From 0790dcea1056298d63f97dec904c8ade5d21f439 Mon Sep 17 00:00:00 2001 From: Derek Lamberti Date: Mon, 15 Apr 2019 18:37:35 +0100 Subject: IVGCVSW-2957 MergerLayer subtensor optimization now backend agnostic + Update clframework pin + Cl and Neon Merger workloads updated to use MemoryLayout agnostic API + Workloads only use sub-tensor optimization if ALL input tensors are sub-tensors + Refactor LayerSupportCommon code to be a bit more succinct Change-Id: Ib61ad4ccbd767e924dff07e61022e0cda4069828 Signed-off-by: Derek Lamberti --- scripts/get_compute_library.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'scripts/get_compute_library.sh') diff --git a/scripts/get_compute_library.sh b/scripts/get_compute_library.sh index f3d1a8cb19..8a35bd3554 100755 --- a/scripts/get_compute_library.sh +++ b/scripts/get_compute_library.sh @@ -10,7 +10,7 @@ CMD=$( basename $0 ) # DEFAULT_CLFRAMEWORKREVISION="branches/arm_compute_19_02" # Release 19.02 # # For pinning to a revision use this: -DEFAULT_CLFRAMEWORKREVISION="a4bba9c594c4022c9f85192bb8fd3593ad1a8d3c" # COMPMID-1995: Fix 32-bit NEDepthwiseConvolution errors. +DEFAULT_CLFRAMEWORKREVISION="9e4824c909b14dbaf7106e9527b0ffa22ef09bdc" usage() { echo "Usage: $CMD (Use the default clframework SHA)" -- cgit v1.2.1