Commit Graph

2 Commits

Author SHA1 Message Date
Stanislav Mekhanoshin 20d4795d93 [AMDGPU] Enable LICM in the BE pipeline
This allows to hoist code portion to compute reciprocal of loop
invariant denominator in integer division after codegen prepare
expansion.

Differential Revision: https://reviews.llvm.org/D48604

llvm-svn: 335988
2018-06-29 16:26:53 +00:00
Tim Renouf 832f90fa0c [AMDGPU] Scratch setup fix on AMDPAL gfx9+ merge shader
Summary:
With OS type AMDPAL, the scratch descriptor is hardwired to be loaded
from offset 0 of the global information table, whose low pointer is
passed in s0. For a merge shader on gfx9+, it needs to be s8 instead, as
the hardware reserves s0-s7.

Reviewers: kzhuravl

Subscribers: arsenm, nhaehnle, dstuttard, llvm-commits, t-tye, yaxunl, wdng, kzhuravl

Differential Revision: https://reviews.llvm.org/D42203

llvm-svn: 326088
2018-02-26 14:46:43 +00:00