A simulator that can be used to analyze energy efficiency for GPUs using a combination of ATTILA and CACTI, a widely used cache power estimation tool is proposed.
Abstract
A graphics processor (GPU) is a dedicated processing unit that handles all graphics-related computation in a given system. With the growth of graphics-based applications in domains such as embedded systems, gaming, and image processing, studying such systems has become more important. We propose to develop a simulator that can be used to analyze energy efficiency for GPUs. No publicly available simulators simulate power utilization in GPUs, which is important because energy consumption is one of the key design criteria for any modern system. Existing power simulators like Simple Power, Wattch, and PowerTimer are not GPU specific. GPU simulators, such as ATTILA, that simulate the graphics pipeline thoroughly do not model power. Our plan is to use the existing ATTILA simulator and extend it to do the power modeling. This thesis focuses on modeling GPU caches using a combination of ATTILA and CACTI, a widely used cache power estimation tool.
This paper presents an OpenMP-style parallelism API for Uxntal, the stack-based assembly-style language for the Uxn platform, and demonstrates that exemplar code using this API can run at comparable performance even on an integrated GPU.
S. Li, Vladislav Brusokas, Andrei Ghita et al.· 0 citations
G-Power, an architecture-level GPU power modeling framework that utilizes additional known GPU chips to provide additional knowledge and adopts a three-phase algorithm consisting of pre-training with additional known chips, attention-inspired aggregation, and fine-tuning on the target GPU.
Qi-Jun Zhang, Yao Lu, Shang Liu et al.· 0 citations
Simulation-based practice to improve the energy efficiency of Intel Arc GPUs and the Intel CPUs to overcome the issue of power inefficiency, workload imbalance, and thermal limitations indicates that the Intel Arc GPUs used less power compared to CPUs with similar tasks, which makes the argument of their energy efficie...
S. Mishra, K. B. Yadav· Interdisciplinary Journal of...· 0 citations
This project analyzes how the architectural changes introduced across NVIDIA’s Volta, Ampere, and Hopper GPU generations translate into real-world performance and energy efficiency gains and shows that specialization can deliver substantial performance and efficiency gains, but only when workloads can effectively use t...
Matthew Tindale, I. Karlin, Tobias Salamon et al.· Inquiry@Queen's Undergraduat...· 0 citations
This work investigates the memory capabilities of the NVIDIA DGX Spark, a novel platform featuring a unified memory architecture where DDR memory is located on the CPU and is fully accessible from the GPU.
Silvia R. Alcaraz, S. Hepkema, Vasilis Mageirakos et al.· Proceedings of the 4th Works...· 0 citations
An analysis of the benefits and performance challenges of using OpenMP Offloading to address the 3D heat equations, which involve both primary computation, as well as halo computation and communication, and how performance varies in relation to native GPU programming models.
E. Krishnasamy· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
