X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=include%2Fllvm%2FIR%2FIntrinsicsNVVM.td;h=9deed414b50a03ac293e04810523946b49ecbb57;hb=2b762697564ca1e12e0e974e93ceeb4c3420505c;hp=26dc70acfd3ef04b8f9b146b86a089924f7297ca;hpb=77f268945e4d4b777102d4a2089cb86137042883;p=oota-llvm.git

diff --git a/include/llvm/IR/IntrinsicsNVVM.td b/include/llvm/IR/IntrinsicsNVVM.td
index 26dc70acfd3..9deed414b50 100644
--- a/include/llvm/IR/IntrinsicsNVVM.td
+++ b/include/llvm/IR/IntrinsicsNVVM.td
@@ -796,26 +796,31 @@ def llvm_anyi64ptr_ty     : LLVMAnyPointerType<llvm_i64_ty>;     // (space)i64*
 
 
 // Generated within nvvm. Use for ldu on sm_20 or later
-// @TODO: Revisit this, Changed LLVMAnyPointerType to LLVMPointerType
 def int_nvvm_ldu_global_i : Intrinsic<[llvm_anyint_ty],
-  [LLVMPointerType<LLVMMatchType<0>>], [IntrReadMem, NoCapture<0>],
+  [LLVMAnyPointerType<LLVMMatchType<0>>, llvm_i32_ty],
+  [IntrReadMem, NoCapture<0>],
   "llvm.nvvm.ldu.global.i">;
 def int_nvvm_ldu_global_f : Intrinsic<[llvm_anyfloat_ty],
-  [LLVMPointerType<LLVMMatchType<0>>], [IntrReadMem, NoCapture<0>],
+  [LLVMAnyPointerType<LLVMMatchType<0>>, llvm_i32_ty],
+  [IntrReadMem, NoCapture<0>],
   "llvm.nvvm.ldu.global.f">;
 def int_nvvm_ldu_global_p : Intrinsic<[llvm_anyptr_ty],
-  [LLVMPointerType<LLVMMatchType<0>>], [IntrReadMem, NoCapture<0>],
+  [LLVMAnyPointerType<LLVMMatchType<0>>, llvm_i32_ty],
+  [IntrReadMem, NoCapture<0>],
   "llvm.nvvm.ldu.global.p">;
 
 // Generated within nvvm. Use for ldg on sm_35 or later
 def int_nvvm_ldg_global_i : Intrinsic<[llvm_anyint_ty],
-  [LLVMPointerType<LLVMMatchType<0>>], [IntrReadMem, NoCapture<0>],
+  [LLVMAnyPointerType<LLVMMatchType<0>>, llvm_i32_ty],
+  [IntrReadMem, NoCapture<0>],
   "llvm.nvvm.ldg.global.i">;
 def int_nvvm_ldg_global_f : Intrinsic<[llvm_anyfloat_ty],
-  [LLVMPointerType<LLVMMatchType<0>>], [IntrReadMem, NoCapture<0>],
+  [LLVMAnyPointerType<LLVMMatchType<0>>, llvm_i32_ty],
+  [IntrReadMem, NoCapture<0>],
   "llvm.nvvm.ldg.global.f">;
 def int_nvvm_ldg_global_p : Intrinsic<[llvm_anyptr_ty],
-  [LLVMPointerType<LLVMMatchType<0>>], [IntrReadMem, NoCapture<0>],
+  [LLVMAnyPointerType<LLVMMatchType<0>>, llvm_i32_ty],
+  [IntrReadMem, NoCapture<0>],
   "llvm.nvvm.ldg.global.p">;
 
 // Use for generic pointers
@@ -889,12 +894,164 @@ def int_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
-def int_nvvm_tex_1d_v4f32_i32
+// 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.i32">;
+              "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], [],
@@ -908,28 +1065,45 @@ def int_nvvm_tex_1d_grad_v4f32_f32
               [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
+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.v4i32.i32">;
-def int_nvvm_tex_1d_v4i32_f32
+              "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.v4i32.f32">;
-def int_nvvm_tex_1d_level_v4i32_f32
+              "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.v4i32.f32.level">;
-def int_nvvm_tex_1d_grad_v4i32_f32
+              "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.v4i32.f32">;
+              "llvm.nvvm.tex.1d.grad.v4u32.f32">;
 
-def int_nvvm_tex_1d_array_v4f32_i32
+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.i32">;
+              "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], [],
@@ -944,29 +1118,47 @@ def int_nvvm_tex_1d_array_grad_v4f32_f32
               [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
+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.v4i32.i32">;
-def int_nvvm_tex_1d_array_v4i32_f32
+              "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.v4i32.f32">;
-def int_nvvm_tex_1d_array_level_v4i32_f32
+              "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.v4i32.f32">;
-def int_nvvm_tex_1d_array_grad_v4i32_f32
+              "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.v4i32.f32">;
+              "llvm.nvvm.tex.1d.array.grad.v4u32.f32">;
 
-def int_nvvm_tex_2d_v4f32_i32
+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.i32">;
+              "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], [],
@@ -981,30 +1173,48 @@ def int_nvvm_tex_2d_grad_v4f32_f32
               [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
+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.v4i32.i32">;
-def int_nvvm_tex_2d_v4i32_f32
+              "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.v4i32.f32">;
-def int_nvvm_tex_2d_level_v4i32_f32
+              "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.v4i32.f32">;
-def int_nvvm_tex_2d_grad_v4i32_f32
+              "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.v4i32.f32">;
+              "llvm.nvvm.tex.2d.grad.v4u32.f32">;
 
-def int_nvvm_tex_2d_array_v4f32_i32
+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.i32">;
+              "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,
@@ -1021,32 +1231,53 @@ def int_nvvm_tex_2d_array_grad_v4f32_f32
                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
+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.v4i32.i32">;
-def int_nvvm_tex_2d_array_v4i32_f32
+              "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.v4i32.f32">;
-def int_nvvm_tex_2d_array_level_v4i32_f32
+              "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.v4i32.f32">;
-def int_nvvm_tex_2d_array_grad_v4i32_f32
+              "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.v4i32.f32">;
+              "llvm.nvvm.tex.2d.array.grad.v4u32.f32">;
 
-def int_nvvm_tex_3d_v4f32_i32
+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.i32">;
+              [], "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,
@@ -1063,212 +1294,1237 @@ def int_nvvm_tex_3d_grad_v4f32_f32
                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
+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.v4i32.i32">;
-def int_nvvm_tex_3d_v4i32_f32
+              [], "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.v4i32.f32">;
-def int_nvvm_tex_3d_level_v4i32_f32
+              "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.v4i32.f32">;
-def int_nvvm_tex_3d_grad_v4i32_f32
+              "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.v4i32.f32">;
+              "llvm.nvvm.tex.3d.grad.v4u32.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],
+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.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.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.suld.1d.v4i16.trap">;
-def int_nvvm_suld_1d_v4i32_trap
+              "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.suld.1d.v4i32.trap">;
+              "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_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],
+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.suld.1d.array.v2i8.trap">;
-def int_nvvm_suld_1d_array_v2i16_trap
-  : Intrinsic<[llvm_i16_ty, llvm_i16_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.suld.1d.array.v2i16.trap">;
-def int_nvvm_suld_1d_array_v2i32_trap
-  : Intrinsic<[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.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.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.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.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.suld.1d.array.v4i16.trap">;
-def int_nvvm_suld_1d_array_v4i32_trap
+              "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.suld.1d.array.v4i32.trap">;
+              "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_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
+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.trap">;
-def int_nvvm_suld_2d_i32_trap
+              "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.trap">;
-def int_nvvm_suld_2d_v2i8_trap
+              "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.trap">;
-def int_nvvm_suld_2d_v2i16_trap
+              "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.trap">;
-def int_nvvm_suld_2d_v2i32_trap
+              "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.trap">;
-def int_nvvm_suld_2d_v4i8_trap
+              "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.trap">;
-def int_nvvm_suld_2d_v4i16_trap
+              "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.trap">;
-def int_nvvm_suld_2d_v4i32_trap
+              "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.trap">;
+              "llvm.nvvm.suld.2d.v4i32.zero">;
 
-def int_nvvm_suld_2d_array_i8_trap
+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.trap">;
-def int_nvvm_suld_2d_array_i16_trap
+              "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.trap">;
-def int_nvvm_suld_2d_array_i32_trap
+              "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.trap">;
-def int_nvvm_suld_2d_array_v2i8_trap
+              "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.trap">;
-def int_nvvm_suld_2d_array_v2i16_trap
+              "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.trap">;
-def int_nvvm_suld_2d_array_v2i32_trap
+              "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.trap">;
-def int_nvvm_suld_2d_array_v4i8_trap
+              "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.trap">;
-def int_nvvm_suld_2d_array_v4i16_trap
+              "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.trap">;
-def int_nvvm_suld_2d_array_v4i32_trap
+              "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.trap">;
+              "llvm.nvvm.suld.2d.array.v4i32.zero">;
 
-def int_nvvm_suld_3d_i8_trap
+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.trap">;
-def int_nvvm_suld_3d_i16_trap
+              "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.trap">;
-def int_nvvm_suld_3d_i32_trap
+              "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.trap">;
-def int_nvvm_suld_3d_v2i8_trap
+              "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.trap">;
-def int_nvvm_suld_3d_v2i16_trap
+              "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.trap">;
-def int_nvvm_suld_3d_v2i32_trap
+              "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.trap">;
-def int_nvvm_suld_3d_v4i8_trap
+              "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.trap">;
-def int_nvvm_suld_3d_v4i16_trap
+              "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.trap">;
-def int_nvvm_suld_3d_v4i32_trap
+              "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.trap">;
+              "llvm.nvvm.suld.3d.v4i32.zero">;
 
 //===- Texture Query ------------------------------------------------------===//
 
@@ -1353,7 +2609,277 @@ def int_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">,
@@ -1366,6 +2892,10 @@ 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">,
@@ -1378,6 +2908,10 @@ 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], [],
@@ -1407,6 +2941,10 @@ 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], [],
@@ -1422,6 +2960,11 @@ def int_nvvm_sust_b_1d_array_v2i32_trap
                    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], [],
@@ -1451,6 +2994,10 @@ 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], [],
@@ -1466,6 +3013,11 @@ def int_nvvm_sust_b_2d_v2i32_trap
                    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], [],
@@ -1498,6 +3050,11 @@ def int_nvvm_sust_b_2d_array_i32_trap
                    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], [],
@@ -1513,6 +3070,11 @@ def int_nvvm_sust_b_2d_array_v2i32_trap
                    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], [],
@@ -1545,6 +3107,11 @@ def int_nvvm_sust_b_3d_i32_trap
                    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], [],
@@ -1560,6 +3127,11 @@ def int_nvvm_sust_b_3d_v2i32_trap
                    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], [],
@@ -1576,6 +3148,278 @@ def int_nvvm_sust_b_3d_v4i32_trap
               "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
@@ -1801,6 +3645,26 @@ def int_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">;
+
 
 // Old PTX back-end intrinsics retained here for backwards-compatibility