Skip to content

AMDGPU: Add gfx950 subtarget definitions #116307

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Nov 18, 2024
Merged

AMDGPU: Add gfx950 subtarget definitions #116307

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c5735e1
AMDGPU: Add gfx950 subtarget definitions
arsenm Nov 17, 2023
1f480f3
Reorder targets
arsenm Nov 15, 2024
fd4cc28
Fix missing diff run line
arsenm Nov 15, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions clang/docs/ReleaseNotes.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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++.
Expand Down
1 change: 1 addition & 0 deletions clang/include/clang/Basic/Cuda.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,6 +107,7 @@ enum class OffloadArch {
GFX940,
GFX941,
GFX942,
GFX950,
GFX10_1_GENERIC,
GFX1010,
GFX1011,
Expand Down
1 change: 1 addition & 0 deletions clang/lib/Basic/Cuda.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
1 change: 1 addition & 0 deletions clang/lib/Basic/Targets/NVPTX.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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:
Expand Down
1 change: 1 addition & 0 deletions clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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:
Expand Down
2 changes: 2 additions & 0 deletions clang/test/CodeGenOpenCL/amdgpu-features.cl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down Expand Up @@ -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"
Expand Down
1 change: 1 addition & 0 deletions clang/test/Driver/amdgpu-macros.cl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
2 changes: 2 additions & 0 deletions clang/test/Driver/amdgpu-mcpu.cl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down Expand Up @@ -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"
Expand Down
1 change: 1 addition & 0 deletions clang/test/Misc/target-invalid-cpu-note/amdgcn.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
1 change: 1 addition & 0 deletions clang/test/Misc/target-invalid-cpu-note/nvptx.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
9 changes: 8 additions & 1 deletion llvm/docs/AMDGPUUsage.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -399,6 +399,13 @@ Every processor supports every OS ABI (see :ref:`amdgpu-os`) with the following
work-item
IDs

``gfx950`` ``amdgcn`` dGPU - sramecc - Architected *TBA*
- tgsplit flat
- xnack scratch .. TODO::
- kernarg preload - Packed
work-item Add product
IDs names.

**GCN GFX10.1 (RDNA 1)** [AMD-GCN-GFX10-RDNA1]_
-----------------------------------------------------------------------------------------------------------------------
``gfx1010`` ``amdgcn`` dGPU - cumode - Absolute - *rocm-amdhsa* - Radeon RX 5700
Expand Down Expand Up @@ -2178,7 +2185,7 @@ The AMDGPU backend uses the following ELF header:
``EF_AMDGPU_MACH_AMDGCN_GFX942`` 0x04c ``gfx942``
*reserved* 0x04d Reserved.
``EF_AMDGPU_MACH_AMDGCN_GFX1201`` 0x04e ``gfx1201``
*reserved* 0x04f Reserved.
``EF_AMDGPU_MACH_AMDGCN_GFX950`` 0x04f ``gfx950``
*reserved* 0x050 Reserved.
``EF_AMDGPU_MACH_AMDGCN_GFX9_GENERIC`` 0x051 ``gfx9-generic``
``EF_AMDGPU_MACH_AMDGCN_GFX10_1_GENERIC`` 0x052 ``gfx10-1-generic``
Expand Down
2 changes: 1 addition & 1 deletion llvm/include/llvm/BinaryFormat/ELF.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -811,7 +811,7 @@ enum : unsigned {
EF_AMDGPU_MACH_AMDGCN_GFX942 = 0x04c,
EF_AMDGPU_MACH_AMDGCN_RESERVED_0X4D = 0x04d,
EF_AMDGPU_MACH_AMDGCN_GFX1201 = 0x04e,
EF_AMDGPU_MACH_AMDGCN_RESERVED_0X4F = 0x04f,
EF_AMDGPU_MACH_AMDGCN_GFX950 = 0x04f,
EF_AMDGPU_MACH_AMDGCN_RESERVED_0X50 = 0x050,
EF_AMDGPU_MACH_AMDGCN_GFX9_GENERIC = 0x051,
EF_AMDGPU_MACH_AMDGCN_GFX10_1_GENERIC = 0x052,
Expand Down
25 changes: 13 additions & 12 deletions llvm/include/llvm/TargetParser/TargetParser.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,18 +86,19 @@ enum GPUKind : uint32_t {
GK_GFX940 = 68,
GK_GFX941 = 69,
GK_GFX942 = 70,

GK_GFX1010 = 71,
GK_GFX1011 = 72,
GK_GFX1012 = 73,
GK_GFX1013 = 74,
GK_GFX1030 = 75,
GK_GFX1031 = 76,
GK_GFX1032 = 77,
GK_GFX1033 = 78,
GK_GFX1034 = 79,
GK_GFX1035 = 80,
GK_GFX1036 = 81,
GK_GFX950 = 71,

GK_GFX1010 = 72,
GK_GFX1011 = 73,
GK_GFX1012 = 74,
GK_GFX1013 = 75,
GK_GFX1030 = 76,
GK_GFX1031 = 77,
GK_GFX1032 = 78,
GK_GFX1033 = 79,
GK_GFX1034 = 80,
GK_GFX1035 = 81,
GK_GFX1036 = 82,

GK_GFX1100 = 90,
GK_GFX1101 = 91,
Expand Down
2 changes: 2 additions & 0 deletions llvm/lib/Object/ELFObjectFile.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -550,6 +550,8 @@ StringRef ELFObjectFileBase::getAMDGPUCPUName() const {
return "gfx941";
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX942:
return "gfx942";
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX950:
return "gfx950";

// AMDGCN GFX10.
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1010:
Expand Down
1 change: 1 addition & 0 deletions llvm/lib/ObjectYAML/ELFYAML.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -609,6 +609,7 @@ void ScalarBitSetTraits<ELFYAML::ELF_EF>::bitset(IO &IO,
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX940, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX941, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX942, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX950, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1010, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1011, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1012, EF_AMDGPU_MACH);
Expand Down
16 changes: 16 additions & 0 deletions llvm/lib/Target/AMDGPU/AMDGPU.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -360,6 +360,12 @@ def FeatureGFX940Insts : SubtargetFeature<"gfx940-insts",
"Additional instructions for GFX940+"
>;

def FeatureGFX950Insts : SubtargetFeature<"gfx950-insts",
"GFX950Insts",
"true",
"Additional instructions for GFX950+"
>;

def FeatureGFX10Insts : SubtargetFeature<"gfx10-insts",
"GFX10Insts",
"true",
Expand Down Expand Up @@ -1470,6 +1476,14 @@ def FeatureISAVersion9_4_Common : FeatureSet<
FeatureFlatBufferGlobalAtomicFaddF64Inst
]>;

def FeatureISAVersion9_5_Common : FeatureSet<
!listconcat(FeatureISAVersion9_4_Common.Features,
[FeatureFP8Insts,
FeatureFP8ConversionInsts,
FeatureCvtFP8VOP1Bug,
FeatureGFX950Insts
])>;

def FeatureISAVersion9_4_0 : FeatureSet<
!listconcat(FeatureISAVersion9_4_Common.Features,
[
Expand Down Expand Up @@ -1503,6 +1517,8 @@ def FeatureISAVersion9_4_Generic : FeatureSet<
!listconcat(FeatureISAVersion9_4_Common.Features,
[FeatureRequiresCOV6])>;

def FeatureISAVersion9_5_0 : FeatureSet<FeatureISAVersion9_5_Common.Features>;

def FeatureISAVersion10_Common : FeatureSet<
[FeatureGFX10,
FeatureLDSBankCount32,
Expand Down
4 changes: 4 additions & 0 deletions llvm/lib/Target/AMDGPU/GCNProcessors.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -204,6 +204,10 @@ def : ProcessorModel<"gfx942", SIDPGFX940FullSpeedModel,
FeatureISAVersion9_4_2.Features
>;

def : ProcessorModel<"gfx950", SIDPGFX940FullSpeedModel,
FeatureISAVersion9_5_0.Features
>;

// [gfx900, gfx902, gfx904, gfx906, gfx909, gfx90c]
def : ProcessorModel<"gfx9-generic", SIQuarterSpeedModel,
FeatureISAVersion9_Generic.Features
Expand Down
1 change: 1 addition & 0 deletions llvm/lib/Target/AMDGPU/GCNSubtarget.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,6 +106,7 @@ class GCNSubtarget final : public AMDGPUGenSubtargetInfo,
bool GFX9Insts = false;
bool GFX90AInsts = false;
bool GFX940Insts = false;
bool GFX950Insts = false;
bool GFX10Insts = false;
bool GFX11Insts = false;
bool GFX12Insts = false;
Expand Down
2 changes: 2 additions & 0 deletions llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,6 +96,7 @@ StringRef AMDGPUTargetStreamer::getArchNameFromElfMach(unsigned ElfMach) {
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX940: AK = GK_GFX940; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX941: AK = GK_GFX941; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX942: AK = GK_GFX942; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX950: AK = GK_GFX950; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1010: AK = GK_GFX1010; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1011: AK = GK_GFX1011; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1012: AK = GK_GFX1012; break;
Expand Down Expand Up @@ -182,6 +183,7 @@ unsigned AMDGPUTargetStreamer::getElfMach(StringRef GPU) {
case GK_GFX940: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX940;
case GK_GFX941: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX941;
case GK_GFX942: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX942;
case GK_GFX950: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX950;
case GK_GFX1010: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1010;
case GK_GFX1011: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1011;
case GK_GFX1012: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1012;
Expand Down
11 changes: 9 additions & 2 deletions llvm/lib/TargetParser/TargetParser.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,6 +107,7 @@ constexpr GPUInfo AMDGCNGPUs[] = {
{{"gfx940"}, {"gfx940"}, GK_GFX940, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_XNACK|FEATURE_SRAMECC},
{{"gfx941"}, {"gfx941"}, GK_GFX941, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_XNACK|FEATURE_SRAMECC},
{{"gfx942"}, {"gfx942"}, GK_GFX942, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_XNACK|FEATURE_SRAMECC},
{{"gfx950"}, {"gfx950"}, GK_GFX950, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_XNACK|FEATURE_SRAMECC},
{{"gfx1010"}, {"gfx1010"}, GK_GFX1010, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_XNACK|FEATURE_WGP},
{{"gfx1011"}, {"gfx1011"}, GK_GFX1011, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_XNACK|FEATURE_WGP},
{{"gfx1012"}, {"gfx1012"}, GK_GFX1012, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_XNACK|FEATURE_WGP},
Expand Down Expand Up @@ -262,6 +263,7 @@ AMDGPU::IsaVersion AMDGPU::getIsaVersion(StringRef GPU) {
case GK_GFX940: return {9, 4, 0};
case GK_GFX941: return {9, 4, 1};
case GK_GFX942: return {9, 4, 2};
case GK_GFX950: return {9, 5, 0};
case GK_GFX1010: return {10, 1, 0};
case GK_GFX1011: return {10, 1, 1};
case GK_GFX1012: return {10, 1, 2};
Expand Down Expand Up @@ -361,7 +363,8 @@ void AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T,
Features["wavefrontsize32"] = true;
Features["wavefrontsize64"] = true;
} else if (T.isAMDGCN()) {
switch (parseArchAMDGCN(GPU)) {
AMDGPU::GPUKind Kind = parseArchAMDGCN(GPU);
switch (Kind) {
case GK_GFX1201:
case GK_GFX1200:
case GK_GFX12_GENERIC:
Expand Down Expand Up @@ -466,12 +469,16 @@ void AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T,
Features["s-memtime-inst"] = true;
Features["gws"] = true;
break;
case GK_GFX950:
Features["gfx950-insts"] = true;
[[fallthrough]];
case GK_GFX942:
case GK_GFX941:
case GK_GFX940:
Features["fp8-insts"] = true;
Features["fp8-conversion-insts"] = true;
Features["xf32-insts"] = true;
if (Kind != GK_GFX950)
Features["xf32-insts"] = true;
[[fallthrough]];
case GK_GFX9_4_GENERIC:
Features["gfx940-insts"] = true;
Expand Down
Loading
Loading