[clang] 89d41f3 - [AMDGPU] Add gfx1033 target
Tim Renouf via cfe-commits
cfe-commits at lists.llvm.org
Tue Nov 3 08:28:35 PST 2020
Author: Tim Renouf
Date: 2020-11-03T16:27:48Z
New Revision: 89d41f3a2b820c17edeb86a2e9d458ca69eca34e
URL: https://github.com/llvm/llvm-project/commit/89d41f3a2b820c17edeb86a2e9d458ca69eca34e
DIFF: https://github.com/llvm/llvm-project/commit/89d41f3a2b820c17edeb86a2e9d458ca69eca34e.diff
LOG: [AMDGPU] Add gfx1033 target
Differential Revision: https://reviews.llvm.org/D90447
Change-Id: If2650fc7f31bbdd49c76e74a9ca8e3734d769761
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
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/elf-header-flags-mach.ll
llvm/test/CodeGen/AMDGPU/hsa-note-no-func.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-readobj/ELF/amdgpu-elf-headers.test
llvm/tools/llvm-readobj/ELFDumper.cpp
Removed:
################################################################################
diff --git a/clang/include/clang/Basic/Cuda.h b/clang/include/clang/Basic/Cuda.h
index 887030e2c49f..b3a2e99fe931 100644
--- a/clang/include/clang/Basic/Cuda.h
+++ b/clang/include/clang/Basic/Cuda.h
@@ -82,6 +82,7 @@ enum class CudaArch {
GFX1030,
GFX1031,
GFX1032,
+ GFX1033,
LAST,
};
diff --git a/clang/lib/Basic/Cuda.cpp b/clang/lib/Basic/Cuda.cpp
index 5977084b5cc1..d9f79a1a10d5 100644
--- a/clang/lib/Basic/Cuda.cpp
+++ b/clang/lib/Basic/Cuda.cpp
@@ -88,7 +88,7 @@ CudaArchToStringMap arch_names[] = {
GFX(810), // stoney
GFX(900), // vega, instinct
GFX(902), GFX(904), GFX(906), GFX(908), GFX(909), GFX(90c),
- GFX(1010), GFX(1011), GFX(1012), GFX(1030), GFX(1031)
+ GFX(1010), GFX(1011), GFX(1012), GFX(1030), GFX(1031), GFX(1032), GFX(1033)
// clang-format on
};
#undef SM
diff --git a/clang/lib/Basic/Targets/AMDGPU.cpp b/clang/lib/Basic/Targets/AMDGPU.cpp
index 5ee887d464c6..4d6a9a5e0b51 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_GFX1033:
case GK_GFX1032:
case GK_GFX1031:
case GK_GFX1030:
diff --git a/clang/lib/Basic/Targets/NVPTX.cpp b/clang/lib/Basic/Targets/NVPTX.cpp
index 7a8ae0d7ce72..b7f0dce33d2b 100644
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -207,6 +207,7 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
case CudaArch::GFX1030:
case CudaArch::GFX1031:
case CudaArch::GFX1032:
+ case CudaArch::GFX1033:
case CudaArch::LAST:
break;
case CudaArch::UNUSED:
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index 6fe99ed89dab..a3540bd30ab3 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -4647,6 +4647,7 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(
case CudaArch::GFX1030:
case CudaArch::GFX1031:
case CudaArch::GFX1032:
+ case CudaArch::GFX1033:
case CudaArch::UNUSED:
case CudaArch::UNKNOWN:
break;
@@ -4714,6 +4715,7 @@ static std::pair<unsigned, unsigned> getSMsBlocksPerSM(CodeGenModule &CGM) {
case CudaArch::GFX1030:
case CudaArch::GFX1031:
case CudaArch::GFX1032:
+ case CudaArch::GFX1033:
case CudaArch::UNUSED:
case CudaArch::UNKNOWN:
break;
diff --git a/clang/test/CodeGenOpenCL/amdgpu-features.cl b/clang/test/CodeGenOpenCL/amdgpu-features.cl
index 67ddf6c70df1..813b39d9ec7b 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-features.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-features.cl
@@ -19,6 +19,7 @@
// 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
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1033 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1033 %s
// GFX600-NOT: "target-features"
// GFX601-NOT: "target-features"
@@ -47,5 +48,6 @@
// 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"
+// GFX1033: "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 38ed743150bb..87544e58c25d 100644
--- a/clang/test/Driver/amdgpu-macros.cl
+++ b/clang/test/Driver/amdgpu-macros.cl
@@ -188,6 +188,7 @@
// 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
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1033 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX1033 %s
// GFX600-DAG: #define FP_FAST_FMA 1
// GFX601-DAG: #define FP_FAST_FMA 1
@@ -216,6 +217,7 @@
// GFX1030-DAG: #define FP_FAST_FMA 1
// GFX1031-DAG: #define FP_FAST_FMA 1
// GFX1032-DAG: #define FP_FAST_FMA 1
+// GFX1033-DAG: #define FP_FAST_FMA 1
// GFX600-DAG: #define FP_FAST_FMAF 1
// GFX601-NOT: #define FP_FAST_FMAF 1
@@ -244,6 +246,7 @@
// GFX1030-DAG: #define FP_FAST_FMAF 1
// GFX1031-DAG: #define FP_FAST_FMAF 1
// GFX1032-DAG: #define FP_FAST_FMAF 1
+// GFX1033-DAG: #define FP_FAST_FMAF 1
// ARCH-GCN-DAG: #define __AMDGCN__ 1
// ARCH-GCN-DAG: #define __AMDGPU__ 1
@@ -276,6 +279,7 @@
// GFX1030-DAG: #define __HAS_FMAF__ 1
// GFX1031-DAG: #define __HAS_FMAF__ 1
// GFX1032-DAG: #define __HAS_FMAF__ 1
+// GFX1033-DAG: #define __HAS_FMAF__ 1
// GFX600-DAG: #define __HAS_FP64__ 1
// GFX601-DAG: #define __HAS_FP64__ 1
@@ -304,6 +308,7 @@
// GFX1030-DAG: #define __HAS_FP64__ 1
// GFX1031-DAG: #define __HAS_FP64__ 1
// GFX1032-DAG: #define __HAS_FP64__ 1
+// GFX1033-DAG: #define __HAS_FP64__ 1
// GFX600-DAG: #define __HAS_LDEXPF__ 1
// GFX601-DAG: #define __HAS_LDEXPF__ 1
@@ -332,6 +337,7 @@
// GFX1030-DAG: #define __HAS_LDEXPF__ 1
// GFX1031-DAG: #define __HAS_LDEXPF__ 1
// GFX1032-DAG: #define __HAS_LDEXPF__ 1
+// GFX1033-DAG: #define __HAS_LDEXPF__ 1
// GFX600-DAG: #define __gfx600__ 1
// GFX601-DAG: #define __gfx601__ 1
@@ -360,6 +366,7 @@
// GFX1030-DAG: #define __gfx1030__ 1
// GFX1031-DAG: #define __gfx1031__ 1
// GFX1032-DAG: #define __gfx1032__ 1
+// GFX1033-DAG: #define __gfx1033__ 1
// GFX600-DAG: #define __amdgcn_processor__ "gfx600"
// GFX601-DAG: #define __amdgcn_processor__ "gfx601"
@@ -388,6 +395,7 @@
// GFX1030-DAG: #define __amdgcn_processor__ "gfx1030"
// GFX1031-DAG: #define __amdgcn_processor__ "gfx1031"
// GFX1032-DAG: #define __amdgcn_processor__ "gfx1032"
+// GFX1033-DAG: #define __amdgcn_processor__ "gfx1033"
// GFX600-DAG: #define __AMDGCN_WAVEFRONT_SIZE 64
// GFX601-DAG: #define __AMDGCN_WAVEFRONT_SIZE 64
diff --git a/clang/test/Driver/amdgpu-mcpu.cl b/clang/test/Driver/amdgpu-mcpu.cl
index d3ffe8f51719..1a6641072f90 100644
--- a/clang/test/Driver/amdgpu-mcpu.cl
+++ b/clang/test/Driver/amdgpu-mcpu.cl
@@ -97,6 +97,7 @@
// 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
+// RUN: %clang -### -target amdgcn -mcpu=gfx1033 %s 2>&1 | FileCheck --check-prefix=GFX1033 %s
// GCNDEFAULT-NOT: -target-cpu
// GFX600: "-target-cpu" "gfx600"
@@ -126,3 +127,4 @@
// GFX1030: "-target-cpu" "gfx1030"
// GFX1031: "-target-cpu" "gfx1031"
// GFX1032: "-target-cpu" "gfx1032"
+// GFX1033: "-target-cpu" "gfx1033"
diff --git a/llvm/docs/AMDGPUUsage.rst b/llvm/docs/AMDGPUUsage.rst
index 58791b8fa8fc..9d8dc1d3286b 100644
--- a/llvm/docs/AMDGPUUsage.rst
+++ b/llvm/docs/AMDGPUUsage.rst
@@ -321,7 +321,13 @@ names from both the *Processor* and *Alternative Processor* can be used.
- cumode
[off]
.. TODO::
-
+ Add product
+ names.
+ ``gfx1033`` ``amdgcn`` APU - wavefrontsize64 *TBA*
+ [off]
+ - cumode
+ [off]
+ .. TODO::
Add product
names.
@@ -871,7 +877,7 @@ The AMDGPU backend uses the following ELF header:
``EF_AMDGPU_MACH_AMDGCN_GFX1030`` 0x036 ``gfx1030``
``EF_AMDGPU_MACH_AMDGCN_GFX1031`` 0x037 ``gfx1031``
``EF_AMDGPU_MACH_AMDGCN_GFX1032`` 0x038 ``gfx1032``
- *reserved* 0x039 Reserved.
+ ``EF_AMDGPU_MACH_AMDGCN_GFX1033`` 0x039 ``gfx1033``
``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 8045aa0b2f41..d49760c5d4c1 100644
--- a/llvm/include/llvm/BinaryFormat/ELF.h
+++ b/llvm/include/llvm/BinaryFormat/ELF.h
@@ -720,7 +720,7 @@ enum : unsigned {
EF_AMDGPU_MACH_AMDGCN_GFX1030 = 0x036,
EF_AMDGPU_MACH_AMDGCN_GFX1031 = 0x037,
EF_AMDGPU_MACH_AMDGCN_GFX1032 = 0x038,
- EF_AMDGPU_MACH_AMDGCN_RESERVED_0X39 = 0x039,
+ EF_AMDGPU_MACH_AMDGCN_GFX1033 = 0x039,
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 d5e0a4bbf1cb..1d82dd80df04 100644
--- a/llvm/include/llvm/Support/TargetParser.h
+++ b/llvm/include/llvm/Support/TargetParser.h
@@ -91,9 +91,10 @@ enum GPUKind : uint32_t {
GK_GFX1030 = 75,
GK_GFX1031 = 76,
GK_GFX1032 = 77,
+ GK_GFX1033 = 78,
GK_AMDGCN_FIRST = GK_GFX600,
- GK_AMDGCN_LAST = GK_GFX1032,
+ GK_AMDGCN_LAST = GK_GFX1033,
};
/// Instruction set architecture version.
diff --git a/llvm/lib/Object/ELFObjectFile.cpp b/llvm/lib/Object/ELFObjectFile.cpp
index bf94993524b9..6dee3ab81b64 100644
--- a/llvm/lib/Object/ELFObjectFile.cpp
+++ b/llvm/lib/Object/ELFObjectFile.cpp
@@ -472,6 +472,8 @@ StringRef ELFObjectFileBase::getAMDGPUCPUName() const {
return "gfx1031";
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1032:
return "gfx1032";
+ case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1033:
+ return "gfx1033";
default:
llvm_unreachable("Unknown EF_AMDGPU_MACH value");
}
diff --git a/llvm/lib/ObjectYAML/ELFYAML.cpp b/llvm/lib/ObjectYAML/ELFYAML.cpp
index f798c22e17eb..211a6abe51e4 100644
--- a/llvm/lib/ObjectYAML/ELFYAML.cpp
+++ b/llvm/lib/ObjectYAML/ELFYAML.cpp
@@ -446,6 +446,7 @@ void ScalarBitSetTraits<ELFYAML::ELF_EF>::bitset(IO &IO,
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);
+ BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1033, 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 4fa64bd7545e..b58fadfc765d 100644
--- a/llvm/lib/Support/TargetParser.cpp
+++ b/llvm/lib/Support/TargetParser.cpp
@@ -111,6 +111,7 @@ constexpr GPUInfo AMDGCNGPUs[] = {
{{"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},
+ {{"gfx1033"}, {"gfx1033"}, GK_GFX1033, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32},
};
const GPUInfo *getArchEntry(AMDGPU::GPUKind AK, ArrayRef<GPUInfo> Table) {
@@ -219,6 +220,7 @@ AMDGPU::IsaVersion AMDGPU::getIsaVersion(StringRef GPU) {
case GK_GFX1030: return {10, 3, 0};
case GK_GFX1031: return {10, 3, 1};
case GK_GFX1032: return {10, 3, 2};
+ case GK_GFX1033: return {10, 3, 3};
default: return {0, 0, 0};
}
}
diff --git a/llvm/lib/Target/AMDGPU/GCNProcessors.td b/llvm/lib/Target/AMDGPU/GCNProcessors.td
index 24cf5e349a3a..7447ec2db188 100644
--- a/llvm/lib/Target/AMDGPU/GCNProcessors.td
+++ b/llvm/lib/Target/AMDGPU/GCNProcessors.td
@@ -215,3 +215,7 @@ def : ProcessorModel<"gfx1031", GFX10SpeedModel,
def : ProcessorModel<"gfx1032", GFX10SpeedModel,
FeatureISAVersion10_3_0.Features
>;
+
+def : ProcessorModel<"gfx1033", GFX10SpeedModel,
+ FeatureISAVersion10_3_0.Features
+>;
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
index 83842940e8c8..ead88a0c8f8d 100644
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
@@ -104,6 +104,7 @@ StringRef AMDGPUTargetStreamer::getArchNameFromElfMach(unsigned ElfMach) {
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_AMDGCN_GFX1033: AK = GK_GFX1033; break;
case ELF::EF_AMDGPU_MACH_NONE: AK = GK_NONE; break;
}
@@ -162,6 +163,7 @@ unsigned AMDGPUTargetStreamer::getElfMach(StringRef GPU) {
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_GFX1033: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1033;
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 4a05c10de872..3750e6bc4c95 100644
--- a/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
+++ b/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
@@ -59,6 +59,7 @@
; 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
+; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1033 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1033 %s
; ARCH-R600: Format: elf32-amdgpu
; ARCH-R600: Arch: r600
@@ -116,6 +117,7 @@
; GFX1030: EF_AMDGPU_MACH_AMDGCN_GFX1030 (0x36)
; GFX1031: EF_AMDGPU_MACH_AMDGCN_GFX1031 (0x37)
; GFX1032: EF_AMDGPU_MACH_AMDGCN_GFX1032 (0x38)
+; GFX1033: EF_AMDGPU_MACH_AMDGCN_GFX1033 (0x39)
; 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 c1f6ac52d91b..fac19dc52b67 100644
--- a/llvm/test/CodeGen/AMDGPU/hsa-note-no-func.ll
+++ b/llvm/test/CodeGen/AMDGPU/hsa-note-no-func.ll
@@ -31,6 +31,7 @@
; 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
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx1033 --amdhsa-code-object-version=2 | FileCheck --check-prefix=HSA --check-prefix=HSA-GFX1033 %s
; HSA: .hsa_code_object_version 2,1
; HSA-SI600: .hsa_code_object_isa 6,0,0,"AMD","AMDGPU"
@@ -56,3 +57,4 @@
; 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"
+; HSA-GFX1033: .hsa_code_object_isa 10,3,3,"AMD","AMDGPU"
diff --git a/llvm/test/MC/AMDGPU/gfx1011_dlops.s b/llvm/test/MC/AMDGPU/gfx1011_dlops.s
index d945d81f61bb..71804695f586 100644
--- a/llvm/test/MC/AMDGPU/gfx1011_dlops.s
+++ b/llvm/test/MC/AMDGPU/gfx1011_dlops.s
@@ -1,5 +1,9 @@
// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1011 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1012 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
+// 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
+// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -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 5ba0283fde24..5a57d3b3048a 100644
--- a/llvm/test/MC/AMDGPU/gfx1030_err.s
+++ b/llvm/test/MC/AMDGPU/gfx1030_err.s
@@ -1,6 +1,7 @@
// 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
+// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1033 %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 5a5e5537da5c..9234b916a71f 100644
--- a/llvm/test/MC/AMDGPU/gfx1030_new.s
+++ b/llvm/test/MC/AMDGPU/gfx1030_new.s
@@ -1,6 +1,7 @@
// 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
+// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -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 a9addc045085..cbb7abe8541b 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
@@ -1,5 +1,9 @@
# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1011 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1012 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
+# 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
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -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 4f7a6b62c00e..0d7a3f032eac 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
@@ -1,6 +1,7 @@
# 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
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -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 42aeccc4a98a..6b0e4612efc2 100644
--- a/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ b/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -170,6 +170,10 @@
# RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX1032 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX1032 %s
# RUN: obj2yaml %t.o.AMDGCN_GFX1032 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX1032 %s
+# RUN: sed -e 's/<BITS>/64/' -e 's/<MACH>/AMDGCN_GFX1033/' %s | yaml2obj -o %t.o.AMDGCN_GFX1033
+# 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
+
# ELF-R600-ALL: Format: elf32-amdgpu
# ELF-R600-ALL: Arch: r600
@@ -317,6 +321,9 @@
# ELF-AMDGCN-GFX1032: EF_AMDGPU_MACH_AMDGCN_GFX1032 (0x38)
# YAML-AMDGCN-GFX1032: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1032 ]
+# ELF-AMDGCN-GFX1033: EF_AMDGPU_MACH_AMDGCN_GFX1033 (0x39)
+# YAML-AMDGCN-GFX1033: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1033 ]
+
# ELF-AMDGCN-ALL: ]
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 26ba944fc040..1fe9a3a99ec9 100644
--- a/llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
+++ b/llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
@@ -79,6 +79,9 @@
# RUN: yaml2obj %s -o %t -DCPU=GFX1032
# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX1032 -DFLAGS=0x38
+# RUN: yaml2obj %s -o %t -DCPU=GFX1033
+# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX1033 -DFLAGS=0x39
+
--- !ELF
FileHeader:
Class: ELFCLASS64
diff --git a/llvm/tools/llvm-readobj/ELFDumper.cpp b/llvm/tools/llvm-readobj/ELFDumper.cpp
index 15ec3cf856bc..1214f0b14e72 100644
--- a/llvm/tools/llvm-readobj/ELFDumper.cpp
+++ b/llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1786,6 +1786,7 @@ static const EnumEntry<unsigned> ElfHeaderAMDGPUFlags[] = {
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_MACH_AMDGCN_GFX1033),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_XNACK),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_SRAM_ECC)
};
More information about the cfe-commits
mailing list