[clang] 464e4dc - [AMDGPU] Add gfx1034 target
Aakanksha Patil via cfe-commits
cfe-commits at lists.llvm.org
Thu May 13 11:25:35 PDT 2021
Author: Aakanksha Patil
Date: 2021-05-13T14:25:18-04:00
New Revision: 464e4dc50f4e6e058e12a7020385d5bf29fd1df6
URL: https://github.com/llvm/llvm-project/commit/464e4dc50f4e6e058e12a7020385d5bf29fd1df6
DIFF: https://github.com/llvm/llvm-project/commit/464e4dc50f4e6e058e12a7020385d5bf29fd1df6.diff
LOG: [AMDGPU] Add gfx1034 target
Differential Revision: https://reviews.llvm.org/D102306
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
llvm/docs/AMDGPUUsage.rst
llvm/include/llvm/BinaryFormat/ELF.h
llvm/include/llvm/Support/TargetParser.h
llvm/lib/Object/ELFObjectFile.cpp
llvm/lib/ObjectYAML/ELFYAML.cpp
llvm/lib/Support/TargetParser.cpp
llvm/lib/Target/AMDGPU/GCNProcessors.td
llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
llvm/test/MC/AMDGPU/gfx1011_dlops.s
llvm/test/MC/AMDGPU/gfx1030_err.s
llvm/test/MC/AMDGPU/gfx1030_new.s
llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
llvm/tools/llvm-readobj/ELFDumper.cpp
openmp/libomptarget/plugins/amdgpu/impl/get_elf_mach_gfx_name.cpp
Removed:
################################################################################
diff --git a/clang/include/clang/Basic/Cuda.h b/clang/include/clang/Basic/Cuda.h
index f1d69d6dce50e..e580fea9c5102 100644
--- a/clang/include/clang/Basic/Cuda.h
+++ b/clang/include/clang/Basic/Cuda.h
@@ -87,6 +87,7 @@ enum class CudaArch {
GFX1031,
GFX1032,
GFX1033,
+ GFX1034,
LAST,
};
diff --git a/clang/lib/Basic/Cuda.cpp b/clang/lib/Basic/Cuda.cpp
index da3bbe110d107..79cc6c9d7489d 100644
--- a/clang/lib/Basic/Cuda.cpp
+++ b/clang/lib/Basic/Cuda.cpp
@@ -109,6 +109,7 @@ static const CudaArchToStringMap arch_names[] = {
GFX(1031), // gfx1031
GFX(1032), // gfx1032
GFX(1033), // gfx1033
+ GFX(1034), // gfx1034
// clang-format on
};
#undef SM
diff --git a/clang/lib/Basic/Targets/AMDGPU.cpp b/clang/lib/Basic/Targets/AMDGPU.cpp
index ead0b69b1ca86..7cffe3d527b86 100644
--- a/clang/lib/Basic/Targets/AMDGPU.cpp
+++ b/clang/lib/Basic/Targets/AMDGPU.cpp
@@ -180,6 +180,7 @@ 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_GFX1034:
case GK_GFX1033:
case GK_GFX1032:
case GK_GFX1031:
diff --git a/clang/lib/Basic/Targets/NVPTX.cpp b/clang/lib/Basic/Targets/NVPTX.cpp
index 25e065ce584e6..70ddff4c7cf35 100644
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -211,6 +211,7 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
case CudaArch::GFX1031:
case CudaArch::GFX1032:
case CudaArch::GFX1033:
+ case CudaArch::GFX1034:
case CudaArch::LAST:
break;
case CudaArch::UNUSED:
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index 1fd9b9c28338d..fd492eaf705d0 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -4486,6 +4486,7 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(
case CudaArch::GFX1031:
case CudaArch::GFX1032:
case CudaArch::GFX1033:
+ case CudaArch::GFX1034:
case CudaArch::UNUSED:
case CudaArch::UNKNOWN:
break;
@@ -4556,6 +4557,7 @@ static std::pair<unsigned, unsigned> getSMsBlocksPerSM(CodeGenModule &CGM) {
case CudaArch::GFX1031:
case CudaArch::GFX1032:
case CudaArch::GFX1033:
+ case CudaArch::GFX1034:
case CudaArch::UNUSED:
case CudaArch::UNKNOWN:
break;
diff --git a/clang/test/CodeGenOpenCL/amdgpu-features.cl b/clang/test/CodeGenOpenCL/amdgpu-features.cl
index 5c9059866e88e..35c1ab3c1a6d8 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-features.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-features.cl
@@ -32,6 +32,7 @@
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1031 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1031 %s
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1032 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1032 %s
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1033 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1033 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1034 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1034 %s
// GFX600: "target-features"="+s-memtime-inst"
// GFX601: "target-features"="+s-memtime-inst"
@@ -62,5 +63,6 @@
// GFX1031: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
// GFX1032: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
// GFX1033: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
+// GFX1034: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
kernel void test() {}
diff --git a/clang/test/Driver/amdgpu-macros.cl b/clang/test/Driver/amdgpu-macros.cl
index 297e82f6c2243..6c30ec27ff2ef 100644
--- a/clang/test/Driver/amdgpu-macros.cl
+++ b/clang/test/Driver/amdgpu-macros.cl
@@ -114,6 +114,7 @@
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1031 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1031
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1032 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1032
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1033 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1033
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1034 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1034
// 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 1dac9883a561d..bb9fd6c062f14 100644
--- a/clang/test/Driver/amdgpu-mcpu.cl
+++ b/clang/test/Driver/amdgpu-mcpu.cl
@@ -99,6 +99,7 @@
// RUN: %clang -### -target amdgcn -mcpu=gfx1031 %s 2>&1 | FileCheck --check-prefix=GFX1031 %s
// RUN: %clang -### -target amdgcn -mcpu=gfx1032 %s 2>&1 | FileCheck --check-prefix=GFX1032 %s
// RUN: %clang -### -target amdgcn -mcpu=gfx1033 %s 2>&1 | FileCheck --check-prefix=GFX1033 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx1034 %s 2>&1 | FileCheck --check-prefix=GFX1034 %s
// GCNDEFAULT-NOT: -target-cpu
// GFX600: "-target-cpu" "gfx600"
@@ -130,3 +131,4 @@
// GFX1031: "-target-cpu" "gfx1031"
// GFX1032: "-target-cpu" "gfx1032"
// GFX1033: "-target-cpu" "gfx1033"
+// GFX1034: "-target-cpu" "gfx1034"
diff --git a/clang/test/Misc/target-invalid-cpu-note.c b/clang/test/Misc/target-invalid-cpu-note.c
index 7f5ebe2879766..b25325a412d23 100644
--- a/clang/test/Misc/target-invalid-cpu-note.c
+++ b/clang/test/Misc/target-invalid-cpu-note.c
@@ -87,7 +87,7 @@
// AMDGCN-SAME: gfx802, iceland, tonga, gfx803, fiji, polaris10, polaris11,
// AMDGCN-SAME: gfx805, tongapro, gfx810, stoney, gfx900, gfx902, gfx904, gfx906,
// AMDGCN-SAME: gfx908, gfx909, gfx90a, gfx90c, gfx1010, gfx1011, gfx1012, gfx1030, gfx1031,
-// AMDGCN-SAME: gfx1032, gfx1033
+// AMDGCN-SAME: gfx1032, gfx1033, gfx1034
// 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/llvm/docs/AMDGPUUsage.rst b/llvm/docs/AMDGPUUsage.rst
index ae9bb58f854cf..4e7efd769705e 100644
--- a/llvm/docs/AMDGPUUsage.rst
+++ b/llvm/docs/AMDGPUUsage.rst
@@ -406,6 +406,12 @@ Every processor supports every OS ABI (see :ref:`amdgpu-os`) with the following
Add product
names.
+ ``gfx1034`` ``amdgcn`` dGPU - cumode - Absolute - *pal-amdpal* *TBA*
+ - wavefrontsize64 flat
+ scratch .. TODO::
+
+ Add product
+ names.
=========== =============== ============ ===== ================= =============== =============== ======================
@@ -1134,6 +1140,7 @@ The AMDGPU backend uses the following ELF header:
``EF_AMDGPU_MACH_AMDGCN_GFX1031`` 0x037 ``gfx1031``
``EF_AMDGPU_MACH_AMDGCN_GFX1032`` 0x038 ``gfx1032``
``EF_AMDGPU_MACH_AMDGCN_GFX1033`` 0x039 ``gfx1033``
+ ``EF_AMDGPU_MACH_AMDGCN_GFX1034`` 0x03e ``gfx1034``
``EF_AMDGPU_MACH_AMDGCN_GFX602`` 0x03a ``gfx602``
``EF_AMDGPU_MACH_AMDGCN_GFX705`` 0x03b ``gfx705``
``EF_AMDGPU_MACH_AMDGCN_GFX805`` 0x03c ``gfx805``
diff --git a/llvm/include/llvm/BinaryFormat/ELF.h b/llvm/include/llvm/BinaryFormat/ELF.h
index f1046dbc87db9..88f4aaea7b977 100644
--- a/llvm/include/llvm/BinaryFormat/ELF.h
+++ b/llvm/include/llvm/BinaryFormat/ELF.h
@@ -734,6 +734,7 @@ enum : unsigned {
EF_AMDGPU_MACH_AMDGCN_GFX1031 = 0x037,
EF_AMDGPU_MACH_AMDGCN_GFX1032 = 0x038,
EF_AMDGPU_MACH_AMDGCN_GFX1033 = 0x039,
+ EF_AMDGPU_MACH_AMDGCN_GFX1034 = 0x03e,
EF_AMDGPU_MACH_AMDGCN_GFX602 = 0x03a,
EF_AMDGPU_MACH_AMDGCN_GFX705 = 0x03b,
EF_AMDGPU_MACH_AMDGCN_GFX805 = 0x03c,
diff --git a/llvm/include/llvm/Support/TargetParser.h b/llvm/include/llvm/Support/TargetParser.h
index 03d4e65d95624..703fd74fe6e8b 100644
--- a/llvm/include/llvm/Support/TargetParser.h
+++ b/llvm/include/llvm/Support/TargetParser.h
@@ -93,9 +93,10 @@ enum GPUKind : uint32_t {
GK_GFX1031 = 76,
GK_GFX1032 = 77,
GK_GFX1033 = 78,
+ GK_GFX1034 = 79,
GK_AMDGCN_FIRST = GK_GFX600,
- GK_AMDGCN_LAST = GK_GFX1033,
+ GK_AMDGCN_LAST = GK_GFX1034,
};
/// Instruction set architecture version.
diff --git a/llvm/lib/Object/ELFObjectFile.cpp b/llvm/lib/Object/ELFObjectFile.cpp
index 8285e3d9e659c..a3911f3df9c23 100644
--- a/llvm/lib/Object/ELFObjectFile.cpp
+++ b/llvm/lib/Object/ELFObjectFile.cpp
@@ -477,6 +477,8 @@ StringRef ELFObjectFileBase::getAMDGPUCPUName() const {
return "gfx1032";
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1033:
return "gfx1033";
+ case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1034:
+ return "gfx1034";
default:
llvm_unreachable("Unknown EF_AMDGPU_MACH value");
}
diff --git a/llvm/lib/ObjectYAML/ELFYAML.cpp b/llvm/lib/ObjectYAML/ELFYAML.cpp
index 9b8920b4800db..f20c26a7f5fc5 100644
--- a/llvm/lib/ObjectYAML/ELFYAML.cpp
+++ b/llvm/lib/ObjectYAML/ELFYAML.cpp
@@ -552,6 +552,7 @@ void ScalarBitSetTraits<ELFYAML::ELF_EF>::bitset(IO &IO,
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1031, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1032, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1033, EF_AMDGPU_MACH);
+ BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1034, EF_AMDGPU_MACH);
switch (Object->Header.ABIVersion) {
default:
// ELFOSABI_AMDGPU_PAL, ELFOSABI_AMDGPU_MESA3D support *_V3 flags.
diff --git a/llvm/lib/Support/TargetParser.cpp b/llvm/lib/Support/TargetParser.cpp
index e0a00a0b9b45f..973da1392f5b6 100644
--- a/llvm/lib/Support/TargetParser.cpp
+++ b/llvm/lib/Support/TargetParser.cpp
@@ -113,6 +113,7 @@ constexpr GPUInfo AMDGCNGPUs[] = {
{{"gfx1031"}, {"gfx1031"}, GK_GFX1031, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32},
{{"gfx1032"}, {"gfx1032"}, GK_GFX1032, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32},
{{"gfx1033"}, {"gfx1033"}, GK_GFX1033, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32},
+ {{"gfx1034"}, {"gfx1034"}, GK_GFX1034, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32},
};
const GPUInfo *getArchEntry(AMDGPU::GPUKind AK, ArrayRef<GPUInfo> Table) {
@@ -223,6 +224,7 @@ AMDGPU::IsaVersion AMDGPU::getIsaVersion(StringRef GPU) {
case GK_GFX1031: return {10, 3, 1};
case GK_GFX1032: return {10, 3, 2};
case GK_GFX1033: return {10, 3, 3};
+ case GK_GFX1034: return {10, 3, 4};
default: return {0, 0, 0};
}
}
diff --git a/llvm/lib/Target/AMDGPU/GCNProcessors.td b/llvm/lib/Target/AMDGPU/GCNProcessors.td
index 888bbbb9d3c1e..2028d4d74bf53 100644
--- a/llvm/lib/Target/AMDGPU/GCNProcessors.td
+++ b/llvm/lib/Target/AMDGPU/GCNProcessors.td
@@ -223,3 +223,7 @@ def : ProcessorModel<"gfx1032", GFX10SpeedModel,
def : ProcessorModel<"gfx1033", GFX10SpeedModel,
FeatureISAVersion10_3_0.Features
>;
+
+def : ProcessorModel<"gfx1034", GFX10SpeedModel,
+ FeatureISAVersion10_3_0.Features
+>;
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
index 3533ff1cb3120..ac12e26f0b8cd 100644
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
@@ -109,6 +109,7 @@ StringRef AMDGPUTargetStreamer::getArchNameFromElfMach(unsigned ElfMach) {
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1031: AK = GK_GFX1031; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1032: AK = GK_GFX1032; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1033: AK = GK_GFX1033; break;
+ case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1034: AK = GK_GFX1034; break;
case ELF::EF_AMDGPU_MACH_NONE: AK = GK_NONE; break;
}
@@ -169,6 +170,7 @@ unsigned AMDGPUTargetStreamer::getElfMach(StringRef GPU) {
case GK_GFX1031: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1031;
case GK_GFX1032: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1032;
case GK_GFX1033: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1033;
+ case GK_GFX1034: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1034;
case GK_NONE: return ELF::EF_AMDGPU_MACH_NONE;
}
diff --git a/llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll b/llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
index 456bdedcd6b28..a79b149afa399 100644
--- a/llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
+++ b/llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
@@ -84,6 +84,7 @@
; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=3 -mcpu=gfx1031 < %s | FileCheck --check-prefixes=V3-GFX1031 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=3 -mcpu=gfx1032 < %s | FileCheck --check-prefixes=V3-GFX1032 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=3 -mcpu=gfx1033 < %s | FileCheck --check-prefixes=V3-GFX1033 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=3 -mcpu=gfx1034 < %s | FileCheck --check-prefixes=V3-GFX1034 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx600 < %s | FileCheck --check-prefixes=GFX600 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tahiti < %s | FileCheck --check-prefixes=GFX600 %s
@@ -171,6 +172,7 @@
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1031 < %s | FileCheck --check-prefixes=GFX1031 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1032 < %s | FileCheck --check-prefixes=GFX1032 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1033 < %s | FileCheck --check-prefixes=GFX1033 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1034 < %s | FileCheck --check-prefixes=GFX1034 %s
; V3-GFX600: .amdgcn_target "amdgcn-amd-amdhsa--gfx600"
; V3-GFX601: .amdgcn_target "amdgcn-amd-amdhsa--gfx601"
@@ -216,6 +218,7 @@
; V3-GFX1031: .amdgcn_target "amdgcn-amd-amdhsa--gfx1031"
; V3-GFX1032: .amdgcn_target "amdgcn-amd-amdhsa--gfx1032"
; V3-GFX1033: .amdgcn_target "amdgcn-amd-amdhsa--gfx1033"
+; V3-GFX1034: .amdgcn_target "amdgcn-amd-amdhsa--gfx1034"
; GFX600: .amdgcn_target "amdgcn-amd-amdhsa--gfx600"
; GFX601: .amdgcn_target "amdgcn-amd-amdhsa--gfx601"
@@ -281,6 +284,7 @@
; GFX1031: .amdgcn_target "amdgcn-amd-amdhsa--gfx1031"
; GFX1032: .amdgcn_target "amdgcn-amd-amdhsa--gfx1032"
; GFX1033: .amdgcn_target "amdgcn-amd-amdhsa--gfx1033"
+; GFX1034: .amdgcn_target "amdgcn-amd-amdhsa--gfx1034"
define amdgpu_kernel void @directive_amdgcn_target() {
ret void
diff --git a/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll b/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
index 56423f7519d70..3365dd92797de 100644
--- a/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
+++ b/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
@@ -61,6 +61,7 @@
; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1031 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1031 %s
; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1032 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1032 %s
; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1033 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1033 %s
+; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1034 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1034 %s
; FIXME: With the default attributes the eflags are not accurate for
; xnack and sramecc. Subsequent Target-ID patches will address this.
@@ -119,6 +120,7 @@
; GFX1031: EF_AMDGPU_MACH_AMDGCN_GFX1031 (0x37)
; GFX1032: EF_AMDGPU_MACH_AMDGCN_GFX1032 (0x38)
; GFX1033: EF_AMDGPU_MACH_AMDGCN_GFX1033 (0x39)
+; GFX1034: EF_AMDGPU_MACH_AMDGCN_GFX1034 (0x3E)
; ALL: ]
define amdgpu_kernel void @elf_header() {
diff --git a/llvm/test/MC/AMDGPU/gfx1011_dlops.s b/llvm/test/MC/AMDGPU/gfx1011_dlops.s
index 71804695f5868..c2b798782d095 100644
--- a/llvm/test/MC/AMDGPU/gfx1011_dlops.s
+++ b/llvm/test/MC/AMDGPU/gfx1011_dlops.s
@@ -4,6 +4,7 @@
// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1031 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1032 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
+// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1034 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
v_dot2_f32_f16 v0, v1, v2, v3
// GFX10: encoding: [0x00,0x40,0x13,0xcc,0x01,0x05,0x0e,0x1c]
diff --git a/llvm/test/MC/AMDGPU/gfx1030_err.s b/llvm/test/MC/AMDGPU/gfx1030_err.s
index 6d2e44508553d..5f2b395412eb6 100644
--- a/llvm/test/MC/AMDGPU/gfx1030_err.s
+++ b/llvm/test/MC/AMDGPU/gfx1030_err.s
@@ -2,6 +2,7 @@
// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1031 %s 2>&1 | FileCheck --check-prefix=GFX10 --implicit-check-not=error: %s
// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1032 %s 2>&1 | FileCheck --check-prefix=GFX10 --implicit-check-not=error: %s
// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1033 %s 2>&1 | FileCheck --check-prefix=GFX10 --implicit-check-not=error: %s
+// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1034 %s 2>&1 | FileCheck --check-prefix=GFX10 --implicit-check-not=error: %s
v_dot8c_i32_i4 v5, v1, v2
// GFX10: :[[@LINE-1]]:{{[0-9]+}}: error: instruction not supported on this GPU
diff --git a/llvm/test/MC/AMDGPU/gfx1030_new.s b/llvm/test/MC/AMDGPU/gfx1030_new.s
index a95a20ff38e6e..47eb5a6e75db5 100644
--- a/llvm/test/MC/AMDGPU/gfx1030_new.s
+++ b/llvm/test/MC/AMDGPU/gfx1030_new.s
@@ -2,6 +2,7 @@
// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1031 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1032 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
+// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1034 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
global_load_dword_addtid v1, s[2:3] offset:16
// GFX10: encoding: [0x10,0x80,0x58,0xdc,0x00,0x00,0x02,0x01]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
index cbb7abe8541bd..27f9caa09234a 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
@@ -4,6 +4,7 @@
# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1031 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1032 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1034 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
# GFX10: v_dot2_f32_f16 v0, v1, v2, v3 ; encoding: [0x00,0x40,0x13,0xcc,0x01,0x05,0x0e,0x1c]
0x00,0x40,0x13,0xcc,0x01,0x05,0x0e,0x1c
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
index 1445b9a46fb0a..65ed5edcd2681 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
@@ -2,6 +2,7 @@
# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1031 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1032 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1034 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
# GFX10: global_load_dword_addtid v1, s[2:3] offset:16
0x10,0x80,0x58,0xdc,0x00,0x00,0x02,0x01
diff --git a/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml b/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
index 07488b12c872a..c81bb9a0d2869 100644
--- a/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ b/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -178,6 +178,9 @@
# RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX1033 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX1033 %s
# RUN: obj2yaml %t.o.AMDGCN_GFX1033 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX1033 %s
+# RUN: sed -e 's/<BITS>/64/' -e 's/<MACH>/AMDGCN_GFX1034/' %s | yaml2obj -o %t.o.AMDGCN_GFX1034
+# RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX1034 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX1034 %s
+# RUN: obj2yaml %t.o.AMDGCN_GFX1034 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX1034 %s
# ELF-R600-ALL: Format: elf32-amdgpu
# ELF-R600-ALL: Arch: r600
@@ -331,6 +334,9 @@
# ELF-AMDGCN-GFX1033: EF_AMDGPU_MACH_AMDGCN_GFX1033 (0x39)
# YAML-AMDGCN-GFX1033: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1033 ]
+# ELF-AMDGCN-GFX1034: EF_AMDGPU_MACH_AMDGCN_GFX1034 (0x3E)
+# YAML-AMDGCN-GFX1034: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1034 ]
+
# ELF-AMDGCN-ALL: ]
diff --git a/llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll b/llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
index f9575c40492b2..095699614d7e7 100644
--- a/llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
+++ b/llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
@@ -6,6 +6,11 @@ define amdgpu_kernel void @test_kernel() {
;
; ----------------------------------GFX10--------------------------------------
;
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1034 -filetype=obj -O0 -o %t.o %s
+; RUN: llvm-objdump -D --arch-name=amdgcn --mcpu=gfx1034 %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=gfx1033 -filetype=obj -O0 -o %t.o %s
; RUN: llvm-objdump -D --arch-name=amdgcn --mcpu=gfx1033 %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 157ac6aa9d041..10c790c4a85f7 100644
--- a/llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
+++ b/llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
@@ -259,6 +259,16 @@
# RUN: yaml2obj %s -o %t -DABI_VERSION=2 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1033
# 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_GFX1033 -DFLAG_VALUE=0x39
+# RUN: yaml2obj %s -o %t -DABI_VERSION=0 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1034
+# 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_GFX1034 -DFLAG_VALUE=0x3E
+#
+# RUN: yaml2obj %s -o %t -DABI_VERSION=1 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1034
+# 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_GFX1034 -DFLAG_VALUE=0x3E
+#
+# RUN: yaml2obj %s -o %t -DABI_VERSION=2 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1034
+# 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_GFX1034 -DFLAG_VALUE=0x3E
+
+
# RUN: yaml2obj %s -o %t -DABI_VERSION=0 -DFLAG_NAME="EF_AMDGPU_MACH_AMDGCN_GFX90A, EF_AMDGPU_FEATURE_XNACK_V3"
# RUN: llvm-readobj -h %t | FileCheck %s --check-prefixes=ALL,KNOWN-ABI-VERSION,DOUBLE-FLAG --match-full-lines -DABI_VERSION=0 -DFILE=%t -DFLAG_0="EF_AMDGPU_FEATURE_XNACK_V3 (0x100)" -DFLAG_1="EF_AMDGPU_MACH_AMDGCN_GFX90A (0x3F)" -DFLAG_VALUE=0x13F
diff --git a/llvm/tools/llvm-readobj/ELFDumper.cpp b/llvm/tools/llvm-readobj/ELFDumper.cpp
index 200b4602ae1a1..cdedf2313078e 100644
--- a/llvm/tools/llvm-readobj/ELFDumper.cpp
+++ b/llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1478,6 +1478,7 @@ static const EnumEntry<unsigned> ElfHeaderAMDGPUFlagsABIVersion3[] = {
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1031),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1032),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1033),
+ LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1034),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_XNACK_V3),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_SRAMECC_V3)
};
@@ -1529,6 +1530,7 @@ static const EnumEntry<unsigned> ElfHeaderAMDGPUFlagsABIVersion4[] = {
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1031),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1032),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1033),
+ LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1034),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_XNACK_ANY_V4),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_XNACK_OFF_V4),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_XNACK_ON_V4),
diff --git a/openmp/libomptarget/plugins/amdgpu/impl/get_elf_mach_gfx_name.cpp b/openmp/libomptarget/plugins/amdgpu/impl/get_elf_mach_gfx_name.cpp
index 45af34684117c..5554df367faba 100644
--- a/openmp/libomptarget/plugins/amdgpu/impl/get_elf_mach_gfx_name.cpp
+++ b/openmp/libomptarget/plugins/amdgpu/impl/get_elf_mach_gfx_name.cpp
@@ -47,6 +47,8 @@ const char *get_elf_mach_gfx_name(uint32_t EFlags) {
return "gfx1032";
case EF_AMDGPU_MACH_AMDGCN_GFX1033:
return "gfx1033";
+ case EF_AMDGPU_MACH_AMDGCN_GFX1034:
+ return "gfx1034";
default:
return "--unknown gfx";
}
More information about the cfe-commits
mailing list