tpr updated this revision to Diff 301723.
tpr added a comment.
V2: Fixed copy-o in AMDGPUUsage.rst change.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D90419/new/
https://reviews.llvm.org/D90419
Files:
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/tools/llvm-readobj/ELFDumper.cpp
Index: llvm/tools/llvm-readobj/ELFDumper.cpp
===================================================================
--- llvm/tools/llvm-readobj/ELFDumper.cpp
+++ llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1779,6 +1779,7 @@
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),
Index: llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
===================================================================
--- llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -166,6 +166,10 @@
# RUN: llvm-readobj -s -file-headers %t.o.42 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX1032 %s
# RUN: obj2yaml %t.o.42 | FileCheck --check-prefixes=YAML-GFX1032 %s
+# RUN: yaml2obj --docnum=43 %s -o %t.o.43
+# RUN: llvm-readobj -s -file-headers %t.o.43 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX90C %s
+# RUN: obj2yaml %t.o.43 | FileCheck --check-prefixes=YAML-GFX90C %s
+
# ELF-ALL: Flags [
# ELF-R600: EF_AMDGPU_MACH_R600_R600 (0x1)
# ELF-R630: EF_AMDGPU_MACH_R600_R630 (0x2)
@@ -203,6 +207,7 @@
# ELF-GFX906: EF_AMDGPU_MACH_AMDGCN_GFX906 (0x2F)
# ELF-GFX908: EF_AMDGPU_MACH_AMDGCN_GFX908 (0x30)
# ELF-GFX909: EF_AMDGPU_MACH_AMDGCN_GFX909 (0x31)
+# ELF-GFX90C: EF_AMDGPU_MACH_AMDGCN_GFX90C (0x32)
# ELF-GFX1010: EF_AMDGPU_MACH_AMDGCN_GFX1010 (0x33)
# ELF-GFX1011: EF_AMDGPU_MACH_AMDGCN_GFX1011 (0x34)
# ELF-GFX1012: EF_AMDGPU_MACH_AMDGCN_GFX1012 (0x35)
@@ -247,6 +252,7 @@
# YAML-GFX906: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX906 ]
# YAML-GFX908: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX908 ]
# YAML-GFX909: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX909 ]
+# YAML-GFX90C: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX90C ]
# YAML-GFX1010: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1010 ]
# YAML-GFX1011: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1011 ]
# YAML-GFX1012: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1012 ]
@@ -715,3 +721,14 @@
Machine: EM_AMDGPU
Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1032 ]
...
+
+# Doc43
+--- !ELF
+FileHeader:
+ Class: ELFCLASS64
+ Data: ELFDATA2LSB
+ OSABI: ELFOSABI_NONE
+ Type: ET_REL
+ Machine: EM_AMDGPU
+ Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX90C ]
+...
Index: llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
+++ 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
@@ -103,6 +104,7 @@
; 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)
Index: llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
+++ llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
@@ -97,6 +97,7 @@
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 @@
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;
Index: llvm/lib/Target/AMDGPU/GCNProcessors.td
===================================================================
--- llvm/lib/Target/AMDGPU/GCNProcessors.td
+++ llvm/lib/Target/AMDGPU/GCNProcessors.td
@@ -184,6 +184,10 @@
FeatureISAVersion9_0_9.Features
>;
+def : ProcessorModel<"gfx90c", SIQuarterSpeedModel,
+ FeatureISAVersion9_0_C.Features
+>;
+
//===----------------------------------------------------------------------===//
// GCN GFX10.
//===----------------------------------------------------------------------===//
Index: llvm/lib/Target/AMDGPU/AMDGPU.td
===================================================================
--- llvm/lib/Target/AMDGPU/AMDGPU.td
+++ llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -886,6 +886,13 @@
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.
Index: llvm/lib/Support/TargetParser.cpp
===================================================================
--- llvm/lib/Support/TargetParser.cpp
+++ llvm/lib/Support/TargetParser.cpp
@@ -104,6 +104,7 @@
{{"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 @@
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};
Index: llvm/lib/ObjectYAML/ELFYAML.cpp
===================================================================
--- llvm/lib/ObjectYAML/ELFYAML.cpp
+++ llvm/lib/ObjectYAML/ELFYAML.cpp
@@ -439,6 +439,7 @@
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);
Index: llvm/lib/Object/ELFObjectFile.cpp
===================================================================
--- llvm/lib/Object/ELFObjectFile.cpp
+++ llvm/lib/Object/ELFObjectFile.cpp
@@ -456,6 +456,8 @@
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:
Index: llvm/include/llvm/Support/TargetParser.h
===================================================================
--- llvm/include/llvm/Support/TargetParser.h
+++ llvm/include/llvm/Support/TargetParser.h
@@ -83,6 +83,7 @@
GK_GFX906 = 63,
GK_GFX908 = 64,
GK_GFX909 = 65,
+ GK_GFX90C = 66,
GK_GFX1010 = 71,
GK_GFX1011 = 72,
Index: llvm/include/llvm/BinaryFormat/ELF.h
===================================================================
--- llvm/include/llvm/BinaryFormat/ELF.h
+++ llvm/include/llvm/BinaryFormat/ELF.h
@@ -713,7 +713,7 @@
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,
Index: llvm/docs/AMDGPUUsage.rst
===================================================================
--- llvm/docs/AMDGPUUsage.rst
+++ llvm/docs/AMDGPUUsage.rst
@@ -257,6 +257,13 @@
Add product
names.
+ ``gfx90c`` ``amdgcn`` APU - xnack *TBA*
+ [off]
+ .. TODO::
+
+ Add product
+ names.
+
**GCN GFX10** [AMD-GCN-GFX10]_
-----------------------------------------------------------------------------------------------------------
``gfx1010`` ``amdgcn`` dGPU - xnack - Radeon RX 5700
@@ -848,7 +855,7 @@
``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``
Index: clang/test/Driver/amdgpu-mcpu.cl
===================================================================
--- clang/test/Driver/amdgpu-mcpu.cl
+++ 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"
Index: clang/test/Driver/amdgpu-macros.cl
===================================================================
--- clang/test/Driver/amdgpu-macros.cl
+++ 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
Index: clang/test/CodeGenOpenCL/amdgpu-features.cl
===================================================================
--- clang/test/CodeGenOpenCL/amdgpu-features.cl
+++ 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"
Index: clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
===================================================================
--- clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -4640,6 +4640,7 @@
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 @@
case CudaArch::GFX906:
case CudaArch::GFX908:
case CudaArch::GFX909:
+ case CudaArch::GFX90c:
case CudaArch::GFX1010:
case CudaArch::GFX1011:
case CudaArch::GFX1012:
Index: clang/lib/Basic/Targets/NVPTX.cpp
===================================================================
--- clang/lib/Basic/Targets/NVPTX.cpp
+++ clang/lib/Basic/Targets/NVPTX.cpp
@@ -200,6 +200,7 @@
case CudaArch::GFX906:
case CudaArch::GFX908:
case CudaArch::GFX909:
+ case CudaArch::GFX90c:
case CudaArch::GFX1010:
case CudaArch::GFX1011:
case CudaArch::GFX1012:
Index: clang/lib/Basic/Targets/AMDGPU.cpp
===================================================================
--- clang/lib/Basic/Targets/AMDGPU.cpp
+++ clang/lib/Basic/Targets/AMDGPU.cpp
@@ -222,6 +222,7 @@
Features["dot1-insts"] = true;
Features["dot2-insts"] = true;
LLVM_FALLTHROUGH;
+ case GK_GFX90C:
case GK_GFX909:
case GK_GFX904:
case GK_GFX902:
Index: clang/lib/Basic/Cuda.cpp
===================================================================
--- clang/lib/Basic/Cuda.cpp
+++ clang/lib/Basic/Cuda.cpp
@@ -87,7 +87,7 @@
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
};
Index: clang/include/clang/Basic/Cuda.h
===================================================================
--- clang/include/clang/Basic/Cuda.h
+++ clang/include/clang/Basic/Cuda.h
@@ -75,6 +75,7 @@
GFX906,
GFX908,
GFX909,
+ GFX90c,
GFX1010,
GFX1011,
GFX1012,
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
