| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| ... | |
| * | LoopVectorizer: Optimize the vectorization of consecutive memory access when ... | Nadav Rotem | 2012-12-26 | 1 | -1/+2 |
| * | LoopVectorize: Enable vectorization of the fmuladd intrinsic | Hal Finkel | 2012-12-25 | 1 | -0/+60 |
| * | Fix typo "Makre" -> "Make". | Nick Lewycky | 2012-12-24 | 1 | -6/+4 |
| * | LoopVectorizer: When checking for vectorizable types, also check | Nadav Rotem | 2012-12-24 | 1 | -0/+29 |
| * | LoopVectorizer: Fix an endless loop in the code that looks for reductions. | Nadav Rotem | 2012-12-24 | 1 | -0/+44 |
| * | CostModel: Change the default target-independent implementation for finding | Nadav Rotem | 2012-12-23 | 1 | -3/+3 |
| * | Loop Vectorizer: Update the cost model of scatter/gather operations and make | Nadav Rotem | 2012-12-23 | 1 | -1/+4 |
| * | Fix a bug in the code that checks if we can vectorize loops while using dynamic | Nadav Rotem | 2012-12-21 | 2 | -48/+110 |
| * | LoopVectorize: Fix a bug in the scalarization of instructions. | Nadav Rotem | 2012-12-20 | 1 | -0/+48 |
| * | Make TargetLowering::getTypeConversion more resilient against odd illegal MVTs. | Benjamin Kramer | 2012-12-19 | 1 | -0/+22 |
| * | LoopVectorize: Emit reductions as log2(vectorsize) shuffles + vector ops inst... | Benjamin Kramer | 2012-12-18 | 1 | -0/+40 |
| * | Teach the cost model about the optimization in r169904: Truncation of inducti... | Nadav Rotem | 2012-12-13 | 1 | -1/+1 |
| * | LoopVectorizer: Use the "optsize" attribute to decide if we are allowed to in... | Nadav Rotem | 2012-12-12 | 1 | -0/+170 |
| * | PR14574. Fix a bug in the code that calculates the mask the converted PHIs in... | Nadav Rotem | 2012-12-11 | 1 | -0/+44 |
| * | Loop Vectorize: optimize the vectorization of trunc(induction_var). The trunc... | Nadav Rotem | 2012-12-11 | 4 | -4/+33 |
| * | Fix PR14565. Don't if-convert loops that have switch statements in them. | Nadav Rotem | 2012-12-11 | 1 | -0/+39 |
| * | Add support for reverse induction variables. For example: | Nadav Rotem | 2012-12-10 | 1 | -4/+2 |
| * | LoopVectorize: support vectorizing intrinsic calls | Paul Redmond | 2012-12-09 | 1 | -0/+851 |
| * | Fix a bug in vectorization of if-converted reduction variables. If the | Nadav Rotem | 2012-12-04 | 1 | -0/+38 |
| * | Add support for reduction variables when IF-conversion is enabled. | Nadav Rotem | 2012-12-04 | 1 | -0/+48 |
| * | Add the last part that is needed for vectorization of if-converted code. | Nadav Rotem | 2012-12-04 | 1 | -0/+60 |
| * | Add support for pointer induction variables even when there is no integer ind... | Nadav Rotem | 2012-11-25 | 1 | -0/+33 |
| * | LoopVectorizer: Add initial support for pointer induction variables (for exam... | Nadav Rotem | 2012-11-17 | 1 | -2/+1 |
| * | Relax the restrictions on vector of pointer types, and vector getelementptr. | Duncan Sands | 2012-11-13 | 1 | -2/+2 |
| * | Add support for memory runtime check. When we can, we calculate array bounds. | Nadav Rotem | 2012-11-09 | 1 | -0/+36 |
| * | Cost Model: add tables for some avx type-conversion hacks. | Nadav Rotem | 2012-11-06 | 1 | -1/+1 |
| * | Code Model: Improve the accuracy of the zext/sext/trunc vector cost estimation. | Nadav Rotem | 2012-11-05 | 1 | -2/+2 |
| * | Implement the cost of abnormal x86 instruction lowering as a table. | Nadav Rotem | 2012-11-05 | 1 | -1/+1 |
| * | LoopVectorize: Preserve NSW, NUW and IsExact flags. | Nadav Rotem | 2012-10-31 | 7 | -7/+62 |
| * | Fix a bug in the cost calculation of vector casts. Detect situations where bi... | Nadav Rotem | 2012-10-31 | 1 | -0/+48 |
| * | LoopVectorize: Do not vectorize loops with tiny constant trip counts. | Nadav Rotem | 2012-10-31 | 1 | -0/+33 |
| * | Add support for loops that don't start with Zero. | Nadav Rotem | 2012-10-31 | 2 | -0/+84 |
| * | LoopVectorize: Add support for write-only loops when the write destination is... | Nadav Rotem | 2012-10-30 | 1 | -0/+26 |
| * | LoopVectorize: Fix a bug in the initialization of reduction variables. AND ne... | Nadav Rotem | 2012-10-30 | 1 | -0/+1 |
| * | 1. Fix a bug in getTypeConversion. When a *simple* type is split, we need to ... | Nadav Rotem | 2012-10-27 | 1 | -0/+62 |
| * | Refactor the VectorTargetTransformInfo interface. | Nadav Rotem | 2012-10-26 | 1 | -1/+1 |
| * | Move the target-specific tests, which require specific backends, to dirs that... | Nadav Rotem | 2012-10-26 | 3 | -1/+7 |
| * | Fix the cost-model test. | Nadav Rotem | 2012-10-25 | 1 | -1/+1 |
| * | Add the cpu model to the test. | Nadav Rotem | 2012-10-25 | 1 | -1/+1 |
| * | Add support for additional reduction variables: AND, OR, XOR. | Nadav Rotem | 2012-10-25 | 1 | -0/+79 |
| * | Implement a basic cost model for vector and scalar instructions. | Nadav Rotem | 2012-10-24 | 1 | -3/+1 |
| * | LoopVectorizer: Add a basic cost model which uses the VTTI interface. | Nadav Rotem | 2012-10-24 | 10 | -9/+49 |
| * | Use the AliasAnalysis isIdentifiedObj because it also understands mallocs and... | Nadav Rotem | 2012-10-23 | 1 | -0/+46 |
| * | Don't crash if the load/store pointer is not a GEP. | Nadav Rotem | 2012-10-22 | 1 | -0/+57 |
| * | Vectorizer: optimize the generation of selects. If the condition is uniform, ... | Nadav Rotem | 2012-10-22 | 1 | -0/+37 |
| * | Fix a bug in the vectorization of wide load/store operations. | Nadav Rotem | 2012-10-21 | 1 | -0/+30 |
| * | Add support for reduction variables that do not start at zero. | Nadav Rotem | 2012-10-21 | 1 | -4/+34 |
| * | Vectorizer: fix a bug in the classification of induction/reduction phis. | Nadav Rotem | 2012-10-21 | 1 | -0/+15 |
| * | Fix an infinite loop in the loop-vectorizer. | Nadav Rotem | 2012-10-20 | 1 | -0/+12 |
| * | Vectorize: teach cavVectorizeMemory to distinguish between A[i]+=x and A[B[i]... | Nadav Rotem | 2012-10-20 | 2 | -0/+98 |
