[PATCH] D31412: Boost unroll threshold for loops reading local memory

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec created this revision.
Herald added subscribers: nhaehnle, wdng.

This is less important than increase threshold for private memory,
but still brings performance improvements in a wide range of tests.
Unrolling more for local memory serves three purposes: it allows
to combine ds operations if offset becomes static, saves registers
used for offsets in case of static offsets, and allows better lds
latency hiding.


Repository:
  rL LLVM

https://reviews.llvm.org/D31412

Files:
  lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
  test/CodeGen/AMDGPU/unroll.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D31412.93194.patch
Type: text/x-patch
Size: 7186 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170328/2fa98eab/attachment.bin>