[llvm] [LLVM] Update CUDA ABI for all SM values (PR #159354)
Joseph Huber via llvm-commits
llvm-commits at lists.llvm.org
Wed Sep 17 06:11:26 PDT 2025
https://github.com/jhuber6 created https://github.com/llvm/llvm-project/pull/159354
Summary:
Turns out the new CUDA ABI now applies retroactively to all the other
SMs if you upgrade to CUDA 13.0. This patch changes the scheme, keeping
all the SM flags consistent but using an offset.
Fixes: https://github.com/llvm/llvm-project/issues/159088
>From 23c6f6cbb6b8374a89084617655af9471b2cf714 Mon Sep 17 00:00:00 2001
From: Joseph Huber <huberjn at outlook.com>
Date: Wed, 17 Sep 2025 08:09:08 -0500
Subject: [PATCH] [LLVM] Update CUDA ABI for all SM values
Summary:
Turns out the new CUDA ABI now applies retroactively to all the other
SMs if you upgrade to CUDA 13.0. This patch changes the scheme, keeping
all the SM flags consistent but using an offset.
Fixes: https://github.com/llvm/llvm-project/issues/159088
---
llvm/include/llvm/BinaryFormat/ELF.h | 25 +++++-----
llvm/lib/Object/ELFObjectFile.cpp | 3 +-
llvm/tools/llvm-readobj/ELFDumper.cpp | 62 +++++++++++++++++++-----
offload/plugins-nextgen/cuda/src/rtl.cpp | 2 +-
4 files changed, 66 insertions(+), 26 deletions(-)
diff --git a/llvm/include/llvm/BinaryFormat/ELF.h b/llvm/include/llvm/BinaryFormat/ELF.h
index 749971e354f66..39c3549697ea3 100644
--- a/llvm/include/llvm/BinaryFormat/ELF.h
+++ b/llvm/include/llvm/BinaryFormat/ELF.h
@@ -931,6 +931,12 @@ enum : unsigned {
// Processor selection mask for EF_CUDA_SM* values prior to blackwell.
EF_CUDA_SM = 0xff,
+ // Processor selection mask for EF_CUDA_SM* values following blackwell.
+ EF_CUDA_SM_MASK = 0xff00,
+
+ // Processor selection mask for EF_CUDA_SM* values following blackwell.
+ EF_CUDA_SM_OFFSET = 8,
+
// SM based processor values.
EF_CUDA_SM20 = 0x14,
EF_CUDA_SM21 = 0x15,
@@ -951,8 +957,13 @@ enum : unsigned {
EF_CUDA_SM86 = 0x56,
EF_CUDA_SM87 = 0x57,
EF_CUDA_SM89 = 0x59,
- // The sm_90a variant uses the same machine flag.
EF_CUDA_SM90 = 0x5a,
+ EF_CUDA_SM100 = 0x64,
+ EF_CUDA_SM101 = 0x65,
+ EF_CUDA_SM103 = 0x67,
+ EF_CUDA_SM120 = 0x78,
+ EF_CUDA_SM121 = 0x79,
+
// Unified texture binding is enabled.
EF_CUDA_TEXMODE_UNIFIED = 0x100,
@@ -968,17 +979,7 @@ enum : unsigned {
// Virtual processor selection mask for EF_CUDA_VIRTUAL_SM* values.
EF_CUDA_VIRTUAL_SM = 0xff0000,
- // Processor selection mask for EF_CUDA_SM* values following blackwell.
- EF_CUDA_SM_MASK = 0xff00,
-
- // 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.
+ // Set when using an accelerator variant like sm_100a in the new ABI.
EF_CUDA_ACCELERATORS = 0x8,
};
diff --git a/llvm/lib/Object/ELFObjectFile.cpp b/llvm/lib/Object/ELFObjectFile.cpp
index aff047c297cc2..92f5cef80ae18 100644
--- a/llvm/lib/Object/ELFObjectFile.cpp
+++ b/llvm/lib/Object/ELFObjectFile.cpp
@@ -622,7 +622,8 @@ StringRef ELFObjectFileBase::getNVPTXCPUName() const {
assert(getEMachine() == ELF::EM_CUDA);
unsigned SM = getEIdentABIVersion() == ELF::ELFABIVERSION_CUDA_V1
? getPlatformFlags() & ELF::EF_CUDA_SM
- : getPlatformFlags() & ELF::EF_CUDA_SM_MASK;
+ : (getPlatformFlags() & ELF::EF_CUDA_SM_MASK) >>
+ ELF::EF_CUDA_SM_OFFSET;
switch (SM) {
// Fermi architecture.
diff --git a/llvm/tools/llvm-readobj/ELFDumper.cpp b/llvm/tools/llvm-readobj/ELFDumper.cpp
index 7d75f29623ea9..2f3909811b010 100644
--- a/llvm/tools/llvm-readobj/ELFDumper.cpp
+++ b/llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1114,6 +1114,7 @@ const EnumEntry<unsigned> ElfOSABI[] = {
{"FenixOS", "FenixOS", ELF::ELFOSABI_FENIXOS},
{"CloudABI", "CloudABI", ELF::ELFOSABI_CLOUDABI},
{"CUDA", "NVIDIA - CUDA", ELF::ELFOSABI_CUDA},
+ {"CUDA", "NVIDIA - CUDA", ELF::ELFOSABI_CUDA_V2},
{"Standalone", "Standalone App", ELF::ELFOSABI_STANDALONE}};
const EnumEntry<unsigned> AMDGPUElfOSABI[] = {
@@ -1679,19 +1680,56 @@ const EnumEntry<unsigned> ElfHeaderAMDGPUFlagsABIVersion4[] = {
};
const EnumEntry<unsigned> ElfHeaderNVPTXFlags[] = {
- ENUM_ENT(EF_CUDA_SM20, "sm_20"), ENUM_ENT(EF_CUDA_SM21, "sm_21"),
- ENUM_ENT(EF_CUDA_SM30, "sm_30"), ENUM_ENT(EF_CUDA_SM32, "sm_32"),
- ENUM_ENT(EF_CUDA_SM35, "sm_35"), ENUM_ENT(EF_CUDA_SM37, "sm_37"),
- ENUM_ENT(EF_CUDA_SM50, "sm_50"), ENUM_ENT(EF_CUDA_SM52, "sm_52"),
- ENUM_ENT(EF_CUDA_SM53, "sm_53"), ENUM_ENT(EF_CUDA_SM60, "sm_60"),
- ENUM_ENT(EF_CUDA_SM61, "sm_61"), ENUM_ENT(EF_CUDA_SM62, "sm_62"),
- ENUM_ENT(EF_CUDA_SM70, "sm_70"), ENUM_ENT(EF_CUDA_SM72, "sm_72"),
- 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_SM101, "sm_101"),
- ENUM_ENT(EF_CUDA_SM103, "sm_103"), ENUM_ENT(EF_CUDA_SM120, "sm_120"),
+ ENUM_ENT(EF_CUDA_SM20, "sm_20"),
+ ENUM_ENT(EF_CUDA_SM21, "sm_21"),
+ ENUM_ENT(EF_CUDA_SM30, "sm_30"),
+ ENUM_ENT(EF_CUDA_SM32, "sm_32"),
+ ENUM_ENT(EF_CUDA_SM35, "sm_35"),
+ ENUM_ENT(EF_CUDA_SM37, "sm_37"),
+ ENUM_ENT(EF_CUDA_SM50, "sm_50"),
+ ENUM_ENT(EF_CUDA_SM52, "sm_52"),
+ ENUM_ENT(EF_CUDA_SM53, "sm_53"),
+ ENUM_ENT(EF_CUDA_SM60, "sm_60"),
+ ENUM_ENT(EF_CUDA_SM61, "sm_61"),
+ ENUM_ENT(EF_CUDA_SM62, "sm_62"),
+ ENUM_ENT(EF_CUDA_SM70, "sm_70"),
+ ENUM_ENT(EF_CUDA_SM72, "sm_72"),
+ 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_SM101, "sm_101"),
+ ENUM_ENT(EF_CUDA_SM103, "sm_103"),
+ ENUM_ENT(EF_CUDA_SM120, "sm_120"),
ENUM_ENT(EF_CUDA_SM121, "sm_121"),
+ ENUM_ENT(EF_CUDA_SM20 << EF_CUDA_SM_OFFSET, "sm_20"),
+ ENUM_ENT(EF_CUDA_SM21 << EF_CUDA_SM_OFFSET, "sm_21"),
+ ENUM_ENT(EF_CUDA_SM30 << EF_CUDA_SM_OFFSET, "sm_30"),
+ ENUM_ENT(EF_CUDA_SM32 << EF_CUDA_SM_OFFSET, "sm_32"),
+ ENUM_ENT(EF_CUDA_SM35 << EF_CUDA_SM_OFFSET, "sm_35"),
+ ENUM_ENT(EF_CUDA_SM37 << EF_CUDA_SM_OFFSET, "sm_37"),
+ ENUM_ENT(EF_CUDA_SM50 << EF_CUDA_SM_OFFSET, "sm_50"),
+ ENUM_ENT(EF_CUDA_SM52 << EF_CUDA_SM_OFFSET, "sm_52"),
+ ENUM_ENT(EF_CUDA_SM53 << EF_CUDA_SM_OFFSET, "sm_53"),
+ ENUM_ENT(EF_CUDA_SM60 << EF_CUDA_SM_OFFSET, "sm_60"),
+ ENUM_ENT(EF_CUDA_SM61 << EF_CUDA_SM_OFFSET, "sm_61"),
+ ENUM_ENT(EF_CUDA_SM62 << EF_CUDA_SM_OFFSET, "sm_62"),
+ ENUM_ENT(EF_CUDA_SM70 << EF_CUDA_SM_OFFSET, "sm_70"),
+ ENUM_ENT(EF_CUDA_SM72 << EF_CUDA_SM_OFFSET, "sm_72"),
+ ENUM_ENT(EF_CUDA_SM75 << EF_CUDA_SM_OFFSET, "sm_75"),
+ ENUM_ENT(EF_CUDA_SM80 << EF_CUDA_SM_OFFSET, "sm_80"),
+ ENUM_ENT(EF_CUDA_SM86 << EF_CUDA_SM_OFFSET, "sm_86"),
+ ENUM_ENT(EF_CUDA_SM87 << EF_CUDA_SM_OFFSET, "sm_87"),
+ ENUM_ENT(EF_CUDA_SM89 << EF_CUDA_SM_OFFSET, "sm_89"),
+ ENUM_ENT(EF_CUDA_SM90 << EF_CUDA_SM_OFFSET, "sm_90"),
+ ENUM_ENT(EF_CUDA_SM100 << EF_CUDA_SM_OFFSET, "sm_100"),
+ ENUM_ENT(EF_CUDA_SM101 << EF_CUDA_SM_OFFSET, "sm_101"),
+ ENUM_ENT(EF_CUDA_SM103 << EF_CUDA_SM_OFFSET, "sm_103"),
+ ENUM_ENT(EF_CUDA_SM120 << EF_CUDA_SM_OFFSET, "sm_120"),
+ ENUM_ENT(EF_CUDA_SM121 << EF_CUDA_SM_OFFSET, "sm_121"),
};
const EnumEntry<unsigned> ElfHeaderRISCVFlags[] = {
diff --git a/offload/plugins-nextgen/cuda/src/rtl.cpp b/offload/plugins-nextgen/cuda/src/rtl.cpp
index 99195cd8d7c99..d973c2d4dd320 100644
--- a/offload/plugins-nextgen/cuda/src/rtl.cpp
+++ b/offload/plugins-nextgen/cuda/src/rtl.cpp
@@ -1581,7 +1581,7 @@ struct CUDAPluginTy final : public GenericPluginTy {
unsigned SM =
Header.e_ident[ELF::EI_ABIVERSION] == ELF::ELFABIVERSION_CUDA_V1
? Header.e_flags & ELF::EF_CUDA_SM
- : (Header.e_flags & ELF::EF_CUDA_SM_MASK) >> 8;
+ : (Header.e_flags & ELF::EF_CUDA_SM_MASK) >> ELF::EF_CUDA_SM_OFFSET;
CUdevice Device;
CUresult Res = cuDeviceGet(&Device, DeviceId);
More information about the llvm-commits
mailing list