aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/core/CL
diff options
context:
space:
mode:
authorgiuros01 <giuseppe.rossini@arm.com>2018-12-18 19:01:33 +0000
committerGiuseppe Rossini <giuseppe.rossini@arm.com>2018-12-21 13:10:28 +0000
commit8b6b4a959a49127d64293f8b60265f0f5ed486d4 (patch)
treedf36cb65359c55d844f33b16e34df7827711ec20 /arm_compute/core/CL
parent8e5174c1b9531e8e9c457c2b976cf2c929825e73 (diff)
downloadComputeLibrary-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')
-rw-r--r--arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyKernel.h4
-rw-r--r--arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h6
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