| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| ... | |
| * | CastInst::castIsValid should return true if the dest type is the same as | Evan Cheng | 2013-01-10 | 1 | -0/+36 |
| * | Teach InstCombine to hoist FABS and FNEG through FPTRUNC instructions. The a... | Owen Anderson | 2013-01-10 | 1 | -0/+19 |
| * | LoopVectorizer: Fix a bug in the vectorization of BinaryOperators. The Binary... | Nadav Rotem | 2013-01-10 | 1 | -0/+25 |
| * | Fix TryToShrinkGlobalToBoolean in GlobalOpt, so that it does not discard addr... | Joey Gouly | 2013-01-10 | 1 | -11/+16 |
| * | ARM Cost model: Use the size of vector registers and widest vectorizable inst... | Nadav Rotem | 2013-01-09 | 3 | -2/+62 |
| * | LICM: Hoist insertvalue/extractvalue out of loops. | Benjamin Kramer | 2013-01-09 | 1 | -0/+26 |
| * | ARM Cost Model: Add a basic vectorization unrolling test. | Nadav Rotem | 2013-01-09 | 1 | -3/+10 |
| * | Remove the -licm pass from the loop vectorizer test because the loop vectoriz... | Nadav Rotem | 2013-01-09 | 23 | -25/+25 |
| * | Cost Model: Move the 'max unroll factor' variable to the TTI and add initial ... | Nadav Rotem | 2013-01-09 | 3 | -2/+31 |
| * | Consider expression "0.0 - X" as the negation of X if | Shuxin Yang | 2013-01-09 | 1 | -2/+13 |
| * | Make sure we don't emit instructions before a landingpad instruction. | Bill Wendling | 2013-01-08 | 2 | -0/+89 |
| * | LoopVectorizer: Add support for floating point reductions | Nadav Rotem | 2013-01-07 | 1 | -0/+29 |
| * | LoopVectorizer: When we vectorizer and widen loops we process many elements a... | Nadav Rotem | 2013-01-07 | 1 | -0/+50 |
| * | This change is to implement following rules: | Shuxin Yang | 2013-01-07 | 1 | -0/+85 |
| * | When code size is the priority (Oz, MinSize attribute), help llvm | Quentin Colombet | 2013-01-07 | 1 | -0/+29 |
| * | Switch the SCEV expander and LoopStrengthReduce to use | Chandler Carruth | 2013-01-07 | 4 | -12/+13 |
| * | Fix a mistaken commit that included some debugging code. | David Tweed | 2013-01-07 | 1 | -1/+1 |
| * | There was a switch fall-through in the parser for textual LLVM that caused | David Tweed | 2013-01-07 | 2 | -3/+3 |
| * | Switch BBVectorize to directly depend on having a TTI analysis. | Chandler Carruth | 2013-01-07 | 10 | -15/+15 |
| * | Fix a crash in LSR replaceCongruentIVs. | Andrew Trick | 2013-01-06 | 1 | -0/+44 |
| * | Fix a typo. Remove the duplicated test. | Nadav Rotem | 2013-01-05 | 1 | -25/+0 |
| * | iLoopVectorize: Non commutative operators can be used as reduction variables ... | Nadav Rotem | 2013-01-05 | 2 | -3/+31 |
| * | Force a fixed unroll count on the target independent tests. | Nadav Rotem | 2013-01-05 | 27 | -27/+27 |
| * | tabs-to-spaces | Andrew Trick | 2013-01-04 | 1 | -44/+43 |
| * | Do not vectorize loops with subtraction reductions | Paul Redmond | 2013-01-04 | 2 | -1/+51 |
| * | Memory Dependence Analysis: fix a miscompile that uses DT to approxmiate the | Manman Ren | 2013-01-04 | 1 | -0/+54 |
| * | LoopVectorizer: | Nadav Rotem | 2013-01-04 | 2 | -2/+58 |
| * | LoopVectorizer: Test the unrolling flag. | Nadav Rotem | 2013-01-03 | 1 | -0/+39 |
| * | Avoid vectorization when the function has the "noimplicitflot" attribute. | Nadav Rotem | 2013-01-02 | 1 | -0/+29 |
| * | Tests: rewrite 'opt ... %s' to 'opt ... < %s' so that opt does not emit a Mod... | Dmitri Gribenko | 2013-01-01 | 2 | -3/+8 |
| * | Tests: rewrite 'opt ... %s' to 'opt ... < %s' so that opt does not emit a Mod... | Dmitri Gribenko | 2013-01-01 | 29 | -30/+30 |
| * | Make opt grab the triple from the module and use it to initialize the target ... | Nadav Rotem | 2013-01-01 | 1 | -1/+1 |
| * | recommit r171298 (add support for PHI nodes to ObjectSizeOffsetVisitor). Hope... | Nuno Lopes | 2012-12-31 | 1 | -0/+128 |
| * | Revert "add support for PHI nodes to ObjectSizeOffsetVisitor" | Benjamin Kramer | 2012-12-31 | 1 | -54/+0 |
| * | Add extra CHECK to make sure that 'or' instruction was replaced. | Jakub Staszak | 2012-12-31 | 1 | -0/+1 |
| * | add support for PHI nodes to ObjectSizeOffsetVisitor | Nuno Lopes | 2012-12-31 | 1 | -0/+54 |
| * | Fix LICM's memory promotion optimization to preserve TBAA tags when | Chris Lattner | 2012-12-31 | 1 | -2/+40 |
| * | teach instcombine to preserve TBAA tag when merging two stores, part of | Chris Lattner | 2012-12-31 | 1 | -0/+34 |
| * | Transform (A == C1 || A == C2) into (A & ~(C1 ^ C2)) == C1 | Jakub Staszak | 2012-12-31 | 1 | -0/+11 |
| * | LoopVectorizer: Fix a bug in the code that updates the loop exiting block. | Nadav Rotem | 2012-12-30 | 1 | -0/+29 |
| * | Tests: rewrite 'opt ... %s' to 'opt ... < %s' so that opt does not emit a Mod... | Dmitri Gribenko | 2012-12-30 | 21 | -23/+23 |
| * | Tests: rewrite 'opt ... %s' to 'opt ... < %s' so that opt does not emit a Mod... | Dmitri Gribenko | 2012-12-30 | 47 | -48/+48 |
| * | llvm/test/Transforms/GVN/null-aliases-nothing.ll: Fix a RUN line not to emit ... | NAKAMURA Takumi | 2012-12-30 | 1 | -1/+1 |
| * | Fix a stunning oversight in the inline cost analysis. It was never | Chandler Carruth | 2012-12-28 | 1 | -0/+38 |
| * | Teach the inline cost analysis about calls that can be simplified and | Chandler Carruth | 2012-12-28 | 1 | -0/+38 |
| * | Teach instsimplify to use the constant folder where appropriate for | Chandler Carruth | 2012-12-28 | 1 | -0/+52 |
| * | If all of the write objects are identified then we can vectorize the loop eve... | Nadav Rotem | 2012-12-26 | 1 | -0/+53 |
| * | LoopVectorizer: Optimize the vectorization of consecutive memory access when ... | Nadav Rotem | 2012-12-26 | 1 | -1/+2 |
| * | BBVectorize: Use VTTI to compute costs for intrinsics vectorization | Hal Finkel | 2012-12-26 | 1 | -0/+79 |
| * | LoopVectorize: Enable vectorization of the fmuladd intrinsic | Hal Finkel | 2012-12-25 | 1 | -0/+60 |
