aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/core/KernelDescriptors.h
diff options
context:
space:
mode:
authorGian Marco Iodice <gianmarco.iodice@arm.com>2020-10-22 16:37:12 +0100
committerGian Marco Iodice <gianmarco.iodice@arm.com>2020-10-26 14:46:44 +0000
commit9ae06d4986bc3055f7786c1097b465bd321cf8eb (patch)
treeadb50e965f860893fe83e3937026056bf1f054c9 /arm_compute/core/KernelDescriptors.h
parent5f91041aef3eb7373d5d2cebcbe60f279da85904 (diff)
downloadComputeLibrary-9ae06d4986bc3055f7786c1097b465bd321cf8eb.tar.gz
COMPMID-3925: Dispatch CLGEMM with no padding y requirement
- Add has_pad_y flag in GEMMKernelInfo - Skip reinterpret as 3D in CLGEMMMatrixMultiplyReshapedOnlyRHSKernel if has_pad_y = false - Add test to validate CLGEMMMatrixMultiplyReshapedOnlyRHSkernel with had_pad_y = false/true - Configure two variants of CLGEMMMatrixMultiplyReshapedOnlyRHSKernel to run with has_pad_y = false/true in CLGEMM - Check if the lhs/dst tensors have pad y. If not, run CLGEMMMatrixMultiplyReshapedOnlyRHSKernel without padding requirement Change-Id: I68bb43389789736d676b899ac7c77fd9138babaf Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4248 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/core/KernelDescriptors.h')
-rw-r--r--arm_compute/core/KernelDescriptors.h4
1 files changed, 3 insertions, 1 deletions
diff --git a/arm_compute/core/KernelDescriptors.h b/arm_compute/core/KernelDescriptors.h
index 1ee1686fb1..ea46bfa5a6 100644
--- a/arm_compute/core/KernelDescriptors.h
+++ b/arm_compute/core/KernelDescriptors.h
@@ -64,6 +64,7 @@ struct GEMMKernelInfo
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,
@@ -72,7 +73,7 @@ struct GEMMKernelInfo
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),
- activation_info(iactivation_info), mult_transpose1xW_width(inmult_transpose1xW_width), mult_interleave4x4_height(imult_interleave4x4_height), lhs_info(ilhs_info), rhs_info(irhs_info),
+ 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)
{
}
@@ -84,6 +85,7 @@ struct GEMMKernelInfo
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 */