MOVED TO VIRTUAL: Scaling up HBM Efficiency of Top-K SpMV for Approximate Embedding Similarity on FPGAs
TimeWednesday, December 8th11:10am - 11:30am PST
Event Type
Research Manuscript
Virtual Programs
Presented In-Person
Approximate Computing for AI/ML
DescriptionTop-K SpMV is a key component of similarity-search on sparse embeddings. This sparse workload does not perform well on general-purpose NUMA systems that employ traditional caching strategies.
Instead, modern FPGA accelerator cards have a few tricks up their sleeve. We introduce a Top-K SpMV FPGA design that leverages reduced precision and a novel packet-wise CSR matrix compression, enabling custom data layouts and delivering bandwidth efficiency often unreachable even in architectures with higher peak bandwidth.
With HBM-based boards, we are 100x faster than a multi-threaded CPU implementation and 2x faster than a GPU with 20\% higher bandwidth, with 14.2x higher power-efficiency.