aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Target/X86/X86InstrInfo.cpp
Commit message (Expand)AuthorAgeFilesLines
* - Two-address pass should not assume unfolding is always successful.Evan Cheng2010-07-021-4/+21
* Fix the formatting of the switch statement and add a missing break.Bill Wendling2010-06-221-3/+4
* Fix an unintentional commit. I think I typed "git svn dcommit" in the wrong b...Rafael Espindola2010-06-211-49/+34
* wipRafael Espindola2010-06-211-34/+49
* Add a DebugLoc parameter to TargetInstrInfo::InsertBranch(). ThisStuart Hastings2010-06-171-10/+9
* Merge getStoreRegOpcode and getLoadRegOpcode.Rafael Espindola2010-06-121-97/+47
* Slightly change the meaning of the reMaterialize target hook when the originalJakob Stoklund Olesen2010-06-021-9/+3
* Remove the TargetRegisterClass member from CalleeSavedInfoRafael Espindola2010-06-021-8/+6
* Use enums instead of literals for X86 subregisters.Jakob Stoklund Olesen2010-05-251-3/+3
* Rename X86 subregister indices to something shorter.Jakob Stoklund Olesen2010-05-241-5/+5
* Add the SubRegIndex TableGen class.Jakob Stoklund Olesen2010-05-241-2/+2
* Implement @llvm.returnaddress. rdar://8015977.Evan Cheng2010-05-221-2/+4
* Fix assembly parsing and encoding of the pushf and popf family ofDan Gohman2010-05-201-4/+4
* Teach mode load folding and unfolding code about CMP32ri8 and friends.Dan Gohman2010-05-181-3/+9
* When converting a test to a cmp to fold a load, use the cmp that has anDan Gohman2010-05-181-3/+3
* When rematerializing, use the debug location of the originalDan Gohman2010-05-071-1/+1
* Add a DebugLoc argument to TargetInstrInfo::copyRegToReg, so that itDan Gohman2010-05-061-2/+2
* Add argument TargetRegisterInfo to loadRegFromStackSlot and storeRegToStackSlot.Evan Cheng2010-05-061-4/+7
* Frame index can be negative.Evan Cheng2010-04-291-1/+1
* on darwin empty functions need to codegen into something of non-zero length,Chris Lattner2010-04-261-0/+7
* Remove a redundant comment.Evan Cheng2010-04-261-1/+0
* - Move TargetLowering::EmitTargetCodeForFrameDebugValue to TargetInstrInfo an...Evan Cheng2010-04-261-0/+14
* Add const qualifiers to CodeGen's use of LLVM IR constructs.Dan Gohman2010-04-151-1/+1
* Re-apply 101075 and fix it properly. Just reuse the debug info of the branch ...Evan Cheng2010-04-131-1/+44
* Temporarily revert r101075, it's causing invalid iterator assertionsEric Christopher2010-04-131-46/+1
* Micro-optimization:Bill Wendling2010-04-121-1/+46
* rename llvm::llvm_report_error -> llvm::report_fatal_errorChris Lattner2010-04-071-1/+1
* Educate GetInstrSizeInBytes implementations thatDale Johannesen2010-04-071-0/+1
* Properly enable load clustering.Jakob Stoklund Olesen2010-04-051-4/+0
* use DebugLoc default ctor instead of DebugLoc::getUnknownLoc()Chris Lattner2010-04-021-3/+3
* Teach AnalyzeBranch, RemoveBranch and the branchDale Johannesen2010-04-021-0/+4
* Replace V_SET0 with variants for each SSE execution domain.Jakob Stoklund Olesen2010-03-311-3/+8
* Renumber SSE execution domains for better code size.Jakob Stoklund Olesen2010-03-301-16/+16
* Remove the pmulld intrinsic and autoupdate it as a vector multiply.Eric Christopher2010-03-301-1/+0
* Basic implementation of SSEDomainFix pass.Jakob Stoklund Olesen2010-03-291-39/+43
* Add a late SSEDomainFix pass that twiddles SSE instructions to avoid domain c...Jakob Stoklund Olesen2010-03-251-0/+43
* Revert "Add a late SSEDomainFix pass that twiddles SSE instructions to avoid ...Jakob Stoklund Olesen2010-03-231-3/+0
* Add a late SSEDomainFix pass that twiddles SSE instructions to avoid domain c...Jakob Stoklund Olesen2010-03-231-0/+3
* Teach isSafeToClobberEFLAGS to ignore dbg_value's. We need a MachineBasicBloc...Evan Cheng2010-03-231-3/+13
* Do not force indirect tailcall through fixed registers: eax, r11. Add support...Evan Cheng2010-03-141-0/+17
* Don't try to fold V_SET0 and V_SETALLONES to loads in medium andDan Gohman2010-03-091-0/+5
* Revert r97766. It's deleting a tag.Bill Wendling2010-03-051-52/+13
* Micro-optimization:Bill Wendling2010-03-051-13/+52
* Implement XMM subregs.Dan Gohman2010-02-281-14/+4
* movl is a cheaper way to materialize 0 without clobbering EFLAGS than movabsq.Dan Gohman2010-02-261-1/+1
* Fix a typo in a comment.Dan Gohman2010-02-221-1/+1
* add a bunch of mod/rm encoding types for fixed mod/rm bytes.Chris Lattner2010-02-121-0/+8
* refactor the conditional jump instructions in the .td file toChris Lattner2010-02-111-40/+40
* move target-independent opcodes out of TargetInstrInfoChris Lattner2010-02-091-5/+5
* port X86InstrInfo::determineREX over to the new encoder.Chris Lattner2010-02-051-5/+4