ty], [IntrNoMem]>;
+  def int_nvvm_ull2f_rp : GCCBuiltin<"__nvvm_ull2f_rp">,
+      Intrinsic<[llvm_float_ty], [llvm_i64_ty], [IntrNoMem]>;
+
+  def int_nvvm_ll2d_rn : GCCBuiltin<"__nvvm_ll2d_rn">,
+      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
+  def int_nvvm_ll2d_rz : GCCBuiltin<"__nvvm_ll2d_rz">,
+      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
+  def int_nvvm_ll2d_rm : GCCBuiltin<"__nvvm_ll2d_rm">,
+      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
+  def int_nvvm_ll2d_rp : GCCBuiltin<"__nvvm_ll2d_rp">,
+      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
+  def int_nvvm_ull2d_rn : GCCBuiltin<"__nvvm_ull2d_rn">,
+      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
+  def int_nvvm_ull2d_rz : GCCBuiltin<"__nvvm_ull2d_rz">,
+      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
+  def int_nvvm_ull2d_rm : GCCBuiltin<"__nvvm_ull2d_rm">,
+      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
+  def int_nvvm_ull2d_rp : GCCBuiltin<"__nvvm_ull2d_rp">,
+      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
+
+  def int_nvvm_f2h_rn_ftz : GCCBuiltin<"__nvvm_f2h_rn_ftz">,
+      Intrinsic<[llvm_i16_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_f2h_rn : GCCBuiltin<"__nvvm_f2h_rn">,
+      Intrinsic<[llvm_i16_ty], [llvm_float_ty], [IntrNoMem]>;
+
+//
+// Bitcast
+//
+
+  def int_nvvm_bitcast_f2i : GCCBuiltin<"__nvvm_bitcast_f2i">,
+      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
+  def int_nvvm_bitcast_i2f : GCCBuiltin<"__nvvm_bitcast_i2f">,
+      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
+
+  def int_nvvm_bitcast_ll2d : GCCBuiltin<"__nvvm_bitcast_ll2d">,
+      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
+  def int_nvvm_bitcast_d2ll : GCCBuiltin<"__nvvm_bitcast_d2ll">,
+      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
+
+// FNS
+
+  def int_nvvm_fns : GCCBuiltin<"__nvvm_fns">,
+      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+                [IntrNoMem]>;
+
+// Atomics not available as llvm intrinsics.
+  def int_nvvm_atomic_load_add_f32 : Intrinsic<[llvm_float_ty],
+          [LLVMAnyPointerType<llvm_float_ty>, llvm_float_ty],
+                                      [IntrArgMemOnly, NoCapture<0>]>;
+  // Atomic add of f64 requires sm_60.
+  def int_nvvm_atomic_load_add_f64 : Intrinsic<[llvm_double_ty],
+          [LLVMAnyPointerType<llvm_double_ty>, llvm_double_ty],
+                                      [IntrArgMemOnly, NoCapture<0>]>;
+
+  def int_nvvm_atomic_load_inc_32 : Intrinsic<[llvm_i32_ty],
+          [LLVMAnyPointerType<llvm_i32_ty>, llvm_i32_ty],
+                                      [IntrArgMemOnly, NoCapture<0>]>;
+  def int_nvvm_atomic_load_dec_32 : Intrinsic<[llvm_i32_ty],
+          [LLVMAnyPointerType<llvm_i32_ty>, llvm_i32_ty],
+                                      [IntrArgMemOnly, NoCapture<0>]>;
+
+  class SCOPED_ATOMIC2_impl<LLVMType elty>
+        : Intrinsic<[elty],
+          [LLVMAnyPointerType<LLVMMatchType<0>>, LLVMMatchType<0>],
+          [IntrArgMemOnly, NoCapture<0>]>;
+  class SCOPED_ATOMIC3_impl<LLVMType elty>
+        : Intrinsic<[elty],
+          [LLVMAnyPointerType<LLVMMatchType<0>>, LLVMMatchType<0>,
+           LLVMMatchType<0>],
+          [IntrArgMemOnly, NoCapture<0>]>;
+
+  multiclass PTXAtomicWithScope2<LLVMType elty> {
+    def _cta : SCOPED_ATOMIC2_impl<elty>;
+    def _sys : SCOPED_ATOMIC2_impl<elty>;
+  }
+  multiclass PTXAtomicWithScope3<LLVMType elty> {
+    def _cta : SCOPED_ATOMIC3_impl<elty>;
+    def _sys : SCOPED_ATOMIC3_impl<elty>;
+  }
+  multiclass PTXAtomicWithScope2_fi {
+    defm _f: PTXAtomicWithScope2<llvm_anyfloat_ty>;
+    defm _i: PTXAtomicWithScope2<llvm_anyint_ty>;
+  }
+  defm int_nvvm_atomic_add_gen   : PTXAtomicWithScope2_fi;
+  defm int_nvvm_atomic_inc_gen_i : PTXAtomicWithScope2<llvm_anyint_ty>;
+  defm int_nvvm_atomic_dec_gen_i : PTXAtomicWithScope2<llvm_anyint_ty>;
+  defm int_nvvm_atomic_exch_gen_i: PTXAtomicWithScope2<llvm_anyint_ty>;
+  defm int_nvvm_atomic_xor_gen_i : PTXAtomicWithScope2<llvm_anyint_ty>;
+  defm int_nvvm_atomic_max_gen_i : PTXAtomicWithScope2<llvm_anyint_ty>;
+  defm int_nvvm_atomic_min_gen_i : PTXAtomicWithScope2<llvm_anyint_ty>;
+  defm int_nvvm_atomic_or_gen_i  : PTXAtomicWithScope2<llvm_anyint_ty>;
+  defm int_nvvm_atomic_and_gen_i : PTXAtomicWithScope2<llvm_anyint_ty>;
+  defm int_nvvm_atomic_cas_gen_i : PTXAtomicWithScope3<llvm_anyint_ty>;
+
+// Bar.Sync
+
+  // The builtin for "bar.sync 0" is called __syncthreads.  Unlike most of the
+  // intrinsics in this file, this one is a user-facing API.
+  def int_nvvm_barrier0 : GCCBuiltin<"__syncthreads">,
+      Intrinsic<[], [], [IntrConvergent]>;
+  // Synchronize all threads in the CTA at barrier 'n'.
+  def int_nvvm_barrier_n : GCCBuiltin<"__nvvm_bar_n">,
+      Intrinsic<[], [llvm_i32_ty], [IntrConvergent]>;
+  // Synchronize 'm', a multiple of warp size, (arg 2) threads in
+  // the CTA at barrier 'n' (arg 1).
+  def int_nvvm_barrier : GCCBuiltin<"__nvvm_bar">,
+      Intrinsic<[], [llvm_i32_ty, llvm_i32_ty], [IntrConvergent]>;
+  def int_nvvm_barrier0_popc : GCCBuiltin<"__nvvm_bar0_popc">,
+      Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrConvergent]>;
+  def int_nvvm_barrier0_and : GCCBuiltin<"__nvvm_bar0_and">,
+      Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrConvergent]>;
+  def int_nvvm_barrier0_or : GCCBuiltin<"__nvvm_bar0_or">,
+      Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrConvergent]>;
+
+  def int_nvvm_bar_sync :
+      Intrinsic<[], [llvm_i32_ty], [IntrConvergent]>,
+      GCCBuiltin<"__nvvm_bar_sync">;
+  def int_nvvm_bar_warp_sync :
+      Intrinsic<[], [llvm_i32_ty], [IntrConvergent]>,
+      GCCBuiltin<"__nvvm_bar_warp_sync">;
+
+  // barrier.sync id[, cnt]
+  def int_nvvm_barrier_sync :
+      Intrinsic<[], [llvm_i32_ty], [IntrConvergent]>,
+      GCCBuiltin<"__nvvm_barrier_sync">;
+  def int_nvvm_barrier_sync_cnt :
+      Intrinsic<[], [llvm_i32_ty, llvm_i32_ty], [IntrConvergent]>,
+      GCCBuiltin<"__nvvm_barrier_sync_cnt">;
+
+  // Membar
+  def int_nvvm_membar_cta : GCCBuiltin<"__nvvm_membar_cta">,
+      Intrinsic<[], [], []>;
+  def int_nvvm_membar_gl : GCCBuiltin<"__nvvm_membar_gl">,
+      Intrinsic<[], [], []>;
+  def int_nvvm_membar_sys : GCCBuiltin<"__nvvm_membar_sys">,
+      Intrinsic<[], [], []>;
+
+// Generated within nvvm. Use for ldu on sm_20 or later.  Second arg is the
+// pointer's alignment.
+def int_nvvm_ldu_global_i : Intrinsic<[llvm_anyint_ty],
+  [LLVMAnyPointerType<LLVMMatchType<0>>, llvm_i32_ty],
+  [IntrReadMem, IntrArgMemOnly, NoCapture<0>],
+  "llvm.nvvm.ldu.global.i">;
+def int_nvvm_ldu_global_f : Intrinsic<[llvm_anyfloat_ty],
+  [LLVMAnyPointerType<LLVMMatchType<0>>, llvm_i32_ty],
+  [IntrReadMem, IntrArgMemOnly, NoCapture<0>],
+  "llvm.nvvm.ldu.global.f">;
+def int_nvvm_ldu_global_p : Intrinsic<[llvm_anyptr_ty],
+  [LLVMAnyPointerType<LLVMMatchType<0>>, llvm_i32_ty],
+  [IntrReadMem, IntrArgMemOnly, NoCapture<0>],
+  "llvm.nvvm.ldu.global.p">;
+
+// Generated within nvvm. Use for ldg on sm_35 or later.  Second arg is the
+// pointer's alignment.
+def int_nvvm_ldg_global_i : Intrinsic<[llvm_anyint_ty],
+  [LLVMAnyPointerType<LLVMMatchType<0>>, llvm_i32_ty],
+  [IntrReadMem, IntrArgMemOnly, NoCapture<0>],
+  "llvm.nvvm.ldg.global.i">;
+def int_nvvm_ldg_global_f : Intrinsic<[llvm_anyfloat_ty],
+  [LLVMAnyPointerType<LLVMMatchType<0>>, llvm_i32_ty],
+  [IntrReadMem, IntrArgMemOnly, NoCapture<0>],
+  "llvm.nvvm.ldg.global.f">;
+def int_nvvm_ldg_global_p : Intrinsic<[llvm_anyptr_ty],
+  [LLVMAnyPointerType<LLVMMatchType<0>>, llvm_i32_ty],
+  [IntrReadMem, IntrArgMemOnly, NoCapture<0>],
+  "llvm.nvvm.ldg.global.p">;
+
+// Use for generic pointers
+// - These intrinsics are used to convert address spaces.
+// - The input pointer and output pointer must have the same type, except for
+//   the address-space. (This restriction is not enforced here as there is
+//   currently no way to describe it).
+// - This complements the llvm bitcast, which can be used to cast one type
+//   of pointer to another type of pointer, while the address space remains
+//   the same.
+def int_nvvm_ptr_local_to_gen: Intrinsic<[llvm_anyptr_ty],
+                 [llvm_anyptr_ty], [IntrNoMem],
+                 "llvm.nvvm.ptr.local.to.gen">;
+def int_nvvm_ptr_shared_to_gen: Intrinsic<[llvm_anyptr_ty],
+                 [llvm_anyptr_ty], [IntrNoMem],
+                 "llvm.nvvm.ptr.shared.to.gen">;
+def int_nvvm_ptr_global_to_gen: Intrinsic<[llvm_anyptr_ty],
+                 [llvm_anyptr_ty], [IntrNoMem],
+                 "llvm.nvvm.ptr.global.to.gen">;
+def int_nvvm_ptr_constant_to_gen: Intrinsic<[llvm_anyptr_ty],
+                 [llvm_anyptr_ty], [IntrNoMem],
+                 "llvm.nvvm.ptr.constant.to.gen">;
+
+def int_nvvm_ptr_gen_to_global: Intrinsic<[llvm_anyptr_ty],
+                 [llvm_anyptr_ty], [IntrNoMem],
+                 "llvm.nvvm.ptr.gen.to.global">;
+def int_nvvm_ptr_gen_to_shared: Intrinsic<[llvm_anyptr_ty],
+                 [llvm_anyptr_ty], [IntrNoMem],
+                 "llvm.nvvm.ptr.gen.to.shared">;
+def int_nvvm_ptr_gen_to_local: Intrinsic<[llvm_anyptr_ty],
+                 [llvm_anyptr_ty], [IntrNoMem],
+                 "llvm.nvvm.ptr.gen.to.local">;
+def int_nvvm_ptr_gen_to_constant: Intrinsic<[llvm_anyptr_ty],
+                 [llvm_anyptr_ty], [IntrNoMem],
+                 "llvm.nvvm.ptr.gen.to.constant">;
+
+// Used in nvvm internally to help address space opt and ptx code generation
+// This is for params that are passed to kernel functions by pointer by-val.
+def int_nvvm_ptr_gen_to_param: Intrinsic<[llvm_anyptr_ty],
+                                     [llvm_anyptr_ty],
+                                   [IntrNoMem],
+                                   "llvm.nvvm.ptr.gen.to.param">;
+
+// Move intrinsics, used in nvvm internally
+
+def int_nvvm_move_i16 : Intrinsic<[llvm_i16_ty], [llvm_i16_ty], [IntrNoMem],
+  "llvm.nvvm.move.i16">;
+def int_nvvm_move_i32 : Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem],
+  "llvm.nvvm.move.i32">;
+def int_nvvm_move_i64 : Intrinsic<[llvm_i64_ty], [llvm_i64_ty], [IntrNoMem],
+  "llvm.nvvm.move.i64">;
+def int_nvvm_move_float : Intrinsic<[llvm_float_ty], [llvm_float_ty],
+  [IntrNoMem], "llvm.nvvm.move.float">;
+def int_nvvm_move_double : Intrinsic<[llvm_double_ty], [llvm_double_ty],
+  [IntrNoMem], "llvm.nvvm.move.double">;
+def int_nvvm_move_ptr : Intrinsic<[llvm_anyptr_ty], [llvm_anyptr_ty],
+  [IntrNoMem, NoCapture<0>], "llvm.nvvm.move.ptr">;
+
+
+// For getting the handle from a texture or surface variable
+def int_nvvm_texsurf_handle
+  : Intrinsic<[llvm_i64_ty], [llvm_metadata_ty, llvm_anyi64ptr_ty],
+              [IntrNoMem], "llvm.nvvm.texsurf.handle">;
+def int_nvvm_texsurf_handle_internal
+  : Intrinsic<[llvm_i64_ty], [llvm_anyptr_ty],
+              [IntrNoMem], "llvm.nvvm.texsurf.handle.internal">;
+
+/// Error / Warn
+def int_nvvm_compiler_error :
+    Intrinsic<[], [llvm_anyptr_ty], [], "llvm.nvvm.compiler.error">;
+def int_nvvm_compiler_warn :
+    Intrinsic<[], [llvm_anyptr_ty], [], "llvm.nvvm.compiler.warn">;
+
+def int_nvvm_reflect :
+  Intrinsic<[llvm_i32_ty], [llvm_anyptr_ty], [IntrNoMem], "llvm.nvvm.reflect">;
+
+// isspacep.{const, global, local, shared}
+def int_nvvm_isspacep_const
+  : Intrinsic<[llvm_i1_ty], [llvm_ptr_ty], [IntrNoMem],
+              "llvm.nvvm.isspacep.const">,
+    GCCBuiltin<"__nvvm_isspacep_const">;
+def int_nvvm_isspacep_global
+  : Intrinsic<[llvm_i1_ty], [llvm_ptr_ty], [IntrNoMem],
+              "llvm.nvvm.isspacep.global">,
+    GCCBuiltin<"__nvvm_isspacep_global">;
+def int_nvvm_isspacep_local
+  : Intrinsic<[llvm_i1_ty], [llvm_ptr_ty], [IntrNoMem],
+              "llvm.nvvm.isspacep.local">,
+    GCCBuiltin<"__nvvm_isspacep_local">;
+def int_nvvm_isspacep_shared
+  : Intrinsic<[llvm_i1_ty], [llvm_ptr_ty], [IntrNoMem],
+              "llvm.nvvm.isspacep.shared">,
+    GCCBuiltin<"__nvvm_isspacep_shared">;
+
+// Environment register read
+def int_nvvm_read_ptx_sreg_envreg0
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg0">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg0">;
+def int_nvvm_read_ptx_sreg_envreg1
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg1">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg1">;
+def int_nvvm_read_ptx_sreg_envreg2
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg2">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg2">;
+def int_nvvm_read_ptx_sreg_envreg3
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg3">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg3">;
+def int_nvvm_read_ptx_sreg_envreg4
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg4">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg4">;
+def int_nvvm_read_ptx_sreg_envreg5
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg5">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg5">;
+def int_nvvm_read_ptx_sreg_envreg6
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg6">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg6">;
+def int_nvvm_read_ptx_sreg_envreg7
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg7">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg7">;
+def int_nvvm_read_ptx_sreg_envreg8
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg8">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg8">;
+def int_nvvm_read_ptx_sreg_envreg9
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg9">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg9">;
+def int_nvvm_read_ptx_sreg_envreg10
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg10">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg10">;
+def int_nvvm_read_ptx_sreg_envreg11
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg11">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg11">;
+def int_nvvm_read_ptx_sreg_envreg12
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg12">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg12">;
+def int_nvvm_read_ptx_sreg_envreg13
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg13">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg13">;
+def int_nvvm_read_ptx_sreg_envreg14
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg14">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg14">;
+def int_nvvm_read_ptx_sreg_envreg15
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg15">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg15">;
+def int_nvvm_read_ptx_sreg_envreg16
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg16">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg16">;
+def int_nvvm_read_ptx_sreg_envreg17
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg17">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg17">;
+def int_nvvm_read_ptx_sreg_envreg18
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg18">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg18">;
+def int_nvvm_read_ptx_sreg_envreg19
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg19">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg19">;
+def int_nvvm_read_ptx_sreg_envreg20
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg20">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg20">;
+def int_nvvm_read_ptx_sreg_envreg21
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg21">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg21">;
+def int_nvvm_read_ptx_sreg_envreg22
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg22">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg22">;
+def int_nvvm_read_ptx_sreg_envreg23
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg23">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg23">;
+def int_nvvm_read_ptx_sreg_envreg24
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg24">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg24">;
+def int_nvvm_read_ptx_sreg_envreg25
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg25">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg25">;
+def int_nvvm_read_ptx_sreg_envreg26
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg26">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg26">;
+def int_nvvm_read_ptx_sreg_envreg27
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg27">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg27">;
+def int_nvvm_read_ptx_sreg_envreg28
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg28">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg28">;
+def int_nvvm_read_ptx_sreg_envreg29
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg29">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg29">;
+def int_nvvm_read_ptx_sreg_envreg30
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg30">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg30">;
+def int_nvvm_read_ptx_sreg_envreg31
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem],
+              "llvm.nvvm.read.ptx.sreg.envreg31">,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_envreg31">;
+
+
+// Texture Fetch
+// texmode_independent
+def int_nvvm_tex_1d_v4f32_s32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.1d.v4f32.s32">;
+def int_nvvm_tex_1d_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.v4f32.f32">;
+def int_nvvm_tex_1d_level_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.level.v4f32.f32">;
+def int_nvvm_tex_1d_grad_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.grad.v4f32.f32">;
+def int_nvvm_tex_1d_v4s32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.1d.v4s32.s32">;
+def int_nvvm_tex_1d_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.v4s32.f32">;
+def int_nvvm_tex_1d_level_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.level.v4s32.f32">;
+def int_nvvm_tex_1d_grad_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.grad.v4s32.f32">;
+def int_nvvm_tex_1d_v4u32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.1d.v4u32.s32">;
+def int_nvvm_tex_1d_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.v4u32.f32">;
+def int_nvvm_tex_1d_level_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.level.v4u32.f32">;
+def int_nvvm_tex_1d_grad_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.grad.v4u32.f32">;
+
+def int_nvvm_tex_1d_array_v4f32_s32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.1d.array.v4f32.s32">;
+def int_nvvm_tex_1d_array_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.array.v4f32.f32">;
+def int_nvvm_tex_1d_array_level_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.array.level.v4f32.f32">;
+def int_nvvm_tex_1d_array_grad_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.array.grad.v4f32.f32">;
+def int_nvvm_tex_1d_array_v4s32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.1d.array.v4s32.s32">;
+def int_nvvm_tex_1d_array_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.array.v4s32.f32">;
+def int_nvvm_tex_1d_array_level_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.array.level.v4s32.f32">;
+def int_nvvm_tex_1d_array_grad_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.array.grad.v4s32.f32">;
+def int_nvvm_tex_1d_array_v4u32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.1d.array.v4u32.s32">;
+def int_nvvm_tex_1d_array_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.array.v4u32.f32">;
+def int_nvvm_tex_1d_array_level_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.array.level.v4u32.f32">;
+def int_nvvm_tex_1d_array_grad_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.1d.array.grad.v4u32.f32">;
+
+def int_nvvm_tex_2d_v4f32_s32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.2d.v4f32.s32">;
+def int_nvvm_tex_2d_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.v4f32.f32">;
+def int_nvvm_tex_2d_level_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.level.v4f32.f32">;
+def int_nvvm_tex_2d_grad_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.grad.v4f32.f32">;
+def int_nvvm_tex_2d_v4s32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.2d.v4s32.s32">;
+def int_nvvm_tex_2d_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.v4s32.f32">;
+def int_nvvm_tex_2d_level_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.level.v4s32.f32">;
+def int_nvvm_tex_2d_grad_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.grad.v4s32.f32">;
+def int_nvvm_tex_2d_v4u32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.2d.v4u32.s32">;
+def int_nvvm_tex_2d_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.v4u32.f32">;
+def int_nvvm_tex_2d_level_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.level.v4u32.f32">;
+def int_nvvm_tex_2d_grad_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.grad.v4u32.f32">;
+
+def int_nvvm_tex_2d_array_v4f32_s32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+               llvm_i32_ty], [],
+              "llvm.nvvm.tex.2d.array.v4f32.s32">;
+def int_nvvm_tex_2d_array_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.array.v4f32.f32">;
+def int_nvvm_tex_2d_array_level_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.array.level.v4f32.f32">;
+def int_nvvm_tex_2d_array_grad_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.array.grad.v4f32.f32">;
+def int_nvvm_tex_2d_array_v4s32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+               llvm_i32_ty], [],
+              "llvm.nvvm.tex.2d.array.v4s32.s32">;
+def int_nvvm_tex_2d_array_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.array.v4s32.f32">;
+def int_nvvm_tex_2d_array_level_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.array.level.v4s32.f32">;
+def int_nvvm_tex_2d_array_grad_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.array.grad.v4s32.f32">;
+def int_nvvm_tex_2d_array_v4u32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+               llvm_i32_ty], [],
+              "llvm.nvvm.tex.2d.array.v4u32.s32">;
+def int_nvvm_tex_2d_array_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.array.v4u32.f32">;
+def int_nvvm_tex_2d_array_level_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.array.level.v4u32.f32">;
+def int_nvvm_tex_2d_array_grad_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.2d.array.grad.v4u32.f32">;
+
+def int_nvvm_tex_3d_v4f32_s32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [], "llvm.nvvm.tex.3d.v4f32.s32">;
+def int_nvvm_tex_3d_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.3d.v4f32.f32">;
+def int_nvvm_tex_3d_level_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.3d.level.v4f32.f32">;
+def int_nvvm_tex_3d_grad_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.3d.grad.v4f32.f32">;
+def int_nvvm_tex_3d_v4s32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [], "llvm.nvvm.tex.3d.v4s32.s32">;
+def int_nvvm_tex_3d_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.3d.v4s32.f32">;
+def int_nvvm_tex_3d_level_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.3d.level.v4s32.f32">;
+def int_nvvm_tex_3d_grad_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.3d.grad.v4s32.f32">;
+def int_nvvm_tex_3d_v4u32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [], "llvm.nvvm.tex.3d.v4u32.s32">;
+def int_nvvm_tex_3d_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.3d.v4u32.f32">;
+def int_nvvm_tex_3d_level_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.3d.level.v4u32.f32">;
+def int_nvvm_tex_3d_grad_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.3d.grad.v4u32.f32">;
+
+def int_nvvm_tex_cube_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.cube.v4f32.f32">;
+def int_nvvm_tex_cube_level_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.cube.level.v4f32.f32">;
+def int_nvvm_tex_cube_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.cube.v4s32.f32">;
+def int_nvvm_tex_cube_level_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.cube.level.v4s32.f32">;
+def int_nvvm_tex_cube_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.cube.v4u32.f32">;
+def int_nvvm_tex_cube_level_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.cube.level.v4u32.f32">;
+
+def int_nvvm_tex_cube_array_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.cube.array.v4f32.f32">;
+def int_nvvm_tex_cube_array_level_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.cube.array.level.v4f32.f32">;
+def int_nvvm_tex_cube_array_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.cube.array.v4s32.f32">;
+def int_nvvm_tex_cube_array_level_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.cube.array.level.v4s32.f32">;
+def int_nvvm_tex_cube_array_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.cube.array.v4u32.f32">;
+def int_nvvm_tex_cube_array_level_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_i32_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.cube.array.level.v4u32.f32">;
+
+def int_nvvm_tld4_r_2d_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.r.2d.v4f32.f32">;
+def int_nvvm_tld4_g_2d_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.g.2d.v4f32.f32">;
+def int_nvvm_tld4_b_2d_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.b.2d.v4f32.f32">;
+def int_nvvm_tld4_a_2d_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.a.2d.v4f32.f32">;
+def int_nvvm_tld4_r_2d_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.r.2d.v4s32.f32">;
+def int_nvvm_tld4_g_2d_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.g.2d.v4s32.f32">;
+def int_nvvm_tld4_b_2d_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.b.2d.v4s32.f32">;
+def int_nvvm_tld4_a_2d_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.a.2d.v4s32.f32">;
+def int_nvvm_tld4_r_2d_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.r.2d.v4u32.f32">;
+def int_nvvm_tld4_g_2d_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.g.2d.v4u32.f32">;
+def int_nvvm_tld4_b_2d_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.b.2d.v4u32.f32">;
+def int_nvvm_tld4_a_2d_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.a.2d.v4u32.f32">;
+
+
+// texmode_unified
+def int_nvvm_tex_unified_1d_v4f32_s32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.unified.1d.v4f32.s32">;
+def int_nvvm_tex_unified_1d_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.v4f32.f32">;
+def int_nvvm_tex_unified_1d_level_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.level.v4f32.f32">;
+def int_nvvm_tex_unified_1d_grad_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.grad.v4f32.f32">;
+def int_nvvm_tex_unified_1d_v4s32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.unified.1d.v4s32.s32">;
+def int_nvvm_tex_unified_1d_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.v4s32.f32">;
+def int_nvvm_tex_unified_1d_level_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.level.v4s32.f32">;
+def int_nvvm_tex_unified_1d_grad_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.grad.v4s32.f32">;
+def int_nvvm_tex_unified_1d_v4u32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.unified.1d.v4u32.s32">;
+def int_nvvm_tex_unified_1d_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.v4u32.f32">;
+def int_nvvm_tex_unified_1d_level_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.level.v4u32.f32">;
+def int_nvvm_tex_unified_1d_grad_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.grad.v4u32.f32">;
+
+def int_nvvm_tex_unified_1d_array_v4f32_s32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.unified.1d.array.v4f32.s32">;
+def int_nvvm_tex_unified_1d_array_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.array.v4f32.f32">;
+def int_nvvm_tex_unified_1d_array_level_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.array.level.v4f32.f32">;
+def int_nvvm_tex_unified_1d_array_grad_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.array.grad.v4f32.f32">;
+def int_nvvm_tex_unified_1d_array_v4s32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.unified.1d.array.v4s32.s32">;
+def int_nvvm_tex_unified_1d_array_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.array.v4s32.f32">;
+def int_nvvm_tex_unified_1d_array_level_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.array.level.v4s32.f32">;
+def int_nvvm_tex_unified_1d_array_grad_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.array.grad.v4s32.f32">;
+def int_nvvm_tex_unified_1d_array_v4u32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.unified.1d.array.v4u32.s32">;
+def int_nvvm_tex_unified_1d_array_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.array.v4u32.f32">;
+def int_nvvm_tex_unified_1d_array_level_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.array.level.v4u32.f32">;
+def int_nvvm_tex_unified_1d_array_grad_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.1d.array.grad.v4u32.f32">;
+
+def int_nvvm_tex_unified_2d_v4f32_s32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.unified.2d.v4f32.s32">;
+def int_nvvm_tex_unified_2d_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.v4f32.f32">;
+def int_nvvm_tex_unified_2d_level_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.level.v4f32.f32">;
+def int_nvvm_tex_unified_2d_grad_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.grad.v4f32.f32">;
+def int_nvvm_tex_unified_2d_v4s32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.unified.2d.v4s32.s32">;
+def int_nvvm_tex_unified_2d_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.v4s32.f32">;
+def int_nvvm_tex_unified_2d_level_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.level.v4s32.f32">;
+def int_nvvm_tex_unified_2d_grad_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.grad.v4s32.f32">;
+def int_nvvm_tex_unified_2d_v4u32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.tex.unified.2d.v4u32.s32">;
+def int_nvvm_tex_unified_2d_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.v4u32.f32">;
+def int_nvvm_tex_unified_2d_level_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.level.v4u32.f32">;
+def int_nvvm_tex_unified_2d_grad_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.grad.v4u32.f32">;
+
+def int_nvvm_tex_unified_2d_array_v4f32_s32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+               llvm_i32_ty], [],
+              "llvm.nvvm.tex.unified.2d.array.v4f32.s32">;
+def int_nvvm_tex_unified_2d_array_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.array.v4f32.f32">;
+def int_nvvm_tex_unified_2d_array_level_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.array.level.v4f32.f32">;
+def int_nvvm_tex_unified_2d_array_grad_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.array.grad.v4f32.f32">;
+def int_nvvm_tex_unified_2d_array_v4s32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+               llvm_i32_ty], [],
+              "llvm.nvvm.tex.unified.2d.array.v4s32.s32">;
+def int_nvvm_tex_unified_2d_array_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.array.v4s32.f32">;
+def int_nvvm_tex_unified_2d_array_level_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.array.level.v4s32.f32">;
+def int_nvvm_tex_unified_2d_array_grad_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.array.grad.v4s32.f32">;
+def int_nvvm_tex_unified_2d_array_v4u32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+               llvm_i32_ty], [],
+              "llvm.nvvm.tex.unified.2d.array.v4u32.s32">;
+def int_nvvm_tex_unified_2d_array_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.array.v4u32.f32">;
+def int_nvvm_tex_unified_2d_array_level_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.array.level.v4u32.f32">;
+def int_nvvm_tex_unified_2d_array_grad_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.2d.array.grad.v4u32.f32">;
+
+def int_nvvm_tex_unified_3d_v4f32_s32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [], "llvm.nvvm.tex.unified.3d.v4f32.s32">;
+def int_nvvm_tex_unified_3d_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.3d.v4f32.f32">;
+def int_nvvm_tex_unified_3d_level_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.3d.level.v4f32.f32">;
+def int_nvvm_tex_unified_3d_grad_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.3d.grad.v4f32.f32">;
+def int_nvvm_tex_unified_3d_v4s32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [], "llvm.nvvm.tex.unified.3d.v4s32.s32">;
+def int_nvvm_tex_unified_3d_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.3d.v4s32.f32">;
+def int_nvvm_tex_unified_3d_level_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.3d.level.v4s32.f32">;
+def int_nvvm_tex_unified_3d_grad_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.3d.grad.v4s32.f32">;
+def int_nvvm_tex_unified_3d_v4u32_s32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [], "llvm.nvvm.tex.unified.3d.v4u32.s32">;
+def int_nvvm_tex_unified_3d_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.3d.v4u32.f32">;
+def int_nvvm_tex_unified_3d_level_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.3d.level.v4u32.f32">;
+def int_nvvm_tex_unified_3d_grad_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.3d.grad.v4u32.f32">;
+
+def int_nvvm_tex_unified_cube_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.cube.v4f32.f32">;
+def int_nvvm_tex_unified_cube_level_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.cube.level.v4f32.f32">;
+def int_nvvm_tex_unified_cube_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.cube.v4s32.f32">;
+def int_nvvm_tex_unified_cube_level_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.cube.level.v4s32.f32">;
+def int_nvvm_tex_unified_cube_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.cube.v4u32.f32">;
+def int_nvvm_tex_unified_cube_level_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.cube.level.v4u32.f32">;
+
+def int_nvvm_tex_unified_cube_array_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i32_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.cube.array.v4f32.f32">;
+def int_nvvm_tex_unified_cube_array_level_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_i32_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.cube.array.level.v4f32.f32">;
+def int_nvvm_tex_unified_cube_array_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.cube.array.v4s32.f32">;
+def int_nvvm_tex_unified_cube_array_level_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.cube.array.level.v4s32.f32">;
+def int_nvvm_tex_unified_cube_array_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.cube.array.v4u32.f32">;
+def int_nvvm_tex_unified_cube_array_level_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty,
+               llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tex.unified.cube.array.level.v4u32.f32">;
+
+def int_nvvm_tld4_unified_r_2d_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.unified.r.2d.v4f32.f32">;
+def int_nvvm_tld4_unified_g_2d_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.unified.g.2d.v4f32.f32">;
+def int_nvvm_tld4_unified_b_2d_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.unified.b.2d.v4f32.f32">;
+def int_nvvm_tld4_unified_a_2d_v4f32_f32
+  : Intrinsic<[llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.unified.a.2d.v4f32.f32">;
+def int_nvvm_tld4_unified_r_2d_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.unified.r.2d.v4s32.f32">;
+def int_nvvm_tld4_unified_g_2d_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.unified.g.2d.v4s32.f32">;
+def int_nvvm_tld4_unified_b_2d_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.unified.b.2d.v4s32.f32">;
+def int_nvvm_tld4_unified_a_2d_v4s32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.unified.a.2d.v4s32.f32">;
+def int_nvvm_tld4_unified_r_2d_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.unified.r.2d.v4u32.f32">;
+def int_nvvm_tld4_unified_g_2d_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.unified.g.2d.v4u32.f32">;
+def int_nvvm_tld4_unified_b_2d_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.unified.b.2d.v4u32.f32">;
+def int_nvvm_tld4_unified_a_2d_v4u32_f32
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_float_ty, llvm_float_ty], [],
+              "llvm.nvvm.tld4.unified.a.2d.v4u32.f32">;
+
+
+//=== Surface Load
+// .clamp variants
+def int_nvvm_suld_1d_i8_clamp
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.i8.clamp">;
+def int_nvvm_suld_1d_i16_clamp
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.i16.clamp">;
+def int_nvvm_suld_1d_i32_clamp
+  : Intrinsic<[llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.i32.clamp">;
+def int_nvvm_suld_1d_i64_clamp
+  : Intrinsic<[llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.i64.clamp">;
+def int_nvvm_suld_1d_v2i8_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v2i8.clamp">;
+def int_nvvm_suld_1d_v2i16_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v2i16.clamp">;
+def int_nvvm_suld_1d_v2i32_clamp
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v2i32.clamp">;
+def int_nvvm_suld_1d_v2i64_clamp
+  : Intrinsic<[llvm_i64_ty, llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v2i64.clamp">;
+def int_nvvm_suld_1d_v4i8_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v4i8.clamp">;
+def int_nvvm_suld_1d_v4i16_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v4i16.clamp">;
+def int_nvvm_suld_1d_v4i32_clamp
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v4i32.clamp">;
+
+def int_nvvm_suld_1d_array_i8_clamp
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.i8.clamp">;
+def int_nvvm_suld_1d_array_i16_clamp
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.i16.clamp">;
+def int_nvvm_suld_1d_array_i32_clamp
+  : Intrinsic<[llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.i32.clamp">;
+def int_nvvm_suld_1d_array_i64_clamp
+  : Intrinsic<[llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.i64.clamp">;
+def int_nvvm_suld_1d_array_v2i8_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v2i8.clamp">;
+def int_nvvm_suld_1d_array_v2i16_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v2i16.clamp">;
+def int_nvvm_suld_1d_array_v2i32_clamp
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v2i32.clamp">;
+def int_nvvm_suld_1d_array_v2i64_clamp
+  : Intrinsic<[llvm_i64_ty, llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v2i64.clamp">;
+def int_nvvm_suld_1d_array_v4i8_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v4i8.clamp">;
+def int_nvvm_suld_1d_array_v4i16_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v4i16.clamp">;
+def int_nvvm_suld_1d_array_v4i32_clamp
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v4i32.clamp">;
+
+def int_nvvm_suld_2d_i8_clamp
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.i8.clamp">;
+def int_nvvm_suld_2d_i16_clamp
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.i16.clamp">;
+def int_nvvm_suld_2d_i32_clamp
+  : Intrinsic<[llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.i32.clamp">;
+def int_nvvm_suld_2d_i64_clamp
+  : Intrinsic<[llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.i64.clamp">;
+def int_nvvm_suld_2d_v2i8_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v2i8.clamp">;
+def int_nvvm_suld_2d_v2i16_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v2i16.clamp">;
+def int_nvvm_suld_2d_v2i32_clamp
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v2i32.clamp">;
+def int_nvvm_suld_2d_v2i64_clamp
+  : Intrinsic<[llvm_i64_ty, llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v2i64.clamp">;
+def int_nvvm_suld_2d_v4i8_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v4i8.clamp">;
+def int_nvvm_suld_2d_v4i16_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v4i16.clamp">;
+def int_nvvm_suld_2d_v4i32_clamp
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v4i32.clamp">;
+
+def int_nvvm_suld_2d_array_i8_clamp
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.i8.clamp">;
+def int_nvvm_suld_2d_array_i16_clamp
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.i16.clamp">;
+def int_nvvm_suld_2d_array_i32_clamp
+  : Intrinsic<[llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.i32.clamp">;
+def int_nvvm_suld_2d_array_i64_clamp
+  : Intrinsic<[llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.i64.clamp">;
+def int_nvvm_suld_2d_array_v2i8_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v2i8.clamp">;
+def int_nvvm_suld_2d_array_v2i16_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v2i16.clamp">;
+def int_nvvm_suld_2d_array_v2i32_clamp
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v2i32.clamp">;
+def int_nvvm_suld_2d_array_v2i64_clamp
+  : Intrinsic<[llvm_i64_ty, llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v2i64.clamp">;
+def int_nvvm_suld_2d_array_v4i8_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v4i8.clamp">;
+def int_nvvm_suld_2d_array_v4i16_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v4i16.clamp">;
+def int_nvvm_suld_2d_array_v4i32_clamp
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v4i32.clamp">;
+
+def int_nvvm_suld_3d_i8_clamp
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.i8.clamp">;
+def int_nvvm_suld_3d_i16_clamp
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.i16.clamp">;
+def int_nvvm_suld_3d_i32_clamp
+  : Intrinsic<[llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.i32.clamp">;
+def int_nvvm_suld_3d_i64_clamp
+  : Intrinsic<[llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.i64.clamp">;
+def int_nvvm_suld_3d_v2i8_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v2i8.clamp">;
+def int_nvvm_suld_3d_v2i16_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v2i16.clamp">;
+def int_nvvm_suld_3d_v2i32_clamp
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v2i32.clamp">;
+def int_nvvm_suld_3d_v2i64_clamp
+  : Intrinsic<[llvm_i64_ty, llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v2i64.clamp">;
+def int_nvvm_suld_3d_v4i8_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v4i8.clamp">;
+def int_nvvm_suld_3d_v4i16_clamp
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v4i16.clamp">;
+def int_nvvm_suld_3d_v4i32_clamp
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v4i32.clamp">;
+
+// .trap variants
+def int_nvvm_suld_1d_i8_trap
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.i8.trap">;
+def int_nvvm_suld_1d_i16_trap
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.i16.trap">;
+def int_nvvm_suld_1d_i32_trap
+  : Intrinsic<[llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.i32.trap">;
+def int_nvvm_suld_1d_i64_trap
+  : Intrinsic<[llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.i64.trap">;
+def int_nvvm_suld_1d_v2i8_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v2i8.trap">;
+def int_nvvm_suld_1d_v2i16_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v2i16.trap">;
+def int_nvvm_suld_1d_v2i32_trap
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v2i32.trap">;
+def int_nvvm_suld_1d_v2i64_trap
+  : Intrinsic<[llvm_i64_ty, llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v2i64.trap">;
+def int_nvvm_suld_1d_v4i8_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v4i8.trap">;
+def int_nvvm_suld_1d_v4i16_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v4i16.trap">;
+def int_nvvm_suld_1d_v4i32_trap
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v4i32.trap">;
+
+def int_nvvm_suld_1d_array_i8_trap
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.i8.trap">;
+def int_nvvm_suld_1d_array_i16_trap
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.i16.trap">;
+def int_nvvm_suld_1d_array_i32_trap
+  : Intrinsic<[llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.i32.trap">;
+def int_nvvm_suld_1d_array_i64_trap
+  : Intrinsic<[llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.i64.trap">;
+def int_nvvm_suld_1d_array_v2i8_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v2i8.trap">;
+def int_nvvm_suld_1d_array_v2i16_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v2i16.trap">;
+def int_nvvm_suld_1d_array_v2i32_trap
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v2i32.trap">;
+def int_nvvm_suld_1d_array_v2i64_trap
+  : Intrinsic<[llvm_i64_ty, llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v2i64.trap">;
+def int_nvvm_suld_1d_array_v4i8_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v4i8.trap">;
+def int_nvvm_suld_1d_array_v4i16_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v4i16.trap">;
+def int_nvvm_suld_1d_array_v4i32_trap
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v4i32.trap">;
+
+def int_nvvm_suld_2d_i8_trap
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.i8.trap">;
+def int_nvvm_suld_2d_i16_trap
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.i16.trap">;
+def int_nvvm_suld_2d_i32_trap
+  : Intrinsic<[llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.i32.trap">;
+def int_nvvm_suld_2d_i64_trap
+  : Intrinsic<[llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.i64.trap">;
+def int_nvvm_suld_2d_v2i8_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v2i8.trap">;
+def int_nvvm_suld_2d_v2i16_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v2i16.trap">;
+def int_nvvm_suld_2d_v2i32_trap
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v2i32.trap">;
+def int_nvvm_suld_2d_v2i64_trap
+  : Intrinsic<[llvm_i64_ty, llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v2i64.trap">;
+def int_nvvm_suld_2d_v4i8_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v4i8.trap">;
+def int_nvvm_suld_2d_v4i16_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v4i16.trap">;
+def int_nvvm_suld_2d_v4i32_trap
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v4i32.trap">;
+
+def int_nvvm_suld_2d_array_i8_trap
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.i8.trap">;
+def int_nvvm_suld_2d_array_i16_trap
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.i16.trap">;
+def int_nvvm_suld_2d_array_i32_trap
+  : Intrinsic<[llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.i32.trap">;
+def int_nvvm_suld_2d_array_i64_trap
+  : Intrinsic<[llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.i64.trap">;
+def int_nvvm_suld_2d_array_v2i8_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v2i8.trap">;
+def int_nvvm_suld_2d_array_v2i16_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v2i16.trap">;
+def int_nvvm_suld_2d_array_v2i32_trap
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v2i32.trap">;
+def int_nvvm_suld_2d_array_v2i64_trap
+  : Intrinsic<[llvm_i64_ty, llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v2i64.trap">;
+def int_nvvm_suld_2d_array_v4i8_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v4i8.trap">;
+def int_nvvm_suld_2d_array_v4i16_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v4i16.trap">;
+def int_nvvm_suld_2d_array_v4i32_trap
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v4i32.trap">;
+
+def int_nvvm_suld_3d_i8_trap
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.i8.trap">;
+def int_nvvm_suld_3d_i16_trap
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.i16.trap">;
+def int_nvvm_suld_3d_i32_trap
+  : Intrinsic<[llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.i32.trap">;
+def int_nvvm_suld_3d_i64_trap
+  : Intrinsic<[llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.i64.trap">;
+def int_nvvm_suld_3d_v2i8_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v2i8.trap">;
+def int_nvvm_suld_3d_v2i16_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v2i16.trap">;
+def int_nvvm_suld_3d_v2i32_trap
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v2i32.trap">;
+def int_nvvm_suld_3d_v2i64_trap
+  : Intrinsic<[llvm_i64_ty, llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v2i64.trap">;
+def int_nvvm_suld_3d_v4i8_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v4i8.trap">;
+def int_nvvm_suld_3d_v4i16_trap
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v4i16.trap">;
+def int_nvvm_suld_3d_v4i32_trap
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v4i32.trap">;
+
+// .zero variants
+def int_nvvm_suld_1d_i8_zero
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.i8.zero">;
+def int_nvvm_suld_1d_i16_zero
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.i16.zero">;
+def int_nvvm_suld_1d_i32_zero
+  : Intrinsic<[llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.i32.zero">;
+def int_nvvm_suld_1d_i64_zero
+  : Intrinsic<[llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.i64.zero">;
+def int_nvvm_suld_1d_v2i8_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v2i8.zero">;
+def int_nvvm_suld_1d_v2i16_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v2i16.zero">;
+def int_nvvm_suld_1d_v2i32_zero
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v2i32.zero">;
+def int_nvvm_suld_1d_v2i64_zero
+  : Intrinsic<[llvm_i64_ty, llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v2i64.zero">;
+def int_nvvm_suld_1d_v4i8_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v4i8.zero">;
+def int_nvvm_suld_1d_v4i16_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v4i16.zero">;
+def int_nvvm_suld_1d_v4i32_zero
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.v4i32.zero">;
+
+def int_nvvm_suld_1d_array_i8_zero
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.i8.zero">;
+def int_nvvm_suld_1d_array_i16_zero
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.i16.zero">;
+def int_nvvm_suld_1d_array_i32_zero
+  : Intrinsic<[llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.i32.zero">;
+def int_nvvm_suld_1d_array_i64_zero
+  : Intrinsic<[llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.i64.zero">;
+def int_nvvm_suld_1d_array_v2i8_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v2i8.zero">;
+def int_nvvm_suld_1d_array_v2i16_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v2i16.zero">;
+def int_nvvm_suld_1d_array_v2i32_zero
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v2i32.zero">;
+def int_nvvm_suld_1d_array_v2i64_zero
+  : Intrinsic<[llvm_i64_ty, llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v2i64.zero">;
+def int_nvvm_suld_1d_array_v4i8_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v4i8.zero">;
+def int_nvvm_suld_1d_array_v4i16_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v4i16.zero">;
+def int_nvvm_suld_1d_array_v4i32_zero
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.1d.array.v4i32.zero">;
+
+def int_nvvm_suld_2d_i8_zero
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.i8.zero">;
+def int_nvvm_suld_2d_i16_zero
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.i16.zero">;
+def int_nvvm_suld_2d_i32_zero
+  : Intrinsic<[llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.i32.zero">;
+def int_nvvm_suld_2d_i64_zero
+  : Intrinsic<[llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.i64.zero">;
+def int_nvvm_suld_2d_v2i8_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v2i8.zero">;
+def int_nvvm_suld_2d_v2i16_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v2i16.zero">;
+def int_nvvm_suld_2d_v2i32_zero
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v2i32.zero">;
+def int_nvvm_suld_2d_v2i64_zero
+  : Intrinsic<[llvm_i64_ty, llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v2i64.zero">;
+def int_nvvm_suld_2d_v4i8_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v4i8.zero">;
+def int_nvvm_suld_2d_v4i16_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v4i16.zero">;
+def int_nvvm_suld_2d_v4i32_zero
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.v4i32.zero">;
+
+def int_nvvm_suld_2d_array_i8_zero
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.i8.zero">;
+def int_nvvm_suld_2d_array_i16_zero
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.i16.zero">;
+def int_nvvm_suld_2d_array_i32_zero
+  : Intrinsic<[llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.i32.zero">;
+def int_nvvm_suld_2d_array_i64_zero
+  : Intrinsic<[llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.i64.zero">;
+def int_nvvm_suld_2d_array_v2i8_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v2i8.zero">;
+def int_nvvm_suld_2d_array_v2i16_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v2i16.zero">;
+def int_nvvm_suld_2d_array_v2i32_zero
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v2i32.zero">;
+def int_nvvm_suld_2d_array_v2i64_zero
+  : Intrinsic<[llvm_i64_ty, llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v2i64.zero">;
+def int_nvvm_suld_2d_array_v4i8_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v4i8.zero">;
+def int_nvvm_suld_2d_array_v4i16_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v4i16.zero">;
+def int_nvvm_suld_2d_array_v4i32_zero
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.2d.array.v4i32.zero">;
+
+def int_nvvm_suld_3d_i8_zero
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.i8.zero">;
+def int_nvvm_suld_3d_i16_zero
+  : Intrinsic<[llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.i16.zero">;
+def int_nvvm_suld_3d_i32_zero
+  : Intrinsic<[llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.i32.zero">;
+def int_nvvm_suld_3d_i64_zero
+  : Intrinsic<[llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.i64.zero">;
+def int_nvvm_suld_3d_v2i8_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v2i8.zero">;
+def int_nvvm_suld_3d_v2i16_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v2i16.zero">;
+def int_nvvm_suld_3d_v2i32_zero
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v2i32.zero">;
+def int_nvvm_suld_3d_v2i64_zero
+  : Intrinsic<[llvm_i64_ty, llvm_i64_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v2i64.zero">;
+def int_nvvm_suld_3d_v4i8_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v4i8.zero">;
+def int_nvvm_suld_3d_v4i16_zero
+  : Intrinsic<[llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v4i16.zero">;
+def int_nvvm_suld_3d_v4i32_zero
+  : Intrinsic<[llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+              [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.suld.3d.v4i32.zero">;
+
+//===- Texture Query ------------------------------------------------------===//
+
+def int_nvvm_txq_channel_order
+  : Intrinsic<[llvm_i32_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.txq.channel.order">,
+    GCCBuiltin<"__nvvm_txq_channel_order">;
+def int_nvvm_txq_channel_data_type
+  : Intrinsic<[llvm_i32_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.txq.channel.data.type">,
+    GCCBuiltin<"__nvvm_txq_channel_data_type">;
+def int_nvvm_txq_width
+  : Intrinsic<[llvm_i32_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.txq.width">,
+    GCCBuiltin<"__nvvm_txq_width">;
+def int_nvvm_txq_height
+  : Intrinsic<[llvm_i32_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.txq.height">,
+    GCCBuiltin<"__nvvm_txq_height">;
+def int_nvvm_txq_depth
+  : Intrinsic<[llvm_i32_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.txq.depth">,
+    GCCBuiltin<"__nvvm_txq_depth">;
+def int_nvvm_txq_array_size
+  : Intrinsic<[llvm_i32_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.txq.array.size">,
+    GCCBuiltin<"__nvvm_txq_array_size">;
+def int_nvvm_txq_num_samples
+  : Intrinsic<[llvm_i32_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.txq.num.samples">,
+    GCCBuiltin<"__nvvm_txq_num_samples">;
+def int_nvvm_txq_num_mipmap_levels
+  : Intrinsic<[llvm_i32_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.txq.num.mipmap.levels">,
+    GCCBuiltin<"__nvvm_txq_num_mipmap_levels">;
+
+//===- Surface Query ------------------------------------------------------===//
+
+def int_nvvm_suq_channel_order
+  : Intrinsic<[llvm_i32_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.suq.channel.order">,
+    GCCBuiltin<"__nvvm_suq_channel_order">;
+def int_nvvm_suq_channel_data_type
+  : Intrinsic<[llvm_i32_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.suq.channel.data.type">,
+    GCCBuiltin<"__nvvm_suq_channel_data_type">;
+def int_nvvm_suq_width
+  : Intrinsic<[llvm_i32_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.suq.width">,
+    GCCBuiltin<"__nvvm_suq_width">;
+def int_nvvm_suq_height
+  : Intrinsic<[llvm_i32_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.suq.height">,
+    GCCBuiltin<"__nvvm_suq_height">;
+def int_nvvm_suq_depth
+  : Intrinsic<[llvm_i32_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.suq.depth">,
+    GCCBuiltin<"__nvvm_suq_depth">;
+def int_nvvm_suq_array_size
+  : Intrinsic<[llvm_i32_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.suq.array.size">,
+    GCCBuiltin<"__nvvm_suq_array_size">;
+
+
+//===- Handle Query -------------------------------------------------------===//
+
+def int_nvvm_istypep_sampler
+  : Intrinsic<[llvm_i1_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.istypep.sampler">,
+    GCCBuiltin<"__nvvm_istypep_sampler">;
+def int_nvvm_istypep_surface
+  : Intrinsic<[llvm_i1_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.istypep.surface">,
+    GCCBuiltin<"__nvvm_istypep_surface">;
+def int_nvvm_istypep_texture
+  : Intrinsic<[llvm_i1_ty], [llvm_i64_ty], [IntrNoMem],
+              "llvm.nvvm.istypep.texture">,
+    GCCBuiltin<"__nvvm_istypep_texture">;
+
+
+
+//===- Surface Stores -----------------------------------------------------===//
+
+// Unformatted
+// .clamp variant
+def int_nvvm_sust_b_1d_i8_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.i8.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_i8_clamp">;
+def int_nvvm_sust_b_1d_i16_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.i16.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_i16_clamp">;
+def int_nvvm_sust_b_1d_i32_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.i32.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_i32_clamp">;
+def int_nvvm_sust_b_1d_i64_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.1d.i64.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_i64_clamp">;
+def int_nvvm_sust_b_1d_v2i8_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.v2i8.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v2i8_clamp">;
+def int_nvvm_sust_b_1d_v2i16_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.v2i16.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v2i16_clamp">;
+def int_nvvm_sust_b_1d_v2i32_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.v2i32.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v2i32_clamp">;
+def int_nvvm_sust_b_1d_v2i64_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i64_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.1d.v2i64.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v2i64_clamp">;
+def int_nvvm_sust_b_1d_v4i8_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.v4i8.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v4i8_clamp">;
+def int_nvvm_sust_b_1d_v4i16_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.v4i16.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v4i16_clamp">;
+def int_nvvm_sust_b_1d_v4i32_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.v4i32.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v4i32_clamp">;
+
+
+def int_nvvm_sust_b_1d_array_i8_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.i8.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_i8_clamp">;
+def int_nvvm_sust_b_1d_array_i16_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.i16.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_i16_clamp">;
+def int_nvvm_sust_b_1d_array_i32_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.array.i32.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_i32_clamp">;
+def int_nvvm_sust_b_1d_array_i64_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.1d.array.i64.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_i64_clamp">;
+def int_nvvm_sust_b_1d_array_v2i8_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v2i8.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v2i8_clamp">;
+def int_nvvm_sust_b_1d_array_v2i16_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v2i16.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v2i16_clamp">;
+def int_nvvm_sust_b_1d_array_v2i32_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v2i32.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v2i32_clamp">;
+def int_nvvm_sust_b_1d_array_v2i64_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i64_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v2i64.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v2i64_clamp">;
+def int_nvvm_sust_b_1d_array_v4i8_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v4i8.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v4i8_clamp">;
+def int_nvvm_sust_b_1d_array_v4i16_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v4i16.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v4i16_clamp">;
+def int_nvvm_sust_b_1d_array_v4i32_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v4i32.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v4i32_clamp">;
+
+
+def int_nvvm_sust_b_2d_i8_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.i8.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_i8_clamp">;
+def int_nvvm_sust_b_2d_i16_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.i16.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_i16_clamp">;
+def int_nvvm_sust_b_2d_i32_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.i32.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_i32_clamp">;
+def int_nvvm_sust_b_2d_i64_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.2d.i64.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_i64_clamp">;
+def int_nvvm_sust_b_2d_v2i8_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.v2i8.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v2i8_clamp">;
+def int_nvvm_sust_b_2d_v2i16_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.v2i16.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v2i16_clamp">;
+def int_nvvm_sust_b_2d_v2i32_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.v2i32.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v2i32_clamp">;
+def int_nvvm_sust_b_2d_v2i64_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i64_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.2d.v2i64.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v2i64_clamp">;
+def int_nvvm_sust_b_2d_v4i8_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.v4i8.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v4i8_clamp">;
+def int_nvvm_sust_b_2d_v4i16_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.v4i16.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v4i16_clamp">;
+def int_nvvm_sust_b_2d_v4i32_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.v4i32.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v4i32_clamp">;
+
+
+def int_nvvm_sust_b_2d_array_i8_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.i8.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_i8_clamp">;
+def int_nvvm_sust_b_2d_array_i16_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.i16.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_i16_clamp">;
+def int_nvvm_sust_b_2d_array_i32_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.array.i32.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_i32_clamp">;
+def int_nvvm_sust_b_2d_array_i64_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.2d.array.i64.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_i64_clamp">;
+def int_nvvm_sust_b_2d_array_v2i8_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v2i8.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v2i8_clamp">;
+def int_nvvm_sust_b_2d_array_v2i16_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v2i16.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v2i16_clamp">;
+def int_nvvm_sust_b_2d_array_v2i32_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v2i32.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v2i32_clamp">;
+def int_nvvm_sust_b_2d_array_v2i64_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i64_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v2i64.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v2i64_clamp">;
+def int_nvvm_sust_b_2d_array_v4i8_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v4i8.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v4i8_clamp">;
+def int_nvvm_sust_b_2d_array_v4i16_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v4i16.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v4i16_clamp">;
+def int_nvvm_sust_b_2d_array_v4i32_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v4i32.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v4i32_clamp">;
+
+
+def int_nvvm_sust_b_3d_i8_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.i8.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_3d_i8_clamp">;
+def int_nvvm_sust_b_3d_i16_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.i16.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_3d_i16_clamp">;
+def int_nvvm_sust_b_3d_i32_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.3d.i32.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_3d_i32_clamp">;
+def int_nvvm_sust_b_3d_i64_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.3d.i64.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_3d_i64_clamp">;
+def int_nvvm_sust_b_3d_v2i8_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.v2i8.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v2i8_clamp">;
+def int_nvvm_sust_b_3d_v2i16_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.v2i16.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v2i16_clamp">;
+def int_nvvm_sust_b_3d_v2i32_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.3d.v2i32.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v2i32_clamp">;
+def int_nvvm_sust_b_3d_v2i64_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i64_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.3d.v2i64.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v2i64_clamp">;
+def int_nvvm_sust_b_3d_v4i8_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.v4i8.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v4i8_clamp">;
+def int_nvvm_sust_b_3d_v4i16_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.v4i16.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v4i16_clamp">;
+def int_nvvm_sust_b_3d_v4i32_clamp
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.3d.v4i32.clamp">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v4i32_clamp">;
+
+
+// .trap variant
+def int_nvvm_sust_b_1d_i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.i8.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_i8_trap">;
+def int_nvvm_sust_b_1d_i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.i16.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_i16_trap">;
+def int_nvvm_sust_b_1d_i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.i32.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_i32_trap">;
+def int_nvvm_sust_b_1d_i64_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.1d.i64.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_i64_trap">;
+def int_nvvm_sust_b_1d_v2i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.v2i8.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v2i8_trap">;
+def int_nvvm_sust_b_1d_v2i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.v2i16.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v2i16_trap">;
+def int_nvvm_sust_b_1d_v2i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.v2i32.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v2i32_trap">;
+def int_nvvm_sust_b_1d_v2i64_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i64_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.1d.v2i64.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v2i64_trap">;
+def int_nvvm_sust_b_1d_v4i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.v4i8.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v4i8_trap">;
+def int_nvvm_sust_b_1d_v4i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.v4i16.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v4i16_trap">;
+def int_nvvm_sust_b_1d_v4i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.v4i32.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v4i32_trap">;
+
+
+def int_nvvm_sust_b_1d_array_i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.i8.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_i8_trap">;
+def int_nvvm_sust_b_1d_array_i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.i16.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_i16_trap">;
+def int_nvvm_sust_b_1d_array_i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.array.i32.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_i32_trap">;
+def int_nvvm_sust_b_1d_array_i64_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.1d.array.i64.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_i64_trap">;
+def int_nvvm_sust_b_1d_array_v2i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v2i8.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v2i8_trap">;
+def int_nvvm_sust_b_1d_array_v2i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v2i16.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v2i16_trap">;
+def int_nvvm_sust_b_1d_array_v2i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v2i32.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v2i32_trap">;
+def int_nvvm_sust_b_1d_array_v2i64_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i64_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v2i64.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v2i64_trap">;
+def int_nvvm_sust_b_1d_array_v4i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v4i8.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v4i8_trap">;
+def int_nvvm_sust_b_1d_array_v4i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v4i16.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v4i16_trap">;
+def int_nvvm_sust_b_1d_array_v4i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v4i32.trap">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v4i32_trap">;
+
+
+def int_nvvm_sust_b_2d_i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.i8.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_i8_trap">;
+def int_nvvm_sust_b_2d_i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.i16.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_i16_trap">;
+def int_nvvm_sust_b_2d_i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.i32.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_i32_trap">;
+def int_nvvm_sust_b_2d_i64_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.2d.i64.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_i64_trap">;
+def int_nvvm_sust_b_2d_v2i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.v2i8.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v2i8_trap">;
+def int_nvvm_sust_b_2d_v2i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.v2i16.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v2i16_trap">;
+def int_nvvm_sust_b_2d_v2i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.v2i32.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v2i32_trap">;
+def int_nvvm_sust_b_2d_v2i64_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i64_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.2d.v2i64.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v2i64_trap">;
+def int_nvvm_sust_b_2d_v4i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.v4i8.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v4i8_trap">;
+def int_nvvm_sust_b_2d_v4i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.v4i16.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v4i16_trap">;
+def int_nvvm_sust_b_2d_v4i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.v4i32.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v4i32_trap">;
+
+
+def int_nvvm_sust_b_2d_array_i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.i8.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_i8_trap">;
+def int_nvvm_sust_b_2d_array_i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.i16.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_i16_trap">;
+def int_nvvm_sust_b_2d_array_i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.array.i32.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_i32_trap">;
+def int_nvvm_sust_b_2d_array_i64_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.2d.array.i64.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_i64_trap">;
+def int_nvvm_sust_b_2d_array_v2i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v2i8.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v2i8_trap">;
+def int_nvvm_sust_b_2d_array_v2i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v2i16.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v2i16_trap">;
+def int_nvvm_sust_b_2d_array_v2i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v2i32.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v2i32_trap">;
+def int_nvvm_sust_b_2d_array_v2i64_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i64_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v2i64.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v2i64_trap">;
+def int_nvvm_sust_b_2d_array_v4i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v4i8.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v4i8_trap">;
+def int_nvvm_sust_b_2d_array_v4i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v4i16.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v4i16_trap">;
+def int_nvvm_sust_b_2d_array_v4i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v4i32.trap">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v4i32_trap">;
+
+
+def int_nvvm_sust_b_3d_i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.i8.trap">,
+    GCCBuiltin<"__nvvm_sust_b_3d_i8_trap">;
+def int_nvvm_sust_b_3d_i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.i16.trap">,
+    GCCBuiltin<"__nvvm_sust_b_3d_i16_trap">;
+def int_nvvm_sust_b_3d_i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.3d.i32.trap">,
+    GCCBuiltin<"__nvvm_sust_b_3d_i32_trap">;
+def int_nvvm_sust_b_3d_i64_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.3d.i64.trap">,
+    GCCBuiltin<"__nvvm_sust_b_3d_i64_trap">;
+def int_nvvm_sust_b_3d_v2i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.v2i8.trap">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v2i8_trap">;
+def int_nvvm_sust_b_3d_v2i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.v2i16.trap">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v2i16_trap">;
+def int_nvvm_sust_b_3d_v2i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.3d.v2i32.trap">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v2i32_trap">;
+def int_nvvm_sust_b_3d_v2i64_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i64_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.3d.v2i64.trap">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v2i64_trap">;
+def int_nvvm_sust_b_3d_v4i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.v4i8.trap">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v4i8_trap">;
+def int_nvvm_sust_b_3d_v4i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.v4i16.trap">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v4i16_trap">;
+def int_nvvm_sust_b_3d_v4i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.3d.v4i32.trap">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v4i32_trap">;
+
+
+// .zero variant
+def int_nvvm_sust_b_1d_i8_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.i8.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_i8_zero">;
+def int_nvvm_sust_b_1d_i16_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.i16.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_i16_zero">;
+def int_nvvm_sust_b_1d_i32_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.i32.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_i32_zero">;
+def int_nvvm_sust_b_1d_i64_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.1d.i64.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_i64_zero">;
+def int_nvvm_sust_b_1d_v2i8_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.v2i8.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v2i8_zero">;
+def int_nvvm_sust_b_1d_v2i16_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.v2i16.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v2i16_zero">;
+def int_nvvm_sust_b_1d_v2i32_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.v2i32.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v2i32_zero">;
+def int_nvvm_sust_b_1d_v2i64_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i64_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.1d.v2i64.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v2i64_zero">;
+def int_nvvm_sust_b_1d_v4i8_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.v4i8.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v4i8_zero">;
+def int_nvvm_sust_b_1d_v4i16_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.v4i16.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v4i16_zero">;
+def int_nvvm_sust_b_1d_v4i32_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.v4i32.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_v4i32_zero">;
+
+
+def int_nvvm_sust_b_1d_array_i8_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.i8.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_i8_zero">;
+def int_nvvm_sust_b_1d_array_i16_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.i16.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_i16_zero">;
+def int_nvvm_sust_b_1d_array_i32_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.array.i32.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_i32_zero">;
+def int_nvvm_sust_b_1d_array_i64_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.1d.array.i64.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_i64_zero">;
+def int_nvvm_sust_b_1d_array_v2i8_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v2i8.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v2i8_zero">;
+def int_nvvm_sust_b_1d_array_v2i16_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v2i16.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v2i16_zero">;
+def int_nvvm_sust_b_1d_array_v2i32_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v2i32.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v2i32_zero">;
+def int_nvvm_sust_b_1d_array_v2i64_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i64_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v2i64.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v2i64_zero">;
+def int_nvvm_sust_b_1d_array_v4i8_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v4i8.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v4i8_zero">;
+def int_nvvm_sust_b_1d_array_v4i16_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v4i16.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v4i16_zero">;
+def int_nvvm_sust_b_1d_array_v4i32_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.1d.array.v4i32.zero">,
+    GCCBuiltin<"__nvvm_sust_b_1d_array_v4i32_zero">;
+
+
+def int_nvvm_sust_b_2d_i8_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.i8.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_i8_zero">;
+def int_nvvm_sust_b_2d_i16_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.i16.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_i16_zero">;
+def int_nvvm_sust_b_2d_i32_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.i32.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_i32_zero">;
+def int_nvvm_sust_b_2d_i64_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.2d.i64.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_i64_zero">;
+def int_nvvm_sust_b_2d_v2i8_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.v2i8.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v2i8_zero">;
+def int_nvvm_sust_b_2d_v2i16_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.v2i16.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v2i16_zero">;
+def int_nvvm_sust_b_2d_v2i32_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.v2i32.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v2i32_zero">;
+def int_nvvm_sust_b_2d_v2i64_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i64_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.2d.v2i64.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v2i64_zero">;
+def int_nvvm_sust_b_2d_v4i8_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.v4i8.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v4i8_zero">;
+def int_nvvm_sust_b_2d_v4i16_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.v4i16.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v4i16_zero">;
+def int_nvvm_sust_b_2d_v4i32_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.v4i32.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_v4i32_zero">;
+
+
+def int_nvvm_sust_b_2d_array_i8_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.i8.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_i8_zero">;
+def int_nvvm_sust_b_2d_array_i16_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.i16.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_i16_zero">;
+def int_nvvm_sust_b_2d_array_i32_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.array.i32.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_i32_zero">;
+def int_nvvm_sust_b_2d_array_i64_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.2d.array.i64.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_i64_zero">;
+def int_nvvm_sust_b_2d_array_v2i8_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v2i8.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v2i8_zero">;
+def int_nvvm_sust_b_2d_array_v2i16_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v2i16.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v2i16_zero">;
+def int_nvvm_sust_b_2d_array_v2i32_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v2i32.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v2i32_zero">;
+def int_nvvm_sust_b_2d_array_v2i64_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i64_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v2i64.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v2i64_zero">;
+def int_nvvm_sust_b_2d_array_v4i8_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v4i8.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v4i8_zero">;
+def int_nvvm_sust_b_2d_array_v4i16_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v4i16.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v4i16_zero">;
+def int_nvvm_sust_b_2d_array_v4i32_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.2d.array.v4i32.zero">,
+    GCCBuiltin<"__nvvm_sust_b_2d_array_v4i32_zero">;
+
+
+def int_nvvm_sust_b_3d_i8_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.i8.zero">,
+    GCCBuiltin<"__nvvm_sust_b_3d_i8_zero">;
+def int_nvvm_sust_b_3d_i16_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.i16.zero">,
+    GCCBuiltin<"__nvvm_sust_b_3d_i16_zero">;
+def int_nvvm_sust_b_3d_i32_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.3d.i32.zero">,
+    GCCBuiltin<"__nvvm_sust_b_3d_i32_zero">;
+def int_nvvm_sust_b_3d_i64_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.3d.i64.zero">,
+    GCCBuiltin<"__nvvm_sust_b_3d_i64_zero">;
+def int_nvvm_sust_b_3d_v2i8_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.v2i8.zero">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v2i8_zero">;
+def int_nvvm_sust_b_3d_v2i16_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.v2i16.zero">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v2i16_zero">;
+def int_nvvm_sust_b_3d_v2i32_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.3d.v2i32.zero">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v2i32_zero">;
+def int_nvvm_sust_b_3d_v2i64_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i64_ty, llvm_i64_ty], [],
+              "llvm.nvvm.sust.b.3d.v2i64.zero">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v2i64_zero">;
+def int_nvvm_sust_b_3d_v4i8_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.v4i8.zero">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v4i8_zero">;
+def int_nvvm_sust_b_3d_v4i16_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.b.3d.v4i16.zero">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v4i16_zero">;
+def int_nvvm_sust_b_3d_v4i32_zero
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.b.3d.v4i32.zero">,
+    GCCBuiltin<"__nvvm_sust_b_3d_v4i32_zero">;
+
+
+
+// Formatted
+
+def int_nvvm_sust_p_1d_i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.1d.i8.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_i8_trap">;
+def int_nvvm_sust_p_1d_i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.1d.i16.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_i16_trap">;
+def int_nvvm_sust_p_1d_i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.p.1d.i32.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_i32_trap">;
+def int_nvvm_sust_p_1d_v2i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.1d.v2i8.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_v2i8_trap">;
+def int_nvvm_sust_p_1d_v2i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.1d.v2i16.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_v2i16_trap">;
+def int_nvvm_sust_p_1d_v2i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.p.1d.v2i32.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_v2i32_trap">;
+def int_nvvm_sust_p_1d_v4i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.1d.v4i8.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_v4i8_trap">;
+def int_nvvm_sust_p_1d_v4i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.1d.v4i16.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_v4i16_trap">;
+def int_nvvm_sust_p_1d_v4i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.p.1d.v4i32.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_v4i32_trap">;
+
+
+def int_nvvm_sust_p_1d_array_i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.1d.array.i8.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_array_i8_trap">;
+def int_nvvm_sust_p_1d_array_i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.1d.array.i16.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_array_i16_trap">;
+def int_nvvm_sust_p_1d_array_i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.p.1d.array.i32.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_array_i32_trap">;
+def int_nvvm_sust_p_1d_array_v2i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.1d.array.v2i8.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_array_v2i8_trap">;
+def int_nvvm_sust_p_1d_array_v2i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.1d.array.v2i16.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_array_v2i16_trap">;
+def int_nvvm_sust_p_1d_array_v2i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.p.1d.array.v2i32.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_array_v2i32_trap">;
+def int_nvvm_sust_p_1d_array_v4i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.1d.array.v4i8.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_array_v4i8_trap">;
+def int_nvvm_sust_p_1d_array_v4i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.1d.array.v4i16.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_array_v4i16_trap">;
+def int_nvvm_sust_p_1d_array_v4i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.p.1d.array.v4i32.trap">,
+    GCCBuiltin<"__nvvm_sust_p_1d_array_v4i32_trap">;
+
+
+def int_nvvm_sust_p_2d_i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.2d.i8.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_i8_trap">;
+def int_nvvm_sust_p_2d_i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.2d.i16.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_i16_trap">;
+def int_nvvm_sust_p_2d_i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.p.2d.i32.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_i32_trap">;
+def int_nvvm_sust_p_2d_v2i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.2d.v2i8.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_v2i8_trap">;
+def int_nvvm_sust_p_2d_v2i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.2d.v2i16.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_v2i16_trap">;
+def int_nvvm_sust_p_2d_v2i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.p.2d.v2i32.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_v2i32_trap">;
+def int_nvvm_sust_p_2d_v4i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.2d.v4i8.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_v4i8_trap">;
+def int_nvvm_sust_p_2d_v4i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i16_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.2d.v4i16.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_v4i16_trap">;
+def int_nvvm_sust_p_2d_v4i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.p.2d.v4i32.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_v4i32_trap">;
+
+
+def int_nvvm_sust_p_2d_array_i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.2d.array.i8.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_array_i8_trap">;
+def int_nvvm_sust_p_2d_array_i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.2d.array.i16.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_array_i16_trap">;
+def int_nvvm_sust_p_2d_array_i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.p.2d.array.i32.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_array_i32_trap">;
+def int_nvvm_sust_p_2d_array_v2i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.2d.array.v2i8.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_array_v2i8_trap">;
+def int_nvvm_sust_p_2d_array_v2i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.2d.array.v2i16.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_array_v2i16_trap">;
+def int_nvvm_sust_p_2d_array_v2i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.p.2d.array.v2i32.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_array_v2i32_trap">;
+def int_nvvm_sust_p_2d_array_v4i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.2d.array.v4i8.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_array_v4i8_trap">;
+def int_nvvm_sust_p_2d_array_v4i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.2d.array.v4i16.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_array_v4i16_trap">;
+def int_nvvm_sust_p_2d_array_v4i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.p.2d.array.v4i32.trap">,
+    GCCBuiltin<"__nvvm_sust_p_2d_array_v4i32_trap">;
+
+
+def int_nvvm_sust_p_3d_i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.3d.i8.trap">,
+    GCCBuiltin<"__nvvm_sust_p_3d_i8_trap">;
+def int_nvvm_sust_p_3d_i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.3d.i16.trap">,
+    GCCBuiltin<"__nvvm_sust_p_3d_i16_trap">;
+def int_nvvm_sust_p_3d_i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.p.3d.i32.trap">,
+    GCCBuiltin<"__nvvm_sust_p_3d_i32_trap">;
+def int_nvvm_sust_p_3d_v2i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.3d.v2i8.trap">,
+    GCCBuiltin<"__nvvm_sust_p_3d_v2i8_trap">;
+def int_nvvm_sust_p_3d_v2i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.3d.v2i16.trap">,
+    GCCBuiltin<"__nvvm_sust_p_3d_v2i16_trap">;
+def int_nvvm_sust_p_3d_v2i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.p.3d.v2i32.trap">,
+    GCCBuiltin<"__nvvm_sust_p_3d_v2i32_trap">;
+def int_nvvm_sust_p_3d_v4i8_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.3d.v4i8.trap">,
+    GCCBuiltin<"__nvvm_sust_p_3d_v4i8_trap">;
+def int_nvvm_sust_p_3d_v4i16_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i16_ty, llvm_i16_ty, llvm_i16_ty, llvm_i16_ty], [],
+              "llvm.nvvm.sust.p.3d.v4i16.trap">,
+    GCCBuiltin<"__nvvm_sust_p_3d_v4i16_trap">;
+def int_nvvm_sust_p_3d_v4i32_trap
+  : Intrinsic<[], [llvm_i64_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
+                   llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [],
+              "llvm.nvvm.sust.p.3d.v4i32.trap">,
+    GCCBuiltin<"__nvvm_sust_p_3d_v4i32_trap">;
+
+
+def int_nvvm_rotate_b32
+  : Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty],
+              [IntrNoMem], "llvm.nvvm.rotate.b32">,
+              GCCBuiltin<"__nvvm_rotate_b32">;
+
+def int_nvvm_rotate_b64
+  :Intrinsic<[llvm_i64_ty], [llvm_i64_ty, llvm_i32_ty],
+             [IntrNoMem], "llvm.nvvm.rotate.b64">,
+             GCCBuiltin<"__nvvm_rotate_b64">;
+
+def int_nvvm_rotate_right_b64
+  : Intrinsic<[llvm_i64_ty], [llvm_i64_ty, llvm_i32_ty],
+              [IntrNoMem], "llvm.nvvm.rotate.right.b64">,
+              GCCBuiltin<"__nvvm_rotate_right_b64">;
+
+def int_nvvm_swap_lo_hi_b64
+  : Intrinsic<[llvm_i64_ty], [llvm_i64_ty],
+              [IntrNoMem], "llvm.nvvm.swap.lo.hi.b64">,
+              GCCBuiltin<"__nvvm_swap_lo_hi_b64">;
+
+
+// Accessing special registers.
+multiclass PTXReadSRegIntrinsic_v4i32<string regname> {
+// FIXME: Do we need the 128-bit integer type version?
+//    def _r64   : Intrinsic<[llvm_i128_ty],   [], [IntrNoMem]>;
+
+// FIXME: Enable this once v4i32 support is enabled in back-end.
+//    def _v4i16 : Intrinsic<[llvm_v4i32_ty], [], [IntrNoMem]>;
+
+  def _x     : Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
+               GCCBuiltin<"__nvvm_read_ptx_sreg_" # regname # "_x">;
+  def _y     : Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
+               GCCBuiltin<"__nvvm_read_ptx_sreg_" # regname # "_y">;
+  def _z     : Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
+               GCCBuiltin<"__nvvm_read_ptx_sreg_" # regname # "_z">;
+  def _w     : Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
+               GCCBuiltin<"__nvvm_read_ptx_sreg_" # regname # "_w">;
+}
+
+class PTXReadSRegIntrinsic_r32<string name>
+  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_" # name>;
+
+class PTXReadSRegIntrinsic_r64<string name>
+  : Intrinsic<[llvm_i64_ty], [], [IntrNoMem]>,
+    GCCBuiltin<"__nvvm_read_ptx_sreg_" # name>;
+
+defm int_nvvm_read_ptx_sreg_tid : PTXReadSRegIntrinsic_v4i32<"tid">;
+defm int_nvvm_read_ptx_sreg_ntid : PTXReadSRegIntrinsic_v4i32<"ntid">;
+
+def int_nvvm_read_ptx_sreg_laneid : PTXReadSRegIntrinsic_r32<"laneid">;
+def int_nvvm_read_ptx_sreg_warpid : PTXReadSRegIntrinsic_r32<"warpid">;
+def int_nvvm_read_ptx_sreg_nwarpid : PTXReadSRegIntrinsic_r32<"nwarpid">;
+
+defm int_nvvm_read_ptx_sreg_ctaid : PTXReadSRegIntrinsic_v4i32<"ctaid">;
+defm int_nvvm_read_ptx_sreg_nctaid : PTXReadSRegIntrinsic_v4i32<"nctaid">;
+
+def int_nvvm_read_ptx_sreg_smid : PTXReadSRegIntrinsic_r32<"smid">;
+def int_nvvm_read_ptx_sreg_nsmid : PTXReadSRegIntrinsic_r32<"nsmid">;
+def int_nvvm_read_ptx_sreg_gridid : PTXReadSRegIntrinsic_r32<"gridid">;
+
+def int_nvvm_read_ptx_sreg_lanemask_eq :
+    PTXReadSRegIntrinsic_r32<"lanemask_eq">;
+def int_nvvm_read_ptx_sreg_lanemask_le :
+    PTXReadSRegIntrinsic_r32<"lanemask_le">;
+def int_nvvm_read_ptx_sreg_lanemask_lt :
+    PTXReadSRegIntrinsic_r32<"lanemask_lt">;
+def int_nvvm_read_ptx_sreg_lanemask_ge :
+    PTXReadSRegIntrinsic_r32<"lanemask_ge">;
+def int_nvvm_read_ptx_sreg_lanemask_gt :
+    PTXReadSRegIntrinsic_r32<"lanemask_gt">;
+
+def int_nvvm_read_ptx_sreg_clock : PTXReadSRegIntrinsic_r32<"clock">;
+def int_nvvm_read_ptx_sreg_clock64 : PTXReadSRegIntrinsic_r64<"clock64">;
+
+def int_nvvm_read_ptx_sreg_pm0 : PTXReadSRegIntrinsic_r32<"pm0">;
+def int_nvvm_read_ptx_sreg_pm1 : PTXReadSRegIntrinsic_r32<"pm1">;
+def int_nvvm_read_ptx_sreg_pm2 : PTXReadSRegIntrinsic_r32<"pm2">;
+def int_nvvm_read_ptx_sreg_pm3 : PTXReadSRegIntrinsic_r32<"pm3">;
+
+def int_nvvm_read_ptx_sreg_warpsize : PTXReadSRegIntrinsic_r32<"warpsize">;
+
+//
+// SHUFFLE
+//
+
+// shfl.down.b32 dest, val, offset, mask_and_clamp
+def int_nvvm_shfl_down_i32 :
+  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.shfl.down.i32">,
+  GCCBuiltin<"__nvvm_shfl_down_i32">;
+def int_nvvm_shfl_down_f32 :
+  Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.shfl.down.f32">,
+  GCCBuiltin<"__nvvm_shfl_down_f32">;
+
+// shfl.up.b32 dest, val, offset, mask_and_clamp
+def int_nvvm_shfl_up_i32 :
+  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.shfl.up.i32">,
+  GCCBuiltin<"__nvvm_shfl_up_i32">;
+def int_nvvm_shfl_up_f32 :
+  Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.shfl.up.f32">,
+  GCCBuiltin<"__nvvm_shfl_up_f32">;
+
+// shfl.bfly.b32 dest, val, offset, mask_and_clamp
+def int_nvvm_shfl_bfly_i32 :
+  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.shfl.bfly.i32">,
+  GCCBuiltin<"__nvvm_shfl_bfly_i32">;
+def int_nvvm_shfl_bfly_f32 :
+  Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.shfl.bfly.f32">,
+  GCCBuiltin<"__nvvm_shfl_bfly_f32">;
+
+// shfl.idx.b32 dest, val, lane, mask_and_clamp
+def int_nvvm_shfl_idx_i32 :
+  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.shfl.idx.i32">,
+  GCCBuiltin<"__nvvm_shfl_idx_i32">;
+def int_nvvm_shfl_idx_f32 :
+  Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.shfl.idx.f32">,
+  GCCBuiltin<"__nvvm_shfl_idx_f32">;
+
+// Synchronizing shfl variants available in CUDA-9.
+// On sm_70 these don't have to be convergent, so we may eventually want to
+// implement non-convergent variant of this intrinsic.
+
+// shfl.sync.down.b32 dest, threadmask, val, offset , mask_and_clamp
+def int_nvvm_shfl_sync_down_i32 :
+  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.shfl.sync.down.i32">,
+  GCCBuiltin<"__nvvm_shfl_sync_down_i32">;
+def int_nvvm_shfl_sync_down_f32 :
+  Intrinsic<[llvm_float_ty], [llvm_i32_ty, llvm_float_ty, llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.shfl.sync.down.f32">,
+  GCCBuiltin<"__nvvm_shfl_sync_down_f32">;
+
+// shfl.sync.up.b32 dest, threadmask, val, offset, mask_and_clamp
+def int_nvvm_shfl_sync_up_i32 :
+  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.shfl.sync.up.i32">,
+  GCCBuiltin<"__nvvm_shfl_sync_up_i32">;
+def int_nvvm_shfl_sync_up_f32 :
+  Intrinsic<[llvm_float_ty], [llvm_i32_ty, llvm_float_ty, llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.shfl.sync.up.f32">,
+  GCCBuiltin<"__nvvm_shfl_sync_up_f32">;
+
+// shfl.sync.bfly.b32 dest, threadmask, val, offset, mask_and_clamp
+def int_nvvm_shfl_sync_bfly_i32 :
+  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.shfl.sync.bfly.i32">,
+  GCCBuiltin<"__nvvm_shfl_sync_bfly_i32">;
+def int_nvvm_shfl_sync_bfly_f32 :
+  Intrinsic<[llvm_float_ty], [llvm_i32_ty, llvm_float_ty, llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.shfl.sync.bfly.f32">,
+  GCCBuiltin<"__nvvm_shfl_sync_bfly_f32">;
+
+// shfl.sync.idx.b32 dest, threadmask, val, lane, mask_and_clamp
+def int_nvvm_shfl_sync_idx_i32 :
+  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.shfl.sync.idx.i32">,
+  GCCBuiltin<"__nvvm_shfl_sync_idx_i32">;
+def int_nvvm_shfl_sync_idx_f32 :
+  Intrinsic<[llvm_float_ty], [llvm_i32_ty, llvm_float_ty, llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.shfl.sync.idx.f32">,
+  GCCBuiltin<"__nvvm_shfl_sync_idx_f32">;
+
+//
+// VOTE
+//
+
+// vote.all pred
+def int_nvvm_vote_all :
+  Intrinsic<[llvm_i1_ty], [llvm_i1_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.vote.all">,
+  GCCBuiltin<"__nvvm_vote_all">;
+// vote.any pred
+def int_nvvm_vote_any :
+  Intrinsic<[llvm_i1_ty], [llvm_i1_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.vote.any">,
+  GCCBuiltin<"__nvvm_vote_any">;
+// vote.uni pred
+def int_nvvm_vote_uni :
+  Intrinsic<[llvm_i1_ty], [llvm_i1_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.vote.uni">,
+  GCCBuiltin<"__nvvm_vote_uni">;
+// vote.ballot pred
+def int_nvvm_vote_ballot :
+  Intrinsic<[llvm_i32_ty], [llvm_i1_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.vote.ballot">,
+  GCCBuiltin<"__nvvm_vote_ballot">;
+
+//
+// VOTE.SYNC
+//
+
+// vote.sync.all mask, pred
+def int_nvvm_vote_all_sync :
+  Intrinsic<[llvm_i1_ty], [llvm_i32_ty, llvm_i1_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.vote.all.sync">,
+  GCCBuiltin<"__nvvm_vote_all_sync">;
+// vote.sync.any mask, pred
+def int_nvvm_vote_any_sync :
+  Intrinsic<[llvm_i1_ty], [llvm_i32_ty, llvm_i1_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.vote.any.sync">,
+  GCCBuiltin<"__nvvm_vote_any_sync">;
+// vote.sync.uni mask, pred
+def int_nvvm_vote_uni_sync :
+  Intrinsic<[llvm_i1_ty], [llvm_i32_ty, llvm_i1_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.vote.uni.sync">,
+  GCCBuiltin<"__nvvm_vote_uni_sync">;
+// vote.sync.ballot mask, pred
+def int_nvvm_vote_ballot_sync :
+  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i1_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.vote.ballot.sync">,
+  GCCBuiltin<"__nvvm_vote_ballot_sync">;
+
+//
+// MATCH.SYNC
+//
+// match.any.sync.b32 mask, value
+def int_nvvm_match_any_sync_i32 :
+  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.match.any.sync.i32">,
+  GCCBuiltin<"__nvvm_match_any_sync_i32">;
+// match.any.sync.b64 mask, value
+def int_nvvm_match_any_sync_i64 :
+  Intrinsic<[llvm_i64_ty], [llvm_i32_ty, llvm_i64_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.match.any.sync.i64">,
+  GCCBuiltin<"__nvvm_match_any_sync_i64">;
+
+// match.all instruction have two variants -- one returns a single value, another
+// returns a pair {value, predicate}. We currently only implement the latter as
+// that's the variant exposed by CUDA API.
+
+// match.all.sync.b32p mask, value
+def int_nvvm_match_all_sync_i32p :
+  Intrinsic<[llvm_i32_ty, llvm_i1_ty], [llvm_i32_ty, llvm_i32_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.match.all.sync.i32p">;
+// match.all.sync.b64p mask, value
+def int_nvvm_match_all_sync_i64p :
+  Intrinsic<[llvm_i64_ty, llvm_i1_ty], [llvm_i32_ty, llvm_i64_ty],
+            [IntrInaccessibleMemOnly, IntrConvergent], "llvm.nvvm.match.all.sync.i64p">;
+
+//
+// WMMA instructions
+//
+
+// WMMA.LOAD
+class NVVM_WMMA_LD_GALSTS<string Geometry, string Abc, string Layout,
+                          string Type, LLVMType regty, int WithStride>
+  : Intrinsic<!if(!eq(Abc#Type,"cf16"),
+                  [regty, regty, regty, regty],
+                  [regty, regty, regty, regty,
+                   regty, regty, regty, regty]),
+              !if(WithStride, [llvm_anyptr_ty, llvm_i32_ty], [llvm_anyptr_ty]),
+              [IntrReadMem, IntrArgMemOnly, ReadOnly<0>, NoCapture<0>],
+              "llvm.nvvm.wmma."
+                # Geometry
+                # ".load"
+                # "." # Abc
+                # "." # Layout
+                # !if(WithStride, ".stride", "")
+                # "." # Type>;
+
+multiclass NVVM_WMMA_LD_GALT<string Geometry, string Abc, string Layout,
+                             string Type, LLVMType regty> {
+  def _stride: NVVM_WMMA_LD_GALSTS<Geometry, Abc, Layout, Type, regty, 1>;
+  def NAME   : NVVM_WMMA_LD_GALSTS<Geometry, Abc, Layout, Type, regty, 0>;
+}
+
+multiclass NVVM_WMMA_LD_GAT<string Geometry, string Abc,
+                           string Type, LLVMType regty> {
+  defm _row: NVVM_WMMA_LD_GALT<Geometry, Abc, "row", Type, regty>;
+  defm _col: NVVM_WMMA_LD_GALT<Geometry, Abc, "col", Type, regty>;
+}
+
+multiclass NVVM_WMMA_LD_G<string Geometry> {
+  defm _a_f16: NVVM_WMMA_LD_GAT<Geometry, "a", "f16", llvm_v2f16_ty>;
+  defm _b_f16: NVVM_WMMA_LD_GAT<Geometry, "b", "f16", llvm_v2f16_ty>;
+  defm _c_f16: NVVM_WMMA_LD_GAT<Geometry, "c", "f16", llvm_v2f16_ty>;
+  defm _c_f32: NVVM_WMMA_LD_GAT<Geometry, "c", "f32", llvm_float_ty>;
+}
+
+multiclass NVVM_WMMA_LD {
+  defm _m32n8k16_load: NVVM_WMMA_LD_G<"m32n8k16">;
+  defm _m16n16k16_load: NVVM_WMMA_LD_G<"m16n16k16">;
+  defm _m8n32k16_load: NVVM_WMMA_LD_G<"m8n32k16">;
+}
+
+defm int_nvvm_wmma: NVVM_WMMA_LD;
+
+// WMMA.STORE.D
+class NVVM_WMMA_STD_GLSTS<string Geometry, string Layout,
+                          string Type, LLVMType regty, int WithStride,
+                          // This is only used to create a typed empty array we
+                          // need to pass to !if below.
+                          list<LLVMType>Empty=[]>
+  : Intrinsic<[],
+              !listconcat(
+                [llvm_anyptr_ty],
+                !if(!eq(Type,"f16"),
+                    [regty, regty, regty, regty],
+                    [regty, regty, regty, regty,
+                     regty, regty, regty, regty]),
+                !if(WithStride, [llvm_i32_ty], Empty)),
+              [IntrWriteMem, IntrArgMemOnly, WriteOnly<0>, NoCapture<0>],
+              "llvm.nvvm.wmma."
+                   # Geometry
+                   # ".store.d"
+                   # "." # Layout
+                   # !if(WithStride, ".stride", "")
+                   # "." # Type>;
+
+multiclass NVVM_WMMA_STD_GLT<string Geometry, string Layout,
+                             string Type, LLVMType regty> {
+  def _stride: NVVM_WMMA_STD_GLSTS<Geometry, Layout, Type, regty, 1>;
+  def NAME:    NVVM_WMMA_STD_GLSTS<Geometry, Layout, Type, regty, 0>;
+}
+
+multiclass NVVM_WMMA_STD_GT<string Geometry, string Type, LLVMType regty> {
+  defm _row: NVVM_WMMA_STD_GLT<Geometry, "row", Type, regty>;
+  defm _col: NVVM_WMMA_STD_GLT<Geometry, "col", Type, regty>;
+}
+multiclass NVVM_WMMA_STD_G<string Geometry> {
+  defm _d_f16: NVVM_WMMA_STD_GT<Geometry, "f16", llvm_v2f16_ty>;
+  defm _d_f32: NVVM_WMMA_STD_GT<Geometry, "f32", llvm_float_ty>;
+}
+
+multiclass NVVM_WMMA_STD {
+  defm _m32n8k16_store:  NVVM_WMMA_STD_G<"m32n8k16">;
+  defm _m16n16k16_store: NVVM_WMMA_STD_G<"m16n16k16">;
+  defm _m8n32k16_store:  NVVM_WMMA_STD_G<"m8n32k16">;
+}
+
+defm int_nvvm_wmma: NVVM_WMMA_STD;
+
+// WMMA.MMA
+class NVVM_WMMA_MMA_GABDCS<string Geometry,
+                           string ALayout, string BLayout,
+                           string DType, LLVMType d_regty,
+                           string CType, LLVMType c_regty,
+                           string Satfinite = "">
+  : Intrinsic<!if(!eq(DType,"f16"),
+                      [d_regty, d_regty, d_regty, d_regty],
+                      [d_regty, d_regty, d_regty, d_regty,
+                       d_regty, d_regty, d_regty, d_regty]),
+              !listconcat(
+                [// A
+                llvm_v2f16_ty, llvm_v2f16_ty, llvm_v2f16_ty, llvm_v2f16_ty,
+                llvm_v2f16_ty, llvm_v2f16_ty, llvm_v2f16_ty, llvm_v2f16_ty,
+                // B
+                llvm_v2f16_ty, llvm_v2f16_ty, llvm_v2f16_ty, llvm_v2f16_ty,
+                llvm_v2f16_ty, llvm_v2f16_ty, llvm_v2f16_ty, llvm_v2f16_ty],
+                !if(!eq(CType,"f16"),
+                      [c_regty, c_regty, c_regty, c_regty],
+                      [c_regty, c_regty, c_regty, c_regty,
+                       c_regty, c_regty, c_regty, c_regty])),
+              [IntrNoMem],
+              "llvm.nvvm.wmma."
+                # Geometry
+                # ".mma"
+                # "." # ALayout
+                # "." # BLayout
+                # "." # DType
+                # "." # CType
+                # Satfinite> {
+}
+
+multiclass NVVM_WMMA_MMA_GABDC<string Geometry, string ALayout, string BLayout,
+                               string DType, LLVMType d_regty,
+                               string CType, LLVMType c_regty> {
+  def NAME : NVVM_WMMA_MMA_GABDCS<Geometry, ALayout, BLayout,
+                                  DType, d_regty, CType, c_regty>;
+  def _satfinite: NVVM_WMMA_MMA_GABDCS<Geometry, ALayout, BLayout,
+                                       DType, d_regty, CType, c_regty,".satfinite">;
+}
+
+multiclass NVVM_WMMA_MMA_GABD<string Geometry, string ALayout, string BLayout,
+                              string DType, LLVMType d_regty> {
+  defm _f16: NVVM_WMMA_MMA_GABDC<Geometry, ALayout, BLayout, DType, d_regty,
+                                "f16", llvm_v2f16_ty>;
+  defm _f32: NVVM_WMMA_MMA_GABDC<Geometry, ALayout, BLayout, DType, d_regty,
+                                "f32", llvm_float_ty>;
+}
+
+multiclass NVVM_WMMA_MMA_GAB<string Geometry, string ALayout, string BLayout> {
+  defm _f16: NVVM_WMMA_MMA_GABD<Geometry, ALayout, BLayout, "f16", llvm_v2f16_ty>;
+  defm _f32: NVVM_WMMA_MMA_GABD<Geometry, ALayout, BLayout, "f32", llvm_float_ty>;
+}
+
+multiclass NVVM_WMMA_MMA_GA<string Geometry, string ALayout> {
+  defm _col: NVVM_WMMA_MMA_GAB<Geometry, ALayout, "col">;
+  defm _row: NVVM_WMMA_MMA_GAB<Geometry, ALayout, "row">;
+}
+
+multiclass NVVM_WMMA_MMA_G<string Geometry> {
+  defm _col: NVVM_WMMA_MMA_GA<Geometry, "col">;
+  defm _row: NVVM_WMMA_MMA_GA<Geometry, "row">;
+}
+
+multiclass NVVM_WMMA_MMA {
+  defm _m32n8k16_mma : NVVM_WMMA_MMA_G<"m32n8k16">;
+  defm _m16n16k16_mma : NVVM_WMMA_MMA_G<"m16n16k16">;
+  defm _m8n32k16_mma : NVVM_WMMA_MMA_G<"m8n32k16">;
+}
+
+defm int_nvvm_wmma : NVVM_WMMA_MMA;
+
+} // let TargetPrefix = "nvvm"