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

nir/optimize cmp(a, -0.0)

Browse Source 
+0.0 can use an inline constant for AMD hardware,
-0.0 needs a literal.

Foz-DB Navi21:
Totals from 1014 (1.28% of 79395) affected shaders:
Instrs: 3037490 -> 3036849 (-0.02%); split: -0.02%, +0.00%
CodeSize: 17060228 -> 17051276 (-0.05%); split: -0.05%, +0.00%
Latency: 45916788 -> 45916600 (-0.00%); split: -0.00%, +0.00%
InvThroughput: 12982201 -> 12982187 (-0.00%); split: -0.00%, +0.00%
VClause: 79475 -> 79478 (+0.00%)
SClause: 119935 -> 119934 (-0.00%); split: -0.00%, +0.00%
Copies: 301641 -> 300964 (-0.22%); split: -0.23%, +0.00%
PreSGPRs: 59155 -> 59144 (-0.02%)
VALU: 2032016 -> 2032034 (+0.00%)
SALU: 386424 -> 385729 (-0.18%)

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29467>
This commit is contained in:
Georg Lehmann
2024-05-29 17:13:01 +02:00
committed by Marge Bot
parent 8e6bf596cb
commit 98cc57bccb
2 changed files with 25 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/compiler/nir/nir_opt_algebraic.py
View File

@@ -608,6 +608,12 @@ optimizations.extend([
(('fge', -1.0, ('fneg', a)), ('fge', a, 1.0)),
(('fneu', ('fneg', a), -1.0), ('fneu', 1.0, a)),
(('feq', -1.0, ('fneg', a)), ('feq', a, 1.0)),
(('flt', a, '#b(is_negative_zero)'), ('flt', a, 0.0)),
(('flt', '#b(is_negative_zero)', a), ('flt', 0.0, a)),
(('fge', a, '#b(is_negative_zero)'), ('fge', a, 0.0)),
(('fge', '#b(is_negative_zero)', a), ('fge', 0.0, a)),
(('fneu', a, '#b(is_negative_zero)'), ('fneu', 0.0, a)),
(('feq', '#b(is_negative_zero)', a), ('feq', a, 0.0)),
(('ieq', ('ineg', a), 0), ('ieq', a, 0)),
(('ine', ('ineg', a), 0), ('ine', a, 0)),

19
src/compiler/nir/nir_search_helpers.h
View File

@@ -29,6 +29,7 @@
#include <math.h>
#include "util/bitscan.h"
#include "util/u_math.h"
#include "nir.h"
#include "nir_range_analysis.h"
@@ -127,6 +128,24 @@ is_nan(UNUSED struct hash_table *ht, const nir_alu_instr *instr,
return true;
}
static inline bool
is_negative_zero(UNUSED struct hash_table *ht, const nir_alu_instr *instr,
unsigned src, unsigned num_components, const uint8_t *swizzle)
{
/* only constant srcs: */
if (!nir_src_is_const(instr->src[src].src))
return false;
for (unsigned i = 0; i < num_components; i++) {
union di tmp;
tmp.d = nir_src_comp_as_float(instr->src[src].src, swizzle[i]);
if (tmp.ui != 0x8000000000000000ull)
return false;
}
return true;
}
static inline bool
is_any_comp_nan(UNUSED struct hash_table *ht, const nir_alu_instr *instr,
unsigned src, unsigned num_components, const uint8_t *swizzle)