oota-llvm.git
2006-04-03 Andrew Lenharthtest powers of 2
2006-04-03 Andrew Lenharthmul by const conversion sequences. more coming soon
2006-04-03 Andrew Lenharthback this out
2006-04-03 Andrew Lenharthtest some more mul by constant removal
2006-04-02 Andrew LenharthMake sure mul by constant 5 is turned into a s4addq
2006-04-02 Andrew LenharthThis should be a win of every arch
2006-04-02 Andrew LenharthThis makes McCat/12-IOtest go 8x faster or so
2006-04-02 Andrew LenharthThis will be needed soon
2006-04-02 Reid SpencerFor PR722:
2006-04-02 Chris Lattneradd a note
2006-04-02 Chris LattnerInform the dag combiner that the predicate compares...
2006-04-02 Chris Lattnerrelax assertion
2006-04-02 Chris LattnerAllow targets to compute masked bits for intrinsics.
2006-04-02 Chris LattnerAdd a little dag combine to compile this:
2006-04-02 Chris Lattnervector casts of casts are eliminable. Transform this:
2006-04-02 Chris Lattnervector casts never reinterpret bits
2006-04-02 Chris LattnerAllow transforming this:
2006-04-02 Chris LattnerTurn altivec lvx/stvx intrinsics into loads and stores...
2006-04-02 Chris LattnerRemove done item
2006-04-02 Jeff CohenFix tablegen related dependencies in Visual Studio.
2006-04-02 Chris LattnerImplement promotion for EXTRACT_VECTOR_ELT, allowing...
2006-04-02 Chris Lattneradd a note
2006-04-02 Chris LattnerImplement the Expand action for binary vector operation...
2006-04-02 Chris LattnerIntrinsics that just load from memory can be treated...
2006-04-02 Chris LattnerAdjust the Intrinsics.gen interface a little bit
2006-04-02 Chris LattnerAdjust to change in Intrinsics.gen interface.
2006-04-02 Chris LattnerConstant fold all of the vector binops. This allows...
2006-04-02 Chris LattnerAdd a new -view-legalize-dags command line option
2006-04-02 Chris LattnerImplement constant folding of bit_convert of arbitrary...
2006-04-02 Chris LattnerThese entries already exist
2006-04-02 Chris LattnerAdd some missing node names
2006-04-02 Chris Lattnersimplify this method
2006-04-02 Chris LattnerNew note
2006-04-02 Chris LattnerConstant fold casts from things like <4 x int> -> ...
2006-04-02 Chris LattnerCustom lower all BUILD_VECTOR's so that we can compile...
2006-04-02 Chris LattnerPrefer larger register classes over smaller ones when...
2006-04-02 Chris LattnerNew testcase that crashes the compiler.
2006-04-01 Chris Lattneradd valuemapper support for inline asm
2006-04-01 Chris LattnerImplement vnot using VNOR instead of using 'vspltisb...
2006-04-01 Chris LattnerFix InstCombine/2006-04-01-InfLoop.ll
2006-04-01 Chris LattnerNew testcase that caused instcombine to infinitely...
2006-04-01 Chris LattnerFold A^(B&A) -> (B&A)^A
2006-04-01 Chris Lattnernew testcases
2006-04-01 Chris LattnerFix Transforms/IndVarsSimplify/2006-03-31-NegativeStrid...
2006-04-01 Chris Lattnernew testcase for PR726
2006-04-01 Chris LattnerADd a note
2006-03-31 Chris LattnerIf we can look through vector operations to find the...
2006-03-31 Chris LattnerShrinkify some more intrinsic definitions.
2006-03-31 Evan ChengAn entry about packed type alignments.
2006-03-31 Chris LattnerPull operand asm string into base class, shrinkifying...
2006-03-31 Evan ChengTargetData.cpp::getTypeInfo() was returning alignment...
2006-03-31 Chris LattnerDelete identity shuffles, implementing CodeGen/Generic...
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...
next