103 citations · 141 across the 17 of their papers we have counts for
12 papers · 1 filter
TurboFNO: High-Performance Fourier Neural Operator with Fused FFT-GEMM-iFFT on GPU
Shixun Wu, Yujia Zhai, Huangliang Dai +4
Fourier Neural Operators (FNO) are widely used for learning partial differential equation solution operators. However, FNO lacks architecture-aware optimizations,with its Fourier l…
ZCCL: Significantly Improving Collective Communication With Error-Bounded Lossy Compression
Jiajun Huang, Sheng Di, Xiaodong Yu +12
With the ever-increasing computing power of supercomputers and the growing scale of scientific applications, the efficiency of MPI collective communication turns out to be a critic…
TurboFFT: Co-Designed High-Performance and Fault-Tolerant Fast Fourier Transform on GPUs
Shixun Wu, Yujia Zhai, Jinyang Liu +6
GPU-based fast Fourier transform (FFT) is extremely important for scientific computing and signal processing. However, we find the inefficiency of existing FFT libraries and the ab…
FT K-means: A High-Performance K-means on GPU with Fault Tolerance
Shixun Wu, Yitong Ding, Yujia Zhai +8
K-means is a widely used algorithm in clustering, however, its efficiency is primarily constrained by the computational cost of distance computing. Existing implementations suffer…
TurboFFT: A High-Performance Fast Fourier Transform with Fault Tolerance on GPU
Shixun Wu, Yujia Zhai, Jinyang Liu +6
The Fast Fourier Transform (FFT), as a core computation in a wide range of scientific applications, is increasingly threatened by reliability issues. In this paper, we introduce Tu…
gZCCL: Compression-Accelerated Collective Communication Framework for GPU Clusters
Jiajun Huang, Sheng Di, Xiaodong Yu +11
GPU-aware collective communication has become a major bottleneck for modern computing platforms as GPU computing power rapidly rises. A traditional approach is to directly integrat…
Accelerating MPI Collectives with Process-in-Process-based Multi-object Techniques
Jiajun Huang, Kaiming Ouyang, Yujia Zhai +8
In the exascale computing era, optimizing MPI collective performance in high-performance computing (HPC) applications is critical. Current algorithms face performance degradation d…
FT-GEMM: A Fault Tolerant High Performance GEMM Implementation on x86 CPUs
Shixun Wu, Yujia Zhai, Jiajun Huang +2
General matrix/matrix multiplication (GEMM) is crucial for scientific computing and machine learning. However, the increased scale of the computing platforms raises concerns about…
Anatomy of High-Performance GEMM with Online Fault Tolerance on GPUs
Shixun Wu, Yujia Zhai, Jinyang Liu +4
General Matrix Multiplication (GEMM) is a crucial algorithm for various applications such as machine learning and scientific computing, and an efficient GEMM implementation is esse…
An Optimized Error-controlled MPI Collective Framework Integrated with Lossy Compression
Jiajun Huang, Sheng Di, Xiaodong Yu +11
With the ever-increasing computing power of supercomputers and the growing scale of scientific applications, the efficiency of MPI collective communications turns out to be a criti…
FT-BLAS: A High Performance BLAS Implementation With Online Fault Tolerance
Yujia Zhai, Elisabeth Giem, Quan Fan +3
Basic Linear Algebra Subprograms (BLAS) is a core library in scientific computing and machine learning. This paper presents FT-BLAS, a new implementation of BLAS routines that not…
FT-CNN: Algorithm-Based Fault Tolerance for Convolutional Neural Networks
Kai Zhao, Sheng Di, Sihuan Li +6
Convolutional neural networks (CNNs) are becoming more and more important for solving challenging and critical problems in many fields. CNN inference applications have been deploye…