diff options
author | Michael Liao <michael.liao@intel.com> | 2012-10-10 16:32:15 +0000 |
---|---|---|
committer | Michael Liao <michael.liao@intel.com> | 2012-10-10 16:32:15 +0000 |
commit | effae0c8e16010bf93eeca32e28dd9bd45d36959 (patch) | |
tree | eadf4868b8bb4c0bff6f9c254ccb61047dd19e03 /clang/lib/CodeGen/CodeGenModule.cpp | |
parent | 8e50297652a012845daa7d9ea7726fe5b760de77 (diff) | |
download | bcm5719-llvm-effae0c8e16010bf93eeca32e28dd9bd45d36959.tar.gz bcm5719-llvm-effae0c8e16010bf93eeca32e28dd9bd45d36959.zip |
Add alternative support for FP_ROUND from v2f32 to v2f64
- Due to the current matching vector elements constraints in ISD::FP_EXTEND,
rounding from v2f32 to v2f64 is scalarized. Add a customized v2f32 widening
to convert it into a target-specific X86ISD::VFPEXT to work around this
constraints. This patch also reverts a previous attempt to fix this issue by
recovering the scalarized ISD::FP_EXTEND pattern and thus significantly
reduces the overhead of supporting non-power-2 vector FP extend.
llvm-svn: 165625
Diffstat (limited to 'clang/lib/CodeGen/CodeGenModule.cpp')
0 files changed, 0 insertions, 0 deletions