Roofline: an insightful visual performance model for multicore architectures
Communications of the ACM - A Direct Path to Dependable Software
Improving Throughput of Power-Constrained GPUs Using Dynamic Voltage/Frequency and Core Scaling
PACT '11 Proceedings of the 2011 International Conference on Parallel Architectures and Compilation Techniques
Application-level voltage and frequency tuning of multi-phase program on the SCC
Proceedings of the 3rd International Workshop on Adaptive Self-Tuning Computing Systems
Future of GPGPU micro-architectural parameters
Proceedings of the Conference on Design, Automation and Test in Europe
GPUWattch: enabling energy optimizations in GPGPUs
Proceedings of the 40th Annual International Symposium on Computer Architecture
A measurement study of GPU DVFS on energy conservation
Proceedings of the Workshop on Power-Aware Computing and Systems
Effects of Dynamic Voltage and Frequency Scaling on a K20 GPU
ICPP '13 Proceedings of the 2013 42nd International Conference on Parallel Processing
| Hi-index | 0.00 |
Graphics processing units (GPUs) are becoming increasingly popular for compute workloads, mainly because of their large number of processing elements and high-bandwidth to off-chip memory. The roofline model captures the ratio between the two (the compute-memory ratio), an important architectural parameter. This work proposes to change the compute-memory ratio dynamically, scaling the voltage and frequency (DVFS) of 1) memory for compute-intensive workloads and 2) processing elements for memory-intensive workloads. The result is an adaptive roofline-aware GPU that increases energy efficiency (up to 58%) while maintaining performance.