Unbreak fast isel.
[oota-llvm.git] / lib / Target / X86 /
2008-09-03 Evan ChengUnbreak fast isel.
2008-09-03 Evan ChengLet tblgen only generate fastisel routines, not the...
2008-08-31 Gabor Greiffix a bunch of 80-col violations
2008-08-30 Evan ChengFor now, can't mark XOR64rr isAsCheapAsAMove. It's...
2008-08-30 Evan ChengTransform (x << (y&31)) -> (x << y). This takes advanta...
2008-08-29 Evan ChengSwap fp comparison operands and change predicate to...
2008-08-29 Evan ChengUse static_cast instead of C style cast.
2008-08-29 Evan ChengBacking out 55521. Not safe.
2008-08-29 Owen AndersonAdd initial support for fast isel of instructions that...
2008-08-28 Evan ChengSwap fp comparison operands and change predicate to...
2008-08-28 Dan GohmanAdd a target callback for FastISel.
2008-08-28 Gabor Greifremove tabs, fix > 80 cols
2008-08-28 Gabor Greiferect abstraction boundaries for accessing SDValue...
2008-08-28 Rafael EspindolaUse resize instead of reserve. Reserve doesn't change...
2008-08-28 Evan ChengFsFLD0S{S|D} and V_SETALLONES are as cheap as moves.
2008-08-28 Dale JohannesenSplit the ATOMIC NodeType's to include the size, e.g.
2008-08-27 Bill WendlingMake "movdq2q" and "movq2dq" dependent upon having...
2008-08-27 Dan GohmanReinstate the x86-64 portion of r55190. When doing...
2008-08-26 Gabor Greifdisallow direct access to SDValue::ResNo, provide a...
2008-08-26 Owen AndersonThese assertions should be return false's instead,...
2008-08-26 Owen AndersonMake TargetInstrInfo::copyRegToReg return a bool indica...
2008-08-26 Chris LattnerIf an xmm register is referenced explicitly in an inlin...
2008-08-26 Evan ChengThis is done.
2008-08-25 Evan Cheng80 col. violations.
2008-08-25 Evan ChengTry approach to moving call address load inside of...
2008-08-25 Bill WendlingNevermind. This broke the bootstrap (?!).
2008-08-25 Bill WendlingMOVQ2DQ and MOVQ2DQ use SSE2. We should conditionalize...
2008-08-25 Evan ChengFix asm printing of MOVSDto64mr and MOV64toSDrm.
2008-08-24 Bill WendlingTemporarily reverting r55292. It's causing a bootstrapi...
2008-08-24 Evan ChengMove callseq_start above the call address load to allow...
2008-08-24 Cedric VenetUse additionnal include directory instead of ../ in...
2008-08-23 Anton KorobeynikovProvide a 64 bit variant of mmx.maskmovq intrinsic...
2008-08-23 Dan GohmanMove the point at which FastISel taps into the Selectio...
2008-08-22 Bill WendlingReverting r55190, r55191, and r55192. They broke the...
2008-08-22 Dan GohmanAnyext tweaks for x86. When extloading a value to i32...
2008-08-22 Dan GohmanFactor out the predicate check code from DAGISelEmitter.cpp
2008-08-21 Bill WendlingIf part of the mask is "undef", then ignore it as we...
2008-08-21 Bill WendlingFix whitespace. No functionality change.
2008-08-21 Evan ChengFix a number of byval / memcpy / memset related codegen...
2008-08-21 Mon P WangTreat floating point ST1 the same as ST0 when lowering...
2008-08-21 Anton KorobeynikovAllow inline asm nodes with empty bodies inside JIT.
2008-08-21 Dan GohmanSimplify SelectRoot's interface, and factor out some...
2008-08-21 Bill WendlingClean up whitespace.
2008-08-21 Owen AndersonUse raw_ostream throughout the AsmPrinter.
2008-08-20 Dan GohmanMove the handling of ANY_EXTEND, SIGN_EXTEND_INREG...
2008-08-20 Dan GohmanSimplify FastISel's constructor argument list, make...
2008-08-20 Dan GohmanTablegen generated code already tests the opcode value...
2008-08-20 Dan GohmanFix comment spacing.
2008-08-20 Dale JohannesenAdd remaining 64-bit atomic patterns for x86-64.
2008-08-20 Bill WendlingRevert r55018 and apply the correct "fix" for the 64...
2008-08-19 Bill WendlingAdd support for the __sync_sub_and_fetch atomics and...
2008-08-19 Dan GohmanInstantiate FastISel for X86.
2008-08-19 Dan GohmanThe X86 target will soon have an implementation of...
2008-08-19 Dale JohannesenAdd support for 8 and 16 bit forms of __sync
2008-08-19 Chris Lattneradd a note
2008-08-18 Chris Lattnerremove empty file
2008-08-17 Evan ChengFix a (u)comiss intrinsic lowering bug. It was using...
2008-08-17 Cedric VenetMake it compile on VC2005:
2008-08-17 Anton KorobeynikovMove X86 assembler printers into separate directory...
2008-08-16 Anton KorobeynikovUse correct name for TLS address resolution routine...
2008-08-16 Anton KorobeynikovReduce heap trashing due to std::string construction...
2008-08-14 Dan GohmanBuild the X86GenFastISel.inc file.
2008-08-14 Dan GohmanAlso avoid pinsrw and pinsrb with a variable insertelem...
2008-08-14 Owen AndersonConvert uses of std::vector in TargetInstrInfo to Small...
2008-08-14 Dan GohmanDon't try to use the insertps instruction for vector
2008-08-14 Owen AndersonRemove more uses of std::set.
2008-08-13 Dan GohmanOops, check in these files too, for the FastISel -...
2008-08-12 Dale JohannesenWhen resolving a stub in x86-64 JIT, use a PC-relative...
2008-08-12 Dale JohannesenMake x86-64 JIT changes Darwin-specific.
2008-08-12 Dale JohannesenIn the absence of a linker to build the GOT, use the...
2008-08-11 Dale JohannesenSome fixes for x86-64 JIT. Make it use small code
2008-08-08 Dan GohmanAdd an EXTRACTPSmr pattern to match the pattern that
2008-08-08 Anton KorobeynikovGeneralize
2008-08-08 Anton KorobeynikovHandle visibility printing with all generality. Remove...
2008-08-08 Evan ChengFix indentation.
2008-08-07 Anton KorobeynikovRemove dead forward decl
2008-08-07 Anton KorobeynikovSwitch ARM to new section handling stuff
2008-08-07 Dan GohmanRe-enable elimination of unnecessary SUBREG_TO_REG...
2008-08-06 Dan GohmanRe-introduce the 8-bit subreg zext-inreg patterns for...
2008-08-06 Dan Gohmanxchg does not modify FLAGS.
2008-08-05 Evan ChengFix PR2620: Fix X86cmppd selection code so it expects...
2008-08-04 Dan GohmanAdd an assert to catch invalid VECTOR_SHUFFLE mask...
2008-08-03 Andrew LenharthAdd atomic sub for other sizes
2008-07-30 Dan GohmanReapply r54147 with a constraint to only use the 8-bit
2008-07-29 Dan GohmanRevert 54147.
2008-07-28 Dan GohmanAdd x86 isel patterns to match what would be a ZERO_EXT...
2008-07-27 Dan GohmanRename SDOperand to SDValue.
2008-07-27 Dan GohmanTidy SDNode::use_iterator, and complete the transition...
2008-07-25 Nate BegemanDisable mov{L, LP, HP, HLP, *DUP} shuffles for mmx
2008-07-25 Nate BegemanFit in 80 cols
2008-07-25 Nate BegemanRemove dead PatLeaf; there are a number of issues aroun...
2008-07-23 Evan ChengFix PR2485: do all 4-element SSE shuffles in max. of...
2008-07-22 Evan ChengFactor out SSE 4 wide shuffle lowering code into its...
2008-07-22 Evan ChengFix PR2574: implement v2f32 scalar_to_vector.
2008-07-22 Anton KorobeynikovFix encoding of atomic compare and swap for i64
2008-07-21 Evan ChengEliminate a compilation warning.
2008-07-21 Dan GohmanAdd titles to the various SelectionDAG viewGraph calls
2008-07-21 Duncan SandsAdd VerifyNode, a place to put sanity checks on
2008-07-21 Evan ChengUse movaps instead of movups to spill 16-byte vector...
2008-07-20 Bill WendlingFix for first part of PR2562. Generate the "pinsrw...
next