4 Commits

Author	SHA1	Message	Date
Andrew Trick	e4a18605e0	Reapply r198654 "indvars: sink truncates outside the loop." ... This doesn't seem to have actually broken anything. It was paranoia on my part. Trying again now that bots are more stable. This is a follow up of the r198338 commit that added truncates for lcssa phi nodes. Sinking the truncates below the phis cleans up the loop and simplifies subsequent analysis within the indvars pass. llvm-svn: 198678	2014-01-07 06:59:12 +00:00
Andrew Trick	3c0ed08996	Revert "indvars: sink truncates outside the loop." ... This reverts commit r198654. One of the bots reported a SciMark failure. llvm-svn: 198659	2014-01-07 01:50:58 +00:00
Andrew Trick	0b8e3b2cb4	indvars: sink truncates outside the loop. ... This is a follow up of the r198338 commit that added truncates for lcssa phi nodes. Sinking the truncates below the phis cleans up the loop and simplifies subsequent analysis within the indvars pass. llvm-svn: 198654	2014-01-07 01:02:55 +00:00
Andrew Trick	020dd898fc	indvars: insert truncate at loop boundary to avoid redundant IVs. ... When widening an IV to remove s/zext, we generally try to eliminate the original narrow IV. However, LCSSA phi nodes outside the loop were still using the original IV. Clean this up more aggressively to avoid redundancy in generated code. llvm-svn: 198338	2014-01-02 19:29:38 +00:00