This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rG464e4dc50f4e: [AMDGPU] Add gfx1034 target (authored by
aakanksha555).
Herald added a project: OpenMP.
Herald added a subscriber: openmp-commits.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D102306/new/
https://reviews.llvm.org/D102306
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
clang/test/Misc/target-invalid-cpu-note.c
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/directive-amdgcn-target.ll
llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.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-objdump/ELF/AMDGPU/subtarget.ll
llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
llvm/tools/llvm-readobj/ELFDumper.cpp
openmp/libomptarget/plugins/amdgpu/impl/get_elf_mach_gfx_name.cpp
Index: openmp/libomptarget/plugins/amdgpu/impl/get_elf_mach_gfx_name.cpp
===================================================================
--- openmp/libomptarget/plugins/amdgpu/impl/get_elf_mach_gfx_name.cpp
+++ openmp/libomptarget/plugins/amdgpu/impl/get_elf_mach_gfx_name.cpp
@@ -47,6 +47,8 @@
return "gfx1032";
case EF_AMDGPU_MACH_AMDGCN_GFX1033:
return "gfx1033";
+ case EF_AMDGPU_MACH_AMDGCN_GFX1034:
+ return "gfx1034";
default:
return "--unknown gfx";
}
Index: llvm/tools/llvm-readobj/ELFDumper.cpp
===================================================================
--- llvm/tools/llvm-readobj/ELFDumper.cpp
+++ llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1478,6 +1478,7 @@
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_MACH_AMDGCN_GFX1034),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_XNACK_V3),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_SRAMECC_V3)
};
@@ -1529,6 +1530,7 @@
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_MACH_AMDGCN_GFX1034),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_XNACK_ANY_V4),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_XNACK_OFF_V4),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_XNACK_ON_V4),
Index: llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
===================================================================
--- llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
+++ llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
@@ -259,6 +259,16 @@
# RUN: yaml2obj %s -o %t -DABI_VERSION=2 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1033
# RUN: llvm-readobj -h %t | FileCheck %s --check-prefixes=ALL,KNOWN-ABI-VERSION,SINGLE-FLAG --match-full-lines -DABI_VERSION=2 -DFILE=%t -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1033 -DFLAG_VALUE=0x39
+# RUN: yaml2obj %s -o %t -DABI_VERSION=0 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1034
+# RUN: llvm-readobj -h %t | FileCheck %s --check-prefixes=ALL,KNOWN-ABI-VERSION,SINGLE-FLAG --match-full-lines -DABI_VERSION=0 -DFILE=%t -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1034 -DFLAG_VALUE=0x3E
+#
+# RUN: yaml2obj %s -o %t -DABI_VERSION=1 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1034
+# RUN: llvm-readobj -h %t | FileCheck %s --check-prefixes=ALL,KNOWN-ABI-VERSION,SINGLE-FLAG --match-full-lines -DABI_VERSION=1 -DFILE=%t -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1034 -DFLAG_VALUE=0x3E
+#
+# RUN: yaml2obj %s -o %t -DABI_VERSION=2 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1034
+# RUN: llvm-readobj -h %t | FileCheck %s --check-prefixes=ALL,KNOWN-ABI-VERSION,SINGLE-FLAG --match-full-lines -DABI_VERSION=2 -DFILE=%t -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1034 -DFLAG_VALUE=0x3E
+
+
# RUN: yaml2obj %s -o %t -DABI_VERSION=0 -DFLAG_NAME="EF_AMDGPU_MACH_AMDGCN_GFX90A, EF_AMDGPU_FEATURE_XNACK_V3"
# RUN: llvm-readobj -h %t | FileCheck %s --check-prefixes=ALL,KNOWN-ABI-VERSION,DOUBLE-FLAG --match-full-lines -DABI_VERSION=0 -DFILE=%t -DFLAG_0="EF_AMDGPU_FEATURE_XNACK_V3 (0x100)" -DFLAG_1="EF_AMDGPU_MACH_AMDGCN_GFX90A (0x3F)" -DFLAG_VALUE=0x13F
Index: llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
===================================================================
--- llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
+++ llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
@@ -6,6 +6,11 @@
;
; ----------------------------------GFX10--------------------------------------
;
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1034 -filetype=obj -O0 -o %t.o %s
+; RUN: llvm-objdump -D --arch-name=amdgcn --mcpu=gfx1034 %t.o > %t-specify.txt
+; RUN: llvm-objdump -D %t.o > %t-detect.txt
+; RUN: diff %t-specify.txt %t-detect.txt
+
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1033 -filetype=obj -O0 -o %t.o %s
; RUN: llvm-objdump -D --arch-name=amdgcn --mcpu=gfx1033 %t.o > %t-specify.txt
; RUN: llvm-objdump -D %t.o > %t-detect.txt
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
@@ -178,6 +178,9 @@
# 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
+# RUN: sed -e 's/<BITS>/64/' -e 's/<MACH>/AMDGCN_GFX1034/' %s | yaml2obj -o %t.o.AMDGCN_GFX1034
+# RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX1034 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX1034 %s
+# RUN: obj2yaml %t.o.AMDGCN_GFX1034 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX1034 %s
# ELF-R600-ALL: Format: elf32-amdgpu
# ELF-R600-ALL: Arch: r600
@@ -331,6 +334,9 @@
# ELF-AMDGCN-GFX1033: EF_AMDGPU_MACH_AMDGCN_GFX1033 (0x39)
# YAML-AMDGCN-GFX1033: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1033 ]
+# ELF-AMDGCN-GFX1034: EF_AMDGPU_MACH_AMDGCN_GFX1034 (0x3E)
+# YAML-AMDGCN-GFX1034: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1034 ]
+
# ELF-AMDGCN-ALL: ]
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
@@ -2,6 +2,7 @@
# 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
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1034 -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
@@ -4,6 +4,7 @@
# 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
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1034 -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
@@ -2,6 +2,7 @@
// 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
+// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1034 -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
@@ -2,6 +2,7 @@
// 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
+// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1034 %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
@@ -4,6 +4,7 @@
// 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
+// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1034 -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/elf-header-flags-mach.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
+++ llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
@@ -61,6 +61,7 @@
; 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
+; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1034 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1034 %s
; FIXME: With the default attributes the eflags are not accurate for
; xnack and sramecc. Subsequent Target-ID patches will address this.
@@ -119,6 +120,7 @@
; GFX1031: EF_AMDGPU_MACH_AMDGCN_GFX1031 (0x37)
; GFX1032: EF_AMDGPU_MACH_AMDGCN_GFX1032 (0x38)
; GFX1033: EF_AMDGPU_MACH_AMDGCN_GFX1033 (0x39)
+; GFX1034: EF_AMDGPU_MACH_AMDGCN_GFX1034 (0x3E)
; ALL: ]
define amdgpu_kernel void @elf_header() {
Index: llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
+++ llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
@@ -84,6 +84,7 @@
; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=3 -mcpu=gfx1031 < %s | FileCheck --check-prefixes=V3-GFX1031 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=3 -mcpu=gfx1032 < %s | FileCheck --check-prefixes=V3-GFX1032 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=3 -mcpu=gfx1033 < %s | FileCheck --check-prefixes=V3-GFX1033 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=3 -mcpu=gfx1034 < %s | FileCheck --check-prefixes=V3-GFX1034 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx600 < %s | FileCheck --check-prefixes=GFX600 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tahiti < %s | FileCheck --check-prefixes=GFX600 %s
@@ -171,6 +172,7 @@
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1031 < %s | FileCheck --check-prefixes=GFX1031 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1032 < %s | FileCheck --check-prefixes=GFX1032 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1033 < %s | FileCheck --check-prefixes=GFX1033 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1034 < %s | FileCheck --check-prefixes=GFX1034 %s
; V3-GFX600: .amdgcn_target "amdgcn-amd-amdhsa--gfx600"
; V3-GFX601: .amdgcn_target "amdgcn-amd-amdhsa--gfx601"
@@ -216,6 +218,7 @@
; V3-GFX1031: .amdgcn_target "amdgcn-amd-amdhsa--gfx1031"
; V3-GFX1032: .amdgcn_target "amdgcn-amd-amdhsa--gfx1032"
; V3-GFX1033: .amdgcn_target "amdgcn-amd-amdhsa--gfx1033"
+; V3-GFX1034: .amdgcn_target "amdgcn-amd-amdhsa--gfx1034"
; GFX600: .amdgcn_target "amdgcn-amd-amdhsa--gfx600"
; GFX601: .amdgcn_target "amdgcn-amd-amdhsa--gfx601"
@@ -281,6 +284,7 @@
; GFX1031: .amdgcn_target "amdgcn-amd-amdhsa--gfx1031"
; GFX1032: .amdgcn_target "amdgcn-amd-amdhsa--gfx1032"
; GFX1033: .amdgcn_target "amdgcn-amd-amdhsa--gfx1033"
+; GFX1034: .amdgcn_target "amdgcn-amd-amdhsa--gfx1034"
define amdgpu_kernel void @directive_amdgcn_target() {
ret void
Index: llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
+++ llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
@@ -109,6 +109,7 @@
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_AMDGCN_GFX1034: AK = GK_GFX1034; break;
case ELF::EF_AMDGPU_MACH_NONE: AK = GK_NONE; break;
}
@@ -169,6 +170,7 @@
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_GFX1034: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1034;
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
@@ -223,3 +223,7 @@
def : ProcessorModel<"gfx1033", GFX10SpeedModel,
FeatureISAVersion10_3_0.Features
>;
+
+def : ProcessorModel<"gfx1034", GFX10SpeedModel,
+ FeatureISAVersion10_3_0.Features
+>;
Index: llvm/lib/Support/TargetParser.cpp
===================================================================
--- llvm/lib/Support/TargetParser.cpp
+++ llvm/lib/Support/TargetParser.cpp
@@ -113,6 +113,7 @@
{{"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},
+ {{"gfx1034"}, {"gfx1034"}, GK_GFX1034, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32},
};
const GPUInfo *getArchEntry(AMDGPU::GPUKind AK, ArrayRef<GPUInfo> Table) {
@@ -223,6 +224,7 @@
case GK_GFX1031: return {10, 3, 1};
case GK_GFX1032: return {10, 3, 2};
case GK_GFX1033: return {10, 3, 3};
+ case GK_GFX1034: return {10, 3, 4};
default: return {0, 0, 0};
}
}
Index: llvm/lib/ObjectYAML/ELFYAML.cpp
===================================================================
--- llvm/lib/ObjectYAML/ELFYAML.cpp
+++ llvm/lib/ObjectYAML/ELFYAML.cpp
@@ -552,6 +552,7 @@
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);
+ BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1034, EF_AMDGPU_MACH);
switch (Object->Header.ABIVersion) {
default:
// ELFOSABI_AMDGPU_PAL, ELFOSABI_AMDGPU_MESA3D support *_V3 flags.
Index: llvm/lib/Object/ELFObjectFile.cpp
===================================================================
--- llvm/lib/Object/ELFObjectFile.cpp
+++ llvm/lib/Object/ELFObjectFile.cpp
@@ -477,6 +477,8 @@
return "gfx1032";
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1033:
return "gfx1033";
+ case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1034:
+ return "gfx1034";
default:
llvm_unreachable("Unknown EF_AMDGPU_MACH value");
}
Index: llvm/include/llvm/Support/TargetParser.h
===================================================================
--- llvm/include/llvm/Support/TargetParser.h
+++ llvm/include/llvm/Support/TargetParser.h
@@ -93,9 +93,10 @@
GK_GFX1031 = 76,
GK_GFX1032 = 77,
GK_GFX1033 = 78,
+ GK_GFX1034 = 79,
GK_AMDGCN_FIRST = GK_GFX600,
- GK_AMDGCN_LAST = GK_GFX1033,
+ GK_AMDGCN_LAST = GK_GFX1034,
};
/// Instruction set architecture version.
Index: llvm/include/llvm/BinaryFormat/ELF.h
===================================================================
--- llvm/include/llvm/BinaryFormat/ELF.h
+++ llvm/include/llvm/BinaryFormat/ELF.h
@@ -734,6 +734,7 @@
EF_AMDGPU_MACH_AMDGCN_GFX1031 = 0x037,
EF_AMDGPU_MACH_AMDGCN_GFX1032 = 0x038,
EF_AMDGPU_MACH_AMDGCN_GFX1033 = 0x039,
+ EF_AMDGPU_MACH_AMDGCN_GFX1034 = 0x03e,
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
@@ -406,6 +406,12 @@
Add product
names.
+ ``gfx1034`` ``amdgcn`` dGPU - cumode - Absolute - *pal-amdpal* *TBA*
+ - wavefrontsize64 flat
+ scratch .. TODO::
+
+ Add product
+ names.
=========== =============== ============ ===== ================= =============== =============== ======================
@@ -1134,6 +1140,7 @@
``EF_AMDGPU_MACH_AMDGCN_GFX1031`` 0x037 ``gfx1031``
``EF_AMDGPU_MACH_AMDGCN_GFX1032`` 0x038 ``gfx1032``
``EF_AMDGPU_MACH_AMDGCN_GFX1033`` 0x039 ``gfx1033``
+ ``EF_AMDGPU_MACH_AMDGCN_GFX1034`` 0x03e ``gfx1034``
``EF_AMDGPU_MACH_AMDGCN_GFX602`` 0x03a ``gfx602``
``EF_AMDGPU_MACH_AMDGCN_GFX705`` 0x03b ``gfx705``
``EF_AMDGPU_MACH_AMDGCN_GFX805`` 0x03c ``gfx805``
Index: clang/test/Misc/target-invalid-cpu-note.c
===================================================================
--- clang/test/Misc/target-invalid-cpu-note.c
+++ clang/test/Misc/target-invalid-cpu-note.c
@@ -87,7 +87,7 @@
// AMDGCN-SAME: gfx802, iceland, tonga, gfx803, fiji, polaris10, polaris11,
// AMDGCN-SAME: gfx805, tongapro, gfx810, stoney, gfx900, gfx902, gfx904, gfx906,
// AMDGCN-SAME: gfx908, gfx909, gfx90a, gfx90c, gfx1010, gfx1011, gfx1012, gfx1030, gfx1031,
-// AMDGCN-SAME: gfx1032, gfx1033
+// AMDGCN-SAME: gfx1032, gfx1033, gfx1034
// RUN: not %clang_cc1 -triple wasm64--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix WEBASM
// WEBASM: error: unknown target CPU 'not-a-cpu'
Index: clang/test/Driver/amdgpu-mcpu.cl
===================================================================
--- clang/test/Driver/amdgpu-mcpu.cl
+++ clang/test/Driver/amdgpu-mcpu.cl
@@ -99,6 +99,7 @@
// 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
+// RUN: %clang -### -target amdgcn -mcpu=gfx1034 %s 2>&1 | FileCheck --check-prefix=GFX1034 %s
// GCNDEFAULT-NOT: -target-cpu
// GFX600: "-target-cpu" "gfx600"
@@ -130,3 +131,4 @@
// GFX1031: "-target-cpu" "gfx1031"
// GFX1032: "-target-cpu" "gfx1032"
// GFX1033: "-target-cpu" "gfx1033"
+// GFX1034: "-target-cpu" "gfx1034"
Index: clang/test/Driver/amdgpu-macros.cl
===================================================================
--- clang/test/Driver/amdgpu-macros.cl
+++ clang/test/Driver/amdgpu-macros.cl
@@ -114,6 +114,7 @@
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1031 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1031
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1032 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1032
// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1033 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1033
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1034 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1034
// ARCH-GCN-DAG: #define FP_FAST_FMA 1
Index: clang/test/CodeGenOpenCL/amdgpu-features.cl
===================================================================
--- clang/test/CodeGenOpenCL/amdgpu-features.cl
+++ clang/test/CodeGenOpenCL/amdgpu-features.cl
@@ -32,6 +32,7 @@
// 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
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1034 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1034 %s
// GFX600: "target-features"="+s-memtime-inst"
// GFX601: "target-features"="+s-memtime-inst"
@@ -62,5 +63,6 @@
// GFX1031: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
// GFX1032: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
// GFX1033: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
+// GFX1034: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
kernel void test() {}
Index: clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
===================================================================
--- clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -4486,6 +4486,7 @@
case CudaArch::GFX1031:
case CudaArch::GFX1032:
case CudaArch::GFX1033:
+ case CudaArch::GFX1034:
case CudaArch::UNUSED:
case CudaArch::UNKNOWN:
break;
@@ -4556,6 +4557,7 @@
case CudaArch::GFX1031:
case CudaArch::GFX1032:
case CudaArch::GFX1033:
+ case CudaArch::GFX1034:
case CudaArch::UNUSED:
case CudaArch::UNKNOWN:
break;
Index: clang/lib/Basic/Targets/NVPTX.cpp
===================================================================
--- clang/lib/Basic/Targets/NVPTX.cpp
+++ clang/lib/Basic/Targets/NVPTX.cpp
@@ -211,6 +211,7 @@
case CudaArch::GFX1031:
case CudaArch::GFX1032:
case CudaArch::GFX1033:
+ case CudaArch::GFX1034:
case CudaArch::LAST:
break;
case CudaArch::UNUSED:
Index: clang/lib/Basic/Targets/AMDGPU.cpp
===================================================================
--- clang/lib/Basic/Targets/AMDGPU.cpp
+++ clang/lib/Basic/Targets/AMDGPU.cpp
@@ -180,6 +180,7 @@
// XXX - What does the member GPU mean if device name string passed here?
if (isAMDGCN(getTriple())) {
switch (llvm::AMDGPU::parseArchAMDGCN(CPU)) {
+ case GK_GFX1034:
case GK_GFX1033:
case GK_GFX1032:
case GK_GFX1031:
Index: clang/lib/Basic/Cuda.cpp
===================================================================
--- clang/lib/Basic/Cuda.cpp
+++ clang/lib/Basic/Cuda.cpp
@@ -109,6 +109,7 @@
GFX(1031), // gfx1031
GFX(1032), // gfx1032
GFX(1033), // gfx1033
+ GFX(1034), // gfx1034
// clang-format on
};
#undef SM
Index: clang/include/clang/Basic/Cuda.h
===================================================================
--- clang/include/clang/Basic/Cuda.h
+++ clang/include/clang/Basic/Cuda.h
@@ -87,6 +87,7 @@
GFX1031,
GFX1032,
GFX1033,
+ GFX1034,
LAST,
};
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
