forked from OSchip/llvm-project
c4c6b548c5
CodeGenPrepare pass move extension instructions close to load instructions in different BB, so they can be combined later. But the extension instructions can't move through logical and shift instructions in current implementation. This patch enables this enhancement, so we can eliminate more extension instructions. Differential Revision: https://reviews.llvm.org/D45537 This is re-commit of r331783, which was reverted by r333305. The performance regression was caused by some unlucky alignment, not a code generation problem. llvm-svn: 334049 |
||
|---|---|---|
| .. | ||
| AArch64 | ||
| AMDGPU | ||
| ARM | ||
| Mips | ||
| NVPTX | ||
| X86 | ||
| 2008-11-24-RAUW-Self.ll | ||
| basic.ll | ||
| bitreverse-hang.ll | ||
| builtin-condition.ll | ||
| crash-on-large-allocas.ll | ||
| dom-tree.ll | ||
| gep-unmerging.ll | ||
| invariant.group.ll | ||
| nonintegral.ll | ||
| overflow-intrinsics.ll | ||
| section-samplepgo.ll | ||
| section.ll | ||
| skip-merging-case-block.ll | ||
| split-indirect-loop.ll | ||
| statepoint-relocate.ll | ||