nir: Add lrp lowering for doubles in opt_algebraic

Graphics / Mesa 3D Graphics Library / Mesa - Samuel Iglesias Gonsálvez [igalia.com] - 28 April 2016 05:01 UTC

Some hardware (i965 on Broadwell generation, for example) does not support natively the execution of lrp instruction with double arguments.

Add 'lower_flrp64' flag to lower this instruction in that case.

v2:- Rename lower_flrp_double to lower_flrp64 (Jason)- Fix typo (Jason)
- Adapt the code to define bit_size information in the opcodes.

db07b46 nir: Add lrp lowering for doubles in opt_algebraic
src/compiler/nir/nir.h | 2 ++
src/compiler/nir/nir_opt_algebraic.py | 9 ++++++---
2 files changed, 8 insertions(+), 3 deletions(-)

Upstream: cgit.freedesktop.org


  • Share