Increase tolerance_num of Cpu RNNLayer tests

Instead of increasing the tolerance amount, we increase the number of elements we tolerate to 0.02 % of the whole tensor. This ensures we do not affect the tolerance for smaller tests.

This amount is set according to the number of elements above the threshold. it was 1 over 512 elements, 1/512 ~ 0.02 %.

Resolves: COMPMID-6932

Change-Id: I9d3ce29a3972aa8b9daea5288005a0a41a266328
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/11321
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
diff --git a/tests/validation/NEON/RNNLayer.cpp b/tests/validation/NEON/RNNLayer.cpp
index 14d9a5d..979aa0f 100644
--- a/tests/validation/NEON/RNNLayer.cpp
+++ b/tests/validation/NEON/RNNLayer.cpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2018-2021 Arm Limited.
+ * Copyright (c) 2018-2021, 2024 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -139,7 +139,7 @@
 FIXTURE_DATA_TEST_CASE(RunSmall, NERNNLayerFixture<half>, framework::DatasetMode::ALL, combine(datasets::SmallRNNLayerDataset(), framework::dataset::make("DataType", DataType::F16)))
 {
     // Validate output
-    validate(Accessor(_target), _reference, tolerance_f16, 0.f, abs_tolerance_f16);
+    validate(Accessor(_target), _reference, tolerance_f16, 0.02f, abs_tolerance_f16);
 }
 TEST_SUITE_END() // FP16
 #endif           /* __ARM_FEATURE_FP16_VECTOR_ARITHMETIC */