aboutsummaryrefslogtreecommitdiff
path: root/compute_kernel_writer/src/cl/CLTensorArgument.h
diff options
context:
space:
mode:
authorGunes Bayir <gunes.bayir@arm.com>2024-01-17 16:07:03 +0000
committerViet-Hoa Do <viet-hoa.do@arm.com>2024-02-01 16:00:34 +0000
commit2b9fa593a0a172bf36a02b5cdb840c6b9b361d7c (patch)
treea4e2d5ce46443a79a0778e4960462ce3edf106ec /compute_kernel_writer/src/cl/CLTensorArgument.h
parent7ab7fca87cca8775f82b0e9efec6a40975910c17 (diff)
downloadComputeLibrary-2b9fa593a0a172bf36a02b5cdb840c6b9b361d7c.tar.gz
Use the stable CKW API in the GPU dynamic fusion backend
- Refactor all kernels to work with the CKW stable API - Add support for sub-tile in the op_load/op_store CKW operator - Fix mismatch in resize - Add comments in all kernels written with CKW to help developers understand the structure of the code - Add texture image support in depthwise convolution written with CKW - Add support for different block sizes in depthwise convolution - Remove the use of the dynamic fusion helper functions. - Add support for floor in the op_unary() of CKW Resolves: COMPMID-6708, COMPMID-6743, COMPMID-6530 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Signed-off-by: Gunes Bayir <gunes.bayir@arm.com> Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Signed-off-by: Jakub Sujak <jakub.sujak@arm.com> Change-Id: I8104ce4d04a3138a1aeb0b84940e1f1c89e76069 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10914 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'compute_kernel_writer/src/cl/CLTensorArgument.h')
-rw-r--r--compute_kernel_writer/src/cl/CLTensorArgument.h3
1 files changed, 1 insertions, 2 deletions
diff --git a/compute_kernel_writer/src/cl/CLTensorArgument.h b/compute_kernel_writer/src/cl/CLTensorArgument.h
index 35df51422e..a79cf340bb 100644
--- a/compute_kernel_writer/src/cl/CLTensorArgument.h
+++ b/compute_kernel_writer/src/cl/CLTensorArgument.h
@@ -27,6 +27,7 @@
#include "ckw/types/TensorComponentType.h"
#include "ckw/types/TensorStorageType.h"
+#include "src/cl/CLTensorComponent.h"
#include "src/ITensor.h"
#include <memory>
@@ -39,8 +40,6 @@ namespace ckw
class TensorInfo;
class ITensorComponent;
-class CLTensorComponent;
-class CLTensorStorage;
/** OpenCL specific tensor argument
* Internally, the object keeps track of the components and storages used to minimize the number