| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Remove the -licm pass from the loop vectorizer test because the loop ↵ | Nadav Rotem | 2013-01-09 | 1 | -1/+1 |
| | | | | | | | vectorizer does it now. llvm-svn: 171930 | ||||
| * | Fix a typo. Remove the duplicated test. | Nadav Rotem | 2013-01-05 | 1 | -25/+0 |
| | | | | | llvm-svn: 171584 | ||||
| * | iLoopVectorize: Non commutative operators can be used as reduction variables ↵ | Nadav Rotem | 2013-01-05 | 1 | -2/+30 |
| | | | | | | | | | as long as the reduction chain is used in the LHS. PR14803. llvm-svn: 171583 | ||||
| * | Force a fixed unroll count on the target independent tests. | Nadav Rotem | 2013-01-05 | 1 | -1/+1 |
| | | | | | | | This should fix clang-native-arm-cortex-a9. Thanks Renato. llvm-svn: 171582 | ||||
| * | Do not vectorize loops with subtraction reductions | Paul Redmond | 2013-01-04 | 1 | -0/+50 |
| | | | | | | | | | | Since subtraction does not commute the loop vectorizer incorrectly vectorizes reductions such as x = A[i] - x. Disabling for now. llvm-svn: 171537 | ||||
| * | LoopVectorize: Emit reductions as log2(vectorsize) shuffles + vector ops ↵ | Benjamin Kramer | 2012-12-18 | 1 | -0/+40 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | instead of scalar operations. For example on x86 with SSE4.2 a <8 x i8> add reduction becomes movdqa %xmm0, %xmm1 movhlps %xmm1, %xmm1 ## xmm1 = xmm1[1,1] paddw %xmm0, %xmm1 pshufd $1, %xmm1, %xmm0 ## xmm0 = xmm1[1,0,0,0] paddw %xmm1, %xmm0 phaddw %xmm0, %xmm0 pextrb $0, %xmm0, %edx instead of pextrb $2, %xmm0, %esi pextrb $0, %xmm0, %edx addb %sil, %dl pextrb $4, %xmm0, %esi addb %dl, %sil pextrb $6, %xmm0, %edx addb %sil, %dl pextrb $8, %xmm0, %esi addb %dl, %sil pextrb $10, %xmm0, %edi pextrb $14, %xmm0, %edx addb %sil, %dil pextrb $12, %xmm0, %esi addb %dil, %sil addb %sil, %dl llvm-svn: 170439 | ||||
| * | LoopVectorize: Preserve NSW, NUW and IsExact flags. | Nadav Rotem | 2012-10-31 | 1 | -1/+1 |
| | | | | | llvm-svn: 167174 | ||||
| * | LoopVectorize: Fix a bug in the initialization of reduction variables. AND ↵ | Nadav Rotem | 2012-10-30 | 1 | -0/+1 |
| | | | | | | | | | needs to start at all-one while XOR, and OR need to start at zero. llvm-svn: 167032 | ||||
| * | Add support for additional reduction variables: AND, OR, XOR. | Nadav Rotem | 2012-10-25 | 1 | -0/+79 |
| | | | | | | | Patch by Paul Redmond <paul.redmond@intel.com>. llvm-svn: 166649 | ||||
| * | LoopVectorizer: Add a basic cost model which uses the VTTI interface. | Nadav Rotem | 2012-10-24 | 1 | -1/+1 |
| | | | | | llvm-svn: 166620 | ||||
| * | Add support for reduction variables that do not start at zero. | Nadav Rotem | 2012-10-21 | 1 | -4/+34 |
| | | | | | | | | | | | | | This is important for nested-loop reductions such as : In the innermost loop, the induction variable does not start with zero: for (i = 0 .. n) for (j = 0 .. m) sum += ... llvm-svn: 166387 | ||||
| * | Vectorizer: Add support for loop reductions. | Nadav Rotem | 2012-10-19 | 1 | -0/+122 |
| For example: for (i=0; i<n; i++) sum += A[i] + B[i] + i; llvm-svn: 166351 | |||||

