intel/llvm
1
0
Fork 0
mirror of https://github.com/intel/llvm.git synced 2026-01-14 20:10:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

[ELF] handle new NVIDIA GPU variants. (#151604)

Browse Source
This commit is contained in:
Artem Belevich
2025-07-31 17:21:40 -07:00
committed by GitHub
parent 92ca087b45
commit 4e596fc285
3 changed files with 19 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
llvm/include/llvm/BinaryFormat/ELF.h
View File

@@ -973,7 +973,10 @@ enum : unsigned {
// SM based processor values.
EF_CUDA_SM100 = 0x6400,
EF_CUDA_SM101 = 0x6500,
EF_CUDA_SM103 = 0x6700,
EF_CUDA_SM120 = 0x7800,
EF_CUDA_SM121 = 0x7900,
// Set when using an accelerator variant like sm_100a.
EF_CUDA_ACCELERATORS = 0x8,

9
llvm/lib/Object/ELFObjectFile.cpp
View File

@@ -688,11 +688,20 @@ StringRef ELFObjectFileBase::getNVPTXCPUName() const {
case ELF::EF_CUDA_SM100:
return getPlatformFlags() & ELF::EF_CUDA_ACCELERATORS ? "sm_100a"
: "sm_100";
case ELF::EF_CUDA_SM101:
return getPlatformFlags() & ELF::EF_CUDA_ACCELERATORS ? "sm_101a"
: "sm_101";
case ELF::EF_CUDA_SM103:
return getPlatformFlags() & ELF::EF_CUDA_ACCELERATORS ? "sm_103a"
: "sm_103";
// Rubin architecture.
case ELF::EF_CUDA_SM120:
return getPlatformFlags() & ELF::EF_CUDA_ACCELERATORS ? "sm_120a"
: "sm_120";
case ELF::EF_CUDA_SM121:
return getPlatformFlags() & ELF::EF_CUDA_ACCELERATORS ? "sm_121a"
: "sm_121";
default:
llvm_unreachable("Unknown EF_CUDA_SM value");
}

10
llvm/tools/llvm-readobj/ELFDumper.cpp
View File

@@ -1683,7 +1683,9 @@ const EnumEntry<unsigned> ElfHeaderNVPTXFlags[] = {
ENUM_ENT(EF_CUDA_SM75, "sm_75"), ENUM_ENT(EF_CUDA_SM80, "sm_80"),
ENUM_ENT(EF_CUDA_SM86, "sm_86"), ENUM_ENT(EF_CUDA_SM87, "sm_87"),
ENUM_ENT(EF_CUDA_SM89, "sm_89"), ENUM_ENT(EF_CUDA_SM90, "sm_90"),
ENUM_ENT(EF_CUDA_SM100, "sm_100"), ENUM_ENT(EF_CUDA_SM120, "sm_120"),
ENUM_ENT(EF_CUDA_SM100, "sm_100"), ENUM_ENT(EF_CUDA_SM101, "sm_101"),
ENUM_ENT(EF_CUDA_SM103, "sm_103"), ENUM_ENT(EF_CUDA_SM120, "sm_120"),
ENUM_ENT(EF_CUDA_SM121, "sm_121"),
};
const EnumEntry<unsigned> ElfHeaderRISCVFlags[] = {
@@ -3659,8 +3661,10 @@ template <class ELFT> void GNUELFDumper<ELFT>::printFileHeaders() {
ElfFlags = printFlags(e.e_flags, ArrayRef(ElfHeaderXtensaFlags),
unsigned(ELF::EF_XTENSA_MACH));
else if (e.e_machine == EM_CUDA) {
ElfFlags = printFlags(e.e_flags, ArrayRef(ElfHeaderNVPTXFlags),
unsigned(ELF::EF_CUDA_SM));
unsigned Mask = e.e_ident[ELF::EI_ABIVERSION] == ELF::ELFABIVERSION_CUDA_V1
? ELF::EF_CUDA_SM
: ELF::EF_CUDA_SM_MASK;
ElfFlags = printFlags(e.e_flags, ArrayRef(ElfHeaderNVPTXFlags), Mask);
if (e.e_ident[ELF::EI_ABIVERSION] == ELF::ELFABIVERSION_CUDA_V1 &&
(e.e_flags & ELF::EF_CUDA_ACCELERATORS_V1))
ElfFlags += "a";