aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/runtime/NEON/functions/NEGEMM.h
diff options
context:
space:
mode:
authorSang-Hoon Park <sang-hoon.park@arm.com>2021-05-17 17:04:50 +0100
committerSang-Hoon Park <sang-hoon.park@arm.com>2021-05-26 10:16:05 +0000
commitd89e2faa60d148f3c04e57032a28f1065a1be0e8 (patch)
treec95eb97f9c79198cb5db1232b497491df10614f2 /arm_compute/runtime/NEON/functions/NEGEMM.h
parent8b83d4684249bb96e27f95e11cf8f38a1c33b82b (diff)
downloadComputeLibrary-d89e2faa60d148f3c04e57032a28f1065a1be0e8.tar.gz
Create CpuGemmDirectConv2d
As the first phase of making NEGEMMConv2d stateless, CpuGemmDirectConv2d operator is created. Kernels and operators used by the operator use TensorInfo pointers instead of Tensor pointers. The CpuGemmDirectConv2d isn't completely stateless because it manages one intermediate tensor internally. This will be resolved by implementing memory injection mechanism with the following patches. Also, weight manager of CpuGemmAssemblyDispatch is disabled to enable this work. Implements: COMPMID-4506 Change-Id: Iec3ca6de29d98bef7ea95e8f4473d6dc0024a140 Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5672 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/runtime/NEON/functions/NEGEMM.h')
-rw-r--r--arm_compute/runtime/NEON/functions/NEGEMM.h3
1 files changed, 3 insertions, 0 deletions
diff --git a/arm_compute/runtime/NEON/functions/NEGEMM.h b/arm_compute/runtime/NEON/functions/NEGEMM.h
index 9df2e08956..6fa30bd545 100644
--- a/arm_compute/runtime/NEON/functions/NEGEMM.h
+++ b/arm_compute/runtime/NEON/functions/NEGEMM.h
@@ -24,6 +24,7 @@
#ifndef ARM_COMPUTE_NEGEMM_H
#define ARM_COMPUTE_NEGEMM_H
+#include "arm_compute/core/ITensorPack.h"
#include "arm_compute/runtime/IFunction.h"
#include "arm_compute/runtime/IMemoryManager.h"
#include "arm_compute/runtime/IWeightsManager.h"
@@ -144,6 +145,8 @@ private:
bool _run_activation;
bool _reshape_b_only_on_first_run;
bool _is_prepared;
+
+ ITensorPack _asm_glue_tensors{};
};
} // namespace arm_compute
#endif /*ARM_COMPUTE_NEGEMM_H */