oota-llvm.git
2006-03-31 Chris LattnerAn identity shuffle shouldn't generate any permute...
2006-03-31 Chris LattnerFix 80 column violations :)
2006-03-31 Evan ChengUse a X86 target specific node X86ISD::PINSRW instead...
2006-03-31 Chris Lattnerregenerate
2006-03-31 Chris LattnerGeneralize the previous binary operator support and...
2006-03-31 Chris Lattnernew testcase
2006-03-31 Evan ChengAdded support for SSE3 horizontal ops: haddp{s|d} and...
2006-03-31 Evan ChengAdded haddp{s|d} and hsubp{s|d} intrinsics.
2006-03-31 Chris Lattnerfix a pasto
2006-03-31 Chris LattnerAdd vperm support for all datatypes
2006-03-31 Chris LattnerRearrange code a bit
2006-03-31 Chris LattnerAdd, sub and shuffle are legal for all vector types
2006-03-31 Evan ChengAdd support to use pextrw and pinsrw to extract and...
2006-03-31 Evan ChengAdd vector_extract and vector_insert nodes.
2006-03-31 Chris Lattneradd a note
2006-03-31 Chris Lattnerconstant fold extractelement with undef operands.
2006-03-31 Chris Lattnerextractelement(undef,x) -> undef
2006-03-31 Chris LattnerDo not endian swap split vector loads. This fixes...
2006-03-31 Chris LattnerDo not endian swap the operands to a store if the opera...
2006-03-31 Chris LattnerRemove dead *extloads. This allows us to codegen vecto...
2006-03-31 Chris LattnerDelete dead loads in the dag. This allows us to compile
2006-03-31 Chris LattnerMake this test harder, always check generic x86 and...
2006-03-31 Chris LattnerImplement PromoteOp for VEXTRACT_VECTOR_ELT. Thsi...
2006-03-31 Chris LattnerScalarized vector stores need not be legal, e.g. if...
2006-03-31 Jeff CohenFix build breakage.
2006-03-31 Chris Lattnernote to self: *save* file, then check it in
2006-03-31 Chris LattnerImplement an item from the readme, folding vcmp/vcmp...
2006-03-31 Chris Lattnernew testcase
2006-03-31 Chris Lattnercompactify some more instruction definitions
2006-03-31 Chris LattnerCompactify comparisons.
2006-03-31 Chris LattnerAllow bits init values to be used in patterns, turn...
2006-03-31 Chris LattnerLower vector compares to VCMP nodes, just like we lower...
2006-03-31 Chris LattnerThese are done
2006-03-31 Chris LattnerFinal bugfix for PR724. GCC won't inline varargs funct...
2006-03-31 Chris LattnerAdd a new method to verify intrinsic function prototypes.
2006-03-31 Chris LattnerWhen emitting code for the verifier, instead of emittin...
2006-03-31 Chris LattnerMake sure to pass enough values to phi nodes when we...
2006-03-31 Chris LattnerSignificantly improve handling of vectors that are...
2006-03-31 Chris LattnerWas returning the wrong type.
2006-03-31 Chris LattnerMark INSERT_VECTOR_ELT as expand
2006-03-31 Evan ChengExpand all INSERT_VECTOR_ELT (obviously bad) for now.
2006-03-31 Evan ChengExpand INSERT_VECTOR_ELT to store vec, sp; store elt...
2006-03-31 Chris LattnerModify the TargetLowering::getPackedTypeBreakdown metho...
2006-03-31 Evan ChengTypo
2006-03-31 Evan ChengOk for vector_shuffle mask to contain undef elements.
2006-03-31 Chris LattnerImplement TargetLowering::getPackedTypeBreakdown
2006-03-31 Chris LattnerAdd a method useful for decimating vectors.
2006-03-30 Chris LattnerAdd the rest of the vmul instructions and the vmulsum...
2006-03-30 Chris Lattnerfix incorrect prototypes
2006-03-30 Chris LattnerUse a new tblgen feature to significantly shrinkify...
2006-03-30 Chris LattnerAdd a bunch of new instructions for intrinsics.
2006-03-30 Chris Lattnerregenerate
2006-03-30 Chris LattnerImplement Regression/TableGen/DagDefSubst.ll
2006-03-30 Chris LattnerDag operator should be able to be template params.
2006-03-30 Chris LattnerFix Transforms/InstCombine/2006-03-30-ExtractElement.ll
2006-03-30 Chris Lattnernew testcase that crashes instcombine
2006-03-30 Evan ChengMake sure all possible shuffles are matched.
2006-03-30 Chris LattnerAdd vector multiply, multiply sum, pack, unpack, and...
2006-03-30 Evan ChengMore logical ops patterns
2006-03-30 Evan ChengAdd support for _mm_cmp{cc}_ss and _mm_cmp{cc}_ps intri...
2006-03-30 Evan ChengAdd 128-bit pmovmskb intrinsic support.
2006-03-29 Evan ChengChange SSE pack operation definitions to fit what the...
2006-03-29 Evan ChengAdd SSE2 integer pack with saturation intrinsics.
2006-03-29 Evan Cheng- Added some SSE2 128-bit packed integer ops.
2006-03-29 Evan ChengAdd a pshufhw test case.
2006-03-29 Evan ChengNeed to special case splat after all. Make the second...
2006-03-29 Evan ChengUse unpcklpd for v2f64 splat.
2006-03-29 Evan ChengFloating point logical operation patterns should match...
2006-03-29 Evan ChengAdd more SSE intrinsics
2006-03-29 Evan Cheng- More shuffle related bug fixes.
2006-03-29 Evan ChengAnother entry about shuffles.
2006-03-29 Evan Cheng- Only use pshufd for v4i32 vector shuffles.
2006-03-29 Chris Lattneradd a note
2006-03-29 Chris Lattnernew testcase
2006-03-29 Chris LattnerBug fixes: handle constantexpr insert/extract element...
2006-03-28 Evan ChengAdded aliases to scalar SSE instructions, e.g. addss...
2006-03-28 Evan ChengFixing buggy code.
2006-03-28 Evan ChengDon't sort the names before outputing the intrinsic...
2006-03-28 Chris LattnerWhen building a VVECTOR_SHUFFLE node from extract_eleme...
2006-03-28 Chris LattnerCanonicalize VECTOR_SHUFFLE(X, X, Y) -> VECTOR_SHUFFLE...
2006-03-28 Chris Lattnernew testcase
2006-03-28 Chris LattnerTurn a series of extract_element's feeding a build_vect...
2006-03-28 Chris LattnerTeach Legalize how to pack VVECTOR_SHUFFLE nodes into...
2006-03-28 Chris Lattnernew node
2006-03-28 Chris LattnerAdd a new node
2006-03-28 Chris LattnerDon't crash on X^X if X is a vector. Instead, produce...
2006-03-28 Chris LattnerAdd an assertion
2006-03-28 Chris Lattneradd a note
2006-03-28 Jim LaskeyRefactor address attributes. Add base register to...
2006-03-28 Jim LaskeyExpose base register for DwarfWriter. Refactor code...
2006-03-28 Jim LaskeyMore bulletproofing of llvm.dbg.declare.
2006-03-28 Jim LaskeyAdded missing paren on behalf of Ramana Radhakrishnan.
2006-03-28 Evan ChengMissed X86::isUNPCKHMask
2006-03-28 Evan Chengmovlps and movlpd should be modeled as two address...
2006-03-28 Evan ChengUpdate
2006-03-28 Evan ChengTypo
2006-03-28 Evan Cheng* Prefer using operation of matching types. e.g unpcklp...
2006-03-28 Evan ChengUse movhpd is even better than movlhps.
2006-03-28 Nate BegemanFix a couple typos
2006-03-28 Nate BegemanAdd a few more altivec intrinsics
next