[HIP] Fix bug in driver about wavefront size

The static variable causes it only initialized once and take the same value for different GPU archs, whereas they may be different for different GPU archs, e.g. when there are both gfx900 and gfx1010. Removing static fixes that. Differential Revision: https://reviews.llvm.org/D92628
llvm · Dec 4, 2020 · 0519e1d · 0519e1d
1 parent dcec2ca
commit 0519e1d
Show file tree

Hide file tree

Showing 2 changed files with 22 additions and 1 deletion.
diff --git a/clang/lib/Driver/ToolChains/AMDGPU.cpp b/clang/lib/Driver/ToolChains/AMDGPU.cpp
@@ -499,7 +499,7 @@ llvm::DenormalMode AMDGPUToolChain::getDefaultDenormalModeForType(
 bool AMDGPUToolChain::isWave64(const llvm::opt::ArgList &DriverArgs,
                                llvm::AMDGPU::GPUKind Kind) {
   const unsigned ArchAttr = llvm::AMDGPU::getArchAttrAMDGCN(Kind);
-  static bool HasWave32 = (ArchAttr & llvm::AMDGPU::FEATURE_WAVE32);
+  bool HasWave32 = (ArchAttr & llvm::AMDGPU::FEATURE_WAVE32);
 
   return !HasWave32 || DriverArgs.hasFlag(
     options::OPT_mwavefrontsize64, options::OPT_mno_wavefrontsize64, false);

diff --git a/clang/test/Driver/hip-wavefront-size.hip b/clang/test/Driver/hip-wavefront-size.hip
@@ -0,0 +1,21 @@
+// REQUIRES: clang-driver,amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   --cuda-gpu-arch=gfx900 \
+// RUN:   --rocm-path=%S/Inputs/rocm --cuda-device-only %s \
+// RUN:   2>&1 | FileCheck %s --check-prefixes=WAVE64
+// WAVE64: "-mlink-builtin-bitcode" "{{.*}}oclc_wavefrontsize64_on.bc"{{.*}} "-target-cpu" "gfx900"
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   --cuda-gpu-arch=gfx1010 \
+// RUN:   --rocm-path=%S/Inputs/rocm --cuda-device-only %s \
+// RUN:   2>&1 | FileCheck %s --check-prefixes=WAVE32
+// WAVE32: "-mlink-builtin-bitcode" "{{.*}}oclc_wavefrontsize64_off.bc"{{.*}} "-target-cpu" "gfx1010"
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   --cuda-gpu-arch=gfx1010 \
+// RUN:   --cuda-gpu-arch=gfx900 \
+// RUN:   --rocm-path=%S/Inputs/rocm --cuda-device-only %s \
+// RUN:   2>&1 | FileCheck %s --check-prefixes=BOTH
+// BOTH-DAG: "-mlink-builtin-bitcode" "{{.*}}oclc_wavefrontsize64_on.bc"{{.*}} "-target-cpu" "gfx900"
+// BOTH-DAG: "-mlink-builtin-bitcode" "{{.*}}oclc_wavefrontsize64_off.bc"{{.*}} "-target-cpu" "gfx1010"