Simon Peter
University of Washington, WA·Computer Science
Data centers need huge amounts of memory to run services from search engines to scientific computing. Supplying that memory costs a lot of money and energy, and older memory hardware is often thrown away while it still works.
- Fields
Computer Science
Engineering
- Topics
computer systems
operating systems
computer architecture
- Grants
- 1 known grant, through Aug 2029
What they work on
- Design a programmable memory controller that moves data among memory tiers connected by Compute Express Link based on usage patterns, module age and reliability.
- Develop a metric that jointly weighs system efficiency and application performance so software and system tools can make real-time memory placement tradeoffs.
- Build fault-tolerant, transparent data migration that keeps older, less reliable memory modules usable, and validate MemWise prototypes in cloud, private and direct-to-hardware settings.
More about the research
This project asks whether smarter system design can keep older memory in service alongside newer memory without losing performance.
Why it matters
Data center operators could cut costs, energy use and electronic waste by safely reusing older memory modules alongside new ones instead of discarding them early. Practical strategies for longer-lived memory systems could improve the efficiency of computing infrastructure in public clouds and private computing facilities.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Feng Chen
Indiana University, IN·Computer Science
Develop hardware functionality and system-level memory management for in-memory computing over Compute Express Link (CXL), the interconnect standard that lets processors and memory devices share memory, to reduce fragmentation of memory resources.
Peter Alvaro
University of California-Santa Cruz, CA·Computer Science
Design memory protocols that run over network fabrics so that many computers can reliably and quickly reach large pools of remote, disaggregated memory.
Remzi Arpaci-Dusseau
University of Wisconsin-Madison, WI·Computer Science
Characterize dependencies across blockchain computing, storage and network resources to build a foundation for classifying faults that cause transaction data loss.
The school
University of Washington: 81 labs on PI Pages, $1.7B a year on research, 694 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.