[NVPTX] Add preliminary intrinsics and codegen support for textures/surfaces

This commit adds intrinsics and codegen support for the surface read/write and texture read instructions that take an explicit sampler parameter. Codegen operates on image handles at the PTX level, but falls back to direct replacement of handles with kernel arguments if image handles are not enabled. Note that image handles are explicitly disabled for all target architectures in this change (to be enabled later).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205907 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 920 insertions, 0 deletions

diff --git a/include/llvm/IR/IntrinsicsNVVM.td b/include/llvm/IR/IntrinsicsNVVM.td
index 7f72ce8b66..26dc70acfd 100644
--- a/include/llvm/IR/IntrinsicsNVVM.td
+++ b/include/llvm/IR/IntrinsicsNVVM.td
@@ -875,6 +875,14 @@ 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">;
@@ -882,6 +890,918 @@ def int_nvvm_compiler_warn :
     Intrinsic<[], [llvm_anyptr_ty], [], "llvm.nvvm.compiler.warn">;
 
 
+// Texture Fetch
+def int_nvvm_tex_1d_v4f32_i32
+  : 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.i32">;
+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_v4i32_i32
+  : 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.v4i32.i32">;
+def int_nvvm_tex_1d_v4i32_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.v4i32.f32">;
+def int_nvvm_tex_1d_level_v4i32_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.v4i32.f32.level">;
+def int_nvvm_tex_1d_grad_v4i32_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.v4i32.f32">;
+
+def int_nvvm_tex_1d_array_v4f32_i32
+  : 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.i32">;
+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_v4i32_i32
+  : 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.v4i32.i32">;
+def int_nvvm_tex_1d_array_v4i32_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.v4i32.f32">;
+def int_nvvm_tex_1d_array_level_v4i32_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.v4i32.f32">;
+def int_nvvm_tex_1d_array_grad_v4i32_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.v4i32.f32">;
+
+def int_nvvm_tex_2d_v4f32_i32
+  : 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.i32">;
+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_v4i32_i32
+  : 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.v4i32.i32">;
+def int_nvvm_tex_2d_v4i32_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.v4i32.f32">;
+def int_nvvm_tex_2d_level_v4i32_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.v4i32.f32">;
+def int_nvvm_tex_2d_grad_v4i32_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.v4i32.f32">;
+
+def int_nvvm_tex_2d_array_v4f32_i32
+  : 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.i32">;
+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_v4i32_i32
+  : 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.v4i32.i32">;
+def int_nvvm_tex_2d_array_v4i32_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.v4i32.f32">;
+def int_nvvm_tex_2d_array_level_v4i32_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.v4i32.f32">;
+def int_nvvm_tex_2d_array_grad_v4i32_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.v4i32.f32">;
+
+def int_nvvm_tex_3d_v4f32_i32
+  : 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.i32">;
+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_v4i32_i32
+  : 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.v4i32.i32">;
+def int_nvvm_tex_3d_v4i32_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.v4i32.f32">;
+def int_nvvm_tex_3d_level_v4i32_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.v4i32.f32">;
+def int_nvvm_tex_3d_grad_v4i32_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.v4i32.f32">;
+
+// Surface Load
+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_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_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_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_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_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_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_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_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_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_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">;
+
+//===- 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
+
+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_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_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_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_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_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_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_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_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_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_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">;
+
+// 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">;
+
+
+
 // Old PTX back-end intrinsics retained here for backwards-compatibility
 
 multiclass PTXReadSpecialRegisterIntrinsic_v4i32<string prefix> {