The pass should work for all bit sizes but it's less clear that the
extra instructions are worth it on small integers. Also, the hardware
doesn't do mul_high on anything other than 32-bit integers and, absent
any decent mechanism for testing the pass on 8 and 16-bit types, it's
probably best to just leave it disabled for now.
Shader-db results on Sky Lake:
total instructions in shared programs: 15105795 -> 15111403 (0.04%)
instructions in affected programs: 72774 -> 78382 (7.71%)
helped: 0
HURT: 265
Note that hurt here actually means helped because we're getting rid of
integer quotient operations (which are a send on some platforms!) and
replacing them with fairly cheap ALU ops.
---
src/intel/compiler/brw_nir.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/src/intel/compiler/brw_nir.c b/src/intel/compiler/brw_nir.c
index cf5a4a96d67..7e586b25a94 100644
--- a/src/intel/compiler/brw_nir.c
+++ b/src/intel/compiler/brw_nir.c
@@ -570,6 +570,7 @@ brw_nir_optimize(nir_shader *nir, const struct brw_compiler
*compiler,
OPT(nir_opt_cse);
OPT(nir_opt_peephole_select, 0);
OPT(nir_opt_intrinsics);
+ OPT(nir_opt_idiv_const, 32);
OPT(nir_opt_algebraic);
OPT(nir_opt_constant_folding);
OPT(nir_opt_dead_cf);
@@ -676,7 +677,8 @@ brw_preprocess_nir(const struct brw_compiler *compiler,
nir_shader *nir)
*/
OPT(nir_lower_int64, nir_lower_imul64 |
nir_lower_isign64 |
- nir_lower_divmod64);
+ nir_lower_divmod64 |
+ nir_lower_imul_high64);
nir = brw_nir_optimize(nir, compiler, is_scalar, true);
--
2.19.1
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
