diff options
author | giuros01 <giuseppe.rossini@arm.com> | 2018-12-18 19:01:33 +0000 |
---|---|---|
committer | Giuseppe Rossini <giuseppe.rossini@arm.com> | 2018-12-21 13:10:28 +0000 |
commit | 8b6b4a959a49127d64293f8b60265f0f5ed486d4 (patch) | |
tree | df36cb65359c55d844f33b16e34df7827711ec20 /arm_compute/core/CL/kernels | |
parent | 8e5174c1b9531e8e9c457c2b976cf2c929825e73 (diff) | |
download | ComputeLibrary-8b6b4a959a49127d64293f8b60265f0f5ed486d4.tar.gz |
COMPMID-1836: Remove CLGEMMTranspose1xWKernel and replace with CLGEMMReshapeRHSMatrixKernel
Change-Id: Ic5a4f32657a155380684dcd4b44fbb608ef40cb4
Reviewed-on: https://review.mlplatform.org/418
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/core/CL/kernels')
-rw-r--r-- | arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyKernel.h | 4 | ||||
-rw-r--r-- | arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h | 6 |
2 files changed, 5 insertions, 5 deletions
diff --git a/arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyKernel.h b/arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyKernel.h index 82dcd93ce6..616c269b0d 100644 --- a/arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyKernel.h +++ b/arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyKernel.h @@ -58,7 +58,7 @@ public: * @param[in] input0 Input tensor containing the interleaved Matrix A. Data type supported: QASYMM8 * @param[in] input1 Input tensor containing the transposed1xW Matrix B. Data type supported: same as @p input0 * @param[out] output Output tensor to store the result of matrix multiplication. Data type supported: S32 - * @param[in] is_interleaved_transposed (Optional) True if input0 and input1 have been reshaped respectively using @ref CLGEMMInterleave4x4Kernel and @ref CLGEMMTranspose1xWKernel + * @param[in] is_interleaved_transposed (Optional) True if input0 and input1 have been reshaped respectively using @ref CLGEMMInterleave4x4Kernel and @ref CLGEMMReshapeRHSMatrixKernel * @param[in] reshape_info (Optional) GEMM reshape info. If is_interleaved_transposed = true, this object must contain the information to understand how the matrix A and matrix B have been reshaped */ void configure(const ICLTensor *input0, const ICLTensor *input1, ICLTensor *output, bool is_interleaved_transposed = true, const GEMMReshapeInfo &reshape_info = GEMMReshapeInfo()); @@ -67,7 +67,7 @@ public: * @param[in] input0 Input tensor info containing the interleaved Matrix A. Data type supported: QASYMM8 * @param[in] input1 Input tensor info containing the transposed Matrix B. Data type supported: same as @p input0 * @param[in] output Output tensor info to store the result of matrix multiplication. Data type supported: S32 - * @param[in] is_interleaved_transposed True if input0 and input1 have been reshaped respectively using @ref CLGEMMInterleave4x4Kernel and @ref CLGEMMTranspose1xWKernel + * @param[in] is_interleaved_transposed True if input0 and input1 have been reshaped respectively using @ref CLGEMMInterleave4x4Kernel and @ref CLGEMMReshapeRHSMatrixKernel * @param[in] reshape_info GEMM reshape info. If is_interleaved_transposed = true, this object must contain the information to understand how the matrix A and matrix B have been reshaped * * @return a status diff --git a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h index f61c330de6..ce37787862 100644 --- a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h +++ b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h @@ -32,7 +32,7 @@ class ICLTensor; /** OpenCL kernel to multiply two input matrices "A" and "B" . All elements of the output matrix will be multiplied by alpha * - * @note If the input tensors @p input0 and @p input1 have been reshaped respectively with @ref CLGEMMInterleave4x4Kernel" and @ref CLGEMMTranspose1xWKernel, + * @note If the input tensors @p input0 and @p input1 have been reshaped respectively with @ref CLGEMMInterleave4x4Kernel" and @ref CLGEMMReshapeRHSMatrixKernel, * the flag @p is_interleaved_transposed must be set to true * * @attention The second input tensor must have at least 2 dimensions (matrix) @@ -57,7 +57,7 @@ public: * @param[in] input1 Input tensor containing the Matrix B. Data type supported: same as @p input0 * @param[out] output Output tensor to store the result of matrix multiplication. Data type supported: same as @p input0 * @param[in] alpha Weight of the matrix product - * @param[in] is_interleaved_transposed (Optional) True if input0 and input1 have been reshaped respectively using @ref CLGEMMInterleave4x4Kernel and @ref CLGEMMTranspose1xWKernel + * @param[in] is_interleaved_transposed (Optional) True if input0 and input1 have been reshaped respectively using @ref CLGEMMInterleave4x4Kernel and @ref CLGEMMReshapeRHSMatrixKernel * @param[in] reshape_info (Optional) GEMM reshape info. If is_interleaved_transposed = true, this object must contain the information to understand how the matrix A and matrix B have been reshaped * @param[in] fp_mixed_precision (Optional) Use wider accumulators (32 bit instead of 16 for FP16) to improve accuracy * @@ -70,7 +70,7 @@ public: * @param[in] input1 Input tensor containing the Matrix B. Data type supported: same as @p input0 * @param[in] output Output tensor to store the result of matrix multiplication. Data type supported: same as @p input0 * @param[in] alpha Weight of the matrix product - * @param[in] is_interleaved_transposed True if input0 and input1 have been reshaped respectively using @ref CLGEMMInterleave4x4Kernel and @ref CLGEMMTranspose1xWKernel + * @param[in] is_interleaved_transposed True if input0 and input1 have been reshaped respectively using @ref CLGEMMInterleave4x4Kernel and @ref CLGEMMReshapeRHSMatrixKernel * @param[in] reshape_info GEMM reshape info. If is_interleaved_transposed = true, this object must contain the information to understand how the matrix A and matrix B have been reshaped * @param[in] gpu_target GPU Target * @param[in] fp_mixed_precision (Optional) Use wider accumulators (32 bit instead of 16 for FP16) to improve accuracy |