Working at the HPCC
I've been at the HPCC for over four years. In my time here, I have built numerous configurations of high performance and parallel computing clusters, both in front of large audiences at our annual conferences and regularly in the engineering lab. I became so comfortable with Linux that I had to dual-boot on my laptop to get my work done. I have installed and built hardware from diverse hardware companies, including Intel, Mellanox, IBM, and Panasas. As apart of our ME344: Introduction to High Performance Computing course I was able to assist students in learning foundational skills in high performance computing and give them real world experience I certainly never thought I would ever access. I even had the opportunity to work on federal grant proposals to aid our organization in getting systems valued at over $15 million. What I value most from my time at the HPCC is the autonomy to work on large-scale projects with innovative academic researchers: an opportunity to get involved with state of the art research can only be described as amazing.Learn more
Stanford HPC Center Fall Seminar Series Please join the Stanford High Performance Computing Center and Intel for the Fall Seminar Series, every Wednesday at 11AM Pacific, September 8th through October 6th. don't miss out on this workshop!
Session 1: September 8th Intel oneAPI Overview:
The oneAPI specification extends existing developer programming models to enable a diverse set of hardware through language, a set of library APIs, and a low-level hardware interface to support cross-architecture programming. To promote compatibility and enable developer productivity and innovation, the oneAPI specification builds upon industry standards and provides an open, cross-platform developer stack. Introduction to Intel oneAPI DevCloud
Session 2: September 15th Intel DPC++ Overview:
An alternative to single-vendor proprietary languages. Allows code reuse across hardware targets (CPU, GPU, FPGA) and supports custom tuning for a specific platform. Enables each architecture to be programmed and used in isolation, or together.
Session 3: September 22nd Intel Compatibility Tool:
The Intel® DPC++ Compatibility Tool assists in migrating you’re existing CUDA code to Data Parallel C++ (DPC++) code. This tool migrates approximately 80% of the targeted code to DPC++ and included notations to complete 100% migration
Session 4: September 29th Intel Offload Advisor:
A design and analysis tool for achieving high application performance. This is done through efficient threading, vectorization, and memory use, and GPU offload on current and future Intel® hardware. The tool supports C, C++, Fortran, Data Parallel C++ (DPC++), OpenMP*, and Python*.
Session 5: October 6th Deploying oneAPI and oneContainer on OpenHPC:
OpenHPC provides a comprehensive platform to deploy and manage resources for integrated HPC, AI, and Data infrastructure. The final session in the fall series provides detail on how to deploy the oneAPI ecosystem on an OpenHPC cluster.
Registration for the seminar series here!
Stanford HPC-AI Conference Join the Stanford High Performance Computing Center (HPCC) and HPC-AI Advisory Council (HPCAIAC) for two days of invited and contributed talks, hands-on tutorials and workshops on HPC, AI, Data Sciences, Machine Learning and much more.
Focused on contributing to making the world a better place, our only US-based conference draws together renowned subject matter experts (SMEs) - from private and public sectors to startups and global giants, from across interests and industries in the valley and beyond - to explore the domains and disciplines fueling huge advances in new and ongoing research, innovation, and breakthrough discoveries.
Each annual agenda combines thought leadership and practical insights with topics of great societal importance and responsibility – from applications, tools and techniques to delving into emerging trends, technologies and collaborative partnerships inspiring our collective success.
Open to all interested and free of charge, we invite you to step away from the daily din of noise and hype and join us for the next annual Stanford Conference! Visit the following site for up-to-date information: https://www.hpcadvisorycouncil.com
The Stanford High Performance Computing Center (HPCC) is proud to offer CS 74: An Introduction to High Performance Computing Systems to Stanford University. CS 74 provides a once-in-a-lifetime opportunity for students to gain hands-on experience with building high performance computing clusters, from barebones hardware to advanced cluster installation and management. Throughout the course, students become comfortable with Linux and Bash, in addition to software for open source HPC support,and the operating systems necessary to build clusters in the future. Students spend plenty of time in the cluster room to gain the skills and knowledge necessary to work in academia, industry, and national laboratories that have large computing clusters. Register now!Learn more