[clang] 047b2b2 - [NVPTX] Add `-march=general` option to mirror default configuration (#85222)

[via cfe-commits]

Author: Yichen Yan
Date: 2024-03-15T17:16:10-05:00
New Revision: 047b2b241defcad79a6ac0fec9cda092bac0a922

URL: https://github.com/llvm/llvm-project/commit/047b2b241defcad79a6ac0fec9cda092bac0a922
DIFF: https://github.com/llvm/llvm-project/commit/047b2b241defcad79a6ac0fec9cda092bac0a922.diff

LOG: [NVPTX] Add `-march=general` option to mirror default configuration (#85222)

This PR adds `-march=generic` support for the NVPTX backend. This
fulfills a TODO introduced in #79873.

With this PR, users can explicitly request the "default" CUDA
architecture, which makes sure that no specific architecture is
specified.

This PR does not address any compatibility issues between different CUDA
versions.

---------

Co-authored-by: Joseph Huber <huberjn at outlook.com>

Added: 
    

Modified: 
    clang/lib/Driver/ToolChains/Cuda.cpp
    clang/test/Driver/cuda-cross-compiling.c

Removed: 
    


################################################################################
diff  --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
index c6007d3cfab864..5f0b516e1a1a08 100644
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -750,10 +750,12 @@ NVPTXToolChain::TranslateArgs(const llvm::opt::DerivedArgList &Args,
     if (!llvm::is_contained(*DAL, A))
       DAL->append(A);
 
-  // TODO: We should accept 'generic' as a valid architecture.
   if (!DAL->hasArg(options::OPT_march_EQ) && OffloadKind != Action::OFK_None) {
     DAL->AddJoinedArg(nullptr, Opts.getOption(options::OPT_march_EQ),
                       CudaArchToString(CudaArch::CudaDefault));
+  } else if (DAL->getLastArgValue(options::OPT_march_EQ) == "generic" &&
+             OffloadKind == Action::OFK_None) {
+    DAL->eraseArg(options::OPT_march_EQ);
   } else if (DAL->getLastArgValue(options::OPT_march_EQ) == "native") {
     auto GPUsOrErr = getSystemGPUArchs(Args);
     if (!GPUsOrErr) {

diff  --git a/clang/test/Driver/cuda-cross-compiling.c b/clang/test/Driver/cuda-cross-compiling.c
index 086840accebe7f..a1719a6fbe042b 100644
--- a/clang/test/Driver/cuda-cross-compiling.c
+++ b/clang/test/Driver/cuda-cross-compiling.c
@@ -80,11 +80,15 @@
 //
 // RUN: not %clang -target nvptx64-nvidia-cuda %s -### 2>&1 \
 // RUN:   | FileCheck -check-prefix=MISSING %s
+// RUN: not %clang -target nvptx64-nvidia-cuda -march=generic %s -### 2>&1 \
+// RUN:   | FileCheck -check-prefix=MISSING %s
 
 // MISSING: error: Must pass in an explicit nvptx64 gpu architecture to 'ptxas'
 // MISSING: error: Must pass in an explicit nvptx64 gpu architecture to 'nvlink'
 
 // RUN: %clang -target nvptx64-nvidia-cuda -flto -c %s -### 2>&1 \
 // RUN:   | FileCheck -check-prefix=GENERIC %s
+// RUN: %clang -target nvptx64-nvidia-cuda -march=sm_52 -march=generic -flto -c %s -### 2>&1 \
+// RUN:   | FileCheck -check-prefix=GENERIC %s
 
 // GENERIC-NOT: -cc1" "-triple" "nvptx64-nvidia-cuda" {{.*}} "-target-cpu"