Sanjay Patel dbf3b5f114 [InstCombine] fold more shuffles with FP<->Int cast operands ...

shuffle (cast X), (cast Y), Mask --> cast (shuffle X, Y, Mask)

This extends the transform added with 0353c2c996c5.

If the casts are to a larger element type, the transform
reduces shuffle bit width, so that should be a win for
most codegen (if not, it can be inverted).

2022-05-17 14:25:11 -04:00

..

CMakeLists.txt

llvmbuildectomy - replace llvm-build by plain cmake

2020-11-13 10:35:24 +01:00

InstCombineAddSub.cpp

[IR] create and use helper functions that test the signbit; NFCI

2022-05-16 11:26:23 -04:00

InstCombineAndOrXor.cpp

[IR] create and use helper functions that test the signbit; NFCI

2022-05-16 11:26:23 -04:00

InstCombineAtomicRMW.cpp

Cleanup includes: Transform/Scalar

2022-03-03 07:56:34 +01:00

InstCombineCalls.cpp

[InstCombine] Fix unused variable warning (NFC)

2022-05-13 12:43:21 +02:00

InstCombineCasts.cpp

[InstCombine] remove cast-of-signbit to shift transform

2022-05-17 11:10:28 -04:00

InstCombineCompares.cpp

[InstCombine] [NFC] separate a function foldICmpBinOpWithConstant

2022-05-14 10:54:15 +08:00

InstCombineInternal.h

[InstCombine] [NFC] separate a function foldICmpBinOpWithConstant

2022-05-14 10:54:15 +08:00

InstCombineLoadStoreAlloca.cpp

[InstCombine] Remove memset of undef value

2022-04-29 14:51:18 +02:00

InstCombineMulDivRem.cpp

[IR] create and use helper functions that test the signbit; NFCI

2022-05-16 11:26:23 -04:00

InstCombineNegator.cpp

[InstCombine] Fold sub(Y,and(lshr(X,C),1)) --> add(ashr(shl(X,(BW-1)-C),BW-1),Y) (PR53610)

2022-02-15 13:24:20 +00:00

InstCombinePHI.cpp

Reapply [InstCombine] Support switch in phi to cond fold

2022-03-17 10:03:09 +01:00

InstCombineSelect.cpp

[IR] create and use helper functions that test the signbit; NFCI

2022-05-16 11:26:23 -04:00

InstCombineShifts.cpp

Revert "[InstCombine] invert canonicalization for cast of signbit test"

2022-05-16 17:47:02 -04:00

InstCombineSimplifyDemanded.cpp

[InstCombine] SimplifyDemandedUseBits - allow and(srem(X,Pow2),C) -> and(X,C) to work on vector types

2022-04-07 15:24:45 +01:00

InstCombineVectorOps.cpp

[InstCombine] fold more shuffles with FP<->Int cast operands

2022-05-17 14:25:11 -04:00

InstructionCombining.cpp

[IRBuilder] Add IsInBounds parameter to CreateGEP()

2022-05-13 14:30:55 +02:00