[llvm] ee3e642 - [AMDGPU] Add gfx90c target
Tim Renouf via llvm-commits
llvm-commits at lists.llvm.org
Tue Nov 3 08:28:29 PST 2020
Author: Tim Renouf
Date: 2020-11-03T16:27:43Z
New Revision: ee3e642627575bc8fb0a7008f8a02c891e172b7b
URL: https://github.com/llvm/llvm-project/commit/ee3e642627575bc8fb0a7008f8a02c891e172b7b
DIFF: https://github.com/llvm/llvm-project/commit/ee3e642627575bc8fb0a7008f8a02c891e172b7b.diff
LOG: [AMDGPU] Add gfx90c target
This differentiates the Ryzen 4000/4300/4500/4700 series APUs that were
previously included in gfx909.
Differential Revision: https://reviews.llvm.org/D90419
Change-Id: Ia901a7157eb2f73ccd9f25dbacec38427312377d
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/AMDGPU.td
llvm/lib/Target/AMDGPU/GCNProcessors.td
llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
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 501e47b0e2c2..887030e2c49f 100644
--- a/clang/include/clang/Basic/Cuda.h
+++ b/clang/include/clang/Basic/Cuda.h
@@ -75,6 +75,7 @@ enum class CudaArch {
GFX906,
GFX908,
GFX909,
+ GFX90c,
GFX1010,
GFX1011,
GFX1012,
diff --git a/clang/lib/Basic/Cuda.cpp b/clang/lib/Basic/Cuda.cpp
index 42a8a097b1fd..5977084b5cc1 100644
--- a/clang/lib/Basic/Cuda.cpp
+++ b/clang/lib/Basic/Cuda.cpp
@@ -87,7 +87,7 @@ CudaArchToStringMap arch_names[] = {
GFX(805), // tongapro
GFX(810), // stoney
GFX(900), // vega, instinct
- GFX(902), GFX(904), GFX(906), GFX(908), GFX(909),
+ GFX(902), GFX(904), GFX(906), GFX(908), GFX(909), GFX(90c),
GFX(1010), GFX(1011), GFX(1012), GFX(1030), GFX(1031)
// clang-format on
};
diff --git a/clang/lib/Basic/Targets/AMDGPU.cpp b/clang/lib/Basic/Targets/AMDGPU.cpp
index 0b3aebdfa15c..5ee887d464c6 100644
--- a/clang/lib/Basic/Targets/AMDGPU.cpp
+++ b/clang/lib/Basic/Targets/AMDGPU.cpp
@@ -222,6 +222,7 @@ bool AMDGPUTargetInfo::initFeatureMap(
Features["dot1-insts"] = true;
Features["dot2-insts"] = true;
LLVM_FALLTHROUGH;
+ case GK_GFX90C:
case GK_GFX909:
case GK_GFX904:
case GK_GFX902:
diff --git a/clang/lib/Basic/Targets/NVPTX.cpp b/clang/lib/Basic/Targets/NVPTX.cpp
index 26c5b26beeef..7a8ae0d7ce72 100644
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -200,6 +200,7 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
case CudaArch::GFX906:
case CudaArch::GFX908:
case CudaArch::GFX909:
+ case CudaArch::GFX90c:
case CudaArch::GFX1010:
case CudaArch::GFX1011:
case CudaArch::GFX1012:
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index 08903a1444c2..6fe99ed89dab 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -4640,6 +4640,7 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(
case CudaArch::GFX906:
case CudaArch::GFX908:
case CudaArch::GFX909:
+ case CudaArch::GFX90c:
case CudaArch::GFX1010:
case CudaArch::GFX1011:
case CudaArch::GFX1012:
@@ -4706,6 +4707,7 @@ static std::pair<unsigned, unsigned> getSMsBlocksPerSM(CodeGenModule &CGM) {
case CudaArch::GFX906:
case CudaArch::GFX908:
case CudaArch::GFX909:
+ case CudaArch::GFX90c:
case CudaArch::GFX1010:
case CudaArch::GFX1011:
case CudaArch::GFX1012:
diff --git a/clang/test/CodeGenOpenCL/amdgpu-features.cl b/clang/test/CodeGenOpenCL/amdgpu-features.cl
index 6a27c047d58c..67ddf6c70df1 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-features.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-features.cl
@@ -12,6 +12,7 @@
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx906 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX906 %s
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx908 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX908 %s
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx909 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX909 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx90c -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX90C %s
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1010 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1010 %s
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1011 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1011 %s
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1012 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1012 %s
@@ -39,6 +40,7 @@
// GFX906: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dpp,+flat-address-space,+gfx8-insts,+gfx9-insts,+s-memrealtime"
// GFX908: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dpp,+flat-address-space,+gfx8-insts,+gfx9-insts,+mai-insts,+s-memrealtime"
// GFX909: "target-features"="+16-bit-insts,+ci-insts,+dpp,+flat-address-space,+gfx8-insts,+gfx9-insts,+s-memrealtime"
+// GFX90C: "target-features"="+16-bit-insts,+ci-insts,+dpp,+flat-address-space,+gfx8-insts,+gfx9-insts,+s-memrealtime"
// GFX1010: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dpp,+flat-address-space,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime"
// GFX1011: "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"
// 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"
diff --git a/clang/test/Driver/amdgpu-macros.cl b/clang/test/Driver/amdgpu-macros.cl
index 9d028fe9d05a..38ed743150bb 100644
--- a/clang/test/Driver/amdgpu-macros.cl
+++ b/clang/test/Driver/amdgpu-macros.cl
@@ -181,6 +181,7 @@
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx906 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX906 %s
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx908 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX908 %s
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx909 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX909 %s
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx90c %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX90C %s
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1010 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX1010 %s
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1011 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX1011 %s
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1012 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX1012 %s
@@ -208,6 +209,7 @@
// GFX906-DAG: #define FP_FAST_FMA 1
// GFX908-DAG: #define FP_FAST_FMA 1
// GFX909-DAG: #define FP_FAST_FMA 1
+// GFX90C-DAG: #define FP_FAST_FMA 1
// GFX1010-DAG: #define FP_FAST_FMA 1
// GFX1011-DAG: #define FP_FAST_FMA 1
// GFX1012-DAG: #define FP_FAST_FMA 1
@@ -235,6 +237,7 @@
// GFX906-DAG: #define FP_FAST_FMAF 1
// GFX908-DAG: #define FP_FAST_FMAF 1
// GFX909-DAG: #define FP_FAST_FMAF 1
+// GFX90C-DAG: #define FP_FAST_FMAF 1
// GFX1010-DAG: #define FP_FAST_FMAF 1
// GFX1011-DAG: #define FP_FAST_FMAF 1
// GFX1012-DAG: #define FP_FAST_FMAF 1
@@ -266,6 +269,7 @@
// GFX906-DAG: #define __HAS_FMAF__ 1
// GFX908-DAG: #define __HAS_FMAF__ 1
// GFX909-DAG: #define __HAS_FMAF__ 1
+// GFX90C-DAG: #define __HAS_FMAF__ 1
// GFX1010-DAG: #define __HAS_FMAF__ 1
// GFX1011-DAG: #define __HAS_FMAF__ 1
// GFX1012-DAG: #define __HAS_FMAF__ 1
@@ -293,6 +297,7 @@
// GFX906-DAG: #define __HAS_FP64__ 1
// GFX908-DAG: #define __HAS_FP64__ 1
// GFX909-DAG: #define __HAS_FP64__ 1
+// GFX90C-DAG: #define __HAS_FP64__ 1
// GFX1010-DAG: #define __HAS_FP64__ 1
// GFX1011-DAG: #define __HAS_FP64__ 1
// GFX1012-DAG: #define __HAS_FP64__ 1
@@ -320,6 +325,7 @@
// GFX906-DAG: #define __HAS_LDEXPF__ 1
// GFX908-DAG: #define __HAS_LDEXPF__ 1
// GFX909-DAG: #define __HAS_LDEXPF__ 1
+// GFX90C-DAG: #define __HAS_LDEXPF__ 1
// GFX1010-DAG: #define __HAS_LDEXPF__ 1
// GFX1011-DAG: #define __HAS_LDEXPF__ 1
// GFX1012-DAG: #define __HAS_LDEXPF__ 1
@@ -347,6 +353,7 @@
// GFX906-DAG: #define __gfx906__ 1
// GFX908-DAG: #define __gfx908__ 1
// GFX909-DAG: #define __gfx909__ 1
+// GFX90C-DAG: #define __gfx90c__ 1
// GFX1010-DAG: #define __gfx1010__ 1
// GFX1011-DAG: #define __gfx1011__ 1
// GFX1012-DAG: #define __gfx1012__ 1
@@ -374,6 +381,7 @@
// GFX906-DAG: #define __amdgcn_processor__ "gfx906"
// GFX908-DAG: #define __amdgcn_processor__ "gfx908"
// GFX909-DAG: #define __amdgcn_processor__ "gfx909"
+// GFX90C-DAG: #define __amdgcn_processor__ "gfx90c"
// GFX1010-DAG: #define __amdgcn_processor__ "gfx1010"
// GFX1011-DAG: #define __amdgcn_processor__ "gfx1011"
// GFX1012-DAG: #define __amdgcn_processor__ "gfx1012"
@@ -401,6 +409,7 @@
// GFX906-DAG: #define __AMDGCN_WAVEFRONT_SIZE 64
// GFX908-DAG: #define __AMDGCN_WAVEFRONT_SIZE 64
// GFX909-DAG: #define __AMDGCN_WAVEFRONT_SIZE 64
+// GFX90C-DAG: #define __AMDGCN_WAVEFRONT_SIZE 64
// GFX1010-DAG: #define __AMDGCN_WAVEFRONT_SIZE 32
// GFX1011-DAG: #define __AMDGCN_WAVEFRONT_SIZE 32
// GFX1012-DAG: #define __AMDGCN_WAVEFRONT_SIZE 32
diff --git a/clang/test/Driver/amdgpu-mcpu.cl b/clang/test/Driver/amdgpu-mcpu.cl
index c5bd8ed05135..d3ffe8f51719 100644
--- a/clang/test/Driver/amdgpu-mcpu.cl
+++ b/clang/test/Driver/amdgpu-mcpu.cl
@@ -90,6 +90,7 @@
// RUN: %clang -### -target amdgcn -mcpu=gfx906 %s 2>&1 | FileCheck --check-prefix=GFX906 %s
// RUN: %clang -### -target amdgcn -mcpu=gfx908 %s 2>&1 | FileCheck --check-prefix=GFX908 %s
// RUN: %clang -### -target amdgcn -mcpu=gfx909 %s 2>&1 | FileCheck --check-prefix=GFX909 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx90c %s 2>&1 | FileCheck --check-prefix=GFX90C %s
// RUN: %clang -### -target amdgcn -mcpu=gfx1010 %s 2>&1 | FileCheck --check-prefix=GFX1010 %s
// RUN: %clang -### -target amdgcn -mcpu=gfx1011 %s 2>&1 | FileCheck --check-prefix=GFX1011 %s
// RUN: %clang -### -target amdgcn -mcpu=gfx1012 %s 2>&1 | FileCheck --check-prefix=GFX1012 %s
@@ -118,6 +119,7 @@
// GFX906: "-target-cpu" "gfx906"
// GFX908: "-target-cpu" "gfx908"
// GFX909: "-target-cpu" "gfx909"
+// GFX90C: "-target-cpu" "gfx90c"
// GFX1010: "-target-cpu" "gfx1010"
// GFX1011: "-target-cpu" "gfx1011"
// GFX1012: "-target-cpu" "gfx1012"
diff --git a/llvm/docs/AMDGPUUsage.rst b/llvm/docs/AMDGPUUsage.rst
index 0732d1a79ab3..58791b8fa8fc 100644
--- a/llvm/docs/AMDGPUUsage.rst
+++ b/llvm/docs/AMDGPUUsage.rst
@@ -257,6 +257,22 @@ names from both the *Processor* and *Alternative Processor* can be used.
Add product
names.
+ ``gfx90c`` ``amdgcn`` APU - xnack - Ryzen 7 4700G
+ [on] - Ryzen 7 4700GE
+ - Ryzen 7 4700G
+ - Ryzen 7 4700GE
+ - Ryzen 5 4600G
+ - Ryzen 5 4600GE
+ - Ryzen 3 4300G
+ - Ryzen 3 4300GE
+ - Ryzen Pro 4000G
+ - Ryzen 7 Pro 4700G
+ - Ryzen 7 Pro 4750GE
+ - Ryzen 5 Pro 4650G
+ - Ryzen 5 Pro 4650GE
+ - Ryzen 3 Pro 4350G
+ - Ryzen 3 Pro 4350GE
+
**GCN GFX10** [AMD-GCN-GFX10]_
-----------------------------------------------------------------------------------------------------------
``gfx1010`` ``amdgcn`` dGPU - xnack - Radeon RX 5700
@@ -848,7 +864,7 @@ The AMDGPU backend uses the following ELF header:
``EF_AMDGPU_MACH_AMDGCN_GFX906`` 0x02f ``gfx906``
``EF_AMDGPU_MACH_AMDGCN_GFX908`` 0x030 ``gfx908``
``EF_AMDGPU_MACH_AMDGCN_GFX909`` 0x031 ``gfx909``
- *reserved* 0x032 Reserved.
+ ``EF_AMDGPU_MACH_AMDGCN_GFX90C`` 0x032 ``gfx90c``
``EF_AMDGPU_MACH_AMDGCN_GFX1010`` 0x033 ``gfx1010``
``EF_AMDGPU_MACH_AMDGCN_GFX1011`` 0x034 ``gfx1011``
``EF_AMDGPU_MACH_AMDGCN_GFX1012`` 0x035 ``gfx1012``
diff --git a/llvm/include/llvm/BinaryFormat/ELF.h b/llvm/include/llvm/BinaryFormat/ELF.h
index af6cdabcad4f..8045aa0b2f41 100644
--- a/llvm/include/llvm/BinaryFormat/ELF.h
+++ b/llvm/include/llvm/BinaryFormat/ELF.h
@@ -713,7 +713,7 @@ enum : unsigned {
EF_AMDGPU_MACH_AMDGCN_GFX906 = 0x02f,
EF_AMDGPU_MACH_AMDGCN_GFX908 = 0x030,
EF_AMDGPU_MACH_AMDGCN_GFX909 = 0x031,
- EF_AMDGPU_MACH_AMDGCN_RESERVED_0X32 = 0x032,
+ EF_AMDGPU_MACH_AMDGCN_GFX90C = 0x032,
EF_AMDGPU_MACH_AMDGCN_GFX1010 = 0x033,
EF_AMDGPU_MACH_AMDGCN_GFX1011 = 0x034,
EF_AMDGPU_MACH_AMDGCN_GFX1012 = 0x035,
diff --git a/llvm/include/llvm/Support/TargetParser.h b/llvm/include/llvm/Support/TargetParser.h
index ac3a59ed2f69..d5e0a4bbf1cb 100644
--- a/llvm/include/llvm/Support/TargetParser.h
+++ b/llvm/include/llvm/Support/TargetParser.h
@@ -83,6 +83,7 @@ enum GPUKind : uint32_t {
GK_GFX906 = 63,
GK_GFX908 = 64,
GK_GFX909 = 65,
+ GK_GFX90C = 66,
GK_GFX1010 = 71,
GK_GFX1011 = 72,
diff --git a/llvm/lib/Object/ELFObjectFile.cpp b/llvm/lib/Object/ELFObjectFile.cpp
index fda89d85ba25..bf94993524b9 100644
--- a/llvm/lib/Object/ELFObjectFile.cpp
+++ b/llvm/lib/Object/ELFObjectFile.cpp
@@ -456,6 +456,8 @@ StringRef ELFObjectFileBase::getAMDGPUCPUName() const {
return "gfx908";
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX909:
return "gfx909";
+ case ELF::EF_AMDGPU_MACH_AMDGCN_GFX90C:
+ return "gfx90c";
// AMDGCN GFX10.
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1010:
diff --git a/llvm/lib/ObjectYAML/ELFYAML.cpp b/llvm/lib/ObjectYAML/ELFYAML.cpp
index f9ee4ce02a13..f798c22e17eb 100644
--- a/llvm/lib/ObjectYAML/ELFYAML.cpp
+++ b/llvm/lib/ObjectYAML/ELFYAML.cpp
@@ -439,6 +439,7 @@ void ScalarBitSetTraits<ELFYAML::ELF_EF>::bitset(IO &IO,
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX906, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX908, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX909, EF_AMDGPU_MACH);
+ BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX90C, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1010, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1011, EF_AMDGPU_MACH);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1012, EF_AMDGPU_MACH);
diff --git a/llvm/lib/Support/TargetParser.cpp b/llvm/lib/Support/TargetParser.cpp
index cb25fcfdd019..4fa64bd7545e 100644
--- a/llvm/lib/Support/TargetParser.cpp
+++ b/llvm/lib/Support/TargetParser.cpp
@@ -104,6 +104,7 @@ constexpr GPUInfo AMDGCNGPUs[] = {
{{"gfx906"}, {"gfx906"}, GK_GFX906, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_XNACK|FEATURE_SRAM_ECC},
{{"gfx908"}, {"gfx908"}, GK_GFX908, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_XNACK|FEATURE_SRAM_ECC},
{{"gfx909"}, {"gfx909"}, GK_GFX909, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_XNACK},
+ {{"gfx90c"}, {"gfx90c"}, GK_GFX90C, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_XNACK},
{{"gfx1010"}, {"gfx1010"}, GK_GFX1010, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_XNACK},
{{"gfx1011"}, {"gfx1011"}, GK_GFX1011, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_XNACK},
{{"gfx1012"}, {"gfx1012"}, GK_GFX1012, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_XNACK},
@@ -211,6 +212,7 @@ AMDGPU::IsaVersion AMDGPU::getIsaVersion(StringRef GPU) {
case GK_GFX906: return {9, 0, 6};
case GK_GFX908: return {9, 0, 8};
case GK_GFX909: return {9, 0, 9};
+ case GK_GFX90C: return {9, 0, 12};
case GK_GFX1010: return {10, 1, 0};
case GK_GFX1011: return {10, 1, 1};
case GK_GFX1012: return {10, 1, 2};
diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.td b/llvm/lib/Target/AMDGPU/AMDGPU.td
index 85d790234e6d..1df61f8bafcf 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -886,6 +886,13 @@ def FeatureISAVersion9_0_9 : FeatureSet<
FeatureXNACK,
FeatureImageGather4D16Bug]>;
+def FeatureISAVersion9_0_C : FeatureSet<
+ [FeatureGFX9,
+ FeatureMadMixInsts,
+ FeatureLDSBankCount32,
+ FeatureXNACK,
+ FeatureImageGather4D16Bug]>;
+
// TODO: Organize more features into groups.
def FeatureGroup {
// Bugs present on gfx10.1.
diff --git a/llvm/lib/Target/AMDGPU/GCNProcessors.td b/llvm/lib/Target/AMDGPU/GCNProcessors.td
index 1ba76dfdb1c9..24cf5e349a3a 100644
--- a/llvm/lib/Target/AMDGPU/GCNProcessors.td
+++ b/llvm/lib/Target/AMDGPU/GCNProcessors.td
@@ -184,6 +184,10 @@ def : ProcessorModel<"gfx909", SIQuarterSpeedModel,
FeatureISAVersion9_0_9.Features
>;
+def : ProcessorModel<"gfx90c", SIQuarterSpeedModel,
+ FeatureISAVersion9_0_C.Features
+>;
+
//===----------------------------------------------------------------------===//
// GCN GFX10.
//===----------------------------------------------------------------------===//
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
index 36c97fa90e87..83842940e8c8 100644
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
@@ -97,6 +97,7 @@ StringRef AMDGPUTargetStreamer::getArchNameFromElfMach(unsigned ElfMach) {
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX906: AK = GK_GFX906; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX908: AK = GK_GFX908; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX909: AK = GK_GFX909; break;
+ case ELF::EF_AMDGPU_MACH_AMDGCN_GFX90C: AK = GK_GFX90C; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1010: AK = GK_GFX1010; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1011: AK = GK_GFX1011; break;
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1012: AK = GK_GFX1012; break;
@@ -154,6 +155,7 @@ unsigned AMDGPUTargetStreamer::getElfMach(StringRef GPU) {
case GK_GFX906: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX906;
case GK_GFX908: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX908;
case GK_GFX909: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX909;
+ case GK_GFX90C: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX90C;
case GK_GFX1010: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1010;
case GK_GFX1011: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1011;
case GK_GFX1012: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1012;
diff --git a/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll b/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
index b72b1da5ccd3..4a05c10de872 100644
--- a/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
+++ b/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
@@ -52,6 +52,7 @@
; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx906 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX906 %s
; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx908 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX908 %s
; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx909 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX909 %s
+; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx90c < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX90C %s
; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1010 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1010 %s
; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1011 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1011 %s
; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1012 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1012 %s
@@ -108,6 +109,7 @@
; GFX908: EF_AMDGPU_MACH_AMDGCN_GFX908 (0x30)
; GFX908-NEXT: EF_AMDGPU_SRAM_ECC (0x200)
; GFX909: EF_AMDGPU_MACH_AMDGCN_GFX909 (0x31)
+; GFX90C: EF_AMDGPU_MACH_AMDGCN_GFX90C (0x32)
; GFX1010: EF_AMDGPU_MACH_AMDGCN_GFX1010 (0x33)
; GFX1011: EF_AMDGPU_MACH_AMDGCN_GFX1011 (0x34)
; GFX1012: EF_AMDGPU_MACH_AMDGCN_GFX1012 (0x35)
diff --git a/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml b/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
index d84016f651c1..42aeccc4a98a 100644
--- a/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ b/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -142,6 +142,10 @@
# RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX909 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX909 %s
# RUN: obj2yaml %t.o.AMDGCN_GFX909 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX909 %s
+# RUN: sed -e 's/<BITS>/64/' -e 's/<MACH>/AMDGCN_GFX90C/' %s | yaml2obj -o %t.o.AMDGCN_GFX90C
+# RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX90C | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX90C %s
+# RUN: obj2yaml %t.o.AMDGCN_GFX90C | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX90C %s
+
# RUN: sed -e 's/<BITS>/64/' -e 's/<MACH>/AMDGCN_GFX1010/' %s | yaml2obj -o %t.o.AMDGCN_GFX1010
# RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX1010 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX1010 %s
# RUN: obj2yaml %t.o.AMDGCN_GFX1010 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX1010 %s
@@ -292,6 +296,9 @@
# ELF-AMDGCN-GFX909: EF_AMDGPU_MACH_AMDGCN_GFX909 (0x31)
# YAML-AMDGCN-GFX909: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX909 ]
+# ELF-AMDGCN-GFX90C: EF_AMDGPU_MACH_AMDGCN_GFX90C (0x32)
+# YAML-AMDGCN-GFX90C: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX90C ]
+
# ELF-AMDGCN-GFX1010: EF_AMDGPU_MACH_AMDGCN_GFX1010 (0x33)
# YAML-AMDGCN-GFX1010: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1010 ]
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 f1ad7ad561d0..26ba944fc040 100644
--- a/llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
+++ b/llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
@@ -58,6 +58,9 @@
# RUN: yaml2obj %s -o %t -DCPU=GFX909
# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX909 -DFLAGS=0x31
+# RUN: yaml2obj %s -o %t -DCPU=GFX90C
+# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX90C -DFLAGS=0x32
+
# RUN: yaml2obj %s -o %t -DCPU=GFX1010
# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX1010 -DFLAGS=0x33
diff --git a/llvm/tools/llvm-readobj/ELFDumper.cpp b/llvm/tools/llvm-readobj/ELFDumper.cpp
index 470ba491a89b..15ec3cf856bc 100644
--- a/llvm/tools/llvm-readobj/ELFDumper.cpp
+++ b/llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1779,6 +1779,7 @@ static const EnumEntry<unsigned> ElfHeaderAMDGPUFlags[] = {
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX906),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX908),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX909),
+ LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX90C),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1010),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1011),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1012),
More information about the llvm-commits
mailing list