aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/core/KernelDescriptors.h
diff options
context:
space:
mode:
authorJakub Sujak <jakub.sujak@arm.com>2023-08-24 14:01:20 +0100
committerJakub Sujak <jakub.sujak@arm.com>2023-09-04 14:41:16 +0000
commit0d27b2ee8d811d66693555ac1e7be44d93e662e2 (patch)
tree8b62a464a8bb9cd46702c8b5a60f3a97e3821b41 /arm_compute/core/KernelDescriptors.h
parent7ff03b67ba7ce669223f4d807e18fa3efa2f729b (diff)
downloadComputeLibrary-0d27b2ee8d811d66693555ac1e7be44d93e662e2.tar.gz
Remove legacy PostOps code
PostOps was the experimental interface for Dynamic Fusion. It is now replaced by the new Dynamic Fusion interface with code generation using the Compute Kernel Writer. Resolves: COMPMID-6190 Change-Id: I813b48facef2fd6f3aee332588886b4f9b3d33d8 Signed-off-by: Jakub Sujak <jakub.sujak@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10219 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/core/KernelDescriptors.h')
-rw-r--r--arm_compute/core/KernelDescriptors.h74
1 files changed, 35 insertions, 39 deletions
diff --git a/arm_compute/core/KernelDescriptors.h b/arm_compute/core/KernelDescriptors.h
index 305766e825..2bf5dee18c 100644
--- a/arm_compute/core/KernelDescriptors.h
+++ b/arm_compute/core/KernelDescriptors.h
@@ -21,12 +21,11 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
-#ifndef ACL_ARM_COMPUTE_CORE_KERNELDESCRIPTORS
-#define ACL_ARM_COMPUTE_CORE_KERNELDESCRIPTORS
+#ifndef ACL_ARM_COMPUTE_CORE_KERNELDESCRIPTORS_H
+#define ACL_ARM_COMPUTE_CORE_KERNELDESCRIPTORS_H
#include "arm_compute/core/PixelValue.h"
#include "arm_compute/core/Types.h"
-#include "arm_compute/core/experimental/IPostOp.h"
#include "arm_compute/function_info/ActivationLayerInfo.h"
namespace arm_compute
@@ -60,46 +59,43 @@ struct GEMMKernelInfo
{
GEMMKernelInfo() = default;
GEMMKernelInfo(
- unsigned int im,
- unsigned int in,
- unsigned int ik,
- unsigned int idepth_output_gemm3d,
- bool ireinterpret_input_as_3d,
- bool ibroadcast_bias,
- bool ifp_mixed_precision,
- bool ihas_pad_y,
- ActivationLayerInfo iactivation_info,
- int inmult_transpose1xW_width,
- int imult_interleave4x4_height,
- GEMMLHSMatrixInfo ilhs_info,
- GEMMRHSMatrixInfo irhs_info,
- int32_t ina_offset,
- int32_t inb_offset,
- const experimental::PostOpList<ITensorInfo *> &ipost_ops = experimental::PostOpList<ITensorInfo *> {})
+ unsigned int im,
+ unsigned int in,
+ unsigned int ik,
+ unsigned int idepth_output_gemm3d,
+ bool ireinterpret_input_as_3d,
+ bool ibroadcast_bias,
+ bool ifp_mixed_precision,
+ bool ihas_pad_y,
+ ActivationLayerInfo iactivation_info,
+ int inmult_transpose1xW_width,
+ int imult_interleave4x4_height,
+ GEMMLHSMatrixInfo ilhs_info,
+ GEMMRHSMatrixInfo irhs_info,
+ int32_t ina_offset,
+ int32_t inb_offset)
: m(im), n(in), k(ik), depth_output_gemm3d(idepth_output_gemm3d), reinterpret_input_as_3d(ireinterpret_input_as_3d), broadcast_bias(ibroadcast_bias), fp_mixed_precision(ifp_mixed_precision),
has_pad_y(ihas_pad_y), activation_info(iactivation_info), mult_transpose1xW_width(inmult_transpose1xW_width), mult_interleave4x4_height(imult_interleave4x4_height), lhs_info(ilhs_info),
- rhs_info(irhs_info), a_offset(ina_offset), b_offset(inb_offset), post_ops(ipost_ops)
+ rhs_info(irhs_info), a_offset(ina_offset), b_offset(inb_offset)
{
}
- unsigned int m{ 0 }; /**< Number of LHS rows*/
- unsigned int n{ 0 }; /**< Number of RHS columns*/
- unsigned int k{ 0 }; /**< Number of LHS columns or RHS rows */
- unsigned int depth_output_gemm3d{ 0 }; /**< Depth of the output tensor in case is reinterpreted as 3D */
- bool reinterpret_input_as_3d{ false }; /**< Flag used to reinterpret the input as 3D */
- bool broadcast_bias{ false }; /**< Flag used to broadcast the bias addition */
- bool fp_mixed_precision{ false }; /**< Flag used to indicate wider accumulators (32 bit instead of 16 for FP16). */
- bool has_pad_y{ false }; /**< Flag used to indicate if the input/output tensors have internal pad on the y direction */
- ActivationLayerInfo activation_info{}; /**< Activation function to perform after the matrix multiplication */
- int mult_transpose1xW_width{ 1 }; /**< Multiplication factor for the width of the 1xW transposed block */
- int mult_interleave4x4_height{ 1 }; /**< Multiplication factor for the height of the 4x4 interleaved block */
- GEMMLHSMatrixInfo lhs_info{}; /**< LHS matrix information used to retrieve the number of rows processed by each thread */
- GEMMRHSMatrixInfo rhs_info{}; /**< RHS matrix information used for reshaping the RHS matrix */
- int32_t a_offset{ 0 }; /**< Offset to be added to each element of the matrix A */
- int32_t b_offset{ 0 }; /**< Offset to be added to each element of the matrix B */
- GEMMLowpOutputStageInfo output_stage{}; /**< GEMMLowp output stage information */
- experimental::PostOpList<ITensorInfo *> post_ops{}; /**< (EXPERIMENTAL_POST_OPS) Specifies a list of post ops to be fused after the main op. Note unsupported post ops would not be executed.
- * If specified, automatically disable the @ref activation_info */
+ unsigned int m{ 0 }; /**< Number of LHS rows*/
+ unsigned int n{ 0 }; /**< Number of RHS columns*/
+ unsigned int k{ 0 }; /**< Number of LHS columns or RHS rows */
+ unsigned int depth_output_gemm3d{ 0 }; /**< Depth of the output tensor in case is reinterpreted as 3D */
+ bool reinterpret_input_as_3d{ false }; /**< Flag used to reinterpret the input as 3D */
+ bool broadcast_bias{ false }; /**< Flag used to broadcast the bias addition */
+ bool fp_mixed_precision{ false }; /**< Flag used to indicate wider accumulators (32 bit instead of 16 for FP16). */
+ bool has_pad_y{ false }; /**< Flag used to indicate if the input/output tensors have internal pad on the y direction */
+ ActivationLayerInfo activation_info{}; /**< Activation function to perform after the matrix multiplication */
+ int mult_transpose1xW_width{ 1 }; /**< Multiplication factor for the width of the 1xW transposed block */
+ int mult_interleave4x4_height{ 1 }; /**< Multiplication factor for the height of the 4x4 interleaved block */
+ GEMMLHSMatrixInfo lhs_info{}; /**< LHS matrix information used to retrieve the number of rows processed by each thread */
+ GEMMRHSMatrixInfo rhs_info{}; /**< RHS matrix information used for reshaping the RHS matrix */
+ int32_t a_offset{ 0 }; /**< Offset to be added to each element of the matrix A */
+ int32_t b_offset{ 0 }; /**< Offset to be added to each element of the matrix B */
+ GEMMLowpOutputStageInfo output_stage{}; /**< GEMMLowp output stage information */
};
/** Compute descriptor used by the depthwise convolution native kernel */
@@ -240,4 +236,4 @@ struct MatMulKernelInfo
bool export_rhs_to_cl_image{ false }; /**< Flag to know whether the RHS tensor should be exported to cl_image*/
};
} // namespace arm_compute
-#endif /* ACL_ARM_COMPUTE_CORE_KERNELDESCRIPTORS */
+#endif // ACL_ARM_COMPUTE_CORE_KERNELDESCRIPTORS_H