aboutsummaryrefslogtreecommitdiff
path: root/src/backends/cl/workloads/ClConvertFp32ToFp16Workload.hpp
diff options
context:
space:
mode:
authorKevin May <kevin.may@arm.com>2022-03-02 12:11:31 +0000
committerKevin May <kevin.may@arm.com>2022-03-02 12:11:31 +0000
commit998a20832fd511de75c2cd935b7a0e851e91156d (patch)
tree0839bcc53555b06887708cb56429735b8315472d /src/backends/cl/workloads/ClConvertFp32ToFp16Workload.hpp
parent138a88cf568fbc420a310344903f7eb9dec8e1e3 (diff)
downloadarmnn-998a20832fd511de75c2cd935b7a0e851e91156d.tar.gz
Typo in Guide
* Only file changed is shim/BuildGuideShimSupportLibrary.md * All other files are merge squash from Arm NN 22.02 Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Id82a6e9ac8abf74c1073c08744712f50e98dece0
Diffstat (limited to 'src/backends/cl/workloads/ClConvertFp32ToFp16Workload.hpp')
-rw-r--r--src/backends/cl/workloads/ClConvertFp32ToFp16Workload.hpp13
1 files changed, 13 insertions, 0 deletions
diff --git a/src/backends/cl/workloads/ClConvertFp32ToFp16Workload.hpp b/src/backends/cl/workloads/ClConvertFp32ToFp16Workload.hpp
index 1d777b5256..6ce563e4f4 100644
--- a/src/backends/cl/workloads/ClConvertFp32ToFp16Workload.hpp
+++ b/src/backends/cl/workloads/ClConvertFp32ToFp16Workload.hpp
@@ -9,6 +9,8 @@
#include <arm_compute/runtime/CL/functions/CLDepthConvertLayer.h>
+#include <cl/ICLTensorProxy.hpp>
+
namespace armnn
{
@@ -21,8 +23,19 @@ public:
const arm_compute::CLCompileContext& clCompileContext);
virtual void Execute() const override;
+ bool SupportsTensorHandleReplacement() const override { return true;};
+
+ // Replace input tensor handle with the given TensorHandle
+ void ReplaceInputTensorHandle(ITensorHandle* tensorHandle, unsigned int slot) override;
+
+ // Replace output tensor handle with the given TensorHandle
+ void ReplaceOutputTensorHandle(ITensorHandle* tensorHandle, unsigned int slot) override;
private:
mutable arm_compute::CLDepthConvertLayer m_Layer;
+ virtual void Reconfigure();
+
+ std::unique_ptr<ICLTensorProxy> m_InputProxy;
+ std::unique_ptr<ICLTensorProxy> m_OutputProxy;
};
arm_compute::Status ClConvertFp32ToFp16WorkloadValidate(const TensorInfo& input, const TensorInfo& output);