HomePhabricator

[AArch64] Improve loop unrolling performance on Cavium T99

Authored by joelkevinjones on Dec 9 2017, 3:59 PM.

Description

[AArch64] Improve loop unrolling performance on Cavium T99

This patch improves performance on Cavium T99 as shown here (libquantum 0.2.4):

https://docs.google.com/spreadsheets/d/1Lo1o2E1NjrpkwS7DvYYWsiVvPdd93h7KBaqeptMrZPY/edit?usp=sharing

By increasing the LoopMicroOpsBufferSize in the Cavium T99 Scheduler file,
loop unrolling becomes more aggressive. This helps performance on T99.

Test case included.

Patch by Stefan Teleman

Differential Revision: https://reviews.llvm.org/D40695

llvm-svn: 320272

Details

Committed
joelkevinjonesDec 9 2017, 3:59 PM
Differential Revision
D40695: Improve loop unrolling performance on T99
Parents
rG6c63b07a55b1: Update Clang CMake cache to use cxx-headers, NFC
Branches
Unknown
Tags
Unknown