From 8dde32d2dca1eb7bf9618cf2f1d5bfa62cf5585b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sa=C3=BAl?= <33020671+saul44203@users.noreply.github.com>
Date: Thu, 11 Jul 2024 07:08:49 +0200
Subject: [PATCH] arch-riscv: fix initialization for some vector reduction
 insts (#1340)

Vector reduce float (widening and non-widening) and integer (widening)
instructions initialize the reduce loop operation with the first element
of the destination register (i.e. `Vd[0]`).

Since all reductions per spec seem to be `Vd[0] = Vs1[0] + Vs2[*]`
(where `+` is an arbitrary binary op and `*` indicates all active
elements) gem5 will calculate this incorrectly if `Vd[0]` and/or
`Vs1[0]` are non-neutral for the operation (the later case being because
it's not taken into account at all).

To solve this we just have to initialize the reduction loop to `Vs1[0]`
(the non-widening integer reduction already does this).
---
 src/arch/riscv/isa/templates/vector_arith.isa | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/arch/riscv/isa/templates/vector_arith.isa b/src/arch/riscv/isa/templates/vector_arith.isa
index 31d2c26147..33e383b8bf 100644
--- a/src/arch/riscv/isa/templates/vector_arith.isa
+++ b/src/arch/riscv/isa/templates/vector_arith.isa
@@ -1826,7 +1826,7 @@ Fault
 
     auto reduce_loop =
         [&, this](const auto& f, const auto* _, const auto* vs2) {
-            vu tmp_val = Vd[0];
+            vu tmp_val = Vs1[0];
             for (uint32_t i = 0; i < this->microVl; i++) {
                 uint32_t ei = i + vtype_VLMAX(vtype, vlen, true) *
                     this->microIdx;
@@ -1876,7 +1876,7 @@ Fault
 
     auto reduce_loop =
         [&, this](const auto& f, const auto* _, const auto* vs2) {
-            vwu tmp_val = Vd[0];
+            vwu tmp_val = Vs1[0];
             for (uint32_t i = 0; i < this->microVl; i++) {
                 uint32_t ei = i + vtype_VLMAX(vtype, vlen, true) *
                     this->microIdx;
@@ -2230,7 +2230,7 @@ Fault
 
     auto reduce_loop =
         [&, this](const auto& f, const auto* _, const auto* vs2) {
-            vwu tmp_val = Vd[0];
+            vwu tmp_val = Vs1[0];
             for (uint32_t i = 0; i < this->microVl; i++) {
                 uint32_t ei = i + vtype_VLMAX(vtype, vlen, true) *
                     this->microIdx;