summaryrefslogtreecommitdiff
path: root/llvm/lib/Object/ELFObjectFile.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/lib/Object/ELFObjectFile.cpp')
-rw-r--r--llvm/lib/Object/ELFObjectFile.cpp32
1 files changed, 30 insertions, 2 deletions
diff --git a/llvm/lib/Object/ELFObjectFile.cpp b/llvm/lib/Object/ELFObjectFile.cpp
index 0e13d32bbe52..a6b56ae77cf2 100644
--- a/llvm/lib/Object/ELFObjectFile.cpp
+++ b/llvm/lib/Object/ELFObjectFile.cpp
@@ -620,7 +620,10 @@ StringRef ELFObjectFileBase::getAMDGPUCPUName() const {
StringRef ELFObjectFileBase::getNVPTXCPUName() const {
assert(getEMachine() == ELF::EM_CUDA);
- unsigned SM = getPlatformFlags() & ELF::EF_CUDA_SM;
+ unsigned SM = getEIdentABIVersion() == ELF::ELFABIVERSION_CUDA_V1
+ ? getPlatformFlags() & ELF::EF_CUDA_SM
+ : (getPlatformFlags() & ELF::EF_CUDA_SM_MASK) >>
+ ELF::EF_CUDA_SM_OFFSET;
switch (SM) {
// Fermi architecture.
@@ -672,6 +675,8 @@ StringRef ELFObjectFileBase::getNVPTXCPUName() const {
return "sm_86";
case ELF::EF_CUDA_SM87:
return "sm_87";
+ case ELF::EF_CUDA_SM88:
+ return "sm_88";
// Ada architecture.
case ELF::EF_CUDA_SM89:
@@ -679,7 +684,30 @@ StringRef ELFObjectFileBase::getNVPTXCPUName() const {
// Hopper architecture.
case ELF::EF_CUDA_SM90:
- return getPlatformFlags() & ELF::EF_CUDA_ACCELERATORS ? "sm_90a" : "sm_90";
+ return getPlatformFlags() & ELF::EF_CUDA_ACCELERATORS_V1 ? "sm_90a"
+ : "sm_90";
+
+ // Blackwell architecture.
+ 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";
+ case ELF::EF_CUDA_SM110:
+ return getPlatformFlags() & ELF::EF_CUDA_ACCELERATORS ? "sm_110a"
+ : "sm_110";
+
+ // Blackwell 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");
}