COMPMID-662: Integrated the new a64_s8_gemm_12x8 + dot product kernel into ACL.
Change-Id: Id8f919e486a132fc58346c9f84fccbeeb83d19b3
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/94233
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
diff --git a/arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h b/arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h
index 670274b..f145eb6 100644
--- a/arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h
+++ b/arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h
@@ -35,8 +35,8 @@
* @note @ref NEGEMMLowpMatrixMultiplyKernel low precision matrix product kernel
* This kernel performs the following computation:
*
- * -# Convert a values from uint8 to int32
- * -# Convert b values from uint8 to int32
+ * -# Convert a values from int8 to int32
+ * -# Convert b values from int8 to int32
* -# Compute the int32 matrix product of the resulting a * b and store the result as int32
*
*/
@@ -58,7 +58,7 @@
* 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: U8
+ * @param[in] input0 Input tensor containing the interleaved Matrix A. Data type supported: S8
* @param[in] input1 Input tensor containing the transposed 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
*/
@@ -74,4 +74,4 @@
bool _slide_matrix_b;
};
} // namespace arm_compute
-#endif /*__ARM_COMPUTE_NEGEMMLOWPMATRIXMULTIPLYKERNEL_H__*/
\ No newline at end of file
+#endif /*__ARM_COMPUTE_NEGEMMLOWPMATRIXMULTIPLYKERNEL_H__*/