| commit | 14b32e194152f7147d6f531346b923152e58900f | [log] [tgz] |
|---|---|---|
| author | Evan Cheng <evan.cheng@apple.com> | Tue Dec 11 01:46:18 2007 +0000 |
| committer | Evan Cheng <evan.cheng@apple.com> | Tue Dec 11 01:46:18 2007 +0000 |
| tree | 1f539307e974ed81a1a9bddb9e00e990f24c1053 | |
| parent | 844e0f9def5d1caa28e1f2612cb4226e14fd22b3 [diff] |
- Improved v8i16 shuffle lowering. It now uses pshuflw and pshufhw as much as possible before resorting to pextrw and pinsrw. - Better codegen for v4i32 shuffles masquerading as v8i16 or v16i8 shuffles. - Improves (i16 extract_vector_element 0) codegen by recognizing (i32 extract_vector_element 0) does not require a pextrw. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@44836 91177308-0d34-0410-b5e6-96231b3b80d8