From 0c57340c2323cf712b00df44b0f452df6a5a1eb2 Mon Sep 17 00:00:00 2001
From: Georg Lehmann <dadschoorse@gmail.com>
Date: Sun, 17 Mar 2024 12:53:33 +0100
Subject: [PATCH] aco/builder: use 24bit mul if low bits of imm are zero

Foz-DB Navi31:
Totals from 39 (0.05% of 79395) affected shaders:
Instrs: 62712 -> 62696 (-0.03%)
CodeSize: 330096 -> 329896 (-0.06%)
Latency: 192747 -> 192561 (-0.10%)
InvThroughput: 34078 -> 33889 (-0.55%)
VALU: 38979 -> 38963 (-0.04%)

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28223>
---
 src/amd/compiler/aco_builder_h.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/src/amd/compiler/aco_builder_h.py b/src/amd/compiler/aco_builder_h.py
index 7b42d384f8a..85dee11a7d3 100644
--- a/src/amd/compiler/aco_builder_h.py
+++ b/src/amd/compiler/aco_builder_h.py
@@ -417,6 +417,11 @@ public:
    Result v_mul_imm(Definition dst, Temp tmp, uint32_t imm, bool tmpu24=false, bool tmpi24=false)
    {
       assert(tmp.type() == RegType::vgpr);
+      /* Assume 24bit if high 8 bits of tmp don't impact the result. */
+      if ((imm & 0xff) == 0) {
+         tmpu24 = true;
+         tmpi24 = true;
+      }
       tmpu24 &= imm <= 0xffffffu;
       tmpi24 &= imm <= 0x7fffffu || imm >= 0xff800000u;
       bool has_lshl_add = program->gfx_level >= GFX9;