From 732d8798ee83dc871c5468d4faaf63554678a119 Mon Sep 17 00:00:00 2001 From: Sheri Zhang Date: Fri, 17 Sep 2021 11:21:22 +0100 Subject: Update errata Resolves: COMPMID-4816 Signed-off-by: Sheri Zhang Change-Id: Ib8f80bb03dac470511f653b09ac96901c7dffd25 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6282 Tested-by: Arm Jenkins Reviewed-by: Reviewed-by: Giorgio Arena Comments-Addressed: Arm Jenkins --- docs/user_guide/errata.dox | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/user_guide/errata.dox b/docs/user_guide/errata.dox index 53d9059f86..2565faada7 100644 --- a/docs/user_guide/errata.dox +++ b/docs/user_guide/errata.dox @@ -61,7 +61,7 @@ namespace arm_compute - Convolution Layer uses QSYMM8_PER_CHANNEL as the data type of its weight - A wrong test configuration has been found in CLGEMMMatrixMultiplyReshapedOnlyRHS set of tests. - - Versions Affected: >= 20.11 + - Versions Affected: >= 20.11 && < 21.05 - Conditions: - Data type input: F32/F16 - Fused bounded relu activation with coefficient 'a' being negative @@ -87,7 +87,7 @@ namespace arm_compute - Compiled using Android NDK >= r18b in debug mode. - An issue has been identified with CLCast. - - Versions Affected: >= 18.11 + - Versions Affected: >= 18.11 && < 21.05 - Conditions: - Data type input: F32 - Data type output: All integer types -- cgit v1.2.1