diff options
| author | Renato Golin <renato.golin@linaro.org> | 2013-03-19 08:15:38 +0000 |
|---|---|---|
| committer | Renato Golin <renato.golin@linaro.org> | 2013-03-19 08:15:38 +0000 |
| commit | 5ad5f5931e34d5be410b1e901640bc1c2d308612 (patch) | |
| tree | 4cb257e7333a6d8337a30fc6ca7aeec8e54b3713 /cmake/modules/HandleLLVMOptions.cmake | |
| parent | 54e57f8cb79bdc23ed8289cf2a558fa7c9602972 (diff) | |
| download | llvm-5ad5f5931e34d5be410b1e901640bc1c2d308612.tar.gz llvm-5ad5f5931e34d5be410b1e901640bc1c2d308612.tar.bz2 llvm-5ad5f5931e34d5be410b1e901640bc1c2d308612.tar.xz | |
Improve long vector sext/zext lowering on ARM
The ARM backend currently has poor codegen for long sext/zext
operations, such as v8i8 -> v8i32. This patch addresses this
by performing a custom expansion in ARMISelLowering. It also
adds/changes the cost of such lowering in ARMTTI.
This partially addresses PR14867.
Patch by Pete Couperus
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177380 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'cmake/modules/HandleLLVMOptions.cmake')
0 files changed, 0 insertions, 0 deletions