InfoX: An Energy-Efficient ReRAM Accelerator Design with Information-Lossless Low-Bit ADCs
TimeTuesday, July 12th10:30am - 10:52am PDT
Location3002, Level 3
In-memory and Near-memory Computing
DescriptionReRAM-based accelerators have shown great potential in neural network acceleration via in-memory analog computing.
However, high-precision analog-to-digital converters (ADCs), which are required by the ReRAM crossbars to achieve high-accuracy network model inference, play an essential role in the energy-efficiency of the accelerators.
Based on the discovery that the ADC precision requirements of crossbars are different, we propose the model-aware crossbarwise ADC precision assignment and the accompanied information-lossless low-bit ADCs to reduce power overhead without sacrificing model accuracy.
In experiments, the proposed information-lossless ReRAM accelerator, InfoX, only consumes 8.97% ADC energy of the SOTA baseline with no accuracy degradation at all.