aboutsummaryrefslogtreecommitdiffstats
path: root/test/Analysis/ScalarEvolution/nsw.ll
diff options
context:
space:
mode:
authorKalle Raiskila <kalle.raiskila@nokia.com>2011-01-11 09:07:54 +0000
committerKalle Raiskila <kalle.raiskila@nokia.com>2011-01-11 09:07:54 +0000
commit76020ed6f33e3b3943b25c8b5e111afece086f5c (patch)
treea82e35de61771d5249f1ae9eef88b8981b69e319 /test/Analysis/ScalarEvolution/nsw.ll
parent87376839a651ed1221dd46762701f13ad6ece0eb (diff)
downloadexternal_llvm-76020ed6f33e3b3943b25c8b5e111afece086f5c.zip
external_llvm-76020ed6f33e3b3943b25c8b5e111afece086f5c.tar.gz
external_llvm-76020ed6f33e3b3943b25c8b5e111afece086f5c.tar.bz2
Add a "nop filler" pass to SPU.
Filling no-ops is done just before emitting of assembly, when the instruction stream is final. No-ops are inserted to align the instructions so the dual-issue of the pipeline is utilized. This speeds up generated code with a minimum of 1% on a select set of algorithms. This pass may be redundant if the instruction scheduler and all subsequent passes that modify the instruction stream (prolog+epilog inserter, register scavenger, are there others?) are made aware of the instruction alignments. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123226 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Analysis/ScalarEvolution/nsw.ll')
0 files changed, 0 insertions, 0 deletions