llvm/test/Transforms, branch release_24http://llvm.orghttps://git.amat.us/llvm/atom/test/Transforms?h=release_242008-10-17T21:36:29Zremove v[if]cmp functionality from the 2.4 release. These instructions will be removed or substantially changes in mainline after the 2.4 release and we don't want to have to support these for backwards compatibility purposes. Patch by Chris.2008-10-17T21:36:29ZTanya Lattnertonic@nondot.org2008-10-17T21:36:29Zurn:sha1:8c07c4ede04f4a06b8e090da65dc38706543f5cf
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_24@57732 91177308-0d34-0410-b5e6-96231b3b80d8
Merge from mainline.2008-10-17T17:50:35ZTanya Lattnertonic@nondot.org2008-10-17T17:50:35Zurn:sha1:7f3bc26428a8b80958b3dbfe4c7015b4134bed05
Fix PR2697 by rewriting the '(X / pos) op neg' logic. This also changes a couple other cases for clarity, but shouldn't affect correctness.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_24@57698 91177308-0d34-0410-b5e6-96231b3b80d8
Fix typo, fix PR 2865.2008-10-06T23:22:54ZDevang Pateldpatel@apple.com2008-10-06T23:22:54Zurn:sha1:d44b7c1b0798b5b28556314278948a941442c1ec
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57221 91177308-0d34-0410-b5e6-96231b3b80d8
Allow scalarrepl to treat an all-zero GEP just as bitcast.2008-10-06T16:23:31ZMatthijs Kooijmanmatthijs@stdin.nl2008-10-06T16:23:31Zurn:sha1:5fac55fafb53fde5c548bcd08e07418e9d8e549f
This includes not marking a GEP involving a vector as unsafe, but only when it
has all zero indices. This allows scalarrepl to work in a few more cases.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57177 91177308-0d34-0410-b5e6-96231b3b80d8
rewrite bswap matching to be more general, allowing arbitrary2008-10-05T02:13:19ZChris Lattnersabre@nondot.org2008-10-05T02:13:19Zurn:sha1:8c34cd287a07d80491cde1e86da98568675dbe47
shifting and masking inside a bswap expr. This allows it to handle
the cases from PR2842, which involve the intermediate 'or'
expressions being shifted, not just the input value.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57095 91177308-0d34-0410-b5e6-96231b3b80d8
Ignore loads from and stores to local memory (i.e. allocas)2008-10-04T13:24:24ZDuncan Sandsbaldrick@free.fr2008-10-04T13:24:24Zurn:sha1:c82b6a1ed2496ce0d61d2e51ed3a4cac4db786da
when deciding whether to mark a function readnone/readonly.
Since the pass is currently run before SROA, this may be
quite helpful. Requested by Chris on IRC.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57050 91177308-0d34-0410-b5e6-96231b3b80d8
Allow the construction of SCEVs with SCEVCouldNotCompute operands, by2008-10-04T11:19:07ZNick Lewyckynicholas@mxc.ca2008-10-04T11:19:07Zurn:sha1:26e4b216c0c065dece616c1c9931252e2a0e40c6
implementing folding. Fixes PR2857.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57049 91177308-0d34-0410-b5e6-96231b3b80d8
Nick Lewycky's patch.2008-10-03T18:57:37ZDevang Pateldpatel@apple.com2008-10-03T18:57:37Zurn:sha1:20da1f07dac4d771e55ee5c7f105ccedfa4caaaa
While hosting instruction check PHI node.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57025 91177308-0d34-0410-b5e6-96231b3b80d8
Fix misoptimization of: xor i1 (icmp eq (X, C1), icmp s[lg]t (X, C2))2008-09-30T06:08:34ZNick Lewyckynicholas@mxc.ca2008-09-30T06:08:34Zurn:sha1:a06cf82a7b6cbfce77d4449f2c9933dc332adcf0
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@56834 91177308-0d34-0410-b5e6-96231b3b80d8
Support inreg, zext and sext as return value attributes.2008-09-29T20:49:50ZDevang Pateldpatel@apple.com2008-09-29T20:49:50Zurn:sha1:652203f3f3b6dd5062bb450d189a80d8aaa51693
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@56801 91177308-0d34-0410-b5e6-96231b3b80d8