Helps Max Waves / VGPR use in a bunch of Unigine Heaven
shaders.
shader-db results radeonsi (VEGA):
Totals from affected shaders:
SGPRS: 5505440 -> 5505872 (0.01 %)
VGPRS: 3077520 -> 3077296 (-0.01 %)
Spilled SGPRs: 39032 -> 39030 (-0.01 %)
Spilled VGPRs: 16326 -> 16326 (0.00 %)
Private memory VGPRs: 0 -> 0 (0.00 %)
Scratch size: 744 -> 744 (0.00 %) dwords per thread
Code Size: 123755028 -> 123753316 (-0.00 %) bytes
Compile Time: 2751028 -> 2560786 (-6.92 %) milliseconds
LDS: 1415 -> 1415 (0.00 %) blocks
Max Waves: 972192 -> 972240 (0.00 %)
Wait states: 0 -> 0 (0.00 %)
vkpipeline-db results RADV (VEGA):
Totals from affected shaders:
SGPRS: 160 -> 160 (0.00 %)
VGPRS: 88 -> 88 (0.00 %)
Spilled SGPRs: 0 -> 0 (0.00 %)
Spilled VGPRs: 0 -> 0 (0.00 %)
Private memory VGPRs: 0 -> 0 (0.00 %)
Scratch size: 0 -> 0 (0.00 %) dwords per thread
Code Size: 18268 -> 18152 (-0.63 %) bytes
LDS: 0 -> 0 (0.00 %) blocks
Max Waves: 26 -> 26 (0.00 %)
Wait states: 0 -> 0 (0.00 %)
v3: disable opt_for_known_values() for non scalar constants
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.olive...@intel.com> (v2)
---
src/compiler/nir/nir_opt_if.c | 61 +++++++++++++++++++++++++++++++++++
1 file changed, 61 insertions(+)
diff --git a/src/compiler/nir/nir_opt_if.c b/src/compiler/nir/nir_opt_if.c
index 4d3183ed151..d8fa6b04b39 100644
--- a/src/compiler/nir/nir_opt_if.c
+++ b/src/compiler/nir/nir_opt_if.c
@@ -1326,6 +1326,66 @@ opt_if_merge(nir_if *nif)
return progress;
}
+/* Perform optimisations based on the values we can derive from the evaluation
+ * of if-statement conditions.
+ */
+static bool
+opt_for_known_values(nir_builder *b, nir_if *nif)
+{
+ bool progress = false;
+
+ assert(nif->condition.is_ssa);
+ nir_ssa_def *if_cond = nif->condition.ssa;
+
+ if (if_cond->parent_instr->type != nir_instr_type_alu)
+ return false;
+
+ nir_alu_instr *alu = nir_instr_as_alu(if_cond->parent_instr);
+ switch (alu->op) {
+ case nir_op_feq:
+ case nir_op_ieq: {
+ nir_load_const_instr *load_const = NULL;
+ nir_ssa_def *unknown_val = NULL;
+
+ nir_ssa_def *src0 = alu->src[0].src.ssa;
+ nir_ssa_def *src1 = alu->src[1].src.ssa;
+ if (src0->parent_instr->type == nir_instr_type_load_const) {
+ load_const = nir_instr_as_load_const(src0->parent_instr);
+ unknown_val = src1;
+ } else if (src1->parent_instr->type == nir_instr_type_load_const) {
+ load_const = nir_instr_as_load_const(src1->parent_instr);
+ unknown_val = src0;
+ }
+
+ if (!load_const)
+ return false;
+
+ /* TODO: remove this and support swizzles? */
+ if (unknown_val->num_components != 1 ||
+ load_const->def.num_components != 1)
+ return false;
+
+ /* Replace unknown ssa uses with the known constant */
+ nir_foreach_use_safe(use_src, unknown_val) {
+ nir_cursor cursor = nir_before_src(use_src, false);
+ nir_block *use_block = nir_cursor_current_block(cursor);
+ if (nir_block_dominates(nir_if_first_then_block(nif), use_block)) {
+ nir_instr_rewrite_src(use_src->parent_instr, use_src,
+ nir_src_for_ssa(&load_const->def));
+ progress = true;
+ }
+ }
+
+ break;
+ }
+
+ default:
+ return false;
+ }
+
+ return progress;
+}
+
static bool
opt_if_cf_list(nir_builder *b, struct exec_list *cf_list)
{
@@ -1380,6 +1440,7 @@ opt_if_safe_cf_list(nir_builder *b, struct exec_list
*cf_list)
progress |= opt_if_safe_cf_list(b, &nif->then_list);
progress |= opt_if_safe_cf_list(b, &nif->else_list);
progress |= opt_if_evaluate_condition_use(b, nif);
+ progress |= opt_for_known_values(b, nif);
break;
}
--
2.20.1
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
