Login / Signup

A DRAM Bandwidth-Scalable Sparse Matrix-Vector Multiplication Accelerator with 89% Bandwidth Utilization Efficiency for Large Sparse Matrix.

Hyunji KimEunkyung HamSunyoung ParkHana KimJi-Hoon Kim
Published in: A-SSCC (2023)
Keyphrases
  • sparse matrix
  • bandwidth utilization
  • floating point
  • quality of service
  • random projections
  • main memory
  • rows and columns
  • response time
  • similarity search
  • blocking probability