4 Commits

Author SHA1 Message Date
Matt Arsenault
f44beecb78 AMDGPU: Try to use private version of sincos if available
The comment was out of date, the device libs build does provide all
the pointer overloads. An extremely pedantic interpretation of the
spec would suggest only the flat version exists, but the overloads do
exist in the implementation.

https://reviews.llvm.org/D156720
2023-08-14 11:40:04 -04:00
Matt Arsenault
42c6e4209c AMDGPU: Handle multiple uses when matching sincos
Match how the generic implementation handles this. We now will leave
behind the dead other user for later passes to deal with.

https://reviews.llvm.org/D156707
2023-08-14 11:28:41 -04:00
Matt Arsenault
54bda79335 AMDGPU: Simplify and improve sincos matching
The first trivial example I tried failed to merge due to the user scan
logic. Remove the complicated scan of users handling with distance
thresholds, with a same block restriction. The actual expansion of
sincos is basically the same size as sin or cos individually. Copy the
technique the generic optimization uses, which is to just use the
input instruction as the insert point or just insert at the start of
the entry block.

https://reviews.llvm.org/D156706
2023-08-02 17:48:35 -04:00
Matt Arsenault
eb00555c16 AMDGPU: Add more tests for sincos recognition
These show both broken cases and cases which are handled too
conservatively.
2023-08-01 18:20:50 -04:00