2023 · 10 citations · 23 references
ComputingComputer EngineeringComputer ScienceArtificial IntelligenceComputer ArchitectureMachine LearningAccelerator ArchitectureData CompressionDeep LearningHardware AccelerationNeural NetworksScalable Machine LearningCompression RatioDeep Learning AccelerationDeep Learning AcceleratorsHigh PerformanceMemory Access LatencyModel Compression
Tensor-train (TT) decomposition enables ultra-high compression ratio, making the deep neural network (DNN) accelerators based on this method very attractive. TIE, the state-of-the-art TT based DNN accelerator, achieved high performance by leveraging a compact inference scheme to remove unnecessary computations and memory access. However, TIE increases memory costs for stage-wise intermediate results and additional intra-layer data transfer, leading to limited speedups even the models are highly compressed.
23
Channel Pruning for Accelerating Very Deep Neural Networks
Yihui He, Xiangyu Zhang, Jian Sun · 2017 · 2.5K citations
Yu‐Hsin Chen, Joel Emer, Vivienne Sze · ACM SIGARCH Computer Architecture News · 2016 · 1.2K citations
PipeLayer: A Pipelined ReRAM-Based Accelerator for Deep Learning
Linghao Song, Xuehai Qian, Hai Li et al. · 2017 · 821 citations
Cambricon-X: An accelerator for sparse neural networks
Shijin Zhang, Zidong Du, Lei Zhang et al. · 2016 · 597 citations
Alexander Novikov, Dmitry Podoprikhin, Anton Osokin et al. · arXiv (Cornell University) · 2015 · 499 citations · Full text