Technical Blog

Learn about our joint effort in porting the ILT engine to GPU. We also identify future areas for EDA and mask inspection tool vendors to address for ILT to be adopted at logic foundries. 6 MIN READ

Find out how RAPIDS and the cuML support vector machine can achieve faster training time and maximum accuracy when fine-tuning transformers. 7 MIN READ

Learn about the characteristics of various accelerated workload categories and the system features needed to run them. 8 MIN READ

Learn how using the combination of model parallel and data parallel enables practitioners to train large-scale recommender systems in minutes instead of days. 13 MIN READ

The NCCL 2.12 release significantly improves all2all communication collective performance, with the PXN feature. 8 MIN READ

This post details the credit default risk prediction with deep learning and machine learning models. 18 MIN READ