Dalorex: A Data-Local Program Execution and Architecture for Memory-bound Applications

Applications with low data reuse and frequent irregular memory accesses, such as graph or sparse linear algebra workloads, fail to scale well due to memory bottlenecks and poor core utilization. While prior work that utilizes prefetching, decoupling, or pipelining can mitigate memory latency and improve core utilization, memory bandwidth bottlenecks persist due to limited off-chip bandwidth. Approaches using in-memory processing (PIM) with Hybrid Memory Cube (HMC) surpass DRAM bandwidth limitations but fail to achieve high core utilization due to poor task scheduling and synchronization overheads. Moreover, the granularity of the memory available to each processing core with HMC limits the level of parallelism. This work proposes Dalorex, a hardware-software co-design that achieves high parallelism and energy efficiency, demonstrating strong scaling with 16,000 cores when processing graph and sparse linear algebra workloads. Over the prior work in PIM, using both 256 cores, Dalorex improves performance and energy consumption by two orders of magnitude through (1) a tile-based distributed-memory architecture where each processing tile holds an equal amount of data, and all memory operations are local; (2) a task-based parallel programming model where tasks are executed by the processing unit that is co-located with the target data; (3) a network design optimized for irregular traffic, where all communication is one-way, and messages do not contain routing metadata; and (4) a novel traffic-aware task scheduling hardware that maintains high core utilization; and (5) a data placement strategy improving work balance. This work proposes architectural and software innovations to provide, to our knowledge, the fastest design for running graph algorithms, while still being programmable for other domains.