5 Commits

Author	SHA1	Message	Date
Roman Lebedev	98cb1216a6	[InstCombine] foldICmpWithLowBitMaskedVal(): don't miscompile -1 vector elts ... I was finally able to quantify what i thought was missing in the fix, it was vector constants. If we have a scalar (and %x, -1), it will be instsimplified before we reach this code, but if it is a vector, we may still have a -1 element. Thus, we want to avoid the fold if *at least one* element is -1. Or in other words, ignoring the undef elements, no sign bits should be set. Thus, m_NonNegative(). A follow-up for rL348181 https://bugs.llvm.org/show_bug.cgi?id=39861 llvm-svn: 348462	2018-12-06 08:14:24 +00:00
Roman Lebedev	d9941fa270	[NFC][InstCombine] Add more miscompile tests for foldICmpWithLowBitMaskedVal() ... We also have to me aware of vector constants. If at least one element is -1, we can't transform. llvm-svn: 348461	2018-12-06 08:11:20 +00:00
Roman Lebedev	7bf2fed167	[InstCombine] foldICmpWithLowBitMaskedVal(): disable 2 faulty folds. ... These two folds are invalid for this non-constant pattern when the mask ends up being all-ones: https://rise4fun.com/Alive/9au https://rise4fun.com/Alive/UcQM Fixes https://bugs.llvm.org/show_bug.cgi?id=39861 llvm-svn: 348181	2018-12-03 20:07:58 +00:00
Roman Lebedev	f14426101e	[InstCombine] Fold x & (-1 >> y) s>= x to x s<= (-1 >> y) ... https://bugs.llvm.org/show_bug.cgi?id=38123 https://rise4fun.com/Alive/I3O This pattern is not commutative! We must make sure not to fold the commuted version! llvm-svn: 337109	2018-07-14 20:08:37 +00:00
Roman Lebedev	53a014e61d	[NFC][InstCombine] Tests for x & (-1 >> y) s>= x to x s<= (-1 >> y) fold. ... https://bugs.llvm.org/show_bug.cgi?id=38123 https://rise4fun.com/Alive/I3O This pattern is not commutative! We must make sure not to fold the commuted version! llvm-svn: 337108	2018-07-14 20:08:31 +00:00