From a714a19e1626464f73b8f76402d74c52c57d25f4 Mon Sep 17 00:00:00 2001
From: Rhys Perry <pendingchaos02@gmail.com>
Date: Fri, 6 Jun 2025 17:45:48 +0100
Subject: [PATCH] aco/gfx12: fix VALUReadSGPRHazard with carry-out

fossil-db (gfx1201):
Totals from 370 (0.46% of 79653) affected shaders:
Instrs: 3933639 -> 3935914 (+0.06%)
CodeSize: 20743448 -> 20752068 (+0.04%); split: -0.00%, +0.04%
Latency: 26261246 -> 26261921 (+0.00%); split: -0.00%, +0.00%
InvThroughput: 5363675 -> 5363760 (+0.00%); split: -0.00%, +0.00%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Fixes: 65f95ae74e9c ("aco/insert_NOPs: implement VALU -> VALU case for VALUReadSGPRHazard on GFX12")
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35387>
---
 src/amd/compiler/aco_insert_NOPs.cpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/amd/compiler/aco_insert_NOPs.cpp b/src/amd/compiler/aco_insert_NOPs.cpp
index 33aface7a8e..a7116b20259 100644
--- a/src/amd/compiler/aco_insert_NOPs.cpp
+++ b/src/amd/compiler/aco_insert_NOPs.cpp
@@ -1606,9 +1606,9 @@ handle_instruction_gfx11(State& state, NOP_ctx_gfx11& ctx, aco_ptr<Instruction>&
       }
 
       if (instr->isVALU() && !instr->definitions.empty()) {
-         PhysReg reg = instr->definitions[0].physReg();
+         PhysReg reg = instr->definitions.back().physReg();
          if (reg < m0 && ctx.sgpr_read_by_valu[reg / 2]) {
-            for (unsigned i = 0; i < instr->definitions[0].size(); i++)
+            for (unsigned i = 0; i < instr->definitions.back().size(); i++)
                ctx.sgpr_read_by_valu_then_wr_by_valu.set(reg + i);
          }
       } else if (instr->isSALU() && !instr->definitions.empty()) {