[clang] [libclc] [llvm] [AMDGPU] Add a new target gfx1152 (PR #94534)
Shilei Tian via cfe-commits
cfe-commits at lists.llvm.org
Wed Jun 5 13:41:53 PDT 2024
https://github.com/shiltian created https://github.com/llvm/llvm-project/pull/94534
None
>From cf1e045d09d18f19bef4a8eb07f86e00f3b6f7a6 Mon Sep 17 00:00:00 2001
From: Shilei Tian <i at tianshilei.me>
Date: Wed, 5 Jun 2024 16:18:57 -0400
Subject: [PATCH] [AMDGPU] Add a new target gfx1152
---
clang/include/clang/Basic/Cuda.h | 1 +
clang/lib/Basic/Cuda.cpp | 1 +
clang/lib/Basic/Targets/NVPTX.cpp | 1 +
clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp | 1 +
clang/test/CodeGenOpenCL/amdgpu-features.cl | 2 ++
clang/test/CodeGenOpenCL/builtins-amdgcn-gfx11.cl | 1 +
clang/test/Driver/amdgpu-macros.cl | 1 +
clang/test/Driver/amdgpu-mcpu.cl | 2 ++
clang/test/Misc/target-invalid-cpu-note.c | 4 ++--
libclc/CMakeLists.txt | 2 +-
llvm/docs/AMDGPUUsage.rst | 15 +++++++++++++--
llvm/include/llvm/BinaryFormat/ELF.h | 1 +
llvm/include/llvm/TargetParser/TargetParser.h | 1 +
llvm/lib/Object/ELFObjectFile.cpp | 2 ++
llvm/lib/ObjectYAML/ELFYAML.cpp | 1 +
llvm/lib/Target/AMDGPU/AMDGPU.td | 6 ++++++
llvm/lib/Target/AMDGPU/GCNProcessors.td | 6 +++++-
.../AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp | 2 ++
llvm/lib/TargetParser/TargetParser.cpp | 4 ++++
.../CodeGen/AMDGPU/directive-amdgcn-target.ll | 2 ++
llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll | 2 ++
llvm/test/CodeGen/AMDGPU/occupancy-levels.ll | 2 ++
llvm/test/MC/AMDGPU/gfx1150_asm_features.s | 1 +
.../test/Object/AMDGPU/elf-header-flags-mach.yaml | 7 +++++++
.../tools/llvm-objdump/ELF/AMDGPU/subtarget.ll | 5 +++++
.../llvm-readobj/ELF/AMDGPU/elf-headers.test | 9 +++++++++
llvm/tools/llvm-readobj/ELFDumper.cpp | 1 +
offload/DeviceRTL/CMakeLists.txt | 2 +-
28 files changed, 78 insertions(+), 7 deletions(-)
diff --git a/clang/include/clang/Basic/Cuda.h b/clang/include/clang/Basic/Cuda.h
index d15171d959c45..0d5e38e825aa7 100644
--- a/clang/include/clang/Basic/Cuda.h
+++ b/clang/include/clang/Basic/Cuda.h
@@ -124,6 +124,7 @@ enum class CudaArch {
GFX1103,
GFX1150,
GFX1151,
+ GFX1152,
GFX12_GENERIC,
GFX1200,
GFX1201,
diff --git a/clang/lib/Basic/Cuda.cpp b/clang/lib/Basic/Cuda.cpp
index e2609b9573cca..1d96a929f95d8 100644
--- a/clang/lib/Basic/Cuda.cpp
+++ b/clang/lib/Basic/Cuda.cpp
@@ -144,6 +144,7 @@ static const CudaArchToStringMap arch_names[] = {
GFX(1103), // gfx1103
GFX(1150), // gfx1150
GFX(1151), // gfx1151
+ GFX(1152), // gfx1152
{CudaArch::GFX12_GENERIC, "gfx12-generic", "compute_amdgcn"},
GFX(1200), // gfx1200
GFX(1201), // gfx1201
diff --git a/clang/lib/Basic/Targets/NVPTX.cpp b/clang/lib/Basic/Targets/NVPTX.cpp
index fc6ef1119e9cf..ff7d2f1f92aa4 100644
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -228,6 +228,7 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
case CudaArch::GFX1103:
case CudaArch::GFX1150:
case CudaArch::GFX1151:
+ case CudaArch::GFX1152:
case CudaArch::GFX12_GENERIC:
case CudaArch::GFX1200:
case CudaArch::GFX1201:
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index 191bd757831fc..6e9a1bacd9bf5 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -3537,6 +3537,7 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(
case CudaArch::GFX1103:
case CudaArch::GFX1150:
case CudaArch::GFX1151:
+ case CudaArch::GFX1152:
case CudaArch::GFX12_GENERIC:
case CudaArch::GFX1200:
case CudaArch::GFX1201:
diff --git a/clang/test/CodeGenOpenCL/amdgpu-features.cl b/clang/test/CodeGenOpenCL/amdgpu-features.cl
index 2fda52dcd2dc6..854ab39791f16 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-features.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-features.cl
@@ -49,6 +49,7 @@
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1103 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1103 %s
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1150 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1150 %s
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1151 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1151 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1152 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1152 %s
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1200 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1200 %s
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1201 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1201 %s
@@ -100,6 +101,7 @@
// GFX1103: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
// GFX1150: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
// GFX1151: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
+// GFX1152: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
// GFX1200: "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,+dot10-insts,+dot11-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
// GFX1201: "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,+dot10-insts,+dot11-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
diff --git a/clang/test/CodeGenOpenCL/builtins-amdgcn-gfx11.cl b/clang/test/CodeGenOpenCL/builtins-amdgcn-gfx11.cl
index d17ff81e5d43c..66061786cca61 100644
--- a/clang/test/CodeGenOpenCL/builtins-amdgcn-gfx11.cl
+++ b/clang/test/CodeGenOpenCL/builtins-amdgcn-gfx11.cl
@@ -5,6 +5,7 @@
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1103 -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1150 -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1151 -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1152 -emit-llvm -o - %s | FileCheck %s
typedef unsigned int uint;
typedef unsigned long ulong;
diff --git a/clang/test/Driver/amdgpu-macros.cl b/clang/test/Driver/amdgpu-macros.cl
index a878a7decee95..3e4a570671bab 100644
--- a/clang/test/Driver/amdgpu-macros.cl
+++ b/clang/test/Driver/amdgpu-macros.cl
@@ -127,6 +127,7 @@
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1103 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1103 -DFAMILY=GFX11
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1150 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1150 -DFAMILY=GFX11
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1151 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1151 -DFAMILY=GFX11
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1152 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1152 -DFAMILY=GFX11
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1200 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1200 -DFAMILY=GFX12
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1201 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1201 -DFAMILY=GFX12
diff --git a/clang/test/Driver/amdgpu-mcpu.cl b/clang/test/Driver/amdgpu-mcpu.cl
index 5b6a22016f043..4b0ef92b682a5 100644
--- a/clang/test/Driver/amdgpu-mcpu.cl
+++ b/clang/test/Driver/amdgpu-mcpu.cl
@@ -112,6 +112,7 @@
// RUN: %clang -### -target amdgcn -mcpu=gfx1103 %s 2>&1 | FileCheck --check-prefix=GFX1103 %s
// RUN: %clang -### -target amdgcn -mcpu=gfx1150 %s 2>&1 | FileCheck --check-prefix=GFX1150 %s
// RUN: %clang -### -target amdgcn -mcpu=gfx1151 %s 2>&1 | FileCheck --check-prefix=GFX1151 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx1152 %s 2>&1 | FileCheck --check-prefix=GFX1152 %s
// RUN: %clang -### -target amdgcn -mcpu=gfx1200 %s 2>&1 | FileCheck --check-prefix=GFX1200 %s
// RUN: %clang -### -target amdgcn -mcpu=gfx1201 %s 2>&1 | FileCheck --check-prefix=GFX1201 %s
@@ -164,6 +165,7 @@
// GFX1103: "-target-cpu" "gfx1103"
// GFX1150: "-target-cpu" "gfx1150"
// GFX1151: "-target-cpu" "gfx1151"
+// GFX1152: "-target-cpu" "gfx1152"
// GFX1200: "-target-cpu" "gfx1200"
// GFX1201: "-target-cpu" "gfx1201"
diff --git a/clang/test/Misc/target-invalid-cpu-note.c b/clang/test/Misc/target-invalid-cpu-note.c
index bad1374b9397c..0afd9295a753e 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, sm_87, sm_89, sm_90, sm_90a, gfx600, gfx601, gfx602, gfx700, gfx701, gfx702, gfx703, gfx704, gfx705, gfx801, gfx802, gfx803, gfx805, gfx810, gfx9-generic, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx941, gfx942, gfx10-1-generic, gfx1010, gfx1011, gfx1012, gfx1013, gfx10-3-generic, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx11-generic, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx12-generic, gfx1200, gfx1201{{$}}
+// NVPTX-NEXT: note: valid target CPU values are: sm_20, sm_21, sm_30, sm_32, sm_35, sm_37, sm_50, sm_52, sm_53, sm_60, sm_61, sm_62, sm_70, sm_72, sm_75, sm_80, sm_86, sm_87, sm_89, sm_90, sm_90a, gfx600, gfx601, gfx602, gfx700, gfx701, gfx702, gfx703, gfx704, gfx705, gfx801, gfx802, gfx803, gfx805, gfx810, gfx9-generic, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx941, gfx942, gfx10-1-generic, gfx1010, gfx1011, gfx1012, gfx1013, gfx10-3-generic, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx11-generic, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx1152, gfx12-generic, gfx1200, gfx1201{{$}}
// 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'
@@ -37,7 +37,7 @@
// 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, gfx941, gfx942, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx1200, gfx1201, gfx9-generic, gfx10-1-generic, gfx10-3-generic, gfx11-generic, gfx12-generic{{$}}
+// AMDGCN-NEXT: note: valid target CPU values are: gfx600, tahiti, gfx601, pitcairn, verde, gfx602, hainan, oland, gfx700, kaveri, gfx701, hawaii, gfx702, gfx703, kabini, mullins, gfx704, bonaire, gfx705, gfx801, carrizo, gfx802, iceland, tonga, gfx803, fiji, polaris10, polaris11, gfx805, tongapro, gfx810, stoney, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx941, gfx942, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx1152, gfx1200, gfx1201, gfx9-generic, gfx10-1-generic, gfx10-3-generic, gfx11-generic, gfx12-generic{{$}}
// RUN: not %clang_cc1 -triple wasm64--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix WEBASM
// WEBASM: error: unknown target CPU 'not-a-cpu'
diff --git a/libclc/CMakeLists.txt b/libclc/CMakeLists.txt
index 5ce1795243085..9858ae905983f 100644
--- a/libclc/CMakeLists.txt
+++ b/libclc/CMakeLists.txt
@@ -198,7 +198,7 @@ set( tahiti_aliases pitcairn verde oland hainan bonaire kabini kaveri hawaii
gfx1010 gfx1011 gfx1012 gfx1013
gfx1030 gfx1031 gfx1032 gfx1033 gfx1034 gfx1035 gfx1036
gfx1100 gfx1101 gfx1102 gfx1103
- gfx1150 gfx1151
+ gfx1150 gfx1151 gfx1152
gfx1200 gfx1201
)
diff --git a/llvm/docs/AMDGPUUsage.rst b/llvm/docs/AMDGPUUsage.rst
index bb6751038fc9c..aa50ce329d1de 100644
--- a/llvm/docs/AMDGPUUsage.rst
+++ b/llvm/docs/AMDGPUUsage.rst
@@ -504,6 +504,13 @@ Every processor supports every OS ABI (see :ref:`amdgpu-os`) with the following
work-item Add product
IDs names.
+ ``gfx1152`` ``amdgcn`` APU - cumode - Architected *TBA*
+ - wavefrontsize64 flat
+ scratch .. TODO::
+ - Packed
+ work-item Add product
+ IDs names.
+
``gfx1200`` ``amdgcn`` dGPU - cumode - Architected *TBA*
- wavefrontsize64 flat
scratch .. TODO::
@@ -591,11 +598,13 @@ Generic processor code objects are versioned. See :ref:`amdgpu-generic-processor
- ``gfx1102`` - Packed hazards specific to some targets
- ``gfx1103`` work-item within this family.
- ``gfx1150`` IDs
- - ``gfx1151`` Not all VGPRs can be used on:
+ - ``gfx1151``
+ - ``gfx1152`` Not all VGPRs can be used on:
- ``gfx1100``
- ``gfx1101``
- ``gfx1151``
+ - ``gfx1152``
SALU floating point instructions
and single-use VGPR hint
@@ -604,12 +613,14 @@ Generic processor code objects are versioned. See :ref:`amdgpu-generic-processor
- ``gfx1150``
- ``gfx1151``
+ - ``gfx1152``
SGPRs are not supported for src1
in dpp instructions for:
- ``gfx1150``
- ``gfx1151``
+ - ``gfx1152``
``gfx12-generic`` ``amdgcn`` - ``gfx1200`` - wavefrontsize64 - Architected No restrictions.
@@ -1979,7 +1990,7 @@ The AMDGPU backend uses the following ELF header:
``EF_AMDGPU_MACH_AMDGCN_GFX10_1_GENERIC`` 0x052 ``gfx10-1-generic``
``EF_AMDGPU_MACH_AMDGCN_GFX10_3_GENERIC`` 0x053 ``gfx10-3-generic``
``EF_AMDGPU_MACH_AMDGCN_GFX11_GENERIC`` 0x054 ``gfx11-generic``
- *reserved* 0x055 Reserved.
+ ``EF_AMDGPU_MACH_AMDGCN_GFX1152`` 0x055 ``gfx1152``.
*reserved* 0x056 Reserved.
*reserved* 0x057 Reserved.
*reserved* 0x058 Reserved.
diff --git a/llvm/include/llvm/BinaryFormat/ELF.h b/llvm/include/llvm/BinaryFormat/ELF.h
index 7364d619bc1b1..fbfba515fa5fb 100644
--- a/llvm/include/llvm/BinaryFormat/ELF.h
+++ b/llvm/include/llvm/BinaryFormat/ELF.h
@@ -785,6 +785,7 @@ enum : unsigned {
EF_AMDGPU_MACH_AMDGCN_GFX1200 = 0x048,
EF_AMDGPU_MACH_AMDGCN_RESERVED_0X49 = 0x049,
EF_AMDGPU_MACH_AMDGCN_GFX1151 = 0x04a,
+ EF_AMDGPU_MACH_AMDGCN_GFX1152 = 0x055,
EF_AMDGPU_MACH_AMDGCN_GFX941 = 0x04b,
EF_AMDGPU_MACH_AMDGCN_GFX942 = 0x04c,
EF_AMDGPU_MACH_AMDGCN_RESERVED_0X4D = 0x04d,
diff --git a/llvm/include/llvm/TargetParser/TargetParser.h b/llvm/include/llvm/TargetParser/TargetParser.h
index 8fc6fa37cb9aa..e03d8f6eebfca 100644
--- a/llvm/include/llvm/TargetParser/TargetParser.h
+++ b/llvm/include/llvm/TargetParser/TargetParser.h
@@ -105,6 +105,7 @@ enum GPUKind : uint32_t {
GK_GFX1103 = 93,
GK_GFX1150 = 94,
GK_GFX1151 = 95,
+ GK_GFX1152 = 96,
GK_GFX1200 = 100,
GK_GFX1201 = 101,
diff --git a/llvm/lib/Object/ELFObjectFile.cpp b/llvm/lib/Object/ELFObjectFile.cpp
index 2b6bdbf24afa0..cbc55a145e0e6 100644
--- a/llvm/lib/Object/ELFObjectFile.cpp
+++ b/llvm/lib/Object/ELFObjectFile.cpp
@@ -586,6 +586,8 @@ StringRef ELFObjectFileBase::getAMDGPUCPUName() const {
return "gfx1150";
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1151:
return "gfx1151";
+ case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1152:
+ return "gfx1152";
// AMDGCN GFX12.
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1200:
diff --git a/llvm/lib/ObjectYAML/ELFYAML.cpp b/llvm/lib/ObjectYAML/ELFYAML.cpp
index 8e2a9481c9227..0fee299994bc4 100644
--- a/llvm/lib/ObjectYAML/ELFYAML.cpp
+++ b/llvm/lib/ObjectYAML/ELFYAML.cpp
@@ -611,6 +611,7 @@ void ScalarBitSetTraits<ELFYAML::ELF_EF>::bitset(IO &IO,
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1103, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1150, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1151, EF_AMDGPU_MACH);
+ BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1152, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1200, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1201, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX9_GENERIC, EF_AMDGPU_MACH);
diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.td b/llvm/lib/Target/AMDGPU/AMDGPU.td
index 8e302786c746e..d0d7a9dc17247 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -1534,6 +1534,12 @@ def FeatureISAVersion11_5_1 : FeatureSet<
FeatureVGPRSingleUseHintInsts,
Feature1_5xVGPRs])>;
+def FeatureISAVersion11_5_2 : FeatureSet<
+ !listconcat(FeatureISAVersion11_Common.Features,
+ [FeatureSALUFloatInsts,
+ FeatureDPPSrc1SGPR,
+ FeatureVGPRSingleUseHintInsts])>;
+
def FeatureISAVersion12 : FeatureSet<
[FeatureGFX12,
FeatureLDSBankCount32,
diff --git a/llvm/lib/Target/AMDGPU/GCNProcessors.td b/llvm/lib/Target/AMDGPU/GCNProcessors.td
index 2ada981a77cd8..d218ffeb1fec7 100644
--- a/llvm/lib/Target/AMDGPU/GCNProcessors.td
+++ b/llvm/lib/Target/AMDGPU/GCNProcessors.td
@@ -295,7 +295,11 @@ def : ProcessorModel<"gfx1151", GFX11SpeedModel,
FeatureISAVersion11_5_1.Features
>;
-// [gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151]
+def : ProcessorModel<"gfx1152", GFX11SpeedModel,
+ FeatureISAVersion11_5_2.Features
+>;
+
+// [gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx1152]
def : ProcessorModel<"gfx11-generic", GFX11SpeedModel,
FeatureISAVersion11_Generic.Features
>;
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
index d7d6e00d23897..e805e964ffe4e 100644
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
@@ -113,6 +113,7 @@ StringRef AMDGPUTargetStreamer::getArchNameFromElfMach(unsigned ElfMach) {
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1103: AK = GK_GFX1103; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1150: AK = GK_GFX1150; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1151: AK = GK_GFX1151; break;
+ case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1152: AK = GK_GFX1152; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1200: AK = GK_GFX1200; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1201: AK = GK_GFX1201; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX9_GENERIC: AK = GK_GFX9_GENERIC; break;
@@ -196,6 +197,7 @@ unsigned AMDGPUTargetStreamer::getElfMach(StringRef GPU) {
case GK_GFX1103: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1103;
case GK_GFX1150: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1150;
case GK_GFX1151: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1151;
+ case GK_GFX1152: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1152;
case GK_GFX1200: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1200;
case GK_GFX1201: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1201;
case GK_GFX9_GENERIC: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX9_GENERIC;
diff --git a/llvm/lib/TargetParser/TargetParser.cpp b/llvm/lib/TargetParser/TargetParser.cpp
index 7464237d26d48..60a784ef002fe 100644
--- a/llvm/lib/TargetParser/TargetParser.cpp
+++ b/llvm/lib/TargetParser/TargetParser.cpp
@@ -124,6 +124,7 @@ constexpr GPUInfo AMDGCNGPUs[] = {
{{"gfx1103"}, {"gfx1103"}, GK_GFX1103, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_WGP},
{{"gfx1150"}, {"gfx1150"}, GK_GFX1150, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_WGP},
{{"gfx1151"}, {"gfx1151"}, GK_GFX1151, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_WGP},
+ {{"gfx1152"}, {"gfx1152"}, GK_GFX1152, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_WGP},
{{"gfx1200"}, {"gfx1200"}, GK_GFX1200, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_WGP},
{{"gfx1201"}, {"gfx1201"}, GK_GFX1201, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_WGP},
@@ -275,6 +276,7 @@ AMDGPU::IsaVersion AMDGPU::getIsaVersion(StringRef GPU) {
case GK_GFX1103: return {11, 0, 3};
case GK_GFX1150: return {11, 5, 0};
case GK_GFX1151: return {11, 5, 1};
+ case GK_GFX1152: return {11, 5, 2};
case GK_GFX1200: return {12, 0, 0};
case GK_GFX1201: return {12, 0, 1};
@@ -341,6 +343,7 @@ void AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T,
Features["image-insts"] = true;
Features["fp8-conversion-insts"] = true;
break;
+ case GK_GFX1152:
case GK_GFX1151:
case GK_GFX1150:
case GK_GFX1103:
@@ -542,6 +545,7 @@ static bool isWave32Capable(StringRef GPU, const Triple &T) {
switch (parseArchAMDGCN(GPU)) {
case GK_GFX1201:
case GK_GFX1200:
+ case GK_GFX1152:
case GK_GFX1151:
case GK_GFX1150:
case GK_GFX1103:
diff --git a/llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll b/llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
index c347437c30828..40d77a7f51e9d 100644
--- a/llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
+++ b/llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
@@ -105,6 +105,7 @@
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1103 < %s | FileCheck --check-prefixes=GFX1103 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1150 < %s | FileCheck --check-prefixes=GFX1150 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1151 < %s | FileCheck --check-prefixes=GFX1151 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1152 < %s | FileCheck --check-prefixes=GFX1152 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1200 < %s | FileCheck --check-prefixes=GFX1200 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1201 < %s | FileCheck --check-prefixes=GFX1201 %s
@@ -201,6 +202,7 @@
; GFX1103: .amdgcn_target "amdgcn-amd-amdhsa--gfx1103"
; GFX1150: .amdgcn_target "amdgcn-amd-amdhsa--gfx1150"
; GFX1151: .amdgcn_target "amdgcn-amd-amdhsa--gfx1151"
+; GFX1152: .amdgcn_target "amdgcn-amd-amdhsa--gfx1152"
; GFX1200: .amdgcn_target "amdgcn-amd-amdhsa--gfx1200"
; GFX1201: .amdgcn_target "amdgcn-amd-amdhsa--gfx1201"
diff --git a/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll b/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
index edc20153ffd77..19570dce19165 100644
--- a/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
+++ b/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
@@ -74,6 +74,7 @@
; RUN: llc -filetype=obj -mtriple=amdgcn -mcpu=gfx1103 < %s | llvm-readobj --file-header - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1103 %s
; RUN: llc -filetype=obj -mtriple=amdgcn -mcpu=gfx1150 < %s | llvm-readobj --file-header - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1150 %s
; RUN: llc -filetype=obj -mtriple=amdgcn -mcpu=gfx1151 < %s | llvm-readobj --file-header - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1151 %s
+; RUN: llc -filetype=obj -mtriple=amdgcn -mcpu=gfx1152 < %s | llvm-readobj --file-header - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1152 %s
; RUN: llc -filetype=obj -mtriple=amdgcn -mcpu=gfx1200 < %s | llvm-readobj --file-header - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1200 %s
; RUN: llc -filetype=obj -mtriple=amdgcn -mcpu=gfx1201 < %s | llvm-readobj --file-header - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1201 %s
@@ -153,6 +154,7 @@
; GFX1103: EF_AMDGPU_MACH_AMDGCN_GFX1103 (0x44)
; GFX1150: EF_AMDGPU_MACH_AMDGCN_GFX1150 (0x43)
; GFX1151: EF_AMDGPU_MACH_AMDGCN_GFX1151 (0x4A)
+; GFX1152: EF_AMDGPU_MACH_AMDGCN_GFX1151 (0x55)
; GFX1200: EF_AMDGPU_MACH_AMDGCN_GFX1200 (0x48)
; GFX1201: EF_AMDGPU_MACH_AMDGCN_GFX1201 (0x4E)
diff --git a/llvm/test/CodeGen/AMDGPU/occupancy-levels.ll b/llvm/test/CodeGen/AMDGPU/occupancy-levels.ll
index d87eb9711488c..e0ccda1cbb9ed 100644
--- a/llvm/test/CodeGen/AMDGPU/occupancy-levels.ll
+++ b/llvm/test/CodeGen/AMDGPU/occupancy-levels.ll
@@ -13,6 +13,8 @@
; RUN: llc -mtriple=amdgcn -mcpu=gfx1150 -mattr=+wavefrontsize64 < %s | FileCheck --check-prefixes=GCN,GFX10,GFX10W64,GFX1030,GFX1030W64 %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx1151 < %s | FileCheck --check-prefixes=GCN,GFX1100,GFX1100W32 %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx1151 -mattr=+wavefrontsize64 < %s | FileCheck --check-prefixes=GCN,GFX1100,GFX1100W64 %s
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1152 < %s | FileCheck --check-prefixes=GCN,GFX1030,GFX1030W32 %s
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1152 -mattr=+wavefrontsize64 < %s | FileCheck --check-prefixes=GCN,GFX1030,GFX1030W64 %s
; GCN-LABEL: {{^}}max_occupancy:
; GFX9: ; Occupancy: 10
diff --git a/llvm/test/MC/AMDGPU/gfx1150_asm_features.s b/llvm/test/MC/AMDGPU/gfx1150_asm_features.s
index 58b784779ac73..d3f82a217a172 100644
--- a/llvm/test/MC/AMDGPU/gfx1150_asm_features.s
+++ b/llvm/test/MC/AMDGPU/gfx1150_asm_features.s
@@ -1,5 +1,6 @@
// RUN: llvm-mc -triple=amdgcn -show-encoding -mcpu=gfx1150 %s | FileCheck --check-prefix=GFX1150 %s
// RUN: llvm-mc -triple=amdgcn -show-encoding -mcpu=gfx1151 %s | FileCheck --check-prefix=GFX1150 %s
+// RUN: llvm-mc -triple=amdgcn -show-encoding -mcpu=gfx1152 %s | FileCheck --check-prefix=GFX1150 %s
//
// Subtargets allow src1 of VOP3 DPP instructions to be SGPR or inlinable
diff --git a/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml b/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
index 7f36795aa6a9e..7512edd274912 100644
--- a/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ b/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -230,6 +230,10 @@
# RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX1151 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX1151 %s
# RUN: obj2yaml %t.o.AMDGCN_GFX1151 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX1151 %s
+# RUN: sed -e 's/<BITS>/64/' -e 's/<MACH>/AMDGCN_GFX1152/' %s | yaml2obj -o %t.o.AMDGCN_GFX1152
+# RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX1152 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX1152 %s
+# RUN: obj2yaml %t.o.AMDGCN_GFX1152 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX1152 %s
+
# RUN: sed -e 's/<BITS>/64/' -e 's/<MACH>/AMDGCN_GFX1200/' %s | yaml2obj -o %t.o.AMDGCN_GFX1200
# RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX1200 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX1200 %s
# RUN: obj2yaml %t.o.AMDGCN_GFX1200 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX1200 %s
@@ -450,6 +454,9 @@
# ELF-AMDGCN-GFX1151: EF_AMDGPU_MACH_AMDGCN_GFX1151 (0x4A)
# YAML-AMDGCN-GFX1151: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1151 ]
+# ELF-AMDGCN-GFX1152: EF_AMDGPU_MACH_AMDGCN_GFX1152 (0x55)
+# YAML-AMDGCN-GFX1152: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1152 ]
+
# ELF-AMDGCN-GFX1200: EF_AMDGPU_MACH_AMDGCN_GFX1200 (0x48)
# YAML-AMDGCN-GFX1200: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1200 ]
diff --git a/llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll b/llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
index f1262c5a2fc2a..f79f358e83a7c 100644
--- a/llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
+++ b/llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
@@ -28,6 +28,11 @@ define amdgpu_kernel void @test_kernel() {
; RUN: llvm-objdump -D -mllvm --amdhsa-code-object-version=6 %t.o > %t-detect.txt
; RUN: diff %t-specify.txt %t-detect.txt
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1152 -filetype=obj -O0 -o %t.o %s
+; RUN: llvm-objdump -D --arch-name=amdgcn --mcpu=gfx1152 %t.o > %t-specify.txt
+; RUN: llvm-objdump -D %t.o > %t-detect.txt
+; RUN: diff %t-specify.txt %t-detect.txt
+
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1151 -filetype=obj -O0 -o %t.o %s
; RUN: llvm-objdump -D --arch-name=amdgcn --mcpu=gfx1151 %t.o > %t-specify.txt
; RUN: llvm-objdump -D %t.o > %t-detect.txt
diff --git a/llvm/test/tools/llvm-readobj/ELF/AMDGPU/elf-headers.test b/llvm/test/tools/llvm-readobj/ELF/AMDGPU/elf-headers.test
index f9e90e21400ea..50d437b50b69b 100644
--- a/llvm/test/tools/llvm-readobj/ELF/AMDGPU/elf-headers.test
+++ b/llvm/test/tools/llvm-readobj/ELF/AMDGPU/elf-headers.test
@@ -421,6 +421,15 @@
# RUN: yaml2obj %s -o %t -DABI_VERSION=2 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1151
# RUN: llvm-readobj -h %t | FileCheck %s --check-prefixes=ALL,KNOWN-ABI-VERSION,SINGLE-FLAG --match-full-lines -DABI_VERSION=2 -DFILE=%t -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1151 -DFLAG_VALUE=0x4A
+# RUN: yaml2obj %s -o %t -DABI_VERSION=0 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1152
+# RUN: llvm-readobj -h %t | FileCheck %s --check-prefixes=ALL,KNOWN-ABI-VERSION,SINGLE-FLAG --match-full-lines -DABI_VERSION=0 -DFILE=%t -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1152 -DFLAG_VALUE=0x55
+
+# RUN: yaml2obj %s -o %t -DABI_VERSION=1 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1152
+# RUN: llvm-readobj -h %t | FileCheck %s --check-prefixes=ALL,KNOWN-ABI-VERSION,SINGLE-FLAG --match-full-lines -DABI_VERSION=1 -DFILE=%t -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1152 -DFLAG_VALUE=0x55
+
+# RUN: yaml2obj %s -o %t -DABI_VERSION=2 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1152
+# RUN: llvm-readobj -h %t | FileCheck %s --check-prefixes=ALL,KNOWN-ABI-VERSION,SINGLE-FLAG --match-full-lines -DABI_VERSION=2 -DFILE=%t -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1152 -DFLAG_VALUE=0x55
+
# RUN: yaml2obj %s -o %t -DABI_VERSION=0 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1200
# RUN: llvm-readobj -h %t | FileCheck %s --check-prefixes=ALL,KNOWN-ABI-VERSION,SINGLE-FLAG --match-full-lines -DABI_VERSION=0 -DFILE=%t -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1200 -DFLAG_VALUE=0x48
diff --git a/llvm/tools/llvm-readobj/ELFDumper.cpp b/llvm/tools/llvm-readobj/ELFDumper.cpp
index 40494da8b21bd..c696934a959b2 100644
--- a/llvm/tools/llvm-readobj/ELFDumper.cpp
+++ b/llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1631,6 +1631,7 @@ const EnumEntry<unsigned> ElfHeaderMipsFlags[] = {
ENUM_ENT(EF_AMDGPU_MACH_AMDGCN_GFX1103, "gfx1103"), \
ENUM_ENT(EF_AMDGPU_MACH_AMDGCN_GFX1150, "gfx1150"), \
ENUM_ENT(EF_AMDGPU_MACH_AMDGCN_GFX1151, "gfx1151"), \
+ ENUM_ENT(EF_AMDGPU_MACH_AMDGCN_GFX1152, "gfx1152"), \
ENUM_ENT(EF_AMDGPU_MACH_AMDGCN_GFX1200, "gfx1200"), \
ENUM_ENT(EF_AMDGPU_MACH_AMDGCN_GFX1201, "gfx1201"), \
ENUM_ENT(EF_AMDGPU_MACH_AMDGCN_GFX9_GENERIC, "gfx9-generic"), \
diff --git a/offload/DeviceRTL/CMakeLists.txt b/offload/DeviceRTL/CMakeLists.txt
index b356003672760..d88430a52b8b7 100644
--- a/offload/DeviceRTL/CMakeLists.txt
+++ b/offload/DeviceRTL/CMakeLists.txt
@@ -46,7 +46,7 @@ set(all_amdgpu_architectures "gfx700;gfx701;gfx801;gfx803;gfx900;gfx902;gfx906"
"gfx908;gfx90a;gfx90c;gfx940;gfx941;gfx942;gfx1010"
"gfx1030;gfx1031;gfx1032;gfx1033;gfx1034;gfx1035"
"gfx1036;gfx1100;gfx1101;gfx1102;gfx1103;gfx1150"
- "gfx1151")
+ "gfx1151;gfx1152")
set(all_nvptx_architectures "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;sm_87;sm_89;sm_90")
set(all_gpu_architectures
More information about the cfe-commits
mailing list