2024 · 25 citations · 61 references
ComputingComputer EngineeringComputer ScienceComputer ArchitectureParallel AlgorithmsParallel ComputingAccelerator ArchitectureHardware AccelerationMatrix ComputationMemory Hierarchy OptimizationMemory Subsystem DesignParallel ArchitecturesData SparsityHigh PerformanceMatrix MultiplicationPower-performance-area TradeoffsScientific Computing AccelerationSparse Computation AccelerationSparse Linear AlgebraSparse Matrix Computation
Accelerating matrix multiplication is crucial to achieve high performance in many application domains, including neural networks, graph analytics, and scientific computing. These applications process matrices with a wide range of sparsities, from completely dense to highly sparse. Ideally, a single accelerator should handle matrices of all sparsity levels well. However, prior matrix multiplication accelerators each target a limited range of sparsity levels. We present Trapezoid, a versatile accelerator that performs matrix multiplication across all sparsity levels effectively. Trapezoid builds on a 2D spatial array design, which excels at dense matrix multiplication, and extends it with new hardware mechanisms that let it handle sparse inputs. We present a novel innerproduct-based dataflow with a multi-fiber intersection unit that handles mildly sparse matrices. Furthermore, novel Gustavsonbased dataflows and a multi-level memory hierarchy enable high performance on highly sparse matrices. Trapezoid’s hardware extensions are reused across dataflows to minimize area overheads. We evaluate Trapezoid on a broad range of dense and sparse matrix multiplication workloads. Trapezoid has gmean $19.7 \times$, $4.3 \times$, and $2.9 \times$ better performance/area than TPU, SIGMA, and Flexagon, prior state-of-the-art accelerators that target dense, mildly sparse, and highly sparse matrices, respectively.
61
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition · 2009 · 61.8K citations
Llama 2: Open Foundation and Fine-Tuned Chat Models
Hugo Touvron, Louis Martin, Kevin H. Stone et al. · arXiv (Cornell University) · 2023 · 2.6K citations · Full text
Channel Pruning for Accelerating Very Deep Neural Networks
Yihui He, Xiangyu Zhang, Jian Sun · 2017 · 2.5K citations
TSM: Temporal Shift Module for Efficient Video Understanding
Ji Lin, Chuang Gan, Song Han · 2019 · 2K citations