3 papers
cs.AR2026
Bit-Accurate Modeling of GPU Matrix Multiply-Accumulate Units: Demystifying Numerical Discrepancy and Accuracy
Peichen Xie, Shuotao Xu, Yang Wang +2
Modern AI accelerators rely on matrix multiply-accumulate units (MMAUs), such as NVIDIA Tensor Cores and AMD Matrix Cores, to accelerate deep neural network workloads. MMAUs expose…
math.NA2026
Evaluating Numerical Accuracy in Mixed-Precision Computing by Dual-Delta Testing
Peichen Xie
Mixed-precision computing has become increasingly important in modern high-performance computing and machine learning applications. When implementing custom mixed-precision functio…
cs.LG2025
RepDL: Bit-level Reproducible Deep Learning Training and Inference
Peichen Xie, Xian Zhang, Shuo Chen
Non-determinism and non-reproducibility present significant challenges in deep learning, leading to inconsistent results across runs and platforms. These issues stem from two origi…