diff options
| author | Derek Lamberti <derek.lamberti@arm.com> | 2019-04-15 18:37:35 +0100 |
|---|---|---|
| committer | derek.lamberti <derek.lamberti@arm.com> | 2019-04-16 13:50:11 +0000 |
| commit | 0790dcea1056298d63f97dec904c8ade5d21f439 (patch) | |
| tree | d75967e2eabe39ec08dc928fa77a7d4a51d85c5d /src/backends/cl/workloads/ClMergerWorkload.hpp | |
| parent | b98bbcfa2a809c4ad025883c059ae49c82b37cbd (diff) | |
| download | armnn-0790dcea1056298d63f97dec904c8ade5d21f439.tar.gz | |
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 <derek.lamberti@arm.com>
Diffstat (limited to 'src/backends/cl/workloads/ClMergerWorkload.hpp')
| -rw-r--r-- | src/backends/cl/workloads/ClMergerWorkload.hpp | 3 |
1 files changed, 1 insertions, 2 deletions
diff --git a/src/backends/cl/workloads/ClMergerWorkload.hpp b/src/backends/cl/workloads/ClMergerWorkload.hpp index 8189a1b24a..1c2f823b7a 100644 --- a/src/backends/cl/workloads/ClMergerWorkload.hpp +++ b/src/backends/cl/workloads/ClMergerWorkload.hpp @@ -24,8 +24,7 @@ public: void Execute() const override; private: - mutable arm_compute::CLConcatenateLayer m_Layer; - bool m_Execute; + mutable std::unique_ptr<arm_compute::CLConcatenateLayer> m_Layer; }; } //namespace armnn |