| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Optimized instruction sequence for sitofp operation on X86-32 | Elena Demikhovsky | 2016-01-10 | 1 | -0/+43 |
| | | | | | | | | | | | | | | | | | | | | Optimized sitofp i64 %x to double. The current sequence movl %ecx, 8(%esp) movl %edx, 12(%esp) fildll 8(%esp) is replaced with: movd %ecx, %xmm0 movd %edx, %xmm1 punpckldq %xmm1, %xmm0 movq %xmm0, 8(%esp) Differential Revision: http://reviews.llvm.org/D15946 llvm-svn: 257285 | ||||
| * | [X86] Fix sitofp and uitofp instruction matching failures with long double ↵ | Michael Kuperstein | 2015-09-20 | 1 | -0/+132 |
| and avx512 The operation action for i32 and i64 cannot be set to legal, as long double needs custom lowering. Patch by: mitch.l.bodart@intel.com Differential Revision: http://reviews.llvm.org/D12372 llvm-svn: 248114 | |||||
 |
index : bcm5719-llvm | |
| Project Ortega BCM5719 LLVM | Raptor Computing Systems |
| summaryrefslogtreecommitdiffstats |
|