Add v4i32 <-> v4f32 bitconvert patterns.
[oota-llvm.git] / lib / Target / X86 /
2006-03-23 Evan ChengAdd v4i32 <-> v4f32 bitconvert patterns.
2006-03-23 Evan ChengAdd 128-bit integer vector load and add (for testing).
2006-03-23 Nate BegemanAdd support for 8 bit immediates with 16/32 bit cmp...
2006-03-22 Evan ChengAdded a ValueType operand to isShuffleMaskLegal()....
2006-03-22 Evan ChengSHUFP* are two address code.
2006-03-22 Evan ChengSome clean up.
2006-03-22 Evan Cheng- Supposely movlhps is faster / better than unpcklpd.
2006-03-22 Evan Cheng- Implement X86ISelLowering::isShuffleMaskLegal()....
2006-03-22 Evan Cheng- VECTOR_SHUFFLE of v4i32 / v4f32 with undef second...
2006-03-22 Evan ChengFix PSHUF* and SHUF* jit code emission problems
2006-03-22 Chris Lattnerfix a warning
2006-03-22 Evan ChengSome splat and shuffle support.
2006-03-22 Evan ChengAdd a couple more pseudo instructions.
2006-03-21 Evan ChengDidn't mean to check this in. No MMX support yet.
2006-03-21 Evan Cheng- Use movaps to store 128-bit vector integers.
2006-03-21 Chris LattnerThese targets don't support EXTRACT_VECTOR_ELT, though...
2006-03-21 Evan ChengCombine 2 entries
2006-03-21 Evan ChengAdd a note about x86 register coallescing
2006-03-21 Evan Cheng- Remove scalar to vector pseudo ops. They are just...
2006-03-21 Evan Chengx86 ISD::SCALAR_TO_VECTOR support.
2006-03-21 Evan ChengJunk unused vector register classes.
2006-03-20 Chris LattnerAdd a build_vector node
2006-03-20 Evan ChengMove a few things around.
2006-03-19 Chris Lattneradd a note with a testcase
2006-03-19 Evan ChengVector undef's
2006-03-19 Evan ChengTurning on LSR by default
2006-03-19 Evan ChengRemember which tests are hurt by LSR.
2006-03-19 Chris Lattnerrename these nodes
2006-03-18 Evan ChengUse the generic vector register classes VR64 / VR128...
2006-03-17 Evan ChengDarwin should use _setjmp/_longjmp instead of setjmp...
2006-03-17 Evan ChengMove some pattern fragments to the right files.
2006-03-17 Chris LattnerDisable x86 fastcc from passing args in registers
2006-03-17 Chris LattnerParameterize the number of integer arguments to pass...
2006-03-17 Evan ChengAlso fold MOV8r0, MOV16r0, MOV32r0 + store to MOV8mi...
2006-03-17 Evan ChengAdd some missing entries to X86RegisterInfo::foldMemory...
2006-03-17 Evan Cheng- Nuke 16-bit SBB instructions. We'll never use them.
2006-03-17 Nate BegemanRemove BRTWOWAY*
2006-03-16 Evan ChengA new entry.
2006-03-16 Evan ChengBug fix: condition inverted.
2006-03-16 Evan ChengAdded a way for TargetLowering to specify what values...
2006-03-13 Evan ChengAdded getTargetLowering() to TargetMachine. Refactored...
2006-03-13 Evan ChengAdd LSR hooks.
2006-03-09 Evan ChengAdd option -enable-x86-lsr to enable x86 loop strength...
2006-03-09 Chris Lattnera couple of miscellaneous things.
2006-03-07 Evan ChengX86ISD::REP_STOS and X86ISD::REP_MOVS now produces...
2006-03-07 Evan ChengUse rep/stosl; and Count 0x3; rep/stosb for memset...
2006-03-07 Jim LaskeyUse "llvm.metadata" section for debug globals. Filter...
2006-03-07 Evan Cheng- Emit subsections_via_symbols for Darwin.
2006-03-07 Evan ChengEnable Dwarf debugging info.
2006-03-05 Chris LattnerCopysign needs to be expanded everywhere. Note that...
2006-03-05 Chris Lattneradd a note for something evan noticed
2006-03-04 Evan ChengAdd an entry
2006-03-04 Evan ChengMEMSET / MEMCPY lowering bugs: we can't issue a single...
2006-03-04 Evan ChengTypo
2006-03-03 Chris Lattnerremove the read/write port/io intrinsics.
2006-03-01 Evan ChengVector op lowering.
2006-02-28 Evan ChengAnother entry.
2006-02-28 Evan ChengDon't match x << 1 to LEAL. It's better to emit x + x.
2006-02-26 Evan ChengConstantPoolIndex is now the displacement portion of...
2006-02-26 Evan ChengFixed ConstantPoolIndex operand asm print bug. This...
2006-02-25 Evan Cheng* Cleaned up addressing mode matching code.
2006-02-25 Evan ChengUpdates.
2006-02-25 Evan Cheng* Allow mul, shl nodes to be codegen'd as LEA (if appro...
2006-02-25 Evan ChengConstantPoolIndex is now the displacement field of...
2006-02-25 Evan ChengAdded a common about the need for X86ISD::Wrapper.
2006-02-25 Evan ChengAdded an offset field to ConstantPoolSDNode.
2006-02-25 Evan ChengFix an obvious bug exposed when we are doing
2006-02-23 Evan Cheng- Clean up the lowering and selection code of ConstantP...
2006-02-23 Chris Lattner"." isn't enough to get a private label on linux, use...
2006-02-23 Chris Lattneradd a small and simple case.
2006-02-23 Evan ChengA couple of new entries.
2006-02-23 Evan ChengPIC related bug fixes.
2006-02-23 Evan ChengX86 codegen tweak to use lea in another case:
2006-02-22 Evan ChengMissing .globl for weak / link-once .text symbols.
2006-02-22 Evan Cheng- Added option -relocation-model to set relocation...
2006-02-22 Evan ChengAdded MMX, SSE1, and SSE2 vector instructions and some...
2006-02-22 Chris Lattnersplit register class handling from explicit physreg...
2006-02-21 Chris LattnerUpdates to match change of getRegForInlineAsmConstraint...
2006-02-21 Evan ChengOne more round of reorg so sabre doesn't freak out...
2006-02-21 Evan ChengA big more cleaning up.
2006-02-21 Evan ChengMoving things to their proper places.
2006-02-21 Evan ChengSplit instruction info into multiple files, one for...
2006-02-21 Evan ChengAdded separate alias instructions for SSE logical ops...
2006-02-21 Evan ChengAdded MMX and XMM packed integer move instructions...
2006-02-21 Evan ChengAdded SSE2 128-bit integer packed types: V16I8, V8I16...
2006-02-20 Evan ChengAdded x86 integer vector types: 64-bit packed byte...
2006-02-20 Evan ChengSome updates
2006-02-18 Evan ChengIf SSE3 is available, promote FP_TO_UINT i32 to FP_TO_S...
2006-02-18 Evan ChengAdded fisttp for fp to int conversion.
2006-02-18 Evan ChengDisable PIC for JIT.
2006-02-18 Evan ChengJit does not support PIC yet.
2006-02-18 Evan Chengx86 / Darwin PIC support.
2006-02-17 Chris Lattnerunbreak the build
2006-02-17 Evan ChengUnbreak x86 be
2006-02-17 Nate Begemankill ADD_PARTS & SUB_PARTS and replace them with fancy...
2006-02-17 Chris Lattneradd note about div by power of 2
2006-02-17 Evan ChengRemind ourselves to revisit the "pxor vs. xorps/xorpd...
2006-02-17 Nate BegemanKill the x86 pattern isel. boom.
2006-02-17 Evan ChengRemove the entry about using movapd for SSE reg-reg...
2006-02-16 Evan Chengpxor (for FLD0SS) encoding was missing the OpSize prefix.
next