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

intel/compiler: Teach signed integer range analysis about imax and imin

Browse Source 
This is especially helpful for a*isign(a) generated by idiv_by_const
optimization.  On many GPUs, isign(a) is lowered to imax(imin(a, 1),
-1).

There are no changes on fossil-db because ANV uses a different
optimization path for idiv with a constant denominator.  A future MR
will change this.

NOTE: This commit used to help a few hundred shader-db shaders, but
now none are affected.  I suspect this is due to some change in the
idiv_by_const optimization.  This could possibly be dropped.

Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17718>
This commit is contained in:
Ian Romanick
2022-02-03 18:26:40 -08:00
committed by Marge Bot
parent 1b0da3a765
commit 5ec75ca10d
1 changed files with 32 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
src/intel/compiler/brw_nir_opt_peephole_imul32x16.c
View File

@@ -122,6 +122,38 @@ signed_integer_range_analysis(nir_shader *shader, struct hash_table *range_ht,
return root ^ integer_neg;
}
case nir_op_imax: {
int src0_lo, src0_hi;
int src1_lo, src1_hi;
signed_integer_range_analysis(shader, range_ht,
nir_ssa_scalar_chase_alu_src(scalar, 0),
&src0_lo, &src0_hi);
signed_integer_range_analysis(shader, range_ht,
nir_ssa_scalar_chase_alu_src(scalar, 1),
&src1_lo, &src1_hi);
*lo = MAX2(src0_lo, src1_lo);
*hi = MAX2(src0_hi, src1_hi);
break;
}
case nir_op_imin: {
int src0_lo, src0_hi;
int src1_lo, src1_hi;
signed_integer_range_analysis(shader, range_ht,
nir_ssa_scalar_chase_alu_src(scalar, 0),
&src0_lo, &src0_hi);
signed_integer_range_analysis(shader, range_ht,
nir_ssa_scalar_chase_alu_src(scalar, 1),
&src1_lo, &src1_hi);
*lo = MIN2(src0_lo, src1_lo);
*hi = MIN2(src0_hi, src1_hi);
break;
}
default:
break;
}