| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | LoopVectorize: Preserve NSW, NUW and IsExact flags. | Nadav Rotem | 2012-10-31 | 1 | -1/+1 |
| | | | | | llvm-svn: 167174 | ||||
| * | LoopVectorizer: Add a basic cost model which uses the VTTI interface. | Nadav Rotem | 2012-10-24 | 1 | -1/+1 |
| | | | | | llvm-svn: 166620 | ||||
| * | Vectorize: teach cavVectorizeMemory to distinguish between A[i]+=x and ↵ | Nadav Rotem | 2012-10-20 | 1 | -0/+66 |
| | | | | | | | | | | A[B[i]]+=x. If the pointer is consecutive then it is safe to read and write. If the pointer is non-loop-consecutive then it is unsafe to vectorize it because we may hit an ordering issue. llvm-svn: 166371 | ||||
| * | Vectorizer: Add support for loop reductions. | Nadav Rotem | 2012-10-19 | 1 | -35/+0 |
| | | | | | | | | | | For example: for (i=0; i<n; i++) sum += A[i] + B[i] + i; llvm-svn: 166351 | ||||
| * | vectorizer: Add support for reading and writing from the same memory location. | Nadav Rotem | 2012-10-19 | 1 | -0/+35 |
| llvm-svn: 166255 | |||||
 |
index : bcm5719-llvm | |
| Project Ortega BCM5719 LLVM | Raptor Computing Systems |
| summaryrefslogtreecommitdiffstats |
|