Firefly: A high-throughput hardware accelerator for spiking neural networks with efficient dsp and memory optimization
Spiking neural networks (SNNs) have been widely used due to their strong biological
interpretability and high-energy efficiency. With the introduction of the backpropagation …
interpretability and high-energy efficiency. With the introduction of the backpropagation …
Firefly v2: Advancing hardware support for high-performance spiking neural network with a spatiotemporal fpga accelerator
Spiking Neural Networks (SNNs) are expected to be a promising alternative to Artificial
Neural Networks (ANNs) due to their strong biological interpretability and high energy …
Neural Networks (ANNs) due to their strong biological interpretability and high energy …
Revealing Untapped DSP Optimization Potentials for FPGA-Based Systolic Matrix Engines
Systolic architectures are widely embraced by neural network accelerators for their superior
performance in highly parallelized computation. The DSP48E2s serve as dedicated …
performance in highly parallelized computation. The DSP48E2s serve as dedicated …