Bounding the effect of partition camping in GPU kernels
Proceedings of the 8th ACM International Conference on Computing Frontiers
Power Modeling and Characterization of Computing Devices: A Survey
Foundations and Trends in Electronic Design Automation
Power and performance analysis of GPU-accelerated systems
HotPower'12 Proceedings of the 2012 USENIX conference on Power-Aware Computing and Systems
Computer Science - Research and Development
Power efficiency evaluation of block ciphers on GPU-integrated multicore processor
ICA3PP'12 Proceedings of the 12th international conference on Algorithms and Architectures for Parallel Processing - Volume Part I
GPUWattch: enabling energy optimizations in GPGPUs
Proceedings of the 40th Annual International Symposium on Computer Architecture
Starchart: hardware and software optimization using recursive partitioning regression trees
PACT '13 Proceedings of the 22nd international conference on Parallel architectures and compilation techniques
A measurement study of GPU DVFS on energy conservation
Proceedings of the Workshop on Power-Aware Computing and Systems
High-Resolution power profiling of GPU functions using low-resolution measurement
Euro-Par'13 Proceedings of the 19th international conference on Parallel Processing
Measuring GPU Power with the K20 Built-in Sensor
Proceedings of Workshop on General Purpose Processing Using GPUs
Power Modeling for Heterogeneous Processors
Proceedings of Workshop on General Purpose Processing Using GPUs
Hi-index | 0.00 |
We present a statistical approach for estimating power consumption of GPU kernels. We use the GPU performance counters that are exposed for CUDA applications, and train a linear regression model where performance counters are used as independent variables and power consumption is the dependent variable. For model training and evaluation, we use publicly available CUDA applications, consisting of 49 kernels in the CUDA SDK and the Rodinia benchmark suite. Our regression model achieves highly accurate estimates for many of the tested kernels, where the average error ratio is 4.7%. However, we also find that it fails to yield accurate estimates for kernels with texture reads because of the lack of performance counters for monitoring texture accesses, resulting in significant underestimation for such kernels.