[clang] 8bdfc73 - [AMDGPU][clang] Definition of gfx11 subtarget
Joe Nash via cfe-commits
cfe-commits at lists.llvm.org
Fri Apr 29 11:23:05 PDT 2022
Author: Joe Nash
Date: 2022-04-29T13:55:56-04:00
New Revision: 8bdfc73f633dca9859123b8596bcb521700c6a7f
URL: https://github.com/llvm/llvm-project/commit/8bdfc73f633dca9859123b8596bcb521700c6a7f
DIFF: https://github.com/llvm/llvm-project/commit/8bdfc73f633dca9859123b8596bcb521700c6a7f.diff
LOG: [AMDGPU][clang] Definition of gfx11 subtarget
Contributors:
Jay Foad <jay.foad at amd.com>
Konstantin Zhuravlyov <kzhuravl_dev at outlook.com>
Patch 2/N for upstreaming of AMDGPU gfx11 architecture
Depends on D124536
Reviewed By: foad, kzhuravl, #amdgpu, arsenm
Differential Revision: https://reviews.llvm.org/D124537
Added:
Modified:
clang/include/clang/Basic/Cuda.h
clang/lib/Basic/Cuda.cpp
clang/lib/Basic/Targets/AMDGPU.cpp
clang/lib/Basic/Targets/NVPTX.cpp
clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
clang/test/CodeGenOpenCL/amdgpu-features.cl
clang/test/Driver/amdgpu-macros.cl
clang/test/Driver/amdgpu-mcpu.cl
clang/test/Misc/target-invalid-cpu-note.c
Removed:
################################################################################
diff --git a/clang/include/clang/Basic/Cuda.h b/clang/include/clang/Basic/Cuda.h
index 147b04eb57459..18ef373784e5b 100644
--- a/clang/include/clang/Basic/Cuda.h
+++ b/clang/include/clang/Basic/Cuda.h
@@ -97,6 +97,10 @@ enum class CudaArch {
GFX1034,
GFX1035,
GFX1036,
+ GFX1100,
+ GFX1101,
+ GFX1102,
+ GFX1103,
Generic, // A processor model named 'generic' if the target backend defines a
// public one.
LAST,
diff --git a/clang/lib/Basic/Cuda.cpp b/clang/lib/Basic/Cuda.cpp
index adc61a567dbef..412f5c3f45e36 100644
--- a/clang/lib/Basic/Cuda.cpp
+++ b/clang/lib/Basic/Cuda.cpp
@@ -125,6 +125,10 @@ static const CudaArchToStringMap arch_names[] = {
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
};
diff --git a/clang/lib/Basic/Targets/AMDGPU.cpp b/clang/lib/Basic/Targets/AMDGPU.cpp
index 32eacc871093e..c13aec4b2cae5 100644
--- a/clang/lib/Basic/Targets/AMDGPU.cpp
+++ b/clang/lib/Basic/Targets/AMDGPU.cpp
@@ -183,6 +183,26 @@ bool AMDGPUTargetInfo::initFeatureMap(
// 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:
diff --git a/clang/lib/Basic/Targets/NVPTX.cpp b/clang/lib/Basic/Targets/NVPTX.cpp
index f03d5c600e039..ffd69983a0be5 100644
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -217,6 +217,10 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
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;
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index f4228cfb3086e..85efe93d6bd98 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -3946,6 +3946,10 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(
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:
diff --git a/clang/test/CodeGenOpenCL/amdgpu-features.cl b/clang/test/CodeGenOpenCL/amdgpu-features.cl
index 0967e932868eb..cb3a3eff01f70 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-features.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-features.cl
@@ -37,6 +37,10 @@
// 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"
@@ -72,5 +76,9 @@
// 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() {}
diff --git a/clang/test/Driver/amdgpu-macros.cl b/clang/test/Driver/amdgpu-macros.cl
index 9fd103ec1bd44..5e53de409f441 100644
--- a/clang/test/Driver/amdgpu-macros.cl
+++ b/clang/test/Driver/amdgpu-macros.cl
@@ -120,6 +120,10 @@
// 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
diff --git a/clang/test/Driver/amdgpu-mcpu.cl b/clang/test/Driver/amdgpu-mcpu.cl
index 350d0d5f5ed57..dfc7ab24927fc 100644
--- a/clang/test/Driver/amdgpu-mcpu.cl
+++ b/clang/test/Driver/amdgpu-mcpu.cl
@@ -104,6 +104,10 @@
// 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"
@@ -140,3 +144,7 @@
// 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"
diff --git a/clang/test/Misc/target-invalid-cpu-note.c b/clang/test/Misc/target-invalid-cpu-note.c
index 4248090cb9feb..b240eb1428f78 100644
--- a/clang/test/Misc/target-invalid-cpu-note.c
+++ b/clang/test/Misc/target-invalid-cpu-note.c
@@ -29,7 +29,7 @@
// 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'
More information about the cfe-commits
mailing list