| Commit message (Expand) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Remove the pmulld intrinsic and autoupdate it as a vector multiply. | Eric Christopher | 2010-03-30 | 1 | -1/+1 |
| * | Eliminate more uses of llvm-as and llvm-dis. | Dan Gohman | 2009-09-08 | 1 | -1/+1 |
| * | Don't use special heuristics for nodes with no data predecessors | Dan Gohman | 2009-02-11 | 1 | -1/+1 |
| * | Teach 2addr pass to be do more commuting. If both uses of a two-address instr... | Evan Cheng | 2009-01-25 | 1 | -1/+1 |
| * | Fix test to account for generating some vector code for mul v2i64 instead | Mon P Wang | 2008-12-18 | 1 | -2/+2 |
| * | Make this test independent of the target-triple; the stack alignment | Dan Gohman | 2008-05-27 | 1 | -1/+1 |
| * | The Linux ABI emits an extra "movl %esp, %ebp" in function prologue and | Nick Lewycky | 2008-05-26 | 1 | -1/+1 |
| * | Use PMULDQ for v2i64 multiplies when SSE4.1 is available. And add | Dan Gohman | 2008-05-23 | 1 | -0/+32 |
 |
index : external_llvm.git | |
| Android's llvm |
| summaryrefslogtreecommitdiffstats |