Publication | Closed Access
Aquabolt-XL: Samsung HBM2-PIM with in-memory processing for ML accelerators and beyond
53
Citations
0
References
2021
Year
Unknown Venue
In-memory ProcessingMemory ArchitectureEngineeringHardware AccelerationCpu BallHigh Bandwidth MemoryMemory BottleneckHigh-performance ArchitectureBreakthrough IncreaseComputer EngineeringComputer ArchitectureComputing SystemsComputer ScienceParallel ComputingSamsung Hbm2-pimIn-memory ComputingMl Accelerators
Using PIM to overcome memory bottleneck • Although various bandwidth increase methods have been proposed, it is physically impossible to achieve a breakthrough increase. - Limited by # of PCB wires, # of CPU ball, and thermal constraints • PIM has been proposed to improve performance of bandwidth-intensive workloads and improve energy efficiency by reducing computing-memory data movement.