forked from OSchip/llvm-project
2c0390ca4b
needed, and significantly improve the SSSE3 path. This makes the new strategy much more clear. If we can blend, we just go with that. If we can't blend, we try to permute into an unpack so that we handle cases where the unpack doing the blend also simplifies the shuffle. If that fails and we've got SSSE3, we now call into factored-out pshufb lowering code so that we leverage the fact that pshufb can set up a blend for us while shuffling. This generates great code, especially because we *know* we don't have a fast blend at this point. Finally, we fall back on decomposing into permutes and blends because we do at least have a bit-math-based blend if we need to use that. This pretty significantly improves some of the v8i16 code paths. We never need to form pshufb for the single-input shuffles because we have effective target-specific combines to form it there, but we were missing its effectiveness in the blends. llvm-svn: 229851 |
||
|---|---|---|
| .. | ||
| Analysis | ||
| Assembler | ||
| Bindings | ||
| Bitcode | ||
| BugPoint | ||
| CodeGen | ||
| DebugInfo | ||
| ExecutionEngine | ||
| Feature | ||
| FileCheck | ||
| Instrumentation | ||
| Integer | ||
| JitListener | ||
| LTO | ||
| Linker | ||
| MC | ||
| Object | ||
| Other | ||
| SymbolRewriter | ||
| TableGen | ||
| Transforms | ||
| Unit | ||
| Verifier | ||
| YAMLParser | ||
| tools | ||
| .clang-format | ||
| CMakeLists.txt | ||
| Makefile | ||
| Makefile.tests | ||
| TestRunner.sh | ||
| lit.cfg | ||
| lit.site.cfg.in | ||