From 5a62d47762c917633bdd614a184273ed294d26e1 Mon Sep 17 00:00:00 2001
From: Iago Toral Quiroga <itoral@igalia.com>
Date: Tue, 24 Sep 2024 13:07:45 +0200
Subject: [PATCH] broadcom/compiler: don't use small immediates in geometry
 stages

Shader-db shows this is beneficial, even if it comes with a small
increase in register pressure.

total instructions in shared programs: 10889197 -> 10869857 (-0.18%)
instructions in affected programs: 3625014 -> 3605674 (-0.53%)
helped: 14911
HURT: 8324
Instructions are helped.

total threads in shared programs: 431034 -> 431014 (<.01%)
threads in affected programs: 40 -> 20 (-50.00%)
helped: 0
HURT: 10
Threads are HURT.

total uniforms in shared programs: 5308006 -> 5432767 (2.35%)
uniforms in affected programs: 2204951 -> 2329712 (5.66%)
helped: 9
HURT: 30766
Uniforms are HURT.

total max-temps in shared programs: 2226471 -> 2235269 (0.40%)
max-temps in affected programs: 272670 -> 281468 (3.23%)
helped: 2372
HURT: 8479
Max-temps are HURT.

total spills in shared programs: 4318 -> 4331 (0.30%)
spills in affected programs: 39 -> 52 (33.33%)
helped: 2
HURT: 7

total fills in shared programs: 6514 -> 6527 (0.20%)
fills in affected programs: 42 -> 55 (30.95%)
helped: 2
HURT: 7

total sfu-stalls in shared programs: 15166 -> 15808 (4.23%)
sfu-stalls in affected programs: 2389 -> 3031 (26.87%)
helped: 513
HURT: 944
Inconclusive result (%-change mean confidence interval includes 0).

total inst-and-stalls in shared programs: 10904363 -> 10885665 (-0.17%)
inst-and-stalls in affected programs: 3660930 -> 3642232 (-0.51%)
helped: 14878
HURT: 8450
Inst-and-stalls are helped.

total nops in shared programs: 183672 -> 184256 (0.32%)
nops in affected programs: 12532 -> 13116 (4.66%)
helped: 1841
HURT: 2251
Nops are HURT.

Reviewed-by: Jose Maria Casanova Crespo <jmcasanova@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31355>
---
 .../compiler/vir_opt_small_immediates.c       | 29 +++++++------------
 1 file changed, 10 insertions(+), 19 deletions(-)

diff --git a/src/broadcom/compiler/vir_opt_small_immediates.c b/src/broadcom/compiler/vir_opt_small_immediates.c
index 49773a8f85e..551bc1c8649 100644
--- a/src/broadcom/compiler/vir_opt_small_immediates.c
+++ b/src/broadcom/compiler/vir_opt_small_immediates.c
@@ -32,27 +32,10 @@
 
 static bool debug;
 
-static bool
+static inline bool
 skip_inst(struct qinst *inst)
 {
-        if (inst->qpu.type != V3D_QPU_INSTR_TYPE_ALU)
-                return true;
-
-        if (!vir_is_add(inst))
-                return false;
-
-        switch (inst->qpu.alu.add.op) {
-        case V3D_QPU_A_LDVPMV_IN:
-        case V3D_QPU_A_LDVPMG_IN:
-        case V3D_QPU_A_LDVPMD_IN:
-        case V3D_QPU_A_LDVPMP:
-        case V3D_QPU_A_STVPMV:
-        case V3D_QPU_A_STVPMD:
-        case V3D_QPU_A_STVPMP:
-                return true;
-        default:
-                return false;
-        }
+        return inst->qpu.type != V3D_QPU_INSTR_TYPE_ALU;
 }
 
 bool
@@ -60,6 +43,14 @@ vir_opt_small_immediates(struct v3d_compile *c)
 {
         bool progress = false;
 
+        /* Shader-db shows that small immediates generally lead to higher
+         * instruction counts for geometry stages.
+         */
+        if (c->s->info.stage != MESA_SHADER_FRAGMENT &&
+            c->s->info.stage != MESA_SHADER_COMPUTE) {
+                return progress;
+        }
+
         vir_for_each_inst_inorder(inst, c) {
                 if (skip_inst(inst))
                         continue;