summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Target/X86/X86ISelLowering.cpp
Commit message (Expand)AuthorAgeFilesLines
* Remove unused ShouldFoldAtomicFences flag.Tim Northover2013-04-201-7/+0
* Remove unused MEMBARRIER DAG node; it's been replaced by ATOMIC_FENCE.Tim Northover2013-04-201-46/+0
* ArrayRefize getMachineNode(). No functionality change.Michael Liao2013-04-191-8/+3
* Use 'array_lengthof' as possible to avoid magic numbersMichael Liao2013-04-191-23/+32
* X86: Add an SSE2 lowering for 64 bit compares when pcmpgtq (SSE4.2) isn't ava...Benjamin Kramer2013-04-181-15/+40
* Optimize vector select from all 0s or all 1sMichael Liao2013-04-111-0/+45
* Enhance bool simplifcation in X86 to handle more casesMichael Liao2013-04-111-6/+35
* __sincosf_stret returns sinf / cosf in bits 0:31 and 32:63 of xmm0, not inEvan Cheng2013-04-101-5/+19
* Use the target options specified on a function to reset the back-end.Bill Wendling2013-04-051-1/+19
* X86: Promote sitofp <8 x i16> to <8 x i32> when AVX is available.Benjamin Kramer2013-03-311-0/+1
* Remove the old CodePlacementOpt pass.Benjamin Kramer2013-03-291-1/+0
* Add support of RDSEED defined in AVX2 extensionMichael Liao2013-03-281-7/+17
* Enhance boolean simplification to handle 16-/64-bit RDRANDMichael Liao2013-03-281-4/+9
* Skip moving call address loading into callseq when targets prefer register in...Michael Liao2013-03-281-13/+0
* Make Win32 put the SRet address into EAX, fixes PR15556Timur Iskhodzhanov2013-03-281-5/+10
* For the current Atom processor, the fastest way to handle a callPreston Gurd2013-03-271-0/+13
* Fix typo (common to both X86 and PPC)Hal Finkel2013-03-271-1/+1
* Add XTEST codegen supportMichael Liao2013-03-261-0/+13
* Revise alignment checking/calculation on 256-bit unaligned memory accessMichael Liao2013-03-251-7/+6
* Fix PR15296Michael Liao2013-03-201-119/+199
* Mark all variable shifts needing customizingMichael Liao2013-03-201-28/+29
* Move scalar immediate shift lowering into a dedicated funcMichael Liao2013-03-201-5/+20
* Optimize sext <4 x i8> and <4 x i16> to <4 x i64>.Nadav Rotem2013-03-191-2/+17
* TLS support for MinGW targets.Anton Korobeynikov2013-03-181-7/+8
* Fix PR15309Michael Liao2013-03-141-1/+2
* DAGCombiner: Use correct value type for checking legality of BR_CC v3Tom Stellard2013-03-081-1/+7
* X86: Fold EXTRACT_SUBVECTORs of a BUILD_VECTOR into a smaller BUILD_VECTOR.Benjamin Kramer2013-03-071-0/+5
* Fix two remaining issue after fixing PR15355 when CMOV is not availableMichael Liao2013-03-071-6/+22
* Fix PR15355Michael Liao2013-03-061-102/+182
* Bypass Slow DividesPreston Gurd2013-03-041-2/+5
* Fix PR10475Michael Liao2013-03-011-1/+1
* Refine fix to PR10499, no functionality changeMichael Liao2013-02-251-1/+1
* Fix PR10499Michael Liao2013-02-251-1/+1
* Revert r169638 because it broke Mesa llvmpipe tests.Nadav Rotem2013-02-241-6/+1
* Update TargetLowering ivars for name policy.Jim Grosbach2013-02-201-8/+8
* I optimized the following patterns:Elena Demikhovsky2013-02-201-0/+37
* Fix capitalization in comment to match function name.Craig Topper2013-02-191-1/+1
* Use array_pod_sort instead of std::sort.Jakub Staszak2013-02-181-2/+2
* Minor cleanups. No functionality change.Jakub Staszak2013-02-161-9/+8
* 80-colNadav Rotem2013-02-141-1/+2
* Fixed a bug in X86TargetLowering::LowerVectorIntExtend() (assertion failure).Elena Demikhovsky2013-02-141-3/+17
* Don't build tail calls to functions with three inreg arguments on x86-32 PIC.Nick Lewycky2013-02-131-5/+11
* Check i1 as well as i8 variables for 8 bit registers for x86 inlineEric Christopher2013-02-131-1/+1
* Move MRI liveouts to X86 return instructions.Jakob Stoklund Olesen2013-02-051-8/+2
* X86: Open up some opportunities for constant folding by postponing shift lowe...Benjamin Kramer2013-02-041-4/+2
* X86: Simplify code. No functionality change.Benjamin Kramer2013-02-041-19/+5
* Whitespace.Eric Christopher2013-01-311-9/+9
* Check and allow floating point registers to select the size of theEric Christopher2013-01-311-2/+2
* Restrict sin/cos optimization to 64-bit only for now. 32-bit is a bit messy a...Evan Cheng2013-01-301-9/+12
* Remove dead code.Evan Cheng2013-01-291-10/+0
OpenPOWER on IntegriCloud