OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

nir: Add lrp lowering for doubles in opt_algebraic

Browse Source 
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.

Signed-off-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
This commit is contained in:
Samuel Iglesias Gonsálvez
2016-04-26 09:35:30 +02:00
parent 443600d51e
commit db07b46f2c
2 changed files with 8 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/compiler/nir/nir.h
View File

@@ -1625,6 +1625,8 @@ typedef struct nir_shader_compiler_options {
bool lower_fdiv;
bool lower_ffma;
bool lower_flrp32;
/** Lowers flrp when it does not support doubles */
bool lower_flrp64;
bool lower_fpow;
bool lower_fsat;
bool lower_fsqrt;

9
src/compiler/nir/nir_opt_algebraic.py
View File

@@ -98,12 +98,15 @@ optimizations = [
(('~flrp', a, a, b), a),
(('~flrp', 0.0, a, b), ('fmul', a, b)),
(('~flrp', a, b, ('b2f', c)), ('bcsel', c, b, a), 'options->lower_flrp32'),
(('flrp', a, b, c), ('fadd', ('fmul', c, ('fsub', b, a)), a), 'options->lower_flrp32'),
(('flrp@32', a, b, c), ('fadd', ('fmul', c, ('fsub', b, a)), a), 'options->lower_flrp32'),
(('flrp@64', a, b, c), ('fadd', ('fmul', c, ('fsub', b, a)), a), 'options->lower_flrp64'),
(('ffract', a), ('fsub', a, ('ffloor', a)), 'options->lower_ffract'),
(('~fadd', ('fmul', a, ('fadd', 1.0, ('fneg', ('b2f', c)))), ('fmul', b, ('b2f', c))), ('bcsel', c, b, a), 'options->lower_flrp32'),
(('~fadd', ('fmul', a, ('fadd', 1.0, ('fneg', c ))), ('fmul', b, c )), ('flrp', a, b, c), '!options->lower_flrp32'),
(('~fadd@32', ('fmul', a, ('fadd', 1.0, ('fneg', c ))), ('fmul', b, c )), ('flrp', a, b, c), '!options->lower_flrp32'),
(('~fadd@64', ('fmul', a, ('fadd', 1.0, ('fneg', c ))), ('fmul', b, c )), ('flrp', a, b, c), '!options->lower_flrp64'),
(('~fadd', a, ('fmul', ('b2f', c), ('fadd', b, ('fneg', a)))), ('bcsel', c, b, a), 'options->lower_flrp32'),
(('~fadd', a, ('fmul', c , ('fadd', b, ('fneg', a)))), ('flrp', a, b, c), '!options->lower_flrp32'),
(('~fadd@32', a, ('fmul', c , ('fadd', b, ('fneg', a)))), ('flrp', a, b, c), '!options->lower_flrp32'),
(('~fadd@64', a, ('fmul', c , ('fadd', b, ('fneg', a)))), ('flrp', a, b, c), '!options->lower_flrp64'),
(('ffma', a, b, c), ('fadd', ('fmul', a, b), c), 'options->lower_ffma'),
(('~fadd', ('fmul', a, b), c), ('ffma', a, b, c), '!options->lower_ffma'),
# Comparison simplifications