Now Online – Presentations and Videos from Houston 2015 Directives and Tools...
The presentations and videos from the October 12 University of Houston “2015 Directives and Tools for Accelerators” workshop are now available online. As with last year’s workshop, this workshop was...
View ArticlePGI/NVIDIA To Develop LLVM-based Open-Source Fortran Compiler for NNSA and...
PGI (The Portland Group) is working with the NNSA to create an open-source Fortran compiler designed to integrate with the widely used LLVM compiler infrastructure. Recently, PGI announced comparable...
View ArticleCode Modernization Efforts Deliver a 32.9X Speedup in STAC-A2™ Financial...
Global financial industry leaders such as Citi and J.P. Morgan have acknowledged they are currently modernizing their code via collaborative efforts with the Intel Software and Solutions Group. Results...
View ArticlePascal upgrade and Intel Xeon Phi at the Swiss National Supercomputing Centre
It was announced at GTC 2016 that the Piz Daint system at the Swiss National Supercomputing Center (CSCS) in Lugano, Switzerland will be upgraded to 4,500 Pascal GPUs. No date was stated for when the...
View ArticleNVIDIA –“[Intel] Should Get Their Facts Straight” on Machine Learning Benchmarks
NVIDIA responds to the machine learning benchmark results presented by Intel at ISC’16, “It’s great that Intel is now working on deep learning. This is the most important computing revolution with the...
View ArticleUp To Orders of Magnitude More Performance with Intel’s Distribution of Python
Intel has created a freely downloadable, optimized Python distribution that can greatly accelerate Python codes. Benchmarks show that two order of magnitude speedups (over 100x) can be achieved by...
View ArticleCome learn and meet the experts at the 2016 Intel HPC Developer Conference –...
Sponsored Content Come learn and meet the experts at the Intel 2016 HPC Developer Conference – just before SC16! Arrive early at Supercomputing 2016 and fuel your insight with focused technical...
View ArticleAccelerating Python and Deep Learning
Sponsored Content “For deep learning to have a meaningful impact and business value, the time to train a model must be reduced from weeks to hours,” observed Ananth Sankaranarayanan, Intel’s director...
View ArticleSURFsara Achieves Accuracy and Performance Breakthroughs for Both Deep...
Sponsored Content SURFsara posted the best accuracy and an under 40 minute training time on some popular deep learning architectures and data sets to establish new single-model state-of-the-art results...
View ArticleThird-Party Use Cases Illustrate the Success of CPU-based Visualization
John Stone (Research Staff, The Beckman Institute) points out that improvements in the AVX-512 instruction set in the Intel Xeon Phi (and latest generation Intel Xeon processors) can deliver...
View Article