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

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-llvm-binary-utilities

Author: Joseph Huber (jhuber6)

<details>
<summary>Changes</summary>

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.


---
Full diff: https://github.com/llvm/llvm-project/pull/75964.diff


2 Files Affected:

- (modified) llvm/include/llvm/Object/ELFObjectFile.h (+1) 
- (modified) llvm/lib/Object/ELFObjectFile.cpp (+69) 


``````````diff
diff --git a/llvm/include/llvm/Object/ELFObjectFile.h b/llvm/include/llvm/Object/ELFObjectFile.h
index de418a1782acd2..99477644de4de7 100644
--- a/llvm/include/llvm/Object/ELFObjectFile.h
+++ b/llvm/include/llvm/Object/ELFObjectFile.h
@@ -64,6 +64,7 @@ class ELFObjectFileBase : public ObjectFile {
   SubtargetFeatures getLoongArchFeatures() const;
 
   StringRef getAMDGPUCPUName() const;
+  StringRef getNVPTXCPUName() const;
 
 protected:
   ELFObjectFileBase(unsigned int Type, MemoryBufferRef Source);
diff --git a/llvm/lib/Object/ELFObjectFile.cpp b/llvm/lib/Object/ELFObjectFile.cpp
index 3c86b0f25ddac1..95c4f9f8545db2 100644
--- a/llvm/lib/Object/ELFObjectFile.cpp
+++ b/llvm/lib/Object/ELFObjectFile.cpp
@@ -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)

``````````

</details>


https://github.com/llvm/llvm-project/pull/75964