diff options
| author | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2019-03-11 16:07:12 +0000 |
|---|---|---|
| committer | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2019-04-01 11:28:12 +0000 |
| commit | 62251f71792c06dbe4c9d1985816ba15bcad14e4 (patch) | |
| tree | d9d3778a2431486bffbcc80bd2cc51f3000ef116 /src/core/CL/cl_kernels/gemm.cl | |
| parent | b4a44ff3aa98d2b51f1621a7525db3f81108a1bd (diff) | |
| download | ComputeLibrary-62251f71792c06dbe4c9d1985816ba15bcad14e4.tar.gz | |
COMPMID-2002: Implement CLGEMMLowpMatrixMultiplyReshapedOnlyRHS - Transposed
Change-Id: I3907d151107766dc34749fe5710d7219e810b39f
Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-on: https://review.mlplatform.org/c/875
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Diffstat (limited to 'src/core/CL/cl_kernels/gemm.cl')
| -rw-r--r-- | src/core/CL/cl_kernels/gemm.cl | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/src/core/CL/cl_kernels/gemm.cl b/src/core/CL/cl_kernels/gemm.cl index 45c600cd37..da940082ae 100644 --- a/src/core/CL/cl_kernels/gemm.cl +++ b/src/core/CL/cl_kernels/gemm.cl @@ -1267,7 +1267,7 @@ __kernel void gemm_reshape_rhs_matrix_t(TENSOR3D_DECLARATION(src), * - M0 = 1, 2, 3, 4, 5, 6, 7, 8 * - N0 = 2, 3, 4, 8, 16 * - K0 = 2, 3, 4, 8, 16 - * - H0 > 1 + * - H0 >= 1 * * @note In case the input or output have to be reinterpreted as a 3D tensor, the following information must be passed at compile time: * -# REINTERPRET_INPUT_AS_3D: To reinterpret the input as 3D @@ -2401,6 +2401,8 @@ __kernel void gemm_mm_reshaped_only_rhs_nt(IMAGE_DECLARATION(lhs), * - M0 = 1, 2, 3, 4, 5, 6, 7, 8 * - N0 = 2, 3, 4, 8, 16 * - K0 = 2, 3, 4, 8, 16 + * - V0 >= 1 + * - H0 >= 1 * * @note In case the output has to be reinterpreted as a 3D tensor (i.e. output of convolution layer), the following information must be passed at compile time: * -# REINTERPRET_OUTPUT_AS_3D: To reinterpret the output as 3D |