The paper Latency-Tolerant Software Distributed Shared Memory describing UW CSE’s GRAPPA system was recognized today as a Best Paper at the 2015 USENIX Annual Technical Conference.
GRAPPA is a modern take on software distributed shared memory (DSM) for in-memory data-intensive applications. GRAPPA enables users to program a cluster as if it were a single, large, non-uniform memory access (NUMA) machine. Performance scales up even for applications that have poor locality and input-dependent load distribution. GRAPPA addresses deficiencies of previous DSM systems by exploiting application parallelism, trading off latency for throughput.
The paper compares the performance of GRAPPA with an in-memory map/reduce framework (10X faster than Spark), a vertex-centric framework inspired by GraphLab (1.33X faster than native GraphLab), and a relational query execution engine (12.5X faster than Shark).
Congratulations to the GRAPPA team: Jacob Nelson, Brandon Holt, Brandon Myers, Preston Briggs, Luis Ceze, Simon Kahan, and Mark Oskin.
Learn more about GRAPPA here.