Skip to content

[ELF] handle new NVIDIA GPU variants. #151604

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Aug 1, 2025
Merged

[ELF] handle new NVIDIA GPU variants. #151604

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f396d5a
[ELF] handle new NVIDIA GPU variants.
Artem-B Jul 31, 2025
ebfa740
correctly handle new GPU values
Artem-B Jul 31, 2025
0981290
clang-format
Artem-B Jul 31, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions llvm/include/llvm/BinaryFormat/ELF.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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,
Expand Down
9 changes: 9 additions & 0 deletions llvm/lib/Object/ELFObjectFile.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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");
}
Expand Down
10 changes: 7 additions & 3 deletions llvm/tools/llvm-readobj/ELFDumper.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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[] = {
Expand Down Expand Up @@ -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";
Expand Down