search

neurosim / DNN_NeuroSim_V1.3

Benchmark framework of compute-in-memory based accelerators for deep neural network (inference engine focused)
62 stars 36 forks source link

Usage of `adderTreeNM` in `bufferOutputCM` #15

Closed sepehrMSP closed 2 years ago

sepehrMSP commented 2 years ago

Hi, In the ProcessingUnit.cpp, in ProcessingUnitCalculatePerformance function, in the following else clause: https://github.com/neurosim/DNN_NeuroSim_V1.3/blob/930c75772d43c733eb3090a5636761e058a16520/Inference_pytorch/NeuroSIM/ProcessingUnit.cpp#L542 which is used for conventional method, in the CalculatePower and CalculateLatency functions, adderTreeNM is used. However, I think it should be adderTreeCM. @neurosim @alu75

neurosim commented 2 years ago

Thanks for pointing it out! The typo has been corrected.