pvanhout 07c5920487 Reland "[AMDGPU] Wave32 CodeGen for amdgcn.ballot.i64" ...

This time without the extra `->dump()`

A recent addition to the device libs, `__ockl_dm_trim`, caused a series of
failures at O0 due to a i64 ballot intrinsic being inlined into a wave32 function.

The quick fix for this is to support codegen for this rare case.
A proper long-term fix for this type of issue is still being discussed.

Fixes SWDEV-408929, SWDEV-408957, SWDEV-409885, SWDEV-410193

Reviewed By: #amdgpu, arsenm

Differential Revision: https://reviews.llvm.org/D155050

2023-07-13 15:58:48 +02:00

172 KiB

Raw Blame History

View Raw