intel/llvm
1
0
Fork 0
mirror of https://github.com/intel/llvm.git synced 2026-01-31 07:27:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

[ELF] Add CPU name detection for CUDA architectures (#75964)

Browse Source 
Summary:
Recently we added support for detecting the CUDA processor with the ELF
flags. This allows us to get a string representation of it in other
code. This will be used by the offloading runtime.
This commit is contained in:
Joseph Huber
2023-12-19 20:01:15 -06:00
committed by GitHub
parent 56414220df
commit deab58d127
2 changed files with 70 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
llvm/include/llvm/Object/ELFObjectFile.h
View File

@@ -64,6 +64,7 @@ class ELFObjectFileBase : public ObjectFile {
SubtargetFeatures getLoongArchFeatures() const;
StringRef getAMDGPUCPUName() const;
StringRef getNVPTXCPUName() const;
protected:
ELFObjectFileBase(unsigned int Type, MemoryBufferRef Source);

69
llvm/lib/Object/ELFObjectFile.cpp
View File

@@ -358,6 +358,8 @@ std::optional<StringRef> ELFObjectFileBase::tryGetCPUName() const {
switch (getEMachine()) {
case ELF::EM_AMDGPU:
return getAMDGPUCPUName();
case ELF::EM_CUDA:
return getNVPTXCPUName();
case ELF::EM_PPC:
case ELF::EM_PPC64:
return StringRef("future");
@@ -517,6 +519,73 @@ StringRef ELFObjectFileBase::getAMDGPUCPUName() const {
}
}
StringRef ELFObjectFileBase::getNVPTXCPUName() const {
assert(getEMachine() == ELF::EM_CUDA);
unsigned SM = getPlatformFlags() & ELF::EF_CUDA_SM;
switch (SM) {
// Fermi architecture.
case ELF::EF_CUDA_SM20:
return "sm_20";
case ELF::EF_CUDA_SM21:
return "sm_21";
// Kepler architecture.
case ELF::EF_CUDA_SM30:
return "sm_30";
case ELF::EF_CUDA_SM32:
return "sm_32";
case ELF::EF_CUDA_SM35:
return "sm_35";
case ELF::EF_CUDA_SM37:
return "sm_37";
// Maxwell architecture.
case ELF::EF_CUDA_SM50:
return "sm_50";
case ELF::EF_CUDA_SM52:
return "sm_52";
case ELF::EF_CUDA_SM53:
return "sm_53";
// Pascal architecture.
case ELF::EF_CUDA_SM60:
return "sm_60";
case ELF::EF_CUDA_SM61:
return "sm_61";
case ELF::EF_CUDA_SM62:
return "sm_62";
// Volta architecture.
case ELF::EF_CUDA_SM70:
return "sm_70";
case ELF::EF_CUDA_SM72:
return "sm_72";
// Turing architecture.
case ELF::EF_CUDA_SM75:
return "sm_75";
// Ampere architecture.
case ELF::EF_CUDA_SM80:
return "sm_80";
case ELF::EF_CUDA_SM86:
return "sm_86";
case ELF::EF_CUDA_SM87:
return "sm_87";
// Ada architecture.
case ELF::EF_CUDA_SM89:
return "sm_89";
// Hopper architecture.
case ELF::EF_CUDA_SM90:
return getPlatformFlags() & ELF::EF_CUDA_ACCELERATORS ? "sm_90a" : "sm_90";
default:
llvm_unreachable("Unknown EF_CUDA_SM value");
}
}
// FIXME Encode from a tablegen description or target parser.
void ELFObjectFileBase::setARMSubArch(Triple &TheTriple) const {
if (TheTriple.getSubArch() != Triple::NoSubArch)