aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h
diff options
context:
space:
mode:
authorGeorgios Pinitas <georgios.pinitas@arm.com>2017-11-16 19:24:39 +0000
committerAnthony Barbier <anthony.barbier@arm.com>2018-11-02 16:35:24 +0000
commita3b1b469276b10484cd45901ae3a4b48b506caa9 (patch)
tree8c91176708bdede785edbb98c73ce0a479dff243 /arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h
parentfc35b51d598d12e2a0895ed82d2368f07df68829 (diff)
downloadComputeLibrary-a3b1b469276b10484cd45901ae3a4b48b506caa9.tar.gz
COMPMID-667: Add validation static method to NEON GEMMlowp
Change-Id: I8a470cc1351593ad8eeaf4ec92e04865e83d4f3c Reviewed-on: http://mpd-gerrit.cambridge.arm.com/96147 Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Diffstat (limited to 'arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h')
-rw-r--r--arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h11
1 files changed, 10 insertions, 1 deletions
diff --git a/arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h b/arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h
index e9bfe4ea07..d9986b6cdd 100644
--- a/arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h
+++ b/arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h
@@ -58,11 +58,20 @@ public:
* The input matrices @p input0 and @p input1 must 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. Data type supported: ASYMM8
+ * @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
*/
void configure(const ITensor *input0, const ITensor *input1, ITensor *output);
+ /** Static function to check if given info will lead to a valid configuration of @ref NEGEMMLowpMatrixMultiplyKernel
+ *
+ * @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
+ *
+ * @return an error status
+ */
+ static Error validate(const ITensorInfo *input0, const ITensorInfo *input1, const ITensorInfo *output);
// Inherited methods overridden:
void run(const Window &window, const ThreadInfo &info) override;