diff options
| author | SiCongLi <sicong.li@arm.com> | 2021-10-06 15:25:57 +0100 |
|---|---|---|
| committer | SiCong Li <sicong.li@arm.com> | 2021-10-28 11:00:52 +0000 |
| commit | 1af5416917268692fcd4b34b1d7ffebd3a2aea8a (patch) | |
| tree | 81833ecad401eeb0101fb0d464728df8b699caf8 /src/core/CL/cl_kernels/common/gemm.cl | |
| parent | 49956ccf029ff4c1873e3a6702b5bede95d81f7a (diff) | |
| download | ComputeLibrary-1af5416917268692fcd4b34b1d7ffebd3a2aea8a.tar.gz | |
Add experimental PostOp interface to ClGemmMatrixMultiplyReshapedKernel Part 1
This interface supports the fusion of multiple elementwise operations
Partially resolves: COMPMID-4435
Change-Id: If68dd7dd98dcf239fde7cb1f0a4a6d4d1e899a6f
Signed-off-by: SiCongLi <sicong.li@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6483
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/CL/cl_kernels/common/gemm.cl')
| -rw-r--r-- | src/core/CL/cl_kernels/common/gemm.cl | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/src/core/CL/cl_kernels/common/gemm.cl b/src/core/CL/cl_kernels/common/gemm.cl index 431c97becc..dd03147ad6 100644 --- a/src/core/CL/cl_kernels/common/gemm.cl +++ b/src/core/CL/cl_kernels/common/gemm.cl @@ -2524,6 +2524,7 @@ __kernel void gemm_mm_reshaped_only_rhs_nt_texture(IMAGE_DECLARATION(lhs), /** This OpenCL kernel computes the matrix multiplication between 2 matrices. * The LHS matrix must be reshaped with @ref CLGEMMReshapeLHSMatrixKernel and the M0xK0 must be NOT transposed * The RHS matrix must be reshaped with @ref CLGEMMReshapeRHSMatrixKernel and the K0xN0 must be transposed + * @note This kernel is duplicated in /experimental/gemm_fused_post_ops/act_eltwise_op_act/gemm_mm_reshaped.cl * * @note The data type must be passed at compile time using -DDATA_TYPE (e.g. -DDATA_TYPE=float) * @note The data type used for the accumulators must be passed at compile time using -DDATA_TYPE_ACCUMULATOR (e.g. -DDATA_TYPE_ACCUMULATOR=float) @@ -2798,6 +2799,7 @@ __kernel void gemm_mm_reshaped_lhs_nt_rhs_t(IMAGE_DECLARATION(lhs), /** This OpenCL kernel computes the matrix multiplication between 2 matrices. The RHS matrix is stored in OpenCL image object. * The LHS matrix must be reshaped with @ref CLGEMMReshapeLHSMatrixKernel and the M0xK0 must be NOT transposed * The RHS matrix must be reshaped with @ref CLGEMMReshapeRHSMatrixKernel and the K0xN0 must be transposed + * @note This kernel is duplicated in /experimental/gemm_fused_post_ops/act_eltwise_op_act/gemm_mm_reshaped.cl * * @note -DOPENCL_IMAGE_SUPPORT must be passed at compile time in order to compile this OpenCL kernel * @note The data type must be passed at compile time using -DDATA_TYPE (e.g. -DDATA_TYPE=float) @@ -3179,6 +3181,7 @@ __kernel void gemm_mm_reshaped_lhs_nt_rhs_t_texture(IMAGE_DECLARATION(lhs), /** This OpenCL kernel computes the matrix multiplication between 2 matrices. * The LHS matrix must be reshaped with @ref CLGEMMReshapeLHSMatrixKernel and the M0xK0 must be transposed * The RHS matrix must be reshaped with @ref CLGEMMReshapeRHSMatrixKernel and the K0xN0 must be NOT transposed + * @note This kernel is duplicated in /experimental/gemm_fused_post_ops/act_eltwise_op_act/gemm_mm_reshaped.cl * * @note LHS_TRANSPOSE should be passed at compile time in order to compile this OpenCL kernel (e.g. -DLHS_TRANSPOSE). * @note If the first two dimensions of NDRange have been dispatched with "dummy_work_items" support, the option -DDUMMY_WORK_ITEMS must be passed at compile time. @@ -3560,6 +3563,7 @@ __kernel void gemm_mm_reshaped_lhs_t_rhs_nt(IMAGE_DECLARATION(lhs), /** This OpenCL kernel computes the matrix multiplication between 2 matrices. The RHS matrix is stored in OpenCL image object. * The LHS matrix must be reshaped with @ref CLGEMMReshapeLHSMatrixKernel and the M0xK0 must be transposed * The RHS matrix must be reshaped with @ref CLGEMMReshapeRHSMatrixKernel and the K0xN0 must be NOT transposed + * @note This kernel is duplicated in /experimental/gemm_fused_post_ops/act_eltwise_op_act/gemm_mm_reshaped.cl * * @note -DOPENCL_IMAGE_SUPPORT must be passed at compile time in order to compile this OpenCL kernel * @note LHS_TRANSPOSE should be passed at compile time in order to compile this OpenCL kernel (e.g. -DLHS_TRANSPOSE). @@ -3929,7 +3933,7 @@ __kernel void gemm_mm_reshaped_lhs_t_rhs_nt_texture(IMAGE_DECLARATION(lhs), #endif // defined(LHS_TRANSPOSE) -#endif // defined(M0) && defined(N0) && defined(K0) && defined(V0) && defined(H0) && defined(K) && defined(DATA_TYPE) +#endif // defined(M0) && defined(N0) && defined(K0) && defined(V0) && defined(H0) && defined(DATA_TYPE) && defined(DATA_TYPE_ACCUMULATOR) && defined(M) && defined(N) #if defined(M0) && defined(N0) && defined(K0) && defined(K) && defined(DATA_TYPE) |