llvm-project/llvm/test/Transforms/BBVectorize
Artur Pilipenko c6eb6bd9cb [ValueTracking] An improvement to IR ValueTracking on Non-negative Integers
Since this change is known to cause performance degradations in some cases it's commited under a temporary flag which is turned off by default.

Patch by Li Huang

Differential Revision: https://reviews.llvm.org/D18777

llvm-svn: 284022
2016-10-12 16:18:43 +00:00
..
X86 Revert "Change memcpy/memset/memmove to have dest and source alignments." 2015-11-19 05:56:52 +00:00
xcore
cycle.ll
func-alias.ll
ld1.ll
lit.local.cfg
loop1.ll [ValueTracking] An improvement to IR ValueTracking on Non-negative Integers 2016-10-12 16:18:43 +00:00
mem-op-depth.ll
metadata.ll
no-ldstr-conn.ll
req-depth.ll
search-limit.ll
simple-int.ll
simple-ldstr-ptrs.ll
simple-ldstr.ll
simple-sel.ll
simple-tst.ll
simple.ll
simple3.ll Have a single way for creating unique value names. 2015-11-22 00:16:24 +00:00
vector-sel.ll [BBVectorize] Don't vectorize selects with a scalar condition and vector operands. 2016-05-26 18:43:57 +00:00