RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 12:12:47 +01:00
Code Issues Projects Releases Wiki Activity

[AMDGPU] Add gfx1035 target

Browse Source 
Differential Revision: https://reviews.llvm.org/D104804
This commit is contained in:
Aakanksha Patil 2021-06-24 14:32:41 -04:00
parent a6fe9f4fd8
commit d4359ff02a
19 changed files with 53 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docs/AMDGPUUsage.rst
View File

@ -421,6 +421,12 @@ Every processor supports every OS ABI (see :ref:`amdgpu-os`) with the following
Add product
names.
``gfx1035`` ``amdgcn`` APU - cumode - Absolute - *pal-amdpal* *TBA*
- wavefrontsize64 flat
scratch .. TODO::
Add product
names.
=========== =============== ============ ===== ================= =============== =============== ======================
.. _amdgpu-target-features:
@ -1151,7 +1157,7 @@ The AMDGPU backend uses the following ELF header:
``EF_AMDGPU_MACH_AMDGCN_GFX602`` 0x03a ``gfx602``
``EF_AMDGPU_MACH_AMDGCN_GFX705`` 0x03b ``gfx705``
``EF_AMDGPU_MACH_AMDGCN_GFX805`` 0x03c ``gfx805``
*reserved* 0x03d Reserved.
``EF_AMDGPU_MACH_AMDGCN_GFX1035`` 0x03d ``gfx1035``
``EF_AMDGPU_MACH_AMDGCN_GFX1034`` 0x03e ``gfx1034``
``EF_AMDGPU_MACH_AMDGCN_GFX90A`` 0x03f ``gfx90a``
*reserved* 0x040 Reserved.

2
include/llvm/BinaryFormat/ELF.h
View File

@ -737,7 +737,7 @@ enum : unsigned {
EF_AMDGPU_MACH_AMDGCN_GFX602 = 0x03a,
EF_AMDGPU_MACH_AMDGCN_GFX705 = 0x03b,
EF_AMDGPU_MACH_AMDGCN_GFX805 = 0x03c,
EF_AMDGPU_MACH_AMDGCN_RESERVED_0X3D = 0x03d,
EF_AMDGPU_MACH_AMDGCN_GFX1035 = 0x03d,
EF_AMDGPU_MACH_AMDGCN_GFX1034 = 0x03e,
EF_AMDGPU_MACH_AMDGCN_GFX90A = 0x03f,
EF_AMDGPU_MACH_AMDGCN_RESERVED_0X40 = 0x040,

3
include/llvm/Support/TargetParser.h
View File

@ -95,9 +95,10 @@ enum GPUKind : uint32_t {
GK_GFX1032 = 77,
GK_GFX1033 = 78,
GK_GFX1034 = 79,
GK_GFX1035 = 80,
GK_AMDGCN_FIRST = GK_GFX600,
GK_AMDGCN_LAST = GK_GFX1034,
GK_AMDGCN_LAST = GK_GFX1035,
};
/// Instruction set architecture version.

2
lib/Object/ELFObjectFile.cpp
View File

@ -481,6 +481,8 @@ StringRef ELFObjectFileBase::getAMDGPUCPUName() const {
return "gfx1033";
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1034:
return "gfx1034";
case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1035:
return "gfx1035";
default:
llvm_unreachable("Unknown EF_AMDGPU_MACH value");
}

1
lib/ObjectYAML/ELFYAML.cpp
View File

@ -555,6 +555,7 @@ void ScalarBitSetTraits<ELFYAML::ELF_EF>::bitset(IO &IO,
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);
BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1035, EF_AMDGPU_MACH);
switch (Object->Header.ABIVersion) {
default:
// ELFOSABI_AMDGPU_PAL, ELFOSABI_AMDGPU_MESA3D support *_V3 flags.

2
lib/Support/TargetParser.cpp
View File

@ -115,6 +115,7 @@ constexpr GPUInfo AMDGCNGPUs[] = {
{{"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},
{{"gfx1035"}, {"gfx1035"}, GK_GFX1035, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32},
};
const GPUInfo *getArchEntry(AMDGPU::GPUKind AK, ArrayRef<GPUInfo> Table) {
@ -227,6 +228,7 @@ AMDGPU::IsaVersion AMDGPU::getIsaVersion(StringRef GPU) {
case GK_GFX1032: return {10, 3, 2};
case GK_GFX1033: return {10, 3, 3};
case GK_GFX1034: return {10, 3, 4};
case GK_GFX1035: return {10, 3, 5};
default: return {0, 0, 0};
}
}

4
lib/Target/AMDGPU/GCNProcessors.td
View File

@ -231,3 +231,7 @@ def : ProcessorModel<"gfx1033", GFX10SpeedModel,
def : ProcessorModel<"gfx1034", GFX10SpeedModel,
FeatureISAVersion10_3_0.Features
>;
def : ProcessorModel<"gfx1035", GFX10SpeedModel,
FeatureISAVersion10_3_0.Features
>;

2
lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
View File

@ -111,6 +111,7 @@ StringRef AMDGPUTargetStreamer::getArchNameFromElfMach(unsigned ElfMach) {
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_AMDGCN_GFX1035: AK = GK_GFX1035; break;
case ELF::EF_AMDGPU_MACH_NONE: AK = GK_NONE; break;
}
@ -173,6 +174,7 @@ unsigned AMDGPUTargetStreamer::getElfMach(StringRef GPU) {
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_GFX1035: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1035;
case GK_NONE: return ELF::EF_AMDGPU_MACH_NONE;
}

4
test/CodeGen/AMDGPU/directive-amdgcn-target.ll
View File

@ -88,6 +88,7 @@
; 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 --amdhsa-code-object-version=3 -mcpu=gfx1035 < %s | FileCheck --check-prefixes=V3-GFX1035 %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
@ -179,6 +180,7 @@
; 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
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1035 < %s | FileCheck --check-prefixes=GFX1035 %s
; V3-GFX600: .amdgcn_target "amdgcn-amd-amdhsa--gfx600"
; V3-GFX601: .amdgcn_target "amdgcn-amd-amdhsa--gfx601"
@ -227,6 +229,7 @@
; V3-GFX1032: .amdgcn_target "amdgcn-amd-amdhsa--gfx1032"
; V3-GFX1033: .amdgcn_target "amdgcn-amd-amdhsa--gfx1033"
; V3-GFX1034: .amdgcn_target "amdgcn-amd-amdhsa--gfx1034"
; V3-GFX1035: .amdgcn_target "amdgcn-amd-amdhsa--gfx1035"
; GFX600: .amdgcn_target "amdgcn-amd-amdhsa--gfx600"
; GFX601: .amdgcn_target "amdgcn-amd-amdhsa--gfx601"
@ -296,6 +299,7 @@
; GFX1032: .amdgcn_target "amdgcn-amd-amdhsa--gfx1032"
; GFX1033: .amdgcn_target "amdgcn-amd-amdhsa--gfx1033"
; GFX1034: .amdgcn_target "amdgcn-amd-amdhsa--gfx1034"
; GFX1035: .amdgcn_target "amdgcn-amd-amdhsa--gfx1035"
define amdgpu_kernel void @directive_amdgcn_target() {
ret void

2
test/CodeGen/AMDGPU/elf-header-flags-mach.ll
View File

@ -63,6 +63,7 @@
; 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
; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1035 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1035 %s
; FIXME: With the default attributes the eflags are not accurate for
; xnack and sramecc. Subsequent Target-ID patches will address this.
@ -123,6 +124,7 @@
; GFX1032: EF_AMDGPU_MACH_AMDGCN_GFX1032 (0x38)
; GFX1033: EF_AMDGPU_MACH_AMDGCN_GFX1033 (0x39)
; GFX1034: EF_AMDGPU_MACH_AMDGCN_GFX1034 (0x3E)
; GFX1035: EF_AMDGPU_MACH_AMDGCN_GFX1035 (0x3D)
; ALL: ]
define amdgpu_kernel void @elf_header() {

1
test/MC/AMDGPU/gfx1011_dlops.s
View File

@ -5,6 +5,7 @@
// 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
// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1035 -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]

1
test/MC/AMDGPU/gfx1030_err.s
View File

@ -3,6 +3,7 @@
// 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
// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1035 %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

1
test/MC/AMDGPU/gfx1030_new.s
View File

@ -3,6 +3,7 @@
// 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
// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1035 -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]

1
test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
View File

@ -5,6 +5,7 @@
# 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
# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1035 -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

1
test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
View File

@ -3,6 +3,7 @@
# 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
# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1035 -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

7
test/Object/AMDGPU/elf-header-flags-mach.yaml
View File

@ -186,6 +186,10 @@
# 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
# RUN: sed -e 's/<BITS>/64/' -e 's/<MACH>/AMDGCN_GFX1035/' %s | yaml2obj -o %t.o.AMDGCN_GFX1035
# RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX1035 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX1035 %s
# RUN: obj2yaml %t.o.AMDGCN_GFX1035 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX1035 %s
# ELF-R600-ALL: Format: elf32-amdgpu
# ELF-R600-ALL: Arch: r600
# ELF-R600-ALL: AddressSize: 32bit
@ -344,6 +348,9 @@
# ELF-AMDGCN-GFX1034: EF_AMDGPU_MACH_AMDGCN_GFX1034 (0x3E)
# YAML-AMDGCN-GFX1034: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1034 ]
# ELF-AMDGCN-GFX1035: EF_AMDGPU_MACH_AMDGCN_GFX1035 (0x3D)
# YAML-AMDGCN-GFX1035: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1035 ]
#
# ELF-AMDGCN-ALL: ]

4
test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
View File

@ -5,6 +5,10 @@ define amdgpu_kernel void @test_kernel() {
; Test subtarget detection. Disassembly is only supported for GFX8 and beyond.
;
; ----------------------------------GFX10--------------------------------------
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1035 -filetype=obj -O0 -o %t.o %s
; RUN: llvm-objdump -D --arch-name=amdgcn --mcpu=gfx1035 %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=gfx1034 -filetype=obj -O0 -o %t.o %s
; RUN: llvm-objdump -D --arch-name=amdgcn --mcpu=gfx1034 %t.o > %t-specify.txt

8
test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
View File

@ -277,6 +277,14 @@
# 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_GFX1035
# 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_GFX1035 -DFLAG_VALUE=0x3D
#
# RUN: yaml2obj %s -o %t -DABI_VERSION=1 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1035
# 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_GFX1035 -DFLAG_VALUE=0x3D
#
# RUN: yaml2obj %s -o %t -DABI_VERSION=2 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1035
# 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_GFX1035 -DFLAG_VALUE=0x3D
# 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

2
tools/llvm-readobj/ELFDumper.cpp
View File

@ -1493,6 +1493,7 @@ static const EnumEntry<unsigned> ElfHeaderAMDGPUFlagsABIVersion3[] = {
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_MACH_AMDGCN_GFX1035),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_XNACK_V3),
LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_SRAMECC_V3)
};
@ -1546,6 +1547,7 @@ static const EnumEntry<unsigned> ElfHeaderAMDGPUFlagsABIVersion4[] = {
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_MACH_AMDGCN_GFX1035),
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),