[PATCH] D78019: HIP: Fix handling of denormal mode

[Yaxun Liu via Phabricator via cfe-commits]

yaxunl added inline comments.


================
Comment at: clang/lib/Driver/ToolChains/AMDGPU.cpp:286
+
+    // FIXME: Should this use the default mode based on the target? How do we
+    // deal with multiple --cuda-gpu-arch?
----------------
If there are multiple --cuda-gpu-arch, driver will create separate JobAction for launching separate `clang -cc1` command for each arch. This function is called for each JobAction and  getOffloadingArch contains the single arch. Therefore there is no issue for multiple --cuda-gpu-arch and this comment can be removed.


================
Comment at: clang/test/Driver/cuda-flush-denormals-to-zero.cu:27
+// Test multiple offload archs with different defaults.
+// RUN: %clang -x hip -no-canonical-prefixes -### -target x86_64-linux-gnu -c -march=haswell --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 -nocudainc -nogpulib %s 2>&1 | FileCheck -check-prefix=MIXED-DEFAULT-MODE %s
+// RUN: %clang -x hip -no-canonical-prefixes -### -target x86_64-linux-gnu -c -march=haswell -fcuda-flush-denormals-to-zero --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 -nocudainc -nogpulib %s 2>&1 | FileCheck -check-prefix=FTZX2 %s
----------------
this will result in multiple clang -cc1 commands, each one corresponding to an arch. You need to check each arch.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D78019/new/

https://reviews.llvm.org/D78019