论文标题
PCNN：基于模式的细粒定期修剪以优化CNN加速器
PCNN: Pattern-based Fine-Grained Regular Pruning towards Optimizing CNN Accelerators
论文作者
论文摘要
重量修剪是实现模型压缩的强大技术。我们提出了PCNN，这是一种定期的普通一维修剪法。提出了一种称为稀疏图案蒙版（SPM）的新型索引格式，以编码PCNN中的稀疏性。利用具有有限的修剪模式的SPM和具有相同长度的非零序列，PCNN可以有效地用于硬件。在VGG-16和RESNET-18上进行了评估，我们的PCNN可达到8.4倍的压缩率，精度损失仅为0.2％。我们还在55nm的过程中实现了一个模式感知的体系结构，达到9.0倍的速度和28.39的顶部/W效率，只有3.1％的芯片内存内存开销。
Weight pruning is a powerful technique to realize model compression. We propose PCNN, a fine-grained regular 1D pruning method. A novel index format called Sparsity Pattern Mask (SPM) is presented to encode the sparsity in PCNN. Leveraging SPM with limited pruning patterns and non-zero sequences with equal length, PCNN can be efficiently employed in hardware. Evaluated on VGG-16 and ResNet-18, our PCNN achieves the compression rate up to 8.4X with only 0.2% accuracy loss. We also implement a pattern-aware architecture in 55nm process, achieving up to 9.0X speedup and 28.39 TOPS/W efficiency with only 3.1% on-chip memory overhead of indices.
