projects / oota-llvm.git / history
? search:
summary | shortlog | log | commit | commitdiff | tree
first ⋅ prev ⋅ next
Revert "AVX-512: Full implementation for VRNDSCALESS/SD instructions and intrinsics."
[oota-llvm.git] / lib / Target / X86 / X86ISelLowering.cpp
2015-02-20 Eric ChristopherRevert "AVX-512: Full implementation for VRNDSCALESS... blob | commitdiff | raw
2015-02-19 Benjamin KramerDemote vectors to arrays. No functionality change. blob | commitdiff | raw | diff to current
2015-02-19 Chandler Carruth[x86] Delete still more piles of complex code now that... blob | commitdiff | raw | diff to current
2015-02-19 Chandler Carruth[x86] Teach the unpack lowering how to lower with an... blob | commitdiff | raw | diff to current
2015-02-19 Chandler Carruth[x86] Dramatically improve v8i16 shuffle lowering by... blob | commitdiff | raw | diff to current
2015-02-19 Chandler Carruth[x86] Remove the final fallback in the v8i16 lowering... blob | commitdiff | raw | diff to current
2015-02-19 Chandler Carruth[x86] Simplify the pre-SSSE3 v16i8 lowering significant... blob | commitdiff | raw | diff to current
2015-02-19 Chandler Carruth[x86] Remove the insanely over-aggressive unpack loweri... blob | commitdiff | raw | diff to current
2015-02-19 Chandler Carruth[x86] The SELECT x86 DAG combine also does legalization... blob | commitdiff | raw | diff to current
2015-02-19 Elena DemikhovskyAVX-512: Full implementation for VRNDSCALESS/SD instruc... blob | commitdiff | raw | diff to current
2015-02-19 Chandler Carruth[x86] Add support for bit-wise blending and use it... blob | commitdiff | raw | diff to current
2015-02-19 Chandler Carruth[x86,sdag] Two interrelated changes to the x86 and... blob | commitdiff | raw | diff to current
2015-02-18 Benjamin KramerX86: Use bitset to manage a bag of bits. NFC. blob | commitdiff | raw | diff to current
2015-02-18 Chandler Carruth[x86] Tighten the assertions to document that canonical... blob | commitdiff | raw | diff to current
2015-02-18 Chandler Carruth[x86] Switch an if which is trivially true to an assert... blob | commitdiff | raw | diff to current
2015-02-18 Chandler Carruth[x86] Remove some more 'bit' nomenclature from the... blob | commitdiff | raw | diff to current
2015-02-18 Chandler Carruth[x86] Fold together the two shift lowering strategies... blob | commitdiff | raw | diff to current
2015-02-18 Chandler Carruth[x86] Refactor the bit shift code the same as I just... blob | commitdiff | raw | diff to current
2015-02-18 Elena DemikhovskyAVX-512: Added support for FP instructions with embedde... blob | commitdiff | raw | diff to current
2015-02-18 Chandler Carruth[x86] Rewrite the byte shift detection to not use boole... blob | commitdiff | raw | diff to current
2015-02-17 Simon Pilgrim[X86][SSE] Generalised unpckl/unpckh shuffle matching blob | commitdiff | raw | diff to current
2015-02-17 Benjamin KramerPrefer SmallVector::append/insert over push_back loops. blob | commitdiff | raw | diff to current
2015-02-17 Andrea Di Biagio[X86] Silence -Wsign-compare warnings. blob | commitdiff | raw | diff to current
2015-02-17 Michael Kuperstein[X86] Combine vector anyext + and into a vector zext blob | commitdiff | raw | diff to current
2015-02-17 Chandler Carruth[x86] Teach the unpack lowering to try wider element... blob | commitdiff | raw | diff to current
2015-02-16 Cameron McInally[AVX512] Make 512b vector floating point rounds legal... blob | commitdiff | raw | diff to current
2015-02-16 Craig Topper[X86] Remove the multiply by 8 that goes into the shift... blob | commitdiff | raw | diff to current
2015-02-16 Chandler Carruth[x86] Add a generic unpack-targeted lowering technique... blob | commitdiff | raw | diff to current
2015-02-16 Chandler Carruth[x86] Add initial basic support for forming blends... blob | commitdiff | raw | diff to current
2015-02-16 Chandler Carruth[x86] Switch my usage of VariadicFunction to a "normal... blob | commitdiff | raw | diff to current
2015-02-16 Craig Topper[X86] Add support for lowering shuffles to 256-bit... blob | commitdiff | raw | diff to current
2015-02-16 Chandler Carruth[x86] Teach the 128-bit vector shuffle lowering routine... blob | commitdiff | raw | diff to current
2015-02-15 Simon PilgrimCoding style fixes to recent patches. NFC. blob | commitdiff | raw | diff to current
2015-02-15 Simon Pilgrim[X86][AVX2] vpslldq/vpsrldq byte shifts for AVX2 blob | commitdiff | raw | diff to current
2015-02-15 Chandler Carruth[x86] Teach the decomposed shuffle/blend lowering to... blob | commitdiff | raw | diff to current
2015-02-15 Chandler Carruth[x86] Teach the shuffle mask equivalence test to look... blob | commitdiff | raw | diff to current
2015-02-15 Chandler Carruth[x86] Tweak the ordering of unpack matching vs. element... blob | commitdiff | raw | diff to current
2015-02-15 Chandler Carruth[x86] Stop shuffling zero vectors. =] blob | commitdiff | raw | diff to current
2015-02-15 Chandler Carruth[x86] Use a more helpful parenthesizing of these compar... blob | commitdiff | raw | diff to current
2015-02-15 Chandler Carruth[x86] When splitting 256-bit vectors into 128-bit vecto... blob | commitdiff | raw | diff to current
2015-02-15 Chandler Carruth[x86] Make computing the zeroable elements slightly... blob | commitdiff | raw | diff to current
2015-02-15 Chandler Carruth[x86] Add a slight variation on some of the other gener... blob | commitdiff | raw | diff to current
2015-02-14 Duncan P. N. Exon... X86: Canonicalize access to function attributes, NFC blob | commitdiff | raw | diff to current
2015-02-13 Sanjay Patelfix typos; NFC blob | commitdiff | raw | diff to current
2015-02-13 Craig TopperFix a typo in a comment. NFC blob | commitdiff | raw | diff to current
2015-02-12 David MajnemerX86: Don't crash if we can't decode the pshufb mask blob | commitdiff | raw | diff to current
2015-02-12 Benjamin KramerMathExtras: Bring Count(Trailing|Leading)Ones and Count... blob | commitdiff | raw | diff to current
2015-02-12 Elena DemikhovskyAVX-512: Fixed the "test" operation for i1 type blob | commitdiff | raw | diff to current
2015-02-10 David MajnemerX86: Make @llvm.frameaddress work correctly with Window... blob | commitdiff | raw | diff to current
2015-02-08 Sanjay Patelfix typos; NFC blob | commitdiff | raw | diff to current
2015-02-06 Sanjay Pateluse local variables; NFC blob | commitdiff | raw | diff to current
2015-02-05 Ahmed Bougacha[CodeGen] Add hook/combine to form vector extloads... blob | commitdiff | raw | diff to current
2015-02-05 Andrew TrickX86 ABI fix for return values > 24 bytes. blob | commitdiff | raw | diff to current
2015-02-05 Sanjay Patelmove fold comments to the corresponding fold; NFC blob | commitdiff | raw | diff to current
2015-02-05 Bruno Cardoso Lopes[X86][MMX] Handle i32->mmx conversion using movd blob | commitdiff | raw | diff to current
2015-02-05 Larisse VoufoDisable enumeral mismatch warning when compiling llvm... blob | commitdiff | raw | diff to current
2015-02-04 Chandler Carruth[x86] Start to introduce bit-masking based blend lowering. blob | commitdiff | raw | diff to current
2015-02-03 Chandler Carruth[x86] Fix signed vs. unsigned comparison. blob | commitdiff | raw | diff to current
2015-02-03 Simon PilgrimFixed unused variable warning. blob | commitdiff | raw | diff to current
2015-02-03 Simon Pilgrim[X86][SSE] psrl(w/d/q) and psll(w/d/q) bit shifts for... blob | commitdiff | raw | diff to current
2015-02-03 Simon PilgrimFixed signed/unsigned comparison warning. blob | commitdiff | raw | diff to current
2015-02-03 Simon PilgrimFixed unused variable warning. blob | commitdiff | raw | diff to current
2015-02-03 Simon Pilgrim[X86][SSE] Added general integer shuffle matching for... blob | commitdiff | raw | diff to current
2015-02-03 Simon Pilgrim[X86][AVX2] Enabled shuffle matching for the AVX2 zero... blob | commitdiff | raw | diff to current
2015-02-03 Sanjay PatelMerge consecutive 16-byte loads into one 32-byte load... blob | commitdiff | raw | diff to current
2015-02-03 Bruno Cardoso Lopes[X86][MMX] Improve transfer from mmx to i32 blob | commitdiff | raw | diff to current
2015-02-02 Eric ChristopherReuse a bunch of cached subtargets and remove getSubtar... blob | commitdiff | raw | diff to current
2015-02-01 Craig Topper[X86] Add a few target specific nodes to 'getTargetNode... blob | commitdiff | raw | diff to current
2015-01-31 Simon Pilgrim[X86][SSE] Shuffle mask decode support for zero extend... blob | commitdiff | raw | diff to current
2015-01-31 Eric ChristopherRemove the last vestiges of resetOperationActions. blob | commitdiff | raw | diff to current
2015-01-30 Reid KlecknerWin64: Put a REX_W prefix on all TAILJMP* instructions blob | commitdiff | raw | diff to current
2015-01-30 Sanjay Pateltidy up; NFC blob | commitdiff | raw | diff to current
2015-01-30 Reid Klecknerx86: Remove unused variables not caught by MSVC =P blob | commitdiff | raw | diff to current
2015-01-29 Reid Klecknerx86: Fix large model calls to __chkstk for dynamic... blob | commitdiff | raw | diff to current
2015-01-29 Sanjay PatelChange SmallVector param to the more general ArrayRef... blob | commitdiff | raw | diff to current
2015-01-29 Reid Klecknerx86: Remove the W64ALLOCA pseudo blob | commitdiff | raw | diff to current
2015-01-28 Simon PilgrimSpelling fixes. NFC. blob | commitdiff | raw | diff to current
2015-01-28 Sanjay Patelinvert check for less indentation; use local vars to... blob | commitdiff | raw | diff to current
2015-01-28 Sanjay Pateluse SDValue methods directly instead of getNode()-... blob | commitdiff | raw | diff to current
2015-01-28 Michael Kuperstein[X86] Reduce some 32-bit imuls into lea + shl blob | commitdiff | raw | diff to current
2015-01-28 Michael Kuperstein[x32] Enable sibcall optimization on x32. blob | commitdiff | raw | diff to current
2015-01-28 Elena DemikhovskyAVX-512: Added FMA intrinsics with rounding mode blob | commitdiff | raw | diff to current
2015-01-27 Alexey SamsonovRevert "[x86] Combine x86mmx/i64 to v2i64 conversion... blob | commitdiff | raw | diff to current
2015-01-25 Elena DemikhovskyAVX-512: Changes in operations on masks registers for... blob | commitdiff | raw | diff to current
2015-01-24 Bruno Cardoso Lopes[x86] Fix a comment blob | commitdiff | raw | diff to current
2015-01-23 Bruno Cardoso Lopes[x86] Combine x86mmx/i64 to v2i64 conversion to use... blob | commitdiff | raw | diff to current
2015-01-23 Eric ChristopherRemove some local variables in place of just querying... blob | commitdiff | raw | diff to current
2015-01-22 Alexander PotapenkoMark |TLI| variables used to suppress -Wunused-variable... blob | commitdiff | raw | diff to current
2015-01-22 Elena DemikhovskyFixed a bug in type legalizer for masked load/store... blob | commitdiff | raw | diff to current
2015-01-21 Simon Pilgrim[X86][SSE] Added support for SSE3 lane duplication... blob | commitdiff | raw | diff to current
2015-01-21 Ahmed Bougacha[X86] Declare SSE4.1/AVX2 vector extloads covered by... blob | commitdiff | raw | diff to current
2015-01-16 Andrea Di Biagio[X86][DAG] Disable target specific combine on INSERTPS... blob | commitdiff | raw | diff to current
2015-01-13 Adam Nemet[AVX512] Unpack support in new shuffle lowering blob | commitdiff | raw | diff to current
2015-01-12 Simon Pilgrim[X86][SSE] Minor regression fix for r225551 blob | commitdiff | raw | diff to current
2015-01-12 Ahmed Bougacha[X86] Also create+widen FMIN/FMAX nodes for v2f32. blob | commitdiff | raw | diff to current
2015-01-11 David MajnemerRevert most of r225597 blob | commitdiff | raw | diff to current
2015-01-11 David MajnemerX86: Properly decode shuffle masks when the constant... blob | commitdiff | raw | diff to current
2015-01-11 Saleem AbdulrasoolX86: teach X86TargetLowering about L,M,O constraints blob | commitdiff | raw | diff to current
2015-01-10 Simon Pilgrim[X86][SSE] Improved (v)insertps shuffle matching blob | commitdiff | raw | diff to current
2015-01-09 Simon Pilgrim[X86][SSE] Avoid vector byte shuffles with zero by... blob | commitdiff | raw | diff to current
next
C/C++ LLVM-based compilers that forbids OOTA behaviors