1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-02-01 13:11:39 +01:00
Philip Reames eaea7ba7a7 [instcombine][x86] Converted pdep/pext with shifted mask to simple arithmetic
If the mask of a pdep or pext instruction is a shift masked (i.e. one contiguous block of ones) we need at most one and and one shift to represent the operation without the intrinsic. One all platforms I know of, this is faster than the pdep/pext.

The cost modelling for multiple contiguous blocks might be worth exploring in a follow up, but it's not relevant for my current use case. It would almost certainly be a win on AMDs where these are really really slow though.

Differential Revision: https://reviews.llvm.org/D87861
2020-09-18 14:54:24 -07:00
..
2020-07-21 12:15:12 +01:00
2020-09-17 15:56:13 -07:00
2020-09-15 17:29:44 -07:00