Postdoctoral Appointee- Optimizing Data Movement in the Exascale Era with DAOS Storage
Job posting number: #7088496 (Ref:ANL-411805)
Posted: November 5, 2021
Application Deadline: Open Until Filled
ALCF’s performance engineering group is looking for a Postdoctoral Appointee to perform research and development on the open source DAOS storage system, in the context of the upcoming exascale platforms, and Aurora in particular.
Three areas of interest for study are:
- new opportunities for applications to optimize I/O that isn't oriented around file access. DAOS provides very low latency access and the possibility allows applications to write data in a more "read-optimized" format with minimal penalty versus write-optimized formats.
- DAOS supports a prototype "active storage" interface, and exploration of some HPC type workloads (like pointer chasing, lookup tables, etc.)
- With the proliferation of CPUs and accelerators with significant dedicated high performance memory, the DAOS client should provide a mechanism to utilize device memory with direct-to-NIC memory movement bypassing CPU memory.
- Conducts research and support aligned with Argonne’s strategic missions in computation.
- Conducts work in computational science and leadership computing and promotes findings through publications, presentations, program reports, software dissemination and other means of reporting outcomes.
- Contributes to discovery and technological advances in domain science, with emphasis on the applications of exascale (and beyond) computer architectures, e.g., to address data architecture challenges and algorithm implementation challenges of high-performance simulations.
- Strengthens career path opportunities by applying new techniques, developing independent research capabilities and building professional skills such as communication, networking and leadership.
The Argonne Leadership Computing Facility’s (ALCF) mission is to accelerate major scientific discoveries and engineering breakthroughs for humanity by designing and providing world-leading computing facilities in partnership with the computational science community. We help researchers solve some of the world’s largest and most complex problems with our unique combination of supercomputing resources and computational science expertise.
- Ph.D. + 0-3 years of experience in computer science or related field
- Ability to model Argonne's core values: impact, safety, respect, integrity, and teamwork
- Strong knowledge in System Programming
- Experience related to parallel algorithms, I/O architectures, or performance evaluation
- Extensive expertise in parallel I/O, storage systems, or parallel file systems
- Strong written and verbal communication skills
Job FamilyPostdoctoral Family
Job ProfilePostdoctoral Appointee
Worker TypeLong-Term (Fixed Term)
Time TypeFull time
Argonne is an equal opportunity employer, and we value diversity in our workforce. As an equal employment opportunity and affirmative action employer, Argonne National Laboratory is committed to a diverse and inclusive workplace that fosters collaborative scientific discovery and innovation. In support of this commitment, Argonne prohibits discrimination or harassment based on an individual's age, ancestry, citizenship status, color, disability, gender, gender identity, genetic information, marital status, national origin, pregnancy, race, religion, sexual orientation, veteran status or any other characteristic protected by law.