From 905786ea0c1abb2b8df36c56eae93a97823cace1 Mon Sep 17 00:00:00 2001
From: Milos Puzovic <milos.puzovic@arm.com>
Date: Tue, 26 Mar 2024 14:34:30 +0000
Subject: Added new NEON fixed format fast math mode hybrid kernel with maximum
 height of 6 for accumulation and updated heuristics

Change-Id: Ib52ea6825e164f4a8b8422eab7991b50af0b0d7c
Signed-off-by: Milos Puzovic <milos.puzovic@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/11354
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
---
 .../arm_gemm/kernels/a64_ffhybrid_fp32bf16fp32_mmla_4x24.hpp        | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'src/core/NEON/kernels/arm_gemm/kernels/a64_ffhybrid_fp32bf16fp32_mmla_4x24.hpp')

diff --git a/src/core/NEON/kernels/arm_gemm/kernels/a64_ffhybrid_fp32bf16fp32_mmla_4x24.hpp b/src/core/NEON/kernels/arm_gemm/kernels/a64_ffhybrid_fp32bf16fp32_mmla_4x24.hpp
index 923d008bb1..ac3cbf943f 100644
--- a/src/core/NEON/kernels/arm_gemm/kernels/a64_ffhybrid_fp32bf16fp32_mmla_4x24.hpp
+++ b/src/core/NEON/kernels/arm_gemm/kernels/a64_ffhybrid_fp32bf16fp32_mmla_4x24.hpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2022-2023 Arm Limited.
+ * Copyright (c) 2022-2024 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -88,8 +88,10 @@ public:
     {
         if (std::is_same<T, float>::value) {
             switch (ci->get_cpu_model()) {
+                case CPUModel::V1:
+                    return { 23.64 };
                 default:
-                    return { 28.48 };
+                    return { 16.89 };
             }
         }
 
-- 
cgit v1.2.1