COMPMID-434 - Port CLGEMM to support 16 bit fixed point
Change-Id: I30aef3c7ecd1ee740c2a7f2ce65a63c7dcd66e49
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/79630
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
diff --git a/arm_compute/core/CL/kernels/CLGEMMInterleave4x4Kernel.h b/arm_compute/core/CL/kernels/CLGEMMInterleave4x4Kernel.h
index 9466b16..203e0fc 100644
--- a/arm_compute/core/CL/kernels/CLGEMMInterleave4x4Kernel.h
+++ b/arm_compute/core/CL/kernels/CLGEMMInterleave4x4Kernel.h
@@ -64,7 +64,7 @@
CLGEMMInterleave4x4Kernel &operator=(CLGEMMInterleave4x4Kernel &&) = default;
/** Initialise the kernel's input and output.
*
- * @param[in] input Input tensor. Data types supported: U8/S8/QS8/U16/S16/F16/U32/S32/F32
+ * @param[in] input Input tensor. Data types supported: U8/S8/QS8/U16/S16/QS16/F16/U32/S32/F32
* @param[out] output Output tensor. Data type supported: same as @p input
*/
void configure(const ICLTensor *input, ICLTensor *output);
diff --git a/arm_compute/core/CL/kernels/CLGEMMMatrixAdditionKernel.h b/arm_compute/core/CL/kernels/CLGEMMMatrixAdditionKernel.h
index b3a85a1..ada67d1 100644
--- a/arm_compute/core/CL/kernels/CLGEMMMatrixAdditionKernel.h
+++ b/arm_compute/core/CL/kernels/CLGEMMMatrixAdditionKernel.h
@@ -52,7 +52,7 @@
*
* @note The input and output tensors must have the same dimensions
*
- * @param[in] input Input tensor (Matrix C). Data types supported: QS8/F16/F32
+ * @param[in] input Input tensor (Matrix C). Data types supported: QS8/QS16/F16/F32
* @param[in, out] output Output tensor. If this kernel is used to finalize the GEMM result (alpha * AB + beta * C), output must contain the result obtained by @ref CLGEMMMatrixMultiplyKernel. Data type supported: same as @p input
* @param[in] beta Weight of matrix C
*/
diff --git a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h
index 7625358..dec63e0 100644
--- a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h
+++ b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h
@@ -53,7 +53,7 @@
CLGEMMMatrixMultiplyKernel &operator=(CLGEMMMatrixMultiplyKernel &&) = default;
/** Initialise the kernel's input, output and alpha
*
- * @param[in] input0 Input tensor containing the interleaved Matrix A or the vector A. Data types supported: QS8/F16/F32
+ * @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
diff --git a/arm_compute/core/CL/kernels/CLGEMMTranspose1xWKernel.h b/arm_compute/core/CL/kernels/CLGEMMTranspose1xWKernel.h
index 9657a2a..0e467aa 100644
--- a/arm_compute/core/CL/kernels/CLGEMMTranspose1xWKernel.h
+++ b/arm_compute/core/CL/kernels/CLGEMMTranspose1xWKernel.h
@@ -70,7 +70,7 @@
public:
/** Initialise the kernel's input and output.
*
- * @param[in] input Input tensor. Data types supported: U8/S8/QS8/U16/S16/F16/U32/S32/F32
+ * @param[in] input Input tensor. Data types supported: U8/S8/QS8/U16/S16/QS16/F16/U32/S32/F32
* @param[out] output Output tensor. Data type supported: same as @p input
*/
void configure(const ICLTensor *input, ICLTensor *output);
diff --git a/arm_compute/runtime/CL/functions/CLGEMM.h b/arm_compute/runtime/CL/functions/CLGEMM.h
index 080f497..9207efd 100644
--- a/arm_compute/runtime/CL/functions/CLGEMM.h
+++ b/arm_compute/runtime/CL/functions/CLGEMM.h
@@ -57,7 +57,7 @@
*
* @note Whilst the first input tensor can be a vector, the second input tensor must be at least a matrix
*
- * @param[in] a First input tensor (Matrix or Vector A). Data types supported: QS8/F16/F32
+ * @param[in] a First input tensor (Matrix or Vector A). Data types supported: QS8/QS16/F16/F32
* @param[in] b Second input tensor (Matrix B). Data type supported: same as @p a.
* @param[in] c Third input tensor (Matrix C). It can be a nullptr if just the multiplication between @p a and @p b is needed. Data type supported: same as @p a.
* @param[out] output Output tensor. Data type supported: same as @p a