File llvm-Revert-GFX11-Add-a-new-target-gfx1152.patch of Package rocm-llvm
From bac776c5e5d5ec205d343302b3766123fbe0e4e9 Mon Sep 17 00:00:00 2001
From: Jeremy Newton <Jeremy.Newton@amd.com>
Date: Thu, 20 Jun 2024 17:48:59 -0400
Subject: [PATCH] Revert "GFX11: Add a new target gfx1152"
This reverts commit 2ae5c5326a5043a60e21a18ecf65701359f52bd8.
---
amd/comgr/docs/ReleaseNotes.md | 1 -
amd/comgr/src/comgr-isa-metadata.def | 1 -
amd/comgr/test/get_data_isa_name_test.c | 1 -
amd/device-libs/oclc/src/isa_version_1152.cl | 10 -------
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 --
.../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 +--
flang/runtime/CMakeLists.txt | 2 +-
llvm/docs/AMDGPUUsage.rst | 7 -----
llvm/include/llvm/BinaryFormat/ELF.h | 3 +--
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 | 4 ---
.../MCTargetDesc/AMDGPUTargetStreamer.cpp | 2 --
llvm/lib/TargetParser/TargetParser.cpp | 4 ---
.../CodeGen/AMDGPU/directive-amdgcn-target.ll | 2 --
.../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 -
.../Object/AMDGPU/elf-header-flags-mach.yaml | 7 -----
.../llvm-objdump/ELF/AMDGPU/subtarget.ll | 5 ----
.../llvm-readobj/ELF/amdgpu-elf-headers.test | 9 -------
llvm/tools/llvm-readobj/ELFDumper.cpp | 2 --
openmp/libomptarget/DeviceRTL/CMakeLists.txt | 4 +--
openmp/libomptarget/hostexec/CMakeLists.txt | 26 +++++++++----------
33 files changed, 19 insertions(+), 100 deletions(-)
delete mode 100644 amd/device-libs/oclc/src/isa_version_1152.cl
diff --git a/amd/comgr/docs/ReleaseNotes.md b/amd/comgr/docs/ReleaseNotes.md
index c6f5220f9ab0..2f35caa6b075 100644
--- a/amd/comgr/docs/ReleaseNotes.md
+++ b/amd/comgr/docs/ReleaseNotes.md
@@ -166,7 +166,6 @@ New Targets
- gfx1036
- gfx1150
- gfx1151
- - gfx1152
Removed Targets
---------------
diff --git a/amd/comgr/src/comgr-isa-metadata.def b/amd/comgr/src/comgr-isa-metadata.def
index bc22294ca451..156aae5eb2f6 100644
--- a/amd/comgr/src/comgr-isa-metadata.def
+++ b/amd/comgr/src/comgr-isa-metadata.def
@@ -89,7 +89,6 @@ HANDLE_ISA("amdgcn-amd-amdhsa-", "gfx1102", false, false, EF_AMDGPU_MACH_AMDGCN
HANDLE_ISA("amdgcn-amd-amdhsa-", "gfx1103", false, false, EF_AMDGPU_MACH_AMDGCN_GFX1103, true, 65536, 32, 4, 40, 1024, 106, 800, 106, 16, 1024, 256)
HANDLE_ISA("amdgcn-amd-amdhsa-", "gfx1150", false, false, EF_AMDGPU_MACH_AMDGCN_GFX1150, true, 65536, 32, 4, 40, 1024, 106, 800, 106, 16, 1024, 256)
HANDLE_ISA("amdgcn-amd-amdhsa-", "gfx1151", false, false, EF_AMDGPU_MACH_AMDGCN_GFX1151, true, 65536, 32, 4, 40, 1024, 106, 800, 106, 24, 1536, 256)
-HANDLE_ISA("amdgcn-amd-amdhsa-", "gfx1152", false, false, EF_AMDGPU_MACH_AMDGCN_GFX1152, true, 65536, 32, 4, 40, 1024, 106, 800, 106, 16, 1024, 256)
HANDLE_ISA("amdgcn-amd-amdhsa-", "gfx1200", false, false, EF_AMDGPU_MACH_AMDGCN_GFX1200, true, 65536, 32, 4, 40, 1024, 106, 800, 106, 24, 1536, 256)
HANDLE_ISA("amdgcn-amd-amdhsa-", "gfx1201", false, false, EF_AMDGPU_MACH_AMDGCN_GFX1201, true, 65536, 32, 4, 40, 1024, 106, 800, 106, 24, 1536, 256)
diff --git a/amd/comgr/test/get_data_isa_name_test.c b/amd/comgr/test/get_data_isa_name_test.c
index 8b2e1fa1f8ed..58889a4fb286 100644
--- a/amd/comgr/test/get_data_isa_name_test.c
+++ b/amd/comgr/test/get_data_isa_name_test.c
@@ -104,7 +104,6 @@ static isa_features_t IsaFeatures[] = {
{"amdgcn-amd-amdhsa--gfx1103", false, false, none, false, none},
{"amdgcn-amd-amdhsa--gfx1150", false, false, none, false, none},
{"amdgcn-amd-amdhsa--gfx1151", false, false, none, false, none},
- {"amdgcn-amd-amdhsa--gfx1152", false, false, none, false, none},
{"amdgcn-amd-amdhsa--gfx1200", false, false, none, false, none},
{"amdgcn-amd-amdhsa--gfx1201", false, false, none, false, none},
};
diff --git a/amd/device-libs/oclc/src/isa_version_1152.cl b/amd/device-libs/oclc/src/isa_version_1152.cl
deleted file mode 100644
index a210e55ad9eb..000000000000
--- a/amd/device-libs/oclc/src/isa_version_1152.cl
+++ /dev/null
@@ -1,10 +0,0 @@
-/*===--------------------------------------------------------------------------
- * ROCm Device Libraries
- *
- * This file is distributed under the University of Illinois Open Source
- * License. See LICENSE.TXT for details.
- *===------------------------------------------------------------------------*/
-
-#include "oclc.h"
-
-const __constant int __oclc_ISA_version = 11502;
diff --git a/clang/include/clang/Basic/Cuda.h b/clang/include/clang/Basic/Cuda.h
index 6d38e0ed234a..916cb4b7ef34 100644
--- a/clang/include/clang/Basic/Cuda.h
+++ b/clang/include/clang/Basic/Cuda.h
@@ -116,7 +116,6 @@ enum class CudaArch {
GFX1103,
GFX1150,
GFX1151,
- GFX1152,
GFX1200,
GFX1201,
Generic, // A processor model named 'generic' if the target backend defines a
diff --git a/clang/lib/Basic/Cuda.cpp b/clang/lib/Basic/Cuda.cpp
index 81ece07367d9..1b1da6a1356f 100644
--- a/clang/lib/Basic/Cuda.cpp
+++ b/clang/lib/Basic/Cuda.cpp
@@ -138,7 +138,6 @@ static const CudaArchToStringMap arch_names[] = {
GFX(1103), // gfx1103
GFX(1150), // gfx1150
GFX(1151), // gfx1151
- GFX(1152), // gfx1152
GFX(1200), // gfx1200
GFX(1201), // gfx1201
{CudaArch::Generic, "generic", ""},
diff --git a/clang/lib/Basic/Targets/NVPTX.cpp b/clang/lib/Basic/Targets/NVPTX.cpp
index 843fdf82b23c..c0b5db795e27 100644
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -214,7 +214,6 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
case CudaArch::GFX1103:
case CudaArch::GFX1150:
case CudaArch::GFX1151:
- case CudaArch::GFX1152:
case CudaArch::GFX1200:
case CudaArch::GFX1201:
case CudaArch::Generic:
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index 8a5c8c976828..d7b084283e97 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -3749,7 +3749,6 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(
case CudaArch::GFX1103:
case CudaArch::GFX1150:
case CudaArch::GFX1151:
- case CudaArch::GFX1152:
case CudaArch::GFX1200:
case CudaArch::GFX1201:
case CudaArch::Generic:
diff --git a/clang/test/CodeGenOpenCL/amdgpu-features.cl b/clang/test/CodeGenOpenCL/amdgpu-features.cl
index 7c9dd331e381..e1021241728c 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-features.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-features.cl
@@ -49,7 +49,6 @@
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1103 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1103 %s
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1150 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1150 %s
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1151 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1151 %s
-// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1152 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1152 %s
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1200 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1200 %s
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1201 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1201 %s
@@ -101,7 +100,6 @@
// 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,+dot5-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,+dot5-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 49d3751b85ec..cddc83c013c0 100644
--- a/clang/test/CodeGenOpenCL/builtins-amdgcn-gfx11.cl
+++ b/clang/test/CodeGenOpenCL/builtins-amdgcn-gfx11.cl
@@ -5,7 +5,6 @@
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1103 -S -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1150 -S -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1151 -S -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1152 -S -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 8b2b0c1d7024..81c22af460d1 100644
--- a/clang/test/Driver/amdgpu-macros.cl
+++ b/clang/test/Driver/amdgpu-macros.cl
@@ -128,7 +128,6 @@
// 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 d6e31b9ea469..eeb16ae98eba 100644
--- a/clang/test/Driver/amdgpu-mcpu.cl
+++ b/clang/test/Driver/amdgpu-mcpu.cl
@@ -112,7 +112,6 @@
// 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
@@ -159,6 +158,5 @@
// 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 0d70242d94e8..48e9f05d9b03 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, 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{{$}}
+// NVPTX-NEXT: note: valid target CPU values are: sm_20, sm_21, sm_30, sm_32, sm_35, sm_37, sm_50, sm_52, sm_53, sm_60, sm_61, sm_62, sm_70, sm_72, sm_75, sm_80, sm_86, sm_87, sm_89, sm_90, sm_90a, gfx600, gfx601, gfx602, gfx700, gfx701, gfx702, gfx703, gfx704, gfx705, gfx801, gfx802, gfx803, gfx805, gfx810, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx941, gfx942, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx1200, gfx1201{{$}}
// 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, gfx1152, gfx1200, gfx1201{{$}}
+// AMDGCN-NEXT: note: valid target CPU values are: gfx600, tahiti, gfx601, pitcairn, verde, gfx602, hainan, oland, gfx700, kaveri, gfx701, hawaii, gfx702, gfx703, kabini, mullins, gfx704, bonaire, gfx705, gfx801, carrizo, gfx802, iceland, tonga, gfx803, fiji, polaris10, polaris11, gfx805, tongapro, gfx810, stoney, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx941, gfx942, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx1200, gfx1201{{$}}
// 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/flang/runtime/CMakeLists.txt b/flang/runtime/CMakeLists.txt
index c8f1fae56925..dfa9da502db0 100644
--- a/flang/runtime/CMakeLists.txt
+++ b/flang/runtime/CMakeLists.txt
@@ -256,7 +256,7 @@ if (NOT FLANG_EXPERIMENTAL_OMP_OFFLOAD_BUILD STREQUAL "off")
"gfx700;gfx701;gfx801;gfx803;gfx900;gfx902;gfx906"
"gfx908;gfx90a;gfx90c;gfx940;gfx1010;gfx1030"
"gfx1031;gfx1032;gfx1033;gfx1034;gfx1035;gfx1036"
- "gfx1100;gfx1101;gfx1102;gfx1103;gfx1150;gfx1151;gfx1152"
+ "gfx1100;gfx1101;gfx1102;gfx1103;gfx1150;gfx1151"
)
set(all_nvptx_architectures
"sm_35;sm_37;sm_50;sm_52;sm_53;sm_60;sm_61;sm_62"
diff --git a/llvm/docs/AMDGPUUsage.rst b/llvm/docs/AMDGPUUsage.rst
index 8db31e6d3d90..3af1a872c186 100644
--- a/llvm/docs/AMDGPUUsage.rst
+++ b/llvm/docs/AMDGPUUsage.rst
@@ -504,12 +504,6 @@ Every processor supports every OS ABI (see :ref:`amdgpu-os`) with the following
- Packed
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
@@ -1722,7 +1716,6 @@ 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``
- ``EF_AMDGPU_MACH_AMDGCN_GFX1152`` 0x055 ``gfx1152``
==================================== ========== =============================
Sections
diff --git a/llvm/include/llvm/BinaryFormat/ELF.h b/llvm/include/llvm/BinaryFormat/ELF.h
index e6475ca7ae15..81cdd39afc6b 100644
--- a/llvm/include/llvm/BinaryFormat/ELF.h
+++ b/llvm/include/llvm/BinaryFormat/ELF.h
@@ -789,12 +789,11 @@ enum : unsigned {
EF_AMDGPU_MACH_AMDGCN_GFX1201 = 0x04e,
EF_AMDGPU_MACH_AMDGCN_RESERVED_0X4F = 0x04f,
EF_AMDGPU_MACH_AMDGCN_RESERVED_0X50 = 0x050,
- EF_AMDGPU_MACH_AMDGCN_GFX1152 = 0x055,
// clang-format on
// First/last AMDGCN-based processors.
EF_AMDGPU_MACH_AMDGCN_FIRST = EF_AMDGPU_MACH_AMDGCN_GFX600,
- EF_AMDGPU_MACH_AMDGCN_LAST = EF_AMDGPU_MACH_AMDGCN_GFX1152,
+ EF_AMDGPU_MACH_AMDGCN_LAST = EF_AMDGPU_MACH_AMDGCN_GFX1201,
// Indicates if the "xnack" target feature is enabled for all code contained
// in the object.
diff --git a/llvm/include/llvm/TargetParser/TargetParser.h b/llvm/include/llvm/TargetParser/TargetParser.h
index b0ea0acc3f68..6464285980f0 100644
--- a/llvm/include/llvm/TargetParser/TargetParser.h
+++ b/llvm/include/llvm/TargetParser/TargetParser.h
@@ -105,7 +105,6 @@ 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 aba4aa09b3bd..ae21b81c10c8 100644
--- a/llvm/lib/Object/ELFObjectFile.cpp
+++ b/llvm/lib/Object/ELFObjectFile.cpp
@@ -508,8 +508,6 @@ 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 1bf83f3d9137..6ad4a067415a 100644
--- a/llvm/lib/ObjectYAML/ELFYAML.cpp
+++ b/llvm/lib/ObjectYAML/ELFYAML.cpp
@@ -610,7 +610,6 @@ 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);
switch (Object->Header.ABIVersion) {
diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.td b/llvm/lib/Target/AMDGPU/AMDGPU.td
index 6b4287f37ea2..05768503132d 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -1505,12 +1505,6 @@ def FeatureISAVersion11_5_1 : FeatureSet<
FeatureVGPRSingleUseHintInsts,
FeatureGFX11FullVGPRs])>;
-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 ba2b9a11a9b1..96af1a6aab3d 100644
--- a/llvm/lib/Target/AMDGPU/GCNProcessors.td
+++ b/llvm/lib/Target/AMDGPU/GCNProcessors.td
@@ -280,10 +280,6 @@ def : ProcessorModel<"gfx1151", GFX11SpeedModel,
FeatureISAVersion11_5_1.Features
>;
-def : ProcessorModel<"gfx1152", GFX11SpeedModel,
- FeatureISAVersion11_5_2.Features
->;
-
//===----------------------------------------------------------------------===//
// GCN GFX12.
//===----------------------------------------------------------------------===//
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
index 6cb198831756..955b6f6f05ca 100644
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
@@ -126,7 +126,6 @@ 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_NONE: AK = GK_NONE; break;
@@ -205,7 +204,6 @@ 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_NONE: return ELF::EF_AMDGPU_MACH_NONE;
diff --git a/llvm/lib/TargetParser/TargetParser.cpp b/llvm/lib/TargetParser/TargetParser.cpp
index 760dfe5e2f93..ecea6c305852 100644
--- a/llvm/lib/TargetParser/TargetParser.cpp
+++ b/llvm/lib/TargetParser/TargetParser.cpp
@@ -124,7 +124,6 @@ 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},
// clang-format on
@@ -252,7 +251,6 @@ 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};
default: return {0, 0, 0};
@@ -299,7 +297,6 @@ 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:
@@ -497,7 +494,6 @@ 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 6dcf377f3a8b..357fcf8ef156 100644
--- a/llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
+++ b/llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
@@ -105,7 +105,6 @@
; 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
@@ -194,7 +193,6 @@
; 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 e0475f422619..380439d8cd9c 100644
--- a/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
+++ b/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
@@ -74,7 +74,6 @@
; 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
@@ -148,7 +147,6 @@
; 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_GFX1152 (0x55)
; GFX1200: EF_AMDGPU_MACH_AMDGCN_GFX1200 (0x48)
; GFX1201: EF_AMDGPU_MACH_AMDGCN_GFX1201 (0x4E)
; ALL: ]
diff --git a/llvm/test/CodeGen/AMDGPU/occupancy-levels.ll b/llvm/test/CodeGen/AMDGPU/occupancy-levels.ll
index e0ccda1cbb9e..d87eb9711488 100644
--- a/llvm/test/CodeGen/AMDGPU/occupancy-levels.ll
+++ b/llvm/test/CodeGen/AMDGPU/occupancy-levels.ll
@@ -13,8 +13,6 @@
; 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 5a957661f27e..55c855175a89 100644
--- a/llvm/test/MC/AMDGPU/gfx1150_asm_features.s
+++ b/llvm/test/MC/AMDGPU/gfx1150_asm_features.s
@@ -1,6 +1,5 @@
// RUN: llvm-mc -arch=amdgcn -show-encoding -mcpu=gfx1150 %s | FileCheck --check-prefix=GFX1150 %s
// RUN: llvm-mc -arch=amdgcn -show-encoding -mcpu=gfx1151 %s | FileCheck --check-prefix=GFX1150 %s
-// RUN: llvm-mc -arch=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 48cb8ba33c50..7fb33ca662b1 100644
--- a/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ b/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -230,10 +230,6 @@
# 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
@@ -433,9 +429,6 @@
# 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 5efdc437c035..e296d7fb1fc8 100644
--- a/llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
+++ b/llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
@@ -18,11 +18,6 @@ define amdgpu_kernel void @test_kernel() {
; ----------------------------------GFX11--------------------------------------
;
-; 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 e53b8bcf8914..e2266d81d1a5 100644
--- a/llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
+++ b/llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
@@ -409,15 +409,6 @@
# 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 0e338de94c0d..f369a63add11 100644
--- a/llvm/tools/llvm-readobj/ELFDumper.cpp
+++ b/llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1618,7 +1618,6 @@ const EnumEntry<unsigned> ElfHeaderAMDGPUFlagsABIVersion3[] = {
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_FEATURE_XNACK_V3, "xnack"),
@@ -1685,7 +1684,6 @@ const EnumEntry<unsigned> ElfHeaderAMDGPUFlagsABIVersion4[] = {
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_FEATURE_XNACK_ANY_V4, "xnack"),
diff --git a/openmp/libomptarget/DeviceRTL/CMakeLists.txt b/openmp/libomptarget/DeviceRTL/CMakeLists.txt
index 52b0425aba40..070a5e0ccbe2 100644
--- a/openmp/libomptarget/DeviceRTL/CMakeLists.txt
+++ b/openmp/libomptarget/DeviceRTL/CMakeLists.txt
@@ -60,7 +60,7 @@ 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;gfx1152")
+ "gfx1151")
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
@@ -130,7 +130,7 @@ set(src_files
# vectorized accesses to the shared state. Generally, those are "good" but
# the optimizer pipeline (esp. Attributor) does not fully support vectorized
# instructions yet and we end up missing out on way more important constant
-# propagation. That said, we will run the vectorizer again after the runtime
+# propagation. That said, we will run the vectorizer again after the runtime
# has been linked into the user program.
set(clang_opt_flags -O3 -mllvm -openmp-opt-disable -DSHARED_SCRATCHPAD_SIZE=512 -mllvm -vectorize-slp=false )
set(link_opt_flags -O3 -openmp-opt-disable -attributor-enable=module -vectorize-slp=false )
diff --git a/openmp/libomptarget/hostexec/CMakeLists.txt b/openmp/libomptarget/hostexec/CMakeLists.txt
index dc8b255b3b31..b13fba0a9a75 100644
--- a/openmp/libomptarget/hostexec/CMakeLists.txt
+++ b/openmp/libomptarget/hostexec/CMakeLists.txt
@@ -44,10 +44,10 @@ else()
endif()
list(APPEND HOSTRPC_ARCHS "amdgcn")
- add_library(amdgcn_hostexec_services STATIC
- services/amdgcn_hostexec.cpp
- services/execute_service.cpp
- services/devsanitizer.cpp
+ add_library(amdgcn_hostexec_services STATIC
+ services/amdgcn_hostexec.cpp
+ services/execute_service.cpp
+ services/devsanitizer.cpp
services/amdgcn_urilocator.cpp
${HOSTEXEC_EXTRA_SOURCE}
)
@@ -72,7 +72,7 @@ endif()
if (LIBOMPTARGET_DEP_CUDA_FOUND)
list(APPEND HOSTRPC_ARCHS "nvptx")
- add_library(nvptx_hostexec_services STATIC
+ add_library(nvptx_hostexec_services STATIC
services/execute_service.cpp
)
target_include_directories(
@@ -100,7 +100,7 @@ else()
return()
endif()
-set(amdgpu_mcpus 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 gfx1152)
+set(amdgpu_mcpus 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)
if (DEFINED LIBOMPTARGET_AMDGCN_GFXLIST)
set(amdgpu_mcpus ${LIBOMPTARGET_AMDGCN_GFXLIST})
endif()
@@ -158,23 +158,23 @@ foreach(archname ${HOSTRPC_ARCHS})
foreach(mcpu ${mcpus})
if (${archname} STREQUAL "amdgcn")
- set(openmp_device_args
+ set(openmp_device_args
-I../../runtime/src # to pickup omp.h, we may need a dependency
-O${optimization_level}
- -fopenmp -fopenmp-cuda-mode -mllvm -openmp-opt-disable
- -std=c++17 -fvisibility=hidden
+ -fopenmp -fopenmp-cuda-mode -mllvm -openmp-opt-disable
+ -std=c++17 -fvisibility=hidden
-fopenmp-targets=${triple} -Xopenmp-target=${triple} -march=${mcpu}
-Xclang -mcode-object-version=none
-c -emit-llvm --offload-device-only -nogpulib)
endif()
if (${archname} STREQUAL "nvptx")
- set(openmp_device_args
+ set(openmp_device_args
-I../../runtime/src # to pickup omp.h, we may need a dependency
- -fopenmp -fopenmp-cuda-mode -mllvm -openmp-opt-disable
- -std=c++17 -fvisibility=hidden
+ -fopenmp -fopenmp-cuda-mode -mllvm -openmp-opt-disable
+ -std=c++17 -fvisibility=hidden
-fopenmp-targets=${triple} -Xopenmp-target=${triple} -march=${mcpu}
--cuda-feature=+ptx61,+${mcpu}
- -c -emit-llvm --offload-device-only -nocudalib -nogpulib
+ -c -emit-llvm --offload-device-only -nocudalib -nogpulib
-Wno-unknown-cuda-version)
endif()
--
2.45.2