AMDGPU: Add gfx950 subtarget definitions (#116307)

Mostly a stub, but adds some baseline tests and
tests for removed instructions.

Author: arsenm

clang/docs/ReleaseNotes.rst

@@ -712,6 +712,8 @@ Target Specific Changes
 AMDGPU Support
 ^^^^^^^^^^^^^^
 
+- Initial support for gfx950
+
 - Added headers ``gpuintrin.h`` and ``amdgpuintrin.h`` that contains common
   definitions for GPU builtin functions. This header can be included for OpenMP,
   CUDA, HIP, OpenCL, and C/C++.

clang/include/clang/Basic/Cuda.h

@@ -107,6 +107,7 @@ enum class OffloadArch {
   GFX940,
   GFX941,
   GFX942,
+  GFX950,
   GFX10_1_GENERIC,
   GFX1010,
   GFX1011,

clang/lib/Basic/Cuda.cpp

@@ -125,6 +125,7 @@ static const OffloadArchToStringMap arch_names[] = {
     GFX(940),  // gfx940
     GFX(941),  // gfx941
     GFX(942),  // gfx942
+    GFX(950),  // gfx950
     {OffloadArch::GFX10_1_GENERIC, "gfx10-1-generic", "compute_amdgcn"},
     GFX(1010), // gfx1010
     GFX(1011), // gfx1011

clang/lib/Basic/Targets/NVPTX.cpp

@@ -209,6 +209,7 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
       case OffloadArch::GFX940:
       case OffloadArch::GFX941:
       case OffloadArch::GFX942:
+      case OffloadArch::GFX950:
       case OffloadArch::GFX10_1_GENERIC:
       case OffloadArch::GFX1010:
       case OffloadArch::GFX1011:

clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp

@@ -2304,6 +2304,7 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(const OMPRequiresDecl *D) {
       case OffloadArch::GFX940:
       case OffloadArch::GFX941:
       case OffloadArch::GFX942:
+      case OffloadArch::GFX950:
       case OffloadArch::GFX10_1_GENERIC:
       case OffloadArch::GFX1010:
       case OffloadArch::GFX1011:

clang/test/CodeGenOpenCL/amdgpu-features.cl

@@ -32,6 +32,7 @@
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx940 -emit-llvm -o - %s | FileCheck --check-prefix=GFX940 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx941 -emit-llvm -o - %s | FileCheck --check-prefix=GFX941 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx942 -emit-llvm -o - %s | FileCheck --check-prefix=GFX942 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx950 -emit-llvm -o - %s | FileCheck --check-prefix=GFX950 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1010 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1010 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1011 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1011 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1012 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1012 %s
@@ -88,6 +89,7 @@
 // GFX941: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+fp8-conversion-insts,+fp8-insts,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gfx940-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,+xf32-insts"
 // GFX942: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+fp8-conversion-insts,+fp8-insts,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gfx940-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,+xf32-insts"
 // GFX9_4_Generic: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gfx940-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64"
+// GFX950: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+fp8-conversion-insts,+fp8-insts,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gfx940-insts,+gfx950-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64"
 // GFX1010: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32"
 // GFX1011: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32"
 // GFX1012: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32"

clang/test/Driver/amdgpu-macros.cl

@@ -110,6 +110,7 @@
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx940 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=64 -DCPU=gfx940 -DFAMILY=GFX9
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx941 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=64 -DCPU=gfx941 -DFAMILY=GFX9
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx942 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=64 -DCPU=gfx942 -DFAMILY=GFX9
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx950 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=64 -DCPU=gfx950 -DFAMILY=GFX9
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1010 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1010 -DFAMILY=GFX10
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1011 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1011 -DFAMILY=GFX10
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1012 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1012 -DFAMILY=GFX10

clang/test/Driver/amdgpu-mcpu.cl

@@ -95,6 +95,7 @@
 // RUN: %clang -### -target amdgcn -mcpu=gfx940 %s 2>&1 | FileCheck --check-prefix=GFX940 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx941 %s 2>&1 | FileCheck --check-prefix=GFX941 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx942 %s 2>&1 | FileCheck --check-prefix=GFX942 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx950 %s 2>&1 | FileCheck --check-prefix=GFX950 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1010 %s 2>&1 | FileCheck --check-prefix=GFX1010 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1011 %s 2>&1 | FileCheck --check-prefix=GFX1011 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1012 %s 2>&1 | FileCheck --check-prefix=GFX1012 %s
@@ -150,6 +151,7 @@
 // GFX940:    "-target-cpu" "gfx940"
 // GFX941:    "-target-cpu" "gfx941"
 // GFX942:    "-target-cpu" "gfx942"
+// GFX950:    "-target-cpu" "gfx950"
 // GFX1010:   "-target-cpu" "gfx1010"
 // GFX1011:   "-target-cpu" "gfx1011"
 // GFX1012:   "-target-cpu" "gfx1012"

clang/test/Misc/target-invalid-cpu-note/amdgcn.c

@@ -48,6 +48,7 @@
 // CHECK-SAME: {{^}}, gfx940
 // CHECK-SAME: {{^}}, gfx941
 // CHECK-SAME: {{^}}, gfx942
+// CHECK-SAME: {{^}}, gfx950
 // CHECK-SAME: {{^}}, gfx1010
 // CHECK-SAME: {{^}}, gfx1011
 // CHECK-SAME: {{^}}, gfx1012

clang/test/Misc/target-invalid-cpu-note/nvptx.c

@@ -54,6 +54,7 @@
 // CHECK-SAME: {{^}}, gfx940
 // CHECK-SAME: {{^}}, gfx941
 // CHECK-SAME: {{^}}, gfx942
+// CHECK-SAME: {{^}}, gfx950
 // CHECK-SAME: {{^}}, gfx10-1-generic
 // CHECK-SAME: {{^}}, gfx1010
 // CHECK-SAME: {{^}}, gfx1011