From c70dcd1451b62a9c6cffa35ab04b9eae75fcd655 Mon Sep 17 00:00:00 2001
From: Georg Lehmann <dadschoorse@gmail.com>
Date: Wed, 2 Apr 2025 14:43:05 +0200
Subject: [PATCH] aco/gfx9+: use d16 global/scratch/buffer loads

Full register loads are not nessecary and prevent packing optimizations.
Global/Scratch is GFX9+ so D16 loads are always supported.
We already used LDS D16 loads.

Foz-DB Navi31(mostly RA noise):
Totals from 716 (0.90% of 79789) affected shaders:
Instrs: 3854176 -> 3854238 (+0.00%); split: -0.00%, +0.00%
CodeSize: 20034440 -> 20035220 (+0.00%); split: -0.00%, +0.00%
Latency: 24410951 -> 24411120 (+0.00%)
InvThroughput: 5181276 -> 5181301 (+0.00%)
Copies: 320258 -> 320317 (+0.02%)
VALU: 2207307 -> 2207366 (+0.00%)

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34346>
---
 src/amd/compiler/aco_instruction_selection.cpp | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/src/amd/compiler/aco_instruction_selection.cpp b/src/amd/compiler/aco_instruction_selection.cpp
index bea6416cadd..873d7886fc8 100644
--- a/src/amd/compiler/aco_instruction_selection.cpp
+++ b/src/amd/compiler/aco_instruction_selection.cpp
@@ -4587,10 +4587,12 @@ mubuf_load_callback(Builder& bld, const LoadEmitInfo& info, Temp offset, unsigne
    aco_opcode op;
    if (bytes_needed == 1 || align_ % 2) {
       bytes_size = 1;
-      op = aco_opcode::buffer_load_ubyte;
+      op = bld.program->gfx_level >= GFX9 ? aco_opcode::buffer_load_ubyte_d16
+                                          : aco_opcode::buffer_load_ubyte;
    } else if (bytes_needed == 2 || align_ % 4) {
       bytes_size = 2;
-      op = aco_opcode::buffer_load_ushort;
+      op = bld.program->gfx_level >= GFX9 ? aco_opcode::buffer_load_short_d16
+                                          : aco_opcode::buffer_load_ushort;
    } else if (bytes_needed <= 4) {
       bytes_size = 4;
       op = aco_opcode::buffer_load_dword;
@@ -4695,10 +4697,10 @@ scratch_load_callback(Builder& bld, const LoadEmitInfo& info, Temp offset, unsig
    aco_opcode op;
    if (bytes_needed == 1 || align_ % 2u) {
       bytes_size = 1;
-      op = aco_opcode::scratch_load_ubyte;
+      op = aco_opcode::scratch_load_ubyte_d16;
    } else if (bytes_needed == 2 || align_ % 4u) {
       bytes_size = 2;
-      op = aco_opcode::scratch_load_ushort;
+      op = aco_opcode::scratch_load_short_d16;
    } else if (bytes_needed <= 4) {
       bytes_size = 4;
       op = aco_opcode::scratch_load_dword;
@@ -4849,12 +4851,12 @@ global_load_callback(Builder& bld, const LoadEmitInfo& info, Temp offset, unsign
    if (bytes_needed == 1 || align_ % 2u) {
       bytes_size = 1;
       op = use_mubuf ? aco_opcode::buffer_load_ubyte
-           : global  ? aco_opcode::global_load_ubyte
+           : global  ? aco_opcode::global_load_ubyte_d16
                      : aco_opcode::flat_load_ubyte;
    } else if (bytes_needed == 2 || align_ % 4u) {
       bytes_size = 2;
       op = use_mubuf ? aco_opcode::buffer_load_ushort
-           : global  ? aco_opcode::global_load_ushort
+           : global  ? aco_opcode::global_load_short_d16
                      : aco_opcode::flat_load_ushort;
    } else if (bytes_needed <= 4) {
       bytes_size = 4;