paper-with-me

Papers

Efficient Quantized Sparse Matrix Operations on Tensor Cores

2022-09-14 · Shigang Li, Kazuki Osawa, Torsten Hoefler

The exponentially growing model size drives the continued success of deep learning, but it brings prohibitive computation and memory cost. From the algorithm perspective, model sparsification and quantization have been studied to alleviate the problem. From the architecture perspective, hardware vendors provide Tensor cores for acceleration. However, it is very challenging to gain practical speedups from sparse, low-precision matrix operations on Tensor cores, because of the strict requirements for data layout and lack of support for efficiently manipulating the low-precision integers. We propose Magicube, a high-performance sparse-matrix library for low-precision integers on Tensor cores. Magicube supports SpMM and SDDMM, two major sparse operations in deep learning with mixed precision. Experimental results on an NVIDIA A100 GPU show that Magicube achieves on average 1.44x (up to 2.37x) speedup over the vendor-optimized library for sparse kernels, and 1.43x speedup over the state-of-the-art with a comparable accuracy for end-to-end sparse Transformer inference.

📄 PDF Abstract BibTeX arXiv:2209.06979

Code (1)

shigangli/magicube 공식 구현 pytorch

Tasks

GPUQuantization

Methods 이 논문이 사용한 방법론

Library 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Position-Wise Feed-Forward Layer 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Fused3S: Fast Sparse Attention on Tensor Cores

2025-05-12 · Zitong Li, Aparna Chandramowlishwaran

Sparse attention is a core building block in many leading neural network models, from graph-structured learning to sparse sequence modeling. It can be decomposed into a sequence of three sparse matrix operations (3S): sa…

GPU

Quantized sparse PCA for neural network weight compression

2021-09-29 · Andrey Kuzmin, Mart van Baalen, Markus Nagel, Arash Behboodi

In this paper, we introduce a novel method of weight compression. In our method, we store weight tensors as sparse, quantized matrix factors, whose product is computed on the fly during inference to generate the target m…

Quantization

Quantized Sparse Weight Decomposition for Neural Network Compression

2022-07-22 · Andrey Kuzmin, Mart van Baalen, Markus Nagel, Arash Behboodi

In this paper, we introduce a novel method of neural network weight compression. In our method, we store weight tensors as sparse, quantized matrix factors, whose product is computed on the fly during inference to genera…

Neural Network CompressionQuantization

Accelerating Sparse Graph Neural Networks with Tensor Core Optimization

2024-12-16 · Ka Wai Wu

Graph neural networks (GNNs) have seen extensive application in domains such as social networks, bioinformatics, and recommendation systems. However, the irregularity and sparsity of graph data challenge traditional comp…

Computational EfficiencyGPURecommendation Systems

Tensor Recovery from Noisy and Multi-Level Quantized Measurements

2019-12-05 · Ren Wang, Meng Wang, JinJun Xiong

Higher-order tensors can represent scores in a rating system, frames in a video, and images of the same subject. In practice, the measurements are often highly quantized due to the sampling strategies or the quality of d…

Quantization