NERSCPowering Scientific Discovery Since 1974

Cori

.15 NERSC 1870 Cori option 7d big final

Overview

NERSC's newest supercomputer, named Cori, is a Cray XC40. Named for American biochemist Gerty Cori, the first American woman to win a Nobel Prize and the first woman to be so honored with the prize in Physiology or Medicine, Cori ranked as the 5th most powerful supercomputer in the world on the November 2016 list of Top 500 supercomputers in the world.   Cori is a unique among supercomputers of its size with two different kinds of nodes, 2,388 Intel Xeon "Haswell" processor nodes 9,688 Intel Xeon Phi "Knight's Landing" nodes. Cori also features a 1.8 PB Cray Data Warp Burst Buffer with I/O operating at a world's-best 1.7 TB/sec.

Updates and Status

Known issues and status update Read More »

Cori Timeline

This page records a brief timeline of significant events and user environment changes on Cori (in reverse chroniclel order). Read More »

Cori Phase I

The Cori Phase 1 (also known as the "Cori Data Partition") system utilizes Intel Haswell processors and provides approximately the same sustained application performance as the Hopper system. Cori Phase 1 has a number of new features to support data intensive science. Read More »

Cori Phase II Schedule

Before Cori can be released to users, it must be delivered, integrated with Phase I, and accepted. This page is the resource for the Cori upgrade and installation schedule. For the current status of Cori, please see the Cori Updates and Status page. Impact on NERSC Users While NERSC made every effort to minimize inconvenience to users, there were some unavoidable downtimes of Cori Phase I for the upgrade of its operating system and integration with Cori Phase II.  Cori Phase II Preparation and… Read More »

Cori System Overview

Details concerning Cori's hardware and software. Read More »

Getting Started

How to get started using NERSC's Cori supercomputer. Read More »

Programming

Find information on how to compile your application, use MPI and OpenMP optimally, achieve effective vectorization, and use Cray's scientific libraries. Read More »

Running Jobs

Learn how to submit interactive and batch jobs using native SLURM on Cori compute nodes with example batch scripts. and how to monitor your job in the queue and job exit status. Also find information on OpenMP and MPI runtime settings as well as general application tuning options. Read More »

Cori File Systems

The Cori system has 3 different file systems which provide different levels of disk storage, I/O performance and file permanence. Find information on I/O optimization, disk quotas and purging. Read More »

Burst Buffer

The Burst Buffer is a layer of non-volatile storage which sits between memory and the file system on the Cori system, within the high-speed network. The Burst Buffer will serve to accelerate application I/O. Read More »