Chad Rosier 4e6cda2db5 [InstCombine] Fold icmp ugt/ult (udiv i32 C2, X), C1. ...

This patch adds support for two optimizations:
icmp ugt (udiv C2, X), C1 -> icmp ule X, C2/(C1+1)
icmp ult (udiv C2, X), C1 -> icmp ugt X, C2/C1

Differential Revision: http://reviews.llvm.org/D20123

llvm-svn: 269109

2016-05-10 20:22:09 +00:00

..

CMakeLists.txt

…

InstCombineAddSub.cpp

Remove uses of builtin comma operator.

2016-02-18 22:09:30 +00:00

InstCombineAndOrXor.cpp

Typo. NFC.

2016-05-09 21:37:43 +00:00

InstCombineCalls.cpp

[InstCombine] Remove trivially empty va_start/va_end and va_copy/va_end ranges.

2016-05-10 09:24:49 +00:00

InstCombineCasts.cpp

[InstCombine] Propagate operand bundles

2016-04-29 08:07:20 +00:00

InstCombineCompares.cpp

[InstCombine] Fold icmp ugt/ult (udiv i32 C2, X), C1.

2016-05-10 20:22:09 +00:00

InstCombineInternal.h

[InstCombine] Remove trivially empty va_start/va_end and va_copy/va_end ranges.

2016-05-10 09:24:49 +00:00

InstCombineLoadStoreAlloca.cpp

Reapply 267210 with fix for PR27490

2016-05-06 22:17:01 +00:00

InstCombineMulDivRem.cpp

Remove uses of builtin comma operator.

2016-02-18 22:09:30 +00:00

InstCombinePHI.cpp

[InstCombine] Preserve fast math flags when combining PHIs

2016-04-22 11:21:36 +00:00

InstCombineSelect.cpp

[InstCombine] Determine the result of a select based on a dominating condition.

2016-04-29 21:12:31 +00:00

InstCombineShifts.cpp

add FIXME comment; NFC

2016-04-11 17:35:57 +00:00

InstCombineSimplifyDemanded.cpp

[InstCombine] clean up; NFC

2016-04-29 20:54:56 +00:00

InstCombineVectorOps.cpp

Fix an issue where fast math flags were dropped during scalarization.

2016-03-01 19:35:52 +00:00

InstructionCombining.cpp

Test commit: modified comment. NFC

2016-04-25 13:58:05 +00:00

LLVMBuild.txt

…