commit 64e73e8356392f7d4c6c8a499432479bebd46df6
author Krzysztof Drewniak <Krzysztof.Drewniak@amd.com> Thu Nov 18 22:37:53 2021 +0000
committer Copybara-Service <copybara-worker@google.com> Fri Nov 19 14:31:32 2021 -0800
tree 28cdc9e9c78955ae25e4da18e13b8f321a0b0962
parent a59450141256e78248dc469d7c996ba983108966

[MLIR][GPU] Link in device libraries during HSA compilation if needed

To perform some operations, such as sin() or printf(), code compiled
for AMD GPUs must be linked to a series of device libraries. This
commit adds support for linking in these libraries.

However, since these device libraries are delivered as LLVM bitcode,
raising the possibility of version incompatibilities, this commit only
links in libraries when the functions from those libraries are called
by the code being compiled.

This code also sets the math flags to their most conservative values,
as MLIR doesn't have a `-ffast-math` equivalent.

Depends on D114114

Reviewed By: mehdi_amini

Differential Revision: https://reviews.llvm.org/D114117

GitOrigin-RevId: a6f53afbcb4d995139064276b5ad971ad7ced5e2