diff options
Diffstat (limited to 'arm_compute')
| -rw-r--r-- | arm_compute/function_info/GEMMInfo.h | 8 | ||||
| -rw-r--r-- | arm_compute/runtime/NEON/functions/NEConvolutionLayer.h | 8 |
2 files changed, 10 insertions, 6 deletions
diff --git a/arm_compute/function_info/GEMMInfo.h b/arm_compute/function_info/GEMMInfo.h index c24762c0aa..a827c79fda 100644 --- a/arm_compute/function_info/GEMMInfo.h +++ b/arm_compute/function_info/GEMMInfo.h @@ -105,6 +105,7 @@ public: * @param[in] activation_info (Optional) Activation to apply after the matrix multiplication * @param[in] fixed_format (Optional) Specify the selection of fixed format kernels for variable weights support in GEMM. These kernels expect the weights tensor to be in amemory format that is fixed by the kernel itself. For more information, see arm_compute::WeightFormat. * @param[in] weight_format (Optional) arm_gemm:WeightFormat enumeration requested by the user. Default is arm_compute::WeightFormat::UNSPECIFIED. + * @param[in] pretranspose_B (Optional) Pretranspose matrix B (transposition of its lowest 2 dimensions), in addition to and before, any further transformations of B */ GEMMInfo(bool is_a_reshaped, bool is_b_reshaped, @@ -118,7 +119,8 @@ public: bool broadcast_bias = false, const ActivationLayerInfo &activation_info = ActivationLayerInfo(), bool fixed_format = false, - arm_compute::WeightFormat weight_format = arm_compute::WeightFormat::UNSPECIFIED) noexcept + arm_compute::WeightFormat weight_format = arm_compute::WeightFormat::UNSPECIFIED, + bool pretranspose_B = false) noexcept : _is_a_reshaped(is_a_reshaped), _is_b_reshaped(is_b_reshaped), _reshape_b_only_on_first_run(reshape_b_only_on_first_run), @@ -130,7 +132,7 @@ public: _fp_mixed_precision(fp_mixed_precision), _broadcast_bias(broadcast_bias), _pretranspose_A(false), - _pretranspose_B(false), + _pretranspose_B(pretranspose_B), _activation_info(activation_info), _fixed_format(fixed_format), _weight_format(weight_format) @@ -251,6 +253,8 @@ public: _pretranspose_A = flag; } /** Flag which specifies whether b should be pre-transposed if supported. + * More concretely, the "pre-transpose" is the transposition of the b tensor's lowest 2 dimensions + * If specified true, this pre-transpose will occur in addition to and before, any further transformations of the b matrix * * @return True if b should be pre-transposed else false. */ diff --git a/arm_compute/runtime/NEON/functions/NEConvolutionLayer.h b/arm_compute/runtime/NEON/functions/NEConvolutionLayer.h index cdf0f652e1..2d07980ade 100644 --- a/arm_compute/runtime/NEON/functions/NEConvolutionLayer.h +++ b/arm_compute/runtime/NEON/functions/NEConvolutionLayer.h @@ -21,8 +21,8 @@ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ -#ifndef ARM_COMPUTE_NECONVOLUTIONLAYER_H -#define ARM_COMPUTE_NECONVOLUTIONLAYER_H +#ifndef ACL_ARM_COMPUTE_RUNTIME_NEON_FUNCTIONS_NECONVOLUTIONLAYER_H +#define ACL_ARM_COMPUTE_RUNTIME_NEON_FUNCTIONS_NECONVOLUTIONLAYER_H #include "arm_compute/core/ITensorInfo.h" #include "arm_compute/core/Types.h" @@ -38,7 +38,7 @@ namespace arm_compute class ITensor; /** Basic function to simulate a convolution layer. This function calls one of the following functions: - * -# @ref cpu::CpuGemm (executed only in case GEMM is required for the operation) + * -# @ref cpu::CpuGemmConv2d (executed only in case GEMM is required for the operation) * -# @ref cpu::CpuWinogradConv2d (executed only in case Winograd is required for the operation) * -# @ref cpu::CpuDirectConv2d (executed only in case Direct Convolution is required for the operation) * -# @ref NEFFTConvolutionLayer (executed only in case FFT is required for the operation) @@ -196,4 +196,4 @@ private: std::unique_ptr<Impl> _impl; }; } // namespace arm_compute -#endif /* ARM_COMPUTE_NECONVOLUTIONLAYER_H */ +#endif // ACL_ARM_COMPUTE_RUNTIME_NEON_FUNCTIONS_NECONVOLUTIONLAYER_H |