diff options
| author | Oliver Stannard <oliver.stannard@arm.com> | 2015-08-24 09:47:45 +0000 |
|---|---|---|
| committer | Oliver Stannard <oliver.stannard@arm.com> | 2015-08-24 09:47:45 +0000 |
| commit | 284f2bffc9bc5bc3047243d9c929e40b25d233b2 (patch) | |
| tree | 10debef7f4733431ffe4167c76108f2567435226 /lldb/source/Plugins/ObjectFile/ELF/ObjectFileELF.cpp | |
| parent | b9cc0c75939eb82fbd5c9d646c4b1114b952b4b4 (diff) | |
| download | bcm5719-llvm-284f2bffc9bc5bc3047243d9c929e40b25d233b2.tar.gz bcm5719-llvm-284f2bffc9bc5bc3047243d9c929e40b25d233b2.zip | |
Add DAG optimisation for FP16_TO_FP
The FP16_TO_FP node only uses the bottom 16 bits of its input, so the
following pattern can be optimised by removing the AND:
(FP16_TO_FP (AND op, 0xffff)) -> (FP16_TO_FP op)
This is a common pattern for ARM targets when functions have __fp16
arguments, as they are passed as floats (so that they get passed in the
correct registers), but then bitcast and truncated to ignore the top 16
bits.
llvm-svn: 245832
Diffstat (limited to 'lldb/source/Plugins/ObjectFile/ELF/ObjectFileELF.cpp')
0 files changed, 0 insertions, 0 deletions
