Abstract:
Increasing demand for power-efficient, high-performance computing has spurred a growing number and diversity of hardware accelerators in mobile and server Systems on Chip...Show MoreMetadata
Abstract:
Increasing demand for power-efficient, high-performance computing has spurred a growing number and diversity of hardware accelerators in mobile and server Systems on Chip (SoCs). This paper makes the case that the co-design of the accelerator microarchitecture with the system in which it belongs is critical to balanced, efficient accelerator microarchitectures. We find that data movement and coherence management for accelerators are significant yet often unaccounted components of total accelerator runtime, resulting in misleading performance predictions and inefficient accelerator designs. To explore the design space of accelerator-system co-design, we develop gem5-Aladdin, an SoC simulator that captures dynamic interactions between accelerators and the SoC platform, and validate it to within 6% against real hardware. Our co-design studies show that the optimal energy-delay-product (EDP) of an accelerator microarchitecture can improve by up to 7.4× when system-level effects are considered compared to optimizing accelerators in isolation.
Date of Conference: 15-19 October 2016
Date Added to IEEE Xplore: 15 December 2016
ISBN Information:
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- High-performance Computing ,
- Design Space ,
- Load Data ,
- Hardware Accelerators ,
- System-on-chip ,
- Real Hardware ,
- Benchmark ,
- Processing Time ,
- Average Error ,
- Late Time ,
- Design Considerations ,
- State Machine ,
- Memory System ,
- Local Memory ,
- Breadth-first Search ,
- Design Scenarios ,
- Datapath ,
- Data Cache ,
- Memory Bandwidth ,
- Benchmark Suite ,
- Virtual Memory ,
- Cache Misses
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- High-performance Computing ,
- Design Space ,
- Load Data ,
- Hardware Accelerators ,
- System-on-chip ,
- Real Hardware ,
- Benchmark ,
- Processing Time ,
- Average Error ,
- Late Time ,
- Design Considerations ,
- State Machine ,
- Memory System ,
- Local Memory ,
- Breadth-first Search ,
- Design Scenarios ,
- Datapath ,
- Data Cache ,
- Memory Bandwidth ,
- Benchmark Suite ,
- Virtual Memory ,
- Cache Misses