summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen
Commit message (Expand)AuthorAgeFilesLines
* [FastISel][AArch64] Extend floating-point materialization test.Juergen Ributzka2014-08-191-15/+29
* Reapply [FastISel][AArch64] Add support for more addressing modes (r215597).Juergen Ributzka2014-08-191-0/+425
* Reapply [FastISel][X86] Add large code model support for materializing floati...Juergen Ributzka2014-08-191-16/+20
* Reapply [FastISel][X86] Use XOR to materialize the "0" value (r215594).Juergen Ributzka2014-08-193-10/+10
* Reapply [FastISel][X86] Emit more efficient instructions for integer constant...Juergen Ributzka2014-08-192-211/+149
* Reapply [FastISel][AArch64] Make use of the zero register when possible (r215...Juergen Ributzka2014-08-194-15/+46
* Reapply [FastISel] Let the target decide first if it wants to materialize a c...Juergen Ributzka2014-08-198-73/+32
* [FastISel][AArch64] Fix a few BuildMI callsites where the result register was...Juergen Ributzka2014-08-192-10/+10
* [X86, X87 stackifier] Do not mark an operand of a debug instruction as kill.Akira Hatanaka2014-08-191-0/+71
* Teach the AArch64 backend to handle f16Oliver Stannard2014-08-181-0/+109
* [ARM,AArch64] Do not tail-call to an externally-defined function with weak li...Oliver Stannard2014-08-182-0/+21
* AVX-512: Fixed a bug in emitting compare for MVT:i1 type.Elena Demikhovsky2014-08-182-3/+16
* ARM: improve RTABI 4.2 conformance on LinuxSaleem Abdulrasool2014-08-171-20/+9
* llvm/test/CodeGen/X86/fmul-combines.ll: Appease Windows x64. <4 x float> is p...NAKAMURA Takumi2014-08-161-1/+1
* Fix fmul combines with constant splat vectorsMatt Arsenault2014-08-162-6/+103
* [x86] Teach lots of the new vector shuffle lowering to use UNPCKChandler Carruth2014-08-163-19/+19
* [DAGCombiner] Improve the folding of target independet shuffles to Undef.Andrea Di Biagio2014-08-161-0/+191
* [PowerPC] Mark fixed-offset byvals as pointed-to by IR valuesHal Finkel2014-08-161-0/+30
* [AArch32] Add support for FP rounding operations for ARMv8/AArch32.Chad Rosier2014-08-151-0/+110
* R600/SI: Move all fabs / fneg handling to patternsMatt Arsenault2014-08-154-18/+106
* R600/SI: Use source modifiers for f64 fnegMatt Arsenault2014-08-152-0/+148
* R600/SI: Use source modifier for f64 fabsMatt Arsenault2014-08-151-0/+97
* R600/SI: Fix offset folding in some cases with shifted pointers.Matt Arsenault2014-08-151-0/+286
* [x86] Teach the new AVX v4f64 shuffle lowering to use UNPCK instructionsChandler Carruth2014-08-151-1/+25
* R600/SI: Add intrinsic for ldexpMatt Arsenault2014-08-151-0/+22
* [FastISel][ARM] Fix unit test from r215682.Juergen Ributzka2014-08-151-5/+3
* R600/SI: Implement isLegalAddressingModeMatt Arsenault2014-08-151-0/+60
* ARM: Fix and re-enable load/store optimizer for Thumb1.Moritz Roth2014-08-157-25/+97
* [AArch64] Narrow arguments passed in wrong position on the stack inAmara Emerson2014-08-151-0/+24
* [PPC64] Add test case for r215685.Bill Schmidt2014-08-151-0/+534
* [x86] Add the initial skeleton of type-based dispatch for AVX vectors inChandler Carruth2014-08-151-0/+83
* [x86] Fix the very broken formation of vpunpck instructions in theChandler Carruth2014-08-153-14/+23
* [x86] Fix PR20540 where the x86 shuffle DAG combiner had completelyChandler Carruth2014-08-151-0/+12
* [FastISel][ARM] Fall-back to constant pool loads when materializing an i32 co...Juergen Ributzka2014-08-141-0/+12
* Revert several FastISel commits to track down a buildbot error.Juergen Ributzka2014-08-1417-256/+324
* [AVX512] Add test for FMA masking instrinsicsAdam Nemet2014-08-141-0/+14
* [AVX512] Switch FMA intrinsics to the masking versionAdam Nemet2014-08-141-25/+27
* Revert "[FastISel][AArch64] Add support for more addressing modes."Juergen Ributzka2014-08-141-425/+0
* optimize vector fneg of bitcasted integer valueSanjay Patel2014-08-143-48/+68
* [mips] Improve robustness of some tests.Toma Tabacu2014-08-147-65/+65
* [x86] Begin stubbing out the AVX support in the new vector shuffleChandler Carruth2014-08-141-0/+258
* [SDAG] Fix a bug in the DAG combiner where we would fail to return theChandler Carruth2014-08-141-0/+24
* [SDAG] Fix a case where we would iteratively legalize a node duringChandler Carruth2014-08-141-0/+20
* [AArch64, fast-isel] Fall back to SelectionDAG to select tail calls.Akira Hatanaka2014-08-132-1/+14
* [FastISel][AArch64] Add support for more addressing modes.Juergen Ributzka2014-08-131-0/+425
* [FastISel][X86] Add large code model support for materializing floating-point...Juergen Ributzka2014-08-131-16/+20
* [FastISel][X86] Use XOR to materialize the "0" value.Juergen Ributzka2014-08-133-10/+10
* [FastISel][X86] Emit more efficient instructions for integer constant materia...Juergen Ributzka2014-08-132-211/+149
* [FastISel][AArch64] Make use of the zero register when possible.Juergen Ributzka2014-08-134-15/+46
* [FastISel] Let the target decide first if it wants to materialize a constant.Juergen Ributzka2014-08-138-72/+31
OpenPOWER on IntegriCloud