Mesa (master): radeonsi/nir: don't lower fma, instead, fuse fma
GitLab Mirror
gitlab-mirror at kemper.freedesktop.org
Fri Nov 15 19:35:43 UTC 2019
Module: Mesa
Branch: master
Commit: bda3ec5d5507dd10a62e87fc676eeeac93446e3f
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=bda3ec5d5507dd10a62e87fc676eeeac93446e3f
Author: Marek Olšák <marek.olsak at amd.com>
Date: Wed Nov 13 00:21:54 2019 -0500
radeonsi/nir: don't lower fma, instead, fuse fma
We want fma. This decreases compile times by 4% for Borderlands 2.
48505 shaders in 30515 tests
Totals:
SGPRS: 2206584 -> 2204784 (-0.08 %)
VGPRS: 1647892 -> 1648964 (0.07 %)
Spilled SGPRs: 6256 -> 6078 (-2.85 %)
Spilled VGPRs: 72 -> 72 (0.00 %)
Private memory VGPRs: 2176 -> 2176 (0.00 %)
Scratch size: 2240 -> 2240 (0.00 %) dwords per thread
Code Size: 49680804 -> 49837988 (0.32 %) bytes
LDS: 74 -> 74 (0.00 %) blocks
Max Waves: 371387 -> 371352 (-0.01 %)
Reviewed-by: Timothy Arceri <tarceri at itsqueeze.com>
---
src/gallium/drivers/radeonsi/si_get.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/src/gallium/drivers/radeonsi/si_get.c b/src/gallium/drivers/radeonsi/si_get.c
index 9458f6b959a..8dc13ee08b2 100644
--- a/src/gallium/drivers/radeonsi/si_get.c
+++ b/src/gallium/drivers/radeonsi/si_get.c
@@ -511,7 +511,7 @@ static const struct nir_shader_compiler_options nir_options = {
.lower_bitfield_insert_to_bitfield_select = true,
.lower_bitfield_extract = true,
.lower_sub = true,
- .lower_ffma = true,
+ .fuse_ffma = true,
.lower_fmod = true,
.lower_pack_snorm_4x8 = true,
.lower_pack_unorm_4x8 = true,
More information about the mesa-commit
mailing list