diff options
| author | Sanjay Patel <spatel@rotateright.com> | 2015-07-28 00:48:32 +0000 |
|---|---|---|
| committer | Sanjay Patel <spatel@rotateright.com> | 2015-07-28 00:48:32 +0000 |
| commit | 8c13e3680d3f4fc88830c402a2bcf929db0de9dd (patch) | |
| tree | 26687837bdd765f0eb81a1c96076c7f2e3dbe61a /llvm/lib/Transforms/Utils/LoopVersioning.cpp | |
| parent | 203f09223bb0bed16194d6a28431ba6a2fd5346a (diff) | |
| download | llvm-8c13e3680d3f4fc88830c402a2bcf929db0de9dd.zip llvm-8c13e3680d3f4fc88830c402a2bcf929db0de9dd.tar.gz llvm-8c13e3680d3f4fc88830c402a2bcf929db0de9dd.tar.bz2 | |
fix invalid load folding with SSE/AVX FP logical instructions (PR22371)
This is a follow-up to the FIXME that was added with D7474 ( http://reviews.llvm.org/rL229531 ).
I thought this load folding bug had been made hard-to-hit, but it turns out to be very easy
when targeting 32-bit x86 and causes a miscompile/crash in Wine:
https://bugs.winehq.org/show_bug.cgi?id=38826
https://llvm.org/bugs/show_bug.cgi?id=22371#c25
The quick fix is to simply remove the scalar FP logical instructions from the load folding table
in X86InstrInfo, but that causes us to miss load folds that should be possible when lowering fabs,
fneg, fcopysign. So the majority of this patch is altering those lowerings to use *vector* FP
logical instructions (because that's all x86 gives us anyway). That lets us do the load folding
legally.
Differential Revision: http://reviews.llvm.org/D11477
llvm-svn: 243361
Diffstat (limited to 'llvm/lib/Transforms/Utils/LoopVersioning.cpp')
0 files changed, 0 insertions, 0 deletions