commit | 5c31015532bc0e557bda942c69b29d2f2ec955aa | [log] [tgz] |
---|---|---|
author | Andrea Di Biagio <Andrea_DiBiagio@sn.scee.net> | Thu Nov 22 15:47:44 2018 +0000 |
committer | Andrea Di Biagio <Andrea_DiBiagio@sn.scee.net> | Thu Nov 22 15:47:44 2018 +0000 |
tree | e7dc10eedef3ef933acdce711227253de1ccd1b6 | |
parent | fb147dee9d54c7905df5a61539112edc1d5d3a90 [diff] |
[llvm-mca] LSUnit: use a SmallSet to model load/store queues. NFCI Also, try to minimize the number of queries to the memory queues to speedup the analysis. On average, this change gives a small 2% speedup. For memcpy-like kernels, the speedup is up to 5.5%. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@347469 91177308-0d34-0410-b5e6-96231b3b80d8