From f390893a64e57c34ee959b17a7b301909627236b Mon Sep 17 00:00:00 2001
From: Rhys Perry <pendingchaos02@gmail.com>
Date: Wed, 23 Apr 2025 16:28:57 +0100
Subject: [PATCH] aco/gfx12: use s_sub_u64

fossil-db (gfx1201):
Totals from 2 (0.00% of 79377) affected shaders:
Instrs: 243999 -> 243993 (-0.00%)
CodeSize: 1288176 -> 1288152 (-0.00%)
Latency: 1894093 -> 1894091 (-0.00%)
InvThroughput: 378819 -> 378818 (-0.00%)
SALU: 33048 -> 33044 (-0.01%)

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34730>
---
 src/amd/compiler/aco_instruction_selection.cpp | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/src/amd/compiler/aco_instruction_selection.cpp b/src/amd/compiler/aco_instruction_selection.cpp
index c607d8634f8..bcd3895b3cc 100644
--- a/src/amd/compiler/aco_instruction_selection.cpp
+++ b/src/amd/compiler/aco_instruction_selection.cpp
@@ -1934,6 +1934,9 @@ visit_alu_instr(isel_context* ctx, nir_alu_instr* instr)
       } else if (dst.regClass() == v1 && instr->def.bit_size == 16) {
          emit_vop3p_instruction(ctx, instr, aco_opcode::v_pk_sub_u16, dst);
          break;
+      } else if (dst.regClass() == s2 && ctx->program->gfx_level >= GFX12) {
+         emit_sop2_instruction(ctx, instr, aco_opcode::s_sub_u64, dst, false);
+         break;
       }
 
       Temp src0 = get_alu_src(ctx, instr->src[0]);