diff options
Diffstat (limited to 'src/gpu/cl/operators/ClGemm.h')
| -rw-r--r-- | src/gpu/cl/operators/ClGemm.h | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/src/gpu/cl/operators/ClGemm.h b/src/gpu/cl/operators/ClGemm.h index aac463f0b8..ea8a058fd5 100644 --- a/src/gpu/cl/operators/ClGemm.h +++ b/src/gpu/cl/operators/ClGemm.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2016-2022 Arm Limited. + * Copyright (c) 2016-2023 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -75,6 +75,9 @@ public: * * @note Whilst the first input tensor can be a vector, the second input tensor must be at least a matrix * + * @note Batched GEMM only allows RHS tensor's rank to be <= 3 + * @note Batched GEMM only supports broadcasting cases where RHS rank < LHS rank but not the other way around + * * @param[in] compile_context The compile context to be used. * @param[in] a First input tensor (Matrix or Vector A). Data types supported: F16/F32 * @param[in] b Second input tensor (Matrix B). Data type supported: same as @p a. |