aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h
diff options
context:
space:
mode:
authorIoan-Cristian Szabo <ioan-cristian.szabo@arm.com>2017-11-30 17:17:17 +0000
committerAnthony Barbier <anthony.barbier@arm.com>2018-11-02 16:47:40 +0000
commitb4e3e1c371d8091e86ee1c6e704057559bbe1554 (patch)
treed072c9f9d7471e4df9ef5aa6b50cb09c35b0c361 /arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h
parentc1b6e37233e0ebd21cb44bf8863a09c0ba5feeb1 (diff)
downloadComputeLibrary-b4e3e1c371d8091e86ee1c6e704057559bbe1554.tar.gz
COMPMID-617: Add validate support for NEON FullyConnectedLayer
Change-Id: I08987022c8d4cc335c00b8af27bd3edb8fe64d3b Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/111596 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Alexander Gilday <alexander.gilday@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Diffstat (limited to 'arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h')
-rw-r--r--arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h26
1 files changed, 16 insertions, 10 deletions
diff --git a/arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h b/arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h
index 4598e15b8e..d54522c678 100644
--- a/arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h
+++ b/arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h
@@ -58,22 +58,28 @@ public:
* @note If the output tensor is a matrix, the input matrices @p input0 and @p input1 should be the output of the kernels: @ref NEGEMMInterleave4x4Kernel and @ref NEGEMMTranspose1xWKernel
* These two kernels change the layout of the original matrices to be more cache-friendly.
*
- * @param[in] input0 Input tensor containing the interleaved Matrix A or the vector A. Data types supported: QS8/QS16/F16/F32
- * @param[in] input1 Input tensor containing the transposed Matrix B if the first input tensor A is not a vector.
- * If the output tensor is a vector, input1 must contain the matrix B not reshaped. 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] input0 Input tensor containing the interleaved Matrix A or the vector A. Data types supported: QS8/QS16/F16/F32
+ * @param[in] input1 Input tensor containing the transposed Matrix B if the first input tensor A is not a vector.
+ * If the output tensor is a vector, input1 must contain the matrix B not reshaped. 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 (Optional) True if input0 and input1 have been reshaped respectively using @ref NEGEMMInterleave4x4Kernel and @ref NEGEMMTranspose1xWKernel
+ * @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 ITensor *input0, const ITensor *input1, ITensor *output, float alpha);
+ void configure(const ITensor *input0, const ITensor *input1, ITensor *output, float alpha, bool is_interleaved, const GEMMReshapeInfo &reshape_info = GEMMReshapeInfo());
/** Static function to check if given info will lead to a valid configuration of @ref NEGEMMMatrixMultiplyKernel
*
- * @param[in] input0 Input tensor containing the Matrix A. Data types supported: QS8/QS16/F16/F32
- * @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] input0 Input tensor containing the interleaved Matrix A or the vector A. Data types supported: QS8/QS16/F16/F32
+ * @param[in] input1 Input tensor containing the transposed Matrix B if the first input tensor A is not a vector.
+ * If the output tensor is a vector, input1 must contain the matrix B not reshaped. 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 (Optional) True if input0 and input1 have been reshaped respectively using @ref NEGEMMInterleave4x4Kernel and @ref NEGEMMTranspose1xWKernel
+ * @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
*
* @return a status
*/
- static Status validate(const ITensorInfo *input0, const ITensorInfo *input1, const ITensorInfo *output);
+ static Status validate(const ITensorInfo *input0, const ITensorInfo *input1, const ITensorInfo *output, float alpha, bool is_interleaved, const GEMMReshapeInfo &reshape_info);
// Inherited methods overridden:
void run(const Window &window, const ThreadInfo &info) override;