Name
Abstract | ||
|---|---|---|
Current generation GPUs can accelerate high-performance, compute-intensive applications by exploiting massive thread-level parallelism. The high performance, however, comes at the cost of increased power consumption. Recently, commercial GPGPU architectures have introduced support for concurrent kernel execution to better utilize the computational/memory resources and thereby improve overall throughput. In this paper, we argue and experimentally validate the benefits of concurrent kernels towards energy-efficient execution. We design power-performance models to carefully select the appropriate kernel combinations to be executed concurrently, the relative contributions of the kernels to the thread mix, along with the frequency choices for the cores and the memory to achieve high performance per watt metric. Our experimental evaluation shows that the concurrent kernel execution in combination with DVFS can improve energy-efficiency by up to 34.5% compared to the most energy-efficient sequential execution.
|
Year | Venue | Keywords |
|---|---|---|
2015 | CGO | power aware computing,power consumption,dvfs,gpgpu energy-efficiency,gpgpu architecture,concurrency control,parallel architectures,graphics processing units,multi-threading,computational resources,power-performance model,concurrent kernel execution,high-performance compute-intensive applications,memory resources,massive thread-level parallelism,energy-efficient sequential execution,instruction sets,computer architecture,kernel,estimation,concurrent computing |
Field | DocType | ISSN |
Kernel (linear algebra),Instruction set,Computer science,Parallel computing,Real-time computing,Thread (computing),Kernel preemption,General-purpose computing on graphics processing units,Concurrent computing,Throughput,Performance per watt | Conference | 2164-2397 |
ISBN | Citations | PageRank |
978-1-4799-8161-8 | 21 | 0.67 |
References | Authors | |
8 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Qing Jiao | 1 | 77 | 3.26 |
| Mian Lu | 2 | 656 | 29.18 |
| Huynh Phung Huynh | 3 | 252 | 14.38 |
| Tulika Mitra | 4 | 2714 | 135.99 |