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>
diff --git a/src/dynamic_fusion/sketch/gpu/operators/GpuPool2d.cpp b/src/dynamic_fusion/sketch/gpu/operators/GpuPool2d.cpp
index 55c604a..2d04f75 100644
--- a/src/dynamic_fusion/sketch/gpu/operators/GpuPool2d.cpp
+++ b/src/dynamic_fusion/sketch/gpu/operators/GpuPool2d.cpp
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2023 Arm Limited.
+ * Copyright (c) 2023-2024 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -25,6 +25,7 @@
#include "arm_compute/dynamic_fusion/sketch/gpu/operators/GpuPool2d.h"
#include "arm_compute/core/CL/CLCompileContext.h"
+#include "arm_compute/core/Error.h"
#include "arm_compute/core/experimental/Types.h"
#include "arm_compute/core/utils/misc/ShapeCalculator.h"
#include "arm_compute/core/Validate.h"
@@ -52,10 +53,12 @@
const Pool2dAttributes &attributes,
const GpuPool2dSettings &settings)
{
+ ARM_COMPUTE_UNUSED(settings);
+
if (dst->total_size() == 0U)
{
auto shape = misc::shape_calculator::compute_pool_shape(
- *src, convert_pool_attr_to_pool_info(attributes, settings.mixed_precision()));
+ *src, convert_pool_attr_to_pool_info(attributes, /* mixed_precision */ true));
auto_init_if_empty(*dst, src->clone()->set_tensor_shape(shape));
}
}
@@ -63,17 +66,6 @@
constexpr GpuOperatorType operator_type = GpuOperatorType::Complex;
} // namespace
-GpuPool2dSettings &GpuPool2dSettings::mixed_precision(bool mixed_precision)
-{
- _mixed_precision = mixed_precision;
- return *this;
-}
-
-bool GpuPool2dSettings::mixed_precision() const
-{
- return _mixed_precision;
-}
-
GpuPool2dSettings GpuPool2dSettings::use_inf_as_limit(bool use_inf_as_limit)
{
_use_inf_as_limit = use_inf_as_limit;