aboutsummaryrefslogtreecommitdiff
path: root/src/core/NEON/wrapper/intrinsics/intrinsics.h
diff options
context:
space:
mode:
authorSang-Hoon Park <sang-hoon.park@arm.com>2020-10-13 23:34:09 +0100
committerSang-Hoon Park <sang-hoon.park@arm.com>2020-10-16 08:43:24 +0000
commite7280585b317f695a932be5981895377e174946d (patch)
tree3d5662a779d2c3bee9e45a2db27a27cd0275c9d5 /src/core/NEON/wrapper/intrinsics/intrinsics.h
parentcf343e3798d2a8c2ad2fcac488e4b78e2b5c968d (diff)
downloadComputeLibrary-e7280585b317f695a932be5981895377e174946d.tar.gz
COMPMID-3805: Fix SQRT non-zero output for zero input
- For AArch64, NEActivationLayerKernel uses vsqrt rather than vinvsqrt. - For non-AArch64, it masks values to ensure zero input results in zero output without producing NaN. - Test cases for FP16 and FP32's positive boundary values are added. Change-Id: Ic0104ee5d7045059c2e9bd052616a4a3b43a315d Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4150 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Diffstat (limited to 'src/core/NEON/wrapper/intrinsics/intrinsics.h')
-rw-r--r--src/core/NEON/wrapper/intrinsics/intrinsics.h1
1 files changed, 1 insertions, 0 deletions
diff --git a/src/core/NEON/wrapper/intrinsics/intrinsics.h b/src/core/NEON/wrapper/intrinsics/intrinsics.h
index 495321a6a1..070f3c7065 100644
--- a/src/core/NEON/wrapper/intrinsics/intrinsics.h
+++ b/src/core/NEON/wrapper/intrinsics/intrinsics.h
@@ -66,6 +66,7 @@
#include "src/core/NEON/wrapper/intrinsics/round.h"
#include "src/core/NEON/wrapper/intrinsics/setlane.h"
#include "src/core/NEON/wrapper/intrinsics/sin.h"
+#include "src/core/NEON/wrapper/intrinsics/sqrt.h"
#include "src/core/NEON/wrapper/intrinsics/store.h"
#include "src/core/NEON/wrapper/intrinsics/sub.h"
#include "src/core/NEON/wrapper/intrinsics/tanh.h"