summaryrefslogtreecommitdiffstats
path: root/llvm/lib/CodeGen/InterferenceCache.h
diff options
context:
space:
mode:
authorAndrew Trick <atrick@apple.com>2011-04-12 19:54:36 +0000
committerAndrew Trick <atrick@apple.com>2011-04-12 19:54:36 +0000
commitc5dd24a54215f06cb8b1320d0ca2b85ac334a25e (patch)
treea2ed15ecd7de38846a9451ab06b9e92b56f55a1b /llvm/lib/CodeGen/InterferenceCache.h
parent23fe31cc8d50b023cfd3f6fc79388f864eb48311 (diff)
downloadbcm5719-llvm-c5dd24a54215f06cb8b1320d0ca2b85ac334a25e.tar.gz
bcm5719-llvm-c5dd24a54215f06cb8b1320d0ca2b85ac334a25e.zip
PreRA scheduler heuristic fixes: VRegCycle, TokenFactor latency.
UnitsSharePred was a source of randomness in the scheduler: node priority depended on the queue data structure. I rewrote the recent VRegCycle heuristics to completely replace the old heuristic without any randomness. To make these heuristic adjustments to node latency work, I also needed to do something a little more reasonable with TokenFactor. I gave it zero latency to its consumers and always schedule it as low as possible. llvm-svn: 129383
Diffstat (limited to 'llvm/lib/CodeGen/InterferenceCache.h')
0 files changed, 0 insertions, 0 deletions
OpenPOWER on IntegriCloud