This revision was automatically updated to reflect the committed changes.
Closed by commit rG33386b20aa82: [CUDA] Simplify GPU variant handling. NFC.
(authored by tra).
Changed prior to commit:
https://reviews.llvm.org/D77665?vs=255756&id=256078#toc
Repository:
rG LLVM Github Monorepo
CHANG
yaxunl accepted this revision.
yaxunl added a comment.
This revision is now accepted and ready to land.
LGTM. Thanks!
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D77665/new/
https://reviews.llvm.org/D77665
__
tra marked an inline comment as done.
tra added inline comments.
Comment at: clang/lib/Basic/Cuda.cpp:61
+// clang-format off
+SM2(20, "compute_20"), SM2(21, "compute_20"), // Fermi
+SM(30), SM(32), SM(35), SM(37), // Kepler
yaxunl wrote:
> Thanks fo
yaxunl added inline comments.
Comment at: clang/lib/Basic/Cuda.cpp:61
+// clang-format off
+SM2(20, "compute_20"), SM2(21, "compute_20"), // Fermi
+SM(30), SM(32), SM(35), SM(37), // Kepler
Thanks for the efforts. Really appreciate this.
Can we sepa
tra updated this revision to Diff 255756.
tra edited the summary of this revision.
tra added a comment.
Enumerate all known GPU variants during libdevice detection instead of
hardcoding them.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D77665/new/
tra created this revision.
tra added a reviewer: yaxunl.
Herald added subscribers: sanjoy.google, bixia.
Herald added a project: clang.
Instead of hardcoding individual GPU mappings in multiple functions, keep them
all in one table and use it to look up the mappings.
We also don't care about 'vir
