[llvm] d1beb95 - [AMDGPU] gfx1032 target
Stanislav Mekhanoshin via llvm-commits
llvm-commits at lists.llvm.org
Thu Oct 15 12:42:42 PDT 2020
Author: Stanislav Mekhanoshin
Date: 2020-10-15T12:41:18-07:00
New Revision: d1beb95d1241ec50bdf19db351d273374a146a4a
URL: https://github.com/llvm/llvm-project/commit/d1beb95d1241ec50bdf19db351d273374a146a4a
DIFF: https://github.com/llvm/llvm-project/commit/d1beb95d1241ec50bdf19db351d273374a146a4a.diff
LOG: [AMDGPU] gfx1032 target
Differential Revision: https://reviews.llvm.org/D89487
Added:
Modified:
clang/include/clang/Basic/Cuda.h
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
llvm/docs/AMDGPUUsage.rst
llvm/include/llvm/BinaryFormat/ELF.h
llvm/include/llvm/Support/TargetParser.h
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/elf-header-flags-mach.ll
llvm/test/CodeGen/AMDGPU/hsa-note-no-func.ll
llvm/test/MC/AMDGPU/gfx1030_err.s
llvm/test/MC/AMDGPU/gfx1030_new.s
llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
llvm/tools/llvm-readobj/ELFDumper.cpp
Removed:
################################################################################
diff --git a/clang/include/clang/Basic/Cuda.h b/clang/include/clang/Basic/Cuda.h
index 417d40c28adf..501e47b0e2c2 100644
--- a/clang/include/clang/Basic/Cuda.h
+++ b/clang/include/clang/Basic/Cuda.h
@@ -80,6 +80,7 @@ enum class CudaArch {
GFX1012,
GFX1030,
GFX1031,
+ GFX1032,
LAST,
};
diff --git a/clang/lib/Basic/Targets/AMDGPU.cpp b/clang/lib/Basic/Targets/AMDGPU.cpp
index 42db207b9ce5..0b3aebdfa15c 100644
--- a/clang/lib/Basic/Targets/AMDGPU.cpp
+++ b/clang/lib/Basic/Targets/AMDGPU.cpp
@@ -174,6 +174,7 @@ 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_GFX1032:
case GK_GFX1031:
case GK_GFX1030:
Features["ci-insts"] = true;
diff --git a/clang/lib/Basic/Targets/NVPTX.cpp b/clang/lib/Basic/Targets/NVPTX.cpp
index 3780f1cc250c..26c5b26beeef 100644
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -205,6 +205,7 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
case CudaArch::GFX1012:
case CudaArch::GFX1030:
case CudaArch::GFX1031:
+ case CudaArch::GFX1032:
case CudaArch::LAST:
break;
case CudaArch::UNUSED:
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index ab7ee8b33a0c..bcabc5398127 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -4645,6 +4645,7 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(
case CudaArch::GFX1012:
case CudaArch::GFX1030:
case CudaArch::GFX1031:
+ case CudaArch::GFX1032:
case CudaArch::UNUSED:
case CudaArch::UNKNOWN:
break;
@@ -4710,6 +4711,7 @@ static std::pair<unsigned, unsigned> getSMsBlocksPerSM(CodeGenModule &CGM) {
case CudaArch::GFX1012:
case CudaArch::GFX1030:
case CudaArch::GFX1031:
+ case CudaArch::GFX1032:
case CudaArch::UNUSED:
case CudaArch::UNKNOWN:
break;
diff --git a/clang/test/CodeGenOpenCL/amdgpu-features.cl b/clang/test/CodeGenOpenCL/amdgpu-features.cl
index 5a814f36e564..a463c061114e 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-features.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-features.cl
@@ -16,6 +16,7 @@
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1012 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1012 %s
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1030 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1030 %s
// 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
// GFX600-NOT: "target-features"
// GFX601-NOT: "target-features"
@@ -30,5 +31,6 @@
// GFX1012: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dpp,+flat-address-space,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime"
// GFX1030: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime"
// GFX1031: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime"
+// GFX1032: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime"
kernel void test() {}
diff --git a/clang/test/Driver/amdgpu-macros.cl b/clang/test/Driver/amdgpu-macros.cl
index 8c9c71f3e258..9d028fe9d05a 100644
--- a/clang/test/Driver/amdgpu-macros.cl
+++ b/clang/test/Driver/amdgpu-macros.cl
@@ -186,6 +186,7 @@
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1012 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX1012 %s
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1030 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX1030 %s
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1031 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX1031 %s
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1032 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX1032 %s
// GFX600-DAG: #define FP_FAST_FMA 1
// GFX601-DAG: #define FP_FAST_FMA 1
@@ -212,6 +213,7 @@
// GFX1012-DAG: #define FP_FAST_FMA 1
// GFX1030-DAG: #define FP_FAST_FMA 1
// GFX1031-DAG: #define FP_FAST_FMA 1
+// GFX1032-DAG: #define FP_FAST_FMA 1
// GFX600-DAG: #define FP_FAST_FMAF 1
// GFX601-NOT: #define FP_FAST_FMAF 1
@@ -238,6 +240,7 @@
// GFX1012-DAG: #define FP_FAST_FMAF 1
// GFX1030-DAG: #define FP_FAST_FMAF 1
// GFX1031-DAG: #define FP_FAST_FMAF 1
+// GFX1032-DAG: #define FP_FAST_FMAF 1
// ARCH-GCN-DAG: #define __AMDGCN__ 1
// ARCH-GCN-DAG: #define __AMDGPU__ 1
@@ -268,6 +271,7 @@
// GFX1012-DAG: #define __HAS_FMAF__ 1
// GFX1030-DAG: #define __HAS_FMAF__ 1
// GFX1031-DAG: #define __HAS_FMAF__ 1
+// GFX1032-DAG: #define __HAS_FMAF__ 1
// GFX600-DAG: #define __HAS_FP64__ 1
// GFX601-DAG: #define __HAS_FP64__ 1
@@ -294,6 +298,7 @@
// GFX1012-DAG: #define __HAS_FP64__ 1
// GFX1030-DAG: #define __HAS_FP64__ 1
// GFX1031-DAG: #define __HAS_FP64__ 1
+// GFX1032-DAG: #define __HAS_FP64__ 1
// GFX600-DAG: #define __HAS_LDEXPF__ 1
// GFX601-DAG: #define __HAS_LDEXPF__ 1
@@ -320,6 +325,7 @@
// GFX1012-DAG: #define __HAS_LDEXPF__ 1
// GFX1030-DAG: #define __HAS_LDEXPF__ 1
// GFX1031-DAG: #define __HAS_LDEXPF__ 1
+// GFX1032-DAG: #define __HAS_LDEXPF__ 1
// GFX600-DAG: #define __gfx600__ 1
// GFX601-DAG: #define __gfx601__ 1
@@ -346,6 +352,7 @@
// GFX1012-DAG: #define __gfx1012__ 1
// GFX1030-DAG: #define __gfx1030__ 1
// GFX1031-DAG: #define __gfx1031__ 1
+// GFX1032-DAG: #define __gfx1032__ 1
// GFX600-DAG: #define __amdgcn_processor__ "gfx600"
// GFX601-DAG: #define __amdgcn_processor__ "gfx601"
@@ -372,6 +379,7 @@
// GFX1012-DAG: #define __amdgcn_processor__ "gfx1012"
// GFX1030-DAG: #define __amdgcn_processor__ "gfx1030"
// GFX1031-DAG: #define __amdgcn_processor__ "gfx1031"
+// GFX1032-DAG: #define __amdgcn_processor__ "gfx1032"
// GFX600-DAG: #define __AMDGCN_WAVEFRONT_SIZE 64
// GFX601-DAG: #define __AMDGCN_WAVEFRONT_SIZE 64
@@ -398,6 +406,7 @@
// GFX1012-DAG: #define __AMDGCN_WAVEFRONT_SIZE 32
// GFX1030-DAG: #define __AMDGCN_WAVEFRONT_SIZE 32
// GFX1031-DAG: #define __AMDGCN_WAVEFRONT_SIZE 32
+// GFX1032-DAG: #define __AMDGCN_WAVEFRONT_SIZE 32
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx906 -mwavefrontsize64 \
// RUN: %s 2>&1 | FileCheck --check-prefixes=WAVE64 %s
diff --git a/clang/test/Driver/amdgpu-mcpu.cl b/clang/test/Driver/amdgpu-mcpu.cl
index e43082eabc0d..c5bd8ed05135 100644
--- a/clang/test/Driver/amdgpu-mcpu.cl
+++ b/clang/test/Driver/amdgpu-mcpu.cl
@@ -95,6 +95,7 @@
// RUN: %clang -### -target amdgcn -mcpu=gfx1012 %s 2>&1 | FileCheck --check-prefix=GFX1012 %s
// RUN: %clang -### -target amdgcn -mcpu=gfx1030 %s 2>&1 | FileCheck --check-prefix=GFX1030 %s
// 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
// GCNDEFAULT-NOT: -target-cpu
// GFX600: "-target-cpu" "gfx600"
@@ -122,3 +123,4 @@
// GFX1012: "-target-cpu" "gfx1012"
// GFX1030: "-target-cpu" "gfx1030"
// GFX1031: "-target-cpu" "gfx1031"
+// GFX1032: "-target-cpu" "gfx1032"
diff --git a/llvm/docs/AMDGPUUsage.rst b/llvm/docs/AMDGPUUsage.rst
index e2b80509037e..1d1ada396f44 100644
--- a/llvm/docs/AMDGPUUsage.rst
+++ b/llvm/docs/AMDGPUUsage.rst
@@ -277,6 +277,15 @@ names from both the *Processor* and *Alternative Processor* can be used.
.. TODO
Add product
names.
+ ``gfx1032`` ``amdgcn`` dGPU - xnack *TBA*
+ [off]
+ - wavefrontsize64
+ [off]
+ - cumode
+ [off]
+ .. TODO
+ Add product
+ names.
=========== =============== ============ ===== ================= ======= ======================
.. _amdgpu-target-features:
@@ -822,6 +831,7 @@ The AMDGPU backend uses the following ELF header:
``EF_AMDGPU_MACH_AMDGCN_GFX1012`` 0x035 ``gfx1012``
``EF_AMDGPU_MACH_AMDGCN_GFX1030`` 0x036 ``gfx1030``
``EF_AMDGPU_MACH_AMDGCN_GFX1031`` 0x037 ``gfx1031``
+ ``EF_AMDGPU_MACH_AMDGCN_GFX1032`` 0x038 ``gfx1032``
*reserved* 0x038 Reserved.
*reserved* 0x039 Reserved.
``EF_AMDGPU_MACH_AMDGCN_GFX602`` 0x03a ``gfx602``
diff --git a/llvm/include/llvm/BinaryFormat/ELF.h b/llvm/include/llvm/BinaryFormat/ELF.h
index ccfaa86ed0aa..be1a408937b9 100644
--- a/llvm/include/llvm/BinaryFormat/ELF.h
+++ b/llvm/include/llvm/BinaryFormat/ELF.h
@@ -726,6 +726,7 @@ enum : unsigned {
EF_AMDGPU_MACH_AMDGCN_GFX1012 = 0x035,
EF_AMDGPU_MACH_AMDGCN_GFX1030 = 0x036,
EF_AMDGPU_MACH_AMDGCN_GFX1031 = 0x037,
+ EF_AMDGPU_MACH_AMDGCN_GFX1032 = 0x038,
// Reserved for AMDGCN-based processors.
EF_AMDGPU_MACH_AMDGCN_RESERVED0 = 0x027,
diff --git a/llvm/include/llvm/Support/TargetParser.h b/llvm/include/llvm/Support/TargetParser.h
index 260b77b52c5d..14ce4d0ad512 100644
--- a/llvm/include/llvm/Support/TargetParser.h
+++ b/llvm/include/llvm/Support/TargetParser.h
@@ -89,9 +89,10 @@ enum GPUKind : uint32_t {
GK_GFX1012 = 73,
GK_GFX1030 = 75,
GK_GFX1031 = 76,
+ GK_GFX1032 = 77,
GK_AMDGCN_FIRST = GK_GFX600,
- GK_AMDGCN_LAST = GK_GFX1031,
+ GK_AMDGCN_LAST = GK_GFX1032,
};
/// Instruction set architecture version.
diff --git a/llvm/lib/ObjectYAML/ELFYAML.cpp b/llvm/lib/ObjectYAML/ELFYAML.cpp
index 7bb8755aa4bd..b3dfd7f73945 100644
--- a/llvm/lib/ObjectYAML/ELFYAML.cpp
+++ b/llvm/lib/ObjectYAML/ELFYAML.cpp
@@ -444,6 +444,7 @@ void ScalarBitSetTraits<ELFYAML::ELF_EF>::bitset(IO &IO,
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1012, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1030, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1031, EF_AMDGPU_MACH);
+ BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1032, EF_AMDGPU_MACH);
BCase(EF_AMDGPU_XNACK);
BCase(EF_AMDGPU_SRAM_ECC);
break;
diff --git a/llvm/lib/Support/TargetParser.cpp b/llvm/lib/Support/TargetParser.cpp
index 9d2be4bd8d76..4d96b34818a9 100644
--- a/llvm/lib/Support/TargetParser.cpp
+++ b/llvm/lib/Support/TargetParser.cpp
@@ -63,7 +63,7 @@ constexpr GPUInfo R600GPUs[26] = {
// This table should be sorted by the value of GPUKind
// Don't bother listing the implicitly true features
-constexpr GPUInfo AMDGCNGPUs[43] = {
+constexpr GPUInfo AMDGCNGPUs[44] = {
// Name Canonical Kind Features
// Name
{{"gfx600"}, {"gfx600"}, GK_GFX600, FEATURE_FAST_FMA_F32},
@@ -109,6 +109,7 @@ constexpr GPUInfo AMDGCNGPUs[43] = {
{{"gfx1012"}, {"gfx1012"}, GK_GFX1012, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_XNACK},
{{"gfx1030"}, {"gfx1030"}, GK_GFX1030, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32},
{{"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},
};
const GPUInfo *getArchEntry(AMDGPU::GPUKind AK, ArrayRef<GPUInfo> Table) {
@@ -215,6 +216,7 @@ AMDGPU::IsaVersion AMDGPU::getIsaVersion(StringRef GPU) {
case GK_GFX1012: return {10, 1, 2};
case GK_GFX1030: return {10, 3, 0};
case GK_GFX1031: return {10, 3, 1};
+ case GK_GFX1032: return {10, 3, 2};
default: return {0, 0, 0};
}
}
diff --git a/llvm/lib/Target/AMDGPU/GCNProcessors.td b/llvm/lib/Target/AMDGPU/GCNProcessors.td
index accb550db318..1ba76dfdb1c9 100644
--- a/llvm/lib/Target/AMDGPU/GCNProcessors.td
+++ b/llvm/lib/Target/AMDGPU/GCNProcessors.td
@@ -207,3 +207,7 @@ def : ProcessorModel<"gfx1030", GFX10SpeedModel,
def : ProcessorModel<"gfx1031", GFX10SpeedModel,
FeatureISAVersion10_3_0.Features
>;
+
+def : ProcessorModel<"gfx1032", GFX10SpeedModel,
+ FeatureISAVersion10_3_0.Features
+>;
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
index 19ec03609246..36c97fa90e87 100644
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
@@ -102,6 +102,7 @@ StringRef AMDGPUTargetStreamer::getArchNameFromElfMach(unsigned ElfMach) {
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1012: AK = GK_GFX1012; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1030: AK = GK_GFX1030; break;
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_NONE: AK = GK_NONE; break;
}
@@ -158,6 +159,7 @@ unsigned AMDGPUTargetStreamer::getElfMach(StringRef GPU) {
case GK_GFX1012: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1012;
case GK_GFX1030: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1030;
case GK_GFX1031: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1031;
+ case GK_GFX1032: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1032;
case GK_NONE: return ELF::EF_AMDGPU_MACH_NONE;
}
diff --git a/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll b/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
index 9fddf1c32ec3..897561afe316 100644
--- a/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
+++ b/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
@@ -57,6 +57,7 @@
; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1012 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1012 %s
; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1030 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1030 %s
; 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
; ARCH-R600: Arch: r600
; ARCH-GCN: Arch: amdgcn
@@ -107,6 +108,7 @@
; GFX1012: EF_AMDGPU_MACH_AMDGCN_GFX1012 (0x35)
; GFX1030: EF_AMDGPU_MACH_AMDGCN_GFX1030 (0x36)
; GFX1031: EF_AMDGPU_MACH_AMDGCN_GFX1031 (0x37)
+; GFX1032: EF_AMDGPU_MACH_AMDGCN_GFX1032 (0x38)
; ALL: ]
define amdgpu_kernel void @elf_header() {
diff --git a/llvm/test/CodeGen/AMDGPU/hsa-note-no-func.ll b/llvm/test/CodeGen/AMDGPU/hsa-note-no-func.ll
index 4ffaf5e43fbe..c1f6ac52d91b 100644
--- a/llvm/test/CodeGen/AMDGPU/hsa-note-no-func.ll
+++ b/llvm/test/CodeGen/AMDGPU/hsa-note-no-func.ll
@@ -30,6 +30,7 @@
; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx1012 --amdhsa-code-object-version=2 | FileCheck --check-prefix=HSA --check-prefix=HSA-GFX1012 %s
; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx1030 --amdhsa-code-object-version=2 | FileCheck --check-prefix=HSA --check-prefix=HSA-GFX1030 %s
; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx1031 --amdhsa-code-object-version=2 | FileCheck --check-prefix=HSA --check-prefix=HSA-GFX1031 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx1032 --amdhsa-code-object-version=2 | FileCheck --check-prefix=HSA --check-prefix=HSA-GFX1032 %s
; HSA: .hsa_code_object_version 2,1
; HSA-SI600: .hsa_code_object_isa 6,0,0,"AMD","AMDGPU"
@@ -54,3 +55,4 @@
; HSA-GFX1012: .hsa_code_object_isa 10,1,2,"AMD","AMDGPU"
; HSA-GFX1030: .hsa_code_object_isa 10,3,0,"AMD","AMDGPU"
; HSA-GFX1031: .hsa_code_object_isa 10,3,1,"AMD","AMDGPU"
+; HSA-GFX1032: .hsa_code_object_isa 10,3,2,"AMD","AMDGPU"
diff --git a/llvm/test/MC/AMDGPU/gfx1030_err.s b/llvm/test/MC/AMDGPU/gfx1030_err.s
index c6af1736371a..5ba0283fde24 100644
--- a/llvm/test/MC/AMDGPU/gfx1030_err.s
+++ b/llvm/test/MC/AMDGPU/gfx1030_err.s
@@ -1,5 +1,6 @@
// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1030 %s 2>&1 | FileCheck --check-prefix=GFX10 --implicit-check-not=error: %s
// 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
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 ecd4eefe9e68..5a5e5537da5c 100644
--- a/llvm/test/MC/AMDGPU/gfx1030_new.s
+++ b/llvm/test/MC/AMDGPU/gfx1030_new.s
@@ -1,5 +1,6 @@
// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1030 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
// 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
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/gfx1030_dasm_new.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
index cf125ca9c9f8..c22fa4ae6608 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
@@ -1,5 +1,6 @@
# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1030 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
# 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
# GFX10: global_load_dword_addtid v1, s[2:3] offset:16
0x10,0x80,0x58,0xdc,0x00,0x00,0x02,0x01
diff --git a/llvm/tools/llvm-readobj/ELFDumper.cpp b/llvm/tools/llvm-readobj/ELFDumper.cpp
index fcc5c002c624..8594d717f84a 100644
--- a/llvm/tools/llvm-readobj/ELFDumper.cpp
+++ b/llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1781,6 +1781,7 @@ static const EnumEntry<unsigned> ElfHeaderAMDGPUFlags[] = {
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1012),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1030),
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_XNACK),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_SRAM_ECC)
};
More information about the llvm-commits
mailing list