[AMDGPU][clang] Definition of gfx11 subtarget

[Joe_Nash]

Summary

Contributors:
Jay Foad <[e-mail]>
Konstantin Zhuravlyov <[e-mail]>

Patch 2/N for upstreaming of AMDGPU gfx11 architecture

Depends on D124536

[b-sumner]

t-tye should review this too.

clang/include/clang/Basic/Cuda.h

enum class CudaArch {
   GFX1013,
   GFX1030,
   GFX1031,
   GFX1032,
   GFX1033,
   GFX1034,
   GFX1035,
   GFX1036,
+  GFX1100,
+  GFX1101,
+  GFX1102,
+  GFX1103,
   Generic, // A processor model named 'generic' if the target backend defines a
            // public one.
   LAST,
 };
 
 static inline bool IsNVIDIAGpuArch(CudaArch A) {
   return A >= CudaArch::SM_20 && A < CudaArch::GFX600;
 }

clang/lib/Basic/Cuda.cpp

static const CudaArchToStringMap arch_names[] = {
     GFX(1013), // gfx1013
     GFX(1030), // gfx1030
     GFX(1031), // gfx1031
     GFX(1032), // gfx1032
     GFX(1033), // gfx1033
     GFX(1034), // gfx1034
     GFX(1035), // gfx1035
     GFX(1036), // gfx1036
+    GFX(1100), // gfx1100
+    GFX(1101), // gfx1101
+    GFX(1102), // gfx1102
+    GFX(1103), // gfx1103
     {CudaArch::Generic, "generic", ""},
     // clang-format on
 };
 #undef SM
 #undef SM2
 #undef GFX
 
 const char *CudaArchToString(CudaArch A) {

clang/lib/Basic/Targets/AMDGPU.cpp

bool AMDGPUTargetInfo::initFeatureMap(
     llvm::StringMap<bool> &Features, DiagnosticsEngine &Diags, StringRef CPU,
     const std::vector<std::string> &FeatureVec) const {
 
   using namespace llvm::AMDGPU;
 
   // XXX - What does the member GPU mean if device name string passed here?
   if (isAMDGCN(getTriple())) {
     switch (llvm::AMDGPU::parseArchAMDGCN(CPU)) {
+    case GK_GFX1103:
+    case GK_GFX1102:
+    case GK_GFX1101:
+    case GK_GFX1100:
+      Features["ci-insts"] = true;
+      Features["dot1-insts"] = true;
+      Features["dot5-insts"] = true;
+      Features["dot6-insts"] = true;
+      Features["dot7-insts"] = true;
+      Features["dot8-insts"] = true;
+      Features["dl-insts"] = true;
+      Features["flat-address-space"] = true;
+      Features["16-bit-insts"] = true;
+      Features["dpp"] = true;
+      Features["gfx8-insts"] = true;
+      Features["gfx9-insts"] = true;
+      Features["gfx10-insts"] = true;
+      Features["gfx10-3-insts"] = true;
+      Features["gfx11-insts"] = true;
+      break;
     case GK_GFX1036:
     case GK_GFX1035:
     case GK_GFX1034:
     case GK_GFX1033:
     case GK_GFX1032:
     case GK_GFX1031:
     case GK_GFX1030:
       Features["ci-insts"] = true;

clang/lib/Basic/Targets/NVPTX.cpp

std::string CUDAArchCode = [this] {
       case CudaArch::GFX1013:
       case CudaArch::GFX1030:
       case CudaArch::GFX1031:
       case CudaArch::GFX1032:
       case CudaArch::GFX1033:
       case CudaArch::GFX1034:
       case CudaArch::GFX1035:
       case CudaArch::GFX1036:
+      case CudaArch::GFX1100:
+      case CudaArch::GFX1101:
+      case CudaArch::GFX1102:
+      case CudaArch::GFX1103:
       case CudaArch::Generic:
       case CudaArch::LAST:
         break;
       case CudaArch::UNUSED:
       case CudaArch::UNKNOWN:
         assert(false && "No GPU arch when compiling CUDA device code.");
         return "";
       case CudaArch::SM_20:

clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp

if (Clause->getClauseKind() == OMPC_unified_shared_memory) {
       case CudaArch::GFX1013:
       case CudaArch::GFX1030:
       case CudaArch::GFX1031:
       case CudaArch::GFX1032:
       case CudaArch::GFX1033:
       case CudaArch::GFX1034:
       case CudaArch::GFX1035:
       case CudaArch::GFX1036:
+      case CudaArch::GFX1100:
+      case CudaArch::GFX1101:
+      case CudaArch::GFX1102:
+      case CudaArch::GFX1103:
       case CudaArch::Generic:
       case CudaArch::UNUSED:
       case CudaArch::UNKNOWN:
         break;
       case CudaArch::LAST:
         llvm_unreachable("Unexpected Cuda arch.");
       }
     }

clang/test/CodeGenOpenCL/amdgpu-features.cl

 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1013 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1013 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1030 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1030 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1031 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1031 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1032 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1032 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1033 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1033 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1034 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1034 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1035 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1035 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1036 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1036 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1100 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1100 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1101 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1101 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1102 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1102 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1103 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1103 %s
 
 // GFX600: "target-features"="+s-memtime-inst"
 // GFX601: "target-features"="+s-memtime-inst"
 // GFX602: "target-features"="+s-memtime-inst"
 // GFX700: "target-features"="+ci-insts,+flat-address-space,+s-memtime-inst"
 // GFX701: "target-features"="+ci-insts,+flat-address-space,+s-memtime-inst"
 // GFX702: "target-features"="+ci-insts,+flat-address-space,+s-memtime-inst"
 // GFX703: "target-features"="+ci-insts,+flat-address-space,+s-memtime-inst"

 // GFX1013: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dpp,+flat-address-space,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
 // GFX1030: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
 // GFX1031: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
 // GFX1032: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
 // GFX1033: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
 // GFX1034: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
 // GFX1035: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
 // GFX1036: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
+// GFX1100: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dot8-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts"
+// GFX1101: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dot8-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts"
+// GFX1102: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dot8-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts"
+// GFX1103: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dot8-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts"
 
 kernel void test() {}

clang/test/Driver/amdgpu-macros.cl

 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1013 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1013
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1030 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1030
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1031 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1031
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1032 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1032
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1033 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1033
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1034 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1034
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1035 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1035
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1036 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1036
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1100 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1100
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1101 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1101
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1102 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1102
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1103 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1103
 
 // ARCH-GCN-DAG: #define FP_FAST_FMA 1
 
 // FAST_FMAF-DAG: #define FP_FAST_FMAF 1
 // SLOW_FMAF-NOT: #define FP_FAST_FMAF 1
 
 // ARCH-GCN-DAG: #define __AMDGCN__ 1
 // ARCH-GCN-DAG: #define __AMDGPU__ 1

clang/test/Driver/amdgpu-mcpu.cl

 // RUN: %clang -### -target amdgcn -mcpu=gfx1013 %s 2>&1 | FileCheck --check-prefix=GFX1013 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1030 %s 2>&1 | FileCheck --check-prefix=GFX1030 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1031 %s 2>&1 | FileCheck --check-prefix=GFX1031 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1032 %s 2>&1 | FileCheck --check-prefix=GFX1032 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1033 %s 2>&1 | FileCheck --check-prefix=GFX1033 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1034 %s 2>&1 | FileCheck --check-prefix=GFX1034 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1035 %s 2>&1 | FileCheck --check-prefix=GFX1035 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1036 %s 2>&1 | FileCheck --check-prefix=GFX1036 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx1100 %s 2>&1 | FileCheck --check-prefix=GFX1100 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx1101 %s 2>&1 | FileCheck --check-prefix=GFX1101 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx1102 %s 2>&1 | FileCheck --check-prefix=GFX1102 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx1103 %s 2>&1 | FileCheck --check-prefix=GFX1103 %s
 
 // GCNDEFAULT-NOT: -target-cpu
 // GFX600:    "-target-cpu" "gfx600"
 // GFX601:    "-target-cpu" "gfx601"
 // GFX602:    "-target-cpu" "gfx602"
 // GFX700:    "-target-cpu" "gfx700"
 // GFX701:    "-target-cpu" "gfx701"
 // GFX702:    "-target-cpu" "gfx702"

 // GFX1013:   "-target-cpu" "gfx1013"
 // GFX1030:   "-target-cpu" "gfx1030"
 // GFX1031:   "-target-cpu" "gfx1031"
 // GFX1032:   "-target-cpu" "gfx1032"
 // GFX1033:   "-target-cpu" "gfx1033"
 // GFX1034:   "-target-cpu" "gfx1034"
 // GFX1035:   "-target-cpu" "gfx1035"
 // GFX1036:   "-target-cpu" "gfx1036"
+// GFX1100:   "-target-cpu" "gfx1100"
+// GFX1101:   "-target-cpu" "gfx1101"
+// GFX1102:   "-target-cpu" "gfx1102"
+// GFX1103:   "-target-cpu" "gfx1103"

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

 // TUNE_X86-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, x86-64, geode{{$}}
 
 // RUN: not %clang_cc1 -triple x86_64--- -tune-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix TUNE_X86_64
 // TUNE_X86_64: error: unknown target CPU 'not-a-cpu'
 // TUNE_X86_64-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, x86-64, geode{{$}}
 
 // RUN: not %clang_cc1 -triple nvptx--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix NVPTX
 // NVPTX: error: unknown target CPU 'not-a-cpu'
-// NVPTX-NEXT: note: valid target CPU values are: sm_20, sm_21, sm_30, sm_32, sm_35, sm_37, sm_50, sm_52, sm_53, sm_60, sm_61, sm_62, sm_70, sm_72, sm_75, sm_80, sm_86, gfx600, gfx601, gfx602, gfx700, gfx701, gfx702, gfx703, gfx704, gfx705, gfx801, gfx802, gfx803, gfx805, gfx810, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036{{$}}
+// NVPTX-NEXT: note: valid target CPU values are: sm_20, sm_21, sm_30, sm_32, sm_35, sm_37, sm_50, sm_52, sm_53, sm_60, sm_61, sm_62, sm_70, sm_72, sm_75, sm_80, sm_86, gfx600, gfx601, gfx602, gfx700, gfx701, gfx702, gfx703, gfx704, gfx705, gfx801, gfx802, gfx803, gfx805, gfx810, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx1100, gfx1101, gfx1102, gfx1103{{$}}
 
 // RUN: not %clang_cc1 -triple r600--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix R600
 // R600: error: unknown target CPU 'not-a-cpu'
 // R600-NEXT: note: valid target CPU values are: r600, rv630, rv635, r630, rs780, rs880, rv610, rv620, rv670, rv710, rv730, rv740, rv770, cedar, palm, cypress, hemlock, juniper, redwood, sumo, sumo2, barts, caicos, aruba, cayman, turks{{$}}
 
 // RUN: not %clang_cc1 -triple amdgcn--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix AMDGCN
 // AMDGCN: error: unknown target CPU 'not-a-cpu'
 // AMDGCN-NEXT: note: valid target CPU values are: gfx600, tahiti, gfx601, pitcairn, verde, gfx602, hainan, oland, gfx700, kaveri, gfx701, hawaii, gfx702, gfx703, kabini, mullins, gfx704, bonaire, gfx705, gfx801, carrizo, gfx802, iceland, tonga, gfx803, fiji, polaris10, polaris11, gfx805, tongapro, gfx810, stoney, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx1100, gfx1101, gfx1102, gfx1103{{$}}