Scientific Computing Systems

The mission of TID’s Scientific Computing Systems (SCS) Division is to support all of SLAC’s scientific computing workflows and workloads. SCS enables and supports the data-intensive workflows and computing pipelines for SLAC’s research facilities and experiments, and is responsible for developing and supporting a data-centric HPC platform and a portfolio of services using common shared infrastructure. Shaped and driven by SLAC’s and DOE’s mission, we provide baseline capabilities for the entire user community which are a powerful incentive for driving lab-wide collaboration and seeding new lab initiatives. We have continual engagement with users and PIs as a research partner, and engage and consult on all aspects of scientific computing, data movement and data management. SCS is also a key participant in the lab’s Integrated Scientific and Data-intensive Computing Initiative (ISDCI) and supports all three pillars of the initiative - aligning our scientific computing activities with the Department of Energy’s Integrated Research Infrastructure (IRI) program, Edge computing activities and the use of AI/ML for complex, cross-facility workflows.

SCS provides a centralized scientific and data-intensive computing resource – the SLAC Shared Science Data Facility (S3DF), a heterogeneous CPU and GPU accelerated computing resource with high-performance disk, flash and archival storage.  SLAC is at the leading edge of data analytics for massive throughput observational and experimental data. The S3DF provides resources to support work in the key areas of real-time data reduction and feedback, real-time access to HPC facilities for data analysis and new ML techniques to interpret data faster, enabling efficient operation of the next-generation facilities, and improving accelerator, detector, and facility operations. Our group helps architect, develop and deploy data management capabilities and hardware infrastructure to provide a holistic data processing system which integrates sensors and front end electronics in the experimental area, with on-the-fly data monitoring and data reduction fabric, and with complex and configurable processing capabilities in the data center, onsite and remote.

The SCS division manages, in addition to S3DF, the US Data Facility for the LSST-Rubin Observatory (USDF), and the Controls & Data IT System for LCLS (CDS). These resources are closely integrated into the S3DF infrastructure. S3DF also provides scientific computing resources for over 25 other experiments of various sizes at SLAC.