222 citations · 423 across the 6 of their papers we have counts for
6 papers
Retrospective: EIE: Efficient Inference Engine on Sparse and Compressed Neural Network
Song Han, Xingyu Liu, Huizi Mao +4
EIE proposed to accelerate pruned and compressed neural networks, exploiting weight sparsity, activation sparsity, and 4-bit weight-sharing in neural network accelerators. Since pu…
Interstellar: Using Halide's Scheduling Language to Analyze DNN Accelerators
Xuan Yang, Mingyu Gao, Qiaoyi Liu +9
We show that DNN accelerator micro-architectures and their program mappings represent specific choices of loop order and hardware parallelism for computing the seven nested loops o…
Programming Heterogeneous Systems from an Image Processing DSL
Jing Pu, Steven Bell, Xuan Yang +4
Specialized image processing accelerators are necessary to deliver the performance and energy efficiency required by important applications in computer vision, computational photog…
FPMax: a 106GFLOPS/W at 217GFLOPS/mm2 Single-Precision FPU, and a 43.7GFLOPS/W at 74.6GFLOPS/mm2 Double-Precision FPU, in 28nm UTBB FDSOI
Jing Pu, Sameh Galal, Xuan Yang +2
FPMax implements four FPUs optimized for latency or throughput workloads in two precisions, fabricated in 28nm UTBB FDSOI. Each unit's parameters, e.g pipeline stages, booth encodi…
A Systematic Approach to Blocking Convolutional Neural Networks
Xuan Yang, Jing Pu, Blaine Burton Rister +6
Convolutional Neural Networks (CNNs) are the state of the art solution for many computer vision problems, and many researchers have explored optimized implementations. Most impleme…
EIE: Efficient Inference Engine on Compressed Deep Neural Network
Song Han, Xingyu Liu, Huizi Mao +4
State-of-the-art deep neural networks (DNNs) have hundreds of millions of connections and are both computationally and memory intensive, making them difficult to deploy on embedded…