tpr created this revision.
Herald added subscribers: llvm-commits, cfe-commits, dexonsmith, kerbowa,
rupprecht, hiraditya, t-tye, dstuttard, yaxunl, nhaehnle, jvesely, kzhuravl,
arsenm.
Herald added a reviewer: jhenderson.
Herald added projects: clang, LLVM.
tpr requested review of this revision.
Herald added subscribers: MaskRay, wdng.
Change-Id: If2650fc7f31bbdd49c76e74a9ca8e3734d769761
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D90447
Files:
clang/lib/Basic/Targets/AMDGPU.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/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/tools/llvm-readobj/ELFDumper.cpp
Index: llvm/tools/llvm-readobj/ELFDumper.cpp
===================================================================
--- llvm/tools/llvm-readobj/ELFDumper.cpp
+++ llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1786,6 +1786,7 @@
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)
};
Index: llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
===================================================================
--- llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
+++ 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
Index: llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
===================================================================
--- llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
+++ 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
Index: llvm/test/MC/AMDGPU/gfx1030_new.s
===================================================================
--- llvm/test/MC/AMDGPU/gfx1030_new.s
+++ 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]
Index: llvm/test/MC/AMDGPU/gfx1030_err.s
===================================================================
--- llvm/test/MC/AMDGPU/gfx1030_err.s
+++ 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
Index: llvm/test/MC/AMDGPU/gfx1011_dlops.s
===================================================================
--- llvm/test/MC/AMDGPU/gfx1011_dlops.s
+++ 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]
Index: llvm/test/CodeGen/AMDGPU/hsa-note-no-func.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/hsa-note-no-func.ll
+++ 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"
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
@@ -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: Arch: r600
; ARCH-GCN: Arch: amdgcn
@@ -111,6 +112,7 @@
; 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() {
Index: llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
+++ llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
@@ -104,6 +104,7 @@
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 @@
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;
}
Index: llvm/lib/Target/AMDGPU/GCNProcessors.td
===================================================================
--- llvm/lib/Target/AMDGPU/GCNProcessors.td
+++ llvm/lib/Target/AMDGPU/GCNProcessors.td
@@ -215,3 +215,7 @@
def : ProcessorModel<"gfx1032", GFX10SpeedModel,
FeatureISAVersion10_3_0.Features
>;
+
+def : ProcessorModel<"gfx1033", GFX10SpeedModel,
+ FeatureISAVersion10_3_0.Features
+>;
Index: llvm/lib/Support/TargetParser.cpp
===================================================================
--- llvm/lib/Support/TargetParser.cpp
+++ llvm/lib/Support/TargetParser.cpp
@@ -111,6 +111,7 @@
{{"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 @@
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};
}
}
Index: llvm/lib/ObjectYAML/ELFYAML.cpp
===================================================================
--- llvm/lib/ObjectYAML/ELFYAML.cpp
+++ llvm/lib/ObjectYAML/ELFYAML.cpp
@@ -446,6 +446,7 @@
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;
Index: llvm/include/llvm/Support/TargetParser.h
===================================================================
--- llvm/include/llvm/Support/TargetParser.h
+++ llvm/include/llvm/Support/TargetParser.h
@@ -91,9 +91,10 @@
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.
Index: llvm/include/llvm/BinaryFormat/ELF.h
===================================================================
--- llvm/include/llvm/BinaryFormat/ELF.h
+++ llvm/include/llvm/BinaryFormat/ELF.h
@@ -720,7 +720,7 @@
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,
Index: llvm/docs/AMDGPUUsage.rst
===================================================================
--- llvm/docs/AMDGPUUsage.rst
+++ llvm/docs/AMDGPUUsage.rst
@@ -312,7 +312,13 @@
- cumode
[off]
.. TODO::
-
+ Add product
+ names.
+ ``gfx1033`` ``amdgcn`` dGPU - wavefrontsize64 *TBA*
+ [off]
+ - cumode
+ [off]
+ .. TODO::
Add product
names.
@@ -862,7 +868,7 @@
``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``
Index: clang/test/Driver/amdgpu-mcpu.cl
===================================================================
--- clang/test/Driver/amdgpu-mcpu.cl
+++ 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"
Index: clang/test/Driver/amdgpu-macros.cl
===================================================================
--- clang/test/Driver/amdgpu-macros.cl
+++ 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
Index: clang/test/CodeGenOpenCL/amdgpu-features.cl
===================================================================
--- clang/test/CodeGenOpenCL/amdgpu-features.cl
+++ 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() {}
Index: clang/lib/Basic/Targets/AMDGPU.cpp
===================================================================
--- clang/lib/Basic/Targets/AMDGPU.cpp
+++ clang/lib/Basic/Targets/AMDGPU.cpp
@@ -174,6 +174,7 @@
// 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:
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
