aboutsummaryrefslogtreecommitdiffstats
path: root/test/CodeGen/X86
Commit message (Expand)AuthorAgeFilesLines
* fix a case where all operands of BUILD_VECTOR are undefinedMichael Liao2012-08-201-0/+8
* When unsafe math is used, we can use commutative FMAX and FMIN. In some casesNadav Rotem2012-08-191-48/+32
* Reapply r162160 with a fix: Optimize Arith->Trunc->SETCC sequence to allow be...Nadav Rotem2012-08-182-2/+47
* Revert r162160 because it made a few buildbots fail.Nadav Rotem2012-08-182-47/+2
* The X86 backend has a number of optimizations for SETCC nodes which useNadav Rotem2012-08-182-2/+47
* Make atomic load and store of pointers work. Tighten verification of atomic ...Eli Friedman2012-08-171-0/+22
* TargetLowering: Use the large shift amount during legalize types. The legaliz...Benjamin Kramer2012-08-171-0/+32
* Fix broken check lines.Benjamin Kramer2012-08-174-15/+15
* Remove invalid test. This test requires that dead basic blocks be keptBill Wendling2012-08-151-19/+0
* fix PR11334Michael Liao2012-08-141-0/+56
* During the CodeGenPrepare we often lower intrinsics (such as objsize)Nadav Rotem2012-08-143-6/+6
* Rename test since it's not linux-specific.Bill Wendling2012-08-131-0/+0
* Handle extra Tail predecessors in if-conversion.Jakob Stoklund Olesen2012-08-131-0/+30
* Fix failure on Atom bot due to r161769Manman Ren2012-08-131-1/+1
* X86: move Int_CVTSD2SSrr, Int_CVTSI2SSrr, Int_CVTSI2SDrr, Int_CVTSS2SDrr fromManman Ren2012-08-131-0/+14
* fix PR13577, an issue introduced by r161687Michael Liao2012-08-111-0/+8
* PR13578: Teach MachineCSE that instructions that use a constant register can ...Benjamin Kramer2012-08-112-2/+24
* X86: when we are auto-detecting the subtarget features, make sure we turn onManman Ren2012-08-101-1/+3
* add X86-specific DAG optimization to simplify boolean testMichael Liao2012-08-101-0/+42
* Update edge weights correctly in replaceSuccessor().Jakob Stoklund Olesen2012-08-101-1/+1
* Reapply r161633-161634 "Partition use lists so defs always come before uses.""Jakob Stoklund Olesen2012-08-101-1/+1
* Revert r161633-161634 "Partition use lists so defs always come before uses."Jakob Stoklund Olesen2012-08-091-1/+1
* Partition use lists so defs always come before uses.Jakob Stoklund Olesen2012-08-092-3/+3
* Don't use pointer-pointers for the register use lists.Jakob Stoklund Olesen2012-08-091-2/+2
* Add test triples to fix win32 failures. Revert workaround from r161292.Bob Wilson2012-08-084-8/+8
* X86: enable CSE between CMP and SUBManman Ren2012-08-081-0/+23
* X86 cmp lowering is looking past truncate on the condition node. It should onlyEvan Cheng2012-08-071-0/+36
* Add a much more conservative strategy for aligning branch targets.Chandler Carruth2012-08-073-5/+10
* MachineCSE: Update the heuristics for isProfitableToCSE.Manman Ren2012-08-072-1/+36
* Implement proper handling for pcmpistri/pcmpestri intrinsics. Requires custom...Craig Topper2012-08-061-10/+10
* Update test to check for r161305Craig Topper2012-08-051-0/+2
* Refactor and check "onlyReadsMemory" before optimizing builtins.Bob Wilson2012-08-032-4/+4
* Fix memcmp code-gen to honor -fno-builtin.Bob Wilson2012-08-031-0/+3
* Fall back to selection DAG isel for calls to builtin functions.Bob Wilson2012-08-031-0/+8
* X86 Peephole: fold loads to the source register operand if possible.Manman Ren2012-08-022-22/+42
* llvm/test/CodeGen/X86/fold-pcmpeqd-1.ll: Make sure this is testing without +avx.NAKAMURA Takumi2012-08-021-1/+1
* llvm/test/CodeGen/X86/fold-pcmpeqd-1.ll: Rewrite expressions to pass regardle...NAKAMURA Takumi2012-08-021-4/+6
* X86 Peephole: fold loads to the source register operand if possible.Manman Ren2012-08-026-54/+61
* Line endings.Matt Beaumont-Gay2012-08-011-139/+139
* Added FMA functionality to X86 target.Elena Demikhovsky2012-08-013-22/+165
* [x86 frame lowering] In 32-bit mode, use ESI as the base pointer.Chad Rosier2012-07-311-2/+2
* MachineSink: Sort the successors before trying to find SuccToSinkTo.Manman Ren2012-07-311-0/+54
* Reverse order of the two branches at end of a basic block if it is profitable.Manman Ren2012-07-311-0/+104
* Consider address spaces for hashing and CSEing DAG nodes. Otherwise two load...Pete Cooper2012-07-301-0/+16
* Revert r160920 and r160919 due to dragonegg and clang selfhost failureManman Ren2012-07-296-61/+54
* X86 Peephole: fold loads to the source register operand if possible.Manman Ren2012-07-282-4/+4
* X86 Peephole: fold loads to the source register operand if possible.Manman Ren2012-07-286-50/+57
* X86 Peephole: fix PR13475 in optimizeCompare.Manman Ren2012-07-281-0/+16
* Teach CodeGenPrep to look past bitcast when it's duplicating return instructionEvan Cheng2012-07-271-0/+87
* Add <imp-def> of super-register when lowering SUBREG_TO_REG.Jakob Stoklund Olesen2012-07-271-1/+1
generated by cgit v1.1 at 2025-01-08 19:06:03 +0000