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

bi: Lower pack_32_4x8_split and pack_32_2x16_split in algebraic

Browse Source 
Required for OpenCL.

Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed by: Eric R. Smith <eric.smith@collabora.com>

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30088>
This commit is contained in:
Mary Guillemard
2024-07-08 12:38:46 +02:00
committed by Marge Bot
parent 32ef369322
commit 5420b73925
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/panfrost/compiler/bifrost_nir_algebraic.py
View File

@@ -27,6 +27,7 @@ import math
a = 'a' a = 'a'
b = 'b' b = 'b'
c = 'c' c = 'c'
d = 'd'
# In general, bcsel is cheaper than bitwise arithmetic on Mali. On # In general, bcsel is cheaper than bitwise arithmetic on Mali. On
# Bifrost, we can implement bcsel as either CSEL or MUX to schedule to either # Bifrost, we can implement bcsel as either CSEL or MUX to schedule to either
@@ -43,6 +44,10 @@ opt_bool_bitwise = [
] ]
algebraic_late = [ algebraic_late = [
(('pack_32_4x8_split', a, b, c, d),
('pack_32_2x16_split', ('ior', ('u2u16', a), ('ishl', ('u2u16', b), 8)),
('ior', ('u2u16', c), ('ishl', ('u2u16', d), 8)))),
# Canonical form. The scheduler will convert back if it makes sense. # Canonical form. The scheduler will convert back if it makes sense.
(('fmul', a, 2.0), ('fadd', a, a)), (('fmul', a, 2.0), ('fadd', a, a)),