[PATCH] D76795: [HIP] Change default --gpu-max-threads-per-block value to 1024

Brian Sumner via Phabricator via cfe-commits cfe-commits at lists.llvm.org
Wed Mar 25 12:59:38 PDT 2020


b-sumner added inline comments.


================
Comment at: clang/lib/CodeGen/TargetInfo.cpp:8123
+    // --gpu-max-threads-per-block=n or its default value for HIP.
+    const unsigned OpenCLMaxWorkGroupSize = 256;
+    const unsigned MaxWorkGroupSize =
----------------
I'd like to see the word default, e.g. OpenCLDefaultMaxWorkGroupSize, used more since that is what this is about.  Ideally the option would have been named gpu-default-max-threads-per-block, but I suppose I can see why it was shortened.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D76795/new/

https://reviews.llvm.org/D76795





More information about the cfe-commits mailing list