activity
20232026
most citedAnatomy of High-Performance GEMM with Online Fault Tolerance on GPUs

13 citations · 63 across the 28 of their papers we have counts for

collaborators
Showing 2025Show all

11 papers · 1 filter

astro-ph.HE2025

A Giant Peanut-shaped Ultra-High-Energy Gamma-Ray Emitter Off the Galactic Plane

Zhen Cao, Felix Aharonian, Yunxiang Bai +312

Ultra-high-energy (UHE), exceeding 100 TeV (10^12 electronvolts), γ-rays manifests extreme particle acceleration in astrophysical sources. Recent observations by γ-ray telescopes,…

physics.ins-det2025

A borehole muon detector with SiPM-on-tile technology

Miguel Arratia, Jiajun Huang, Sean Preins +3

We developed a compact and rugged muon detector designed for deployment in boreholes. The detector uses a SiPM-on-tile approach in which silicon photomultipliers are directly coupl…

cs.DC2025★ 6 cited

Boosting Scientific Error-Bounded Lossy Compression through Optimized Synergistic Lossy-Lossless Orchestration

Shixun Wu, Jinwen Pan, Jinyang Liu +8

As high-performance computing architectures evolve, more scientific computing workflows are being deployed on advanced computing platforms such as GPUs. These workflows can produce…

cs.DC2025

GPZ: GPU-Accelerated Lossy Compressor for Particle Data

Ruoyu Li, Yafan Huang, Longtao Zhang +10

Particle-based simulations and point-cloud applications generate massive, irregular datasets that challenge storage, I/O, and real-time analytics. Traditional compression technique…

cs.DC2025

IPComp: Interpolation Based Progressive Lossy Compression for Scientific Applications

Zhuoxun Yang, Sheng Di, Longtao Zhang +6

Compression is a crucial solution for data reduction in modern scientific applications due to the exponential growth of data from simulations, experiments, and observations. Compre…

cs.DC2025★ 1 cited

FT-Transformer: Resilient and Reliable Transformer with End-to-End Fault Tolerant Attention

Huangliang Dai, Shixun Wu, Jiajun Huang +4

Transformer models rely on High-Performance Computing (HPC) resources for inference, where soft errors are inevitable in large-scale systems, making the reliability of the model pa…

physics.ins-det2025

Measurement of SiPM Dark Currents and Annealing Recovery for Fluences Expected in ePIC Calorimeters at the Electron-Ion Collider

Jiajun Huang, Sean Preins, Ryan Tsiao +3

Silicon photomultipliers (SiPMs) will be used to read out all calorimeters in the ePIC experiment at the Electron-Ion Collider (EIC). A thorough characterization of the radiation d…

astro-ph.IM2025★ 1 cited

The CONDOR Observatory: A Gamma-Ray Observatory with a 100 GeV Threshold at 5300 Meters Above Sea Level

Miguel Arratia, Will Brooks, Jiajun Huang +8

We present the design of the Compact Network of Detectors with Orbital Range (CONDOR), a proposed high-altitude gamma-ray and cosmic-ray (CR) observatory set to become the highest…

cs.DC2025

Can Tensor Cores Benefit Memory-Bound Kernels? (No!)

Lingqi Zhang, Jiajun Huang, Sheng Di +2

Tensor cores are specialized processing units within GPUs that have demonstrated significant efficiency gains in compute-bound applications such as Deep Learning Training by accele…

cs.DC2025

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…

physics.ins-det2025★ 2 cited

First-Ever Deployment of a SiPM-on-Tile Calorimeter in a Collider: A Parasitic Test with 200 GeV Collisions at RHIC

Weibin Zhang, Sean Preins, Jiajun Huang +7

We describe the testing of a prototype SiPM-on-tile iron-scintillator calorimeter at the Relativistic Heavy Ion Collider (RHIC) during its 200 GeV run in 2024. The prototype,…