Performance Evaluation of CPU-GPU communication Depending on the Characteristic of Co-Located Workloads
Journal Title: International Journal on Computer Science and Engineering - Year 2013, Vol 5, Issue 5
Abstract
Todays, there are many studies in complicated computation and big data processing by using the high performance computability of GPU. Tesla K20X recently announced by NVIDIA provides 3.95 TFLOPS in precision floating point performance [1]. The performance of K20X is 10 times higher than Intel’s high-end CPUs. Due to the high performance computability of GPU, K20X was adapted to Titan, the first super computer in the world [2][3]. However, additional steps are needed in GPU computing process, which aren’t needed in the computation using only CPU. The data required to execute on GPU has to move from main memory to global memory of GPU before GPU computation. The results created on GPU also have to write back to main memory. The data movement is called as CPU-GPU communication. The communication between CPU and GPU is a big part of the computation using GPU. So, many studies tried to optimize CPU-GPU communication [4][5]. In this paper, we evaluated the performance of CPU-GPU communication depending on co-located workloads and presented which workload severely degraded the performance of CPU-GPU communication.
Authors and Affiliations
Dongyou Seo , Shin-gyu Kim , Hyeonsang Eom , Heon Y. Yeom
Keywords
Related Articles
- EP ID EP130625
- DOI -
- Views 126
- Downloads 0
Quantum computation and Biological stress: A Hypothesis
We propose that biological systems may behave as quantum computers.We have earlier hypothesized that patterns of quantum computation may be altered in stress and this leads to the change in the consciousness vector of bi...
MICROCONTROLLER PIN CONFIGURATION TOOL
Configuring the micro controller with large number of pins is tedious. Latest Infine on microcontroller contains more than 200 pins and each pin has classes of signals. Therefore the complexity of the microcontroller is...
PRE-DIAGNOSIS OF LUNG CANCER USING FEED FORWARD NEURAL NETWORK AND BACK PROPAGATION ALGORITHM
Cancer is the most important cause of death for both men and women. The early detection of cancer can be helpful in curing the disease completely. So the requirement of techniques to detect the occurrence of cancer nodul...
An Evaluative Model for Information Retrieval System Evaluation: A Usercentered Approach
The key technology for knowledge management that guarantees access to large corpora of both structured and unstructured data is Information retrieval (IR) Systems. The ones commonly used on an everyday basis are search e...
DESIGN & MODELING OF MANET USING DIFFERENT SLOT TIME SIMULATED BY NS-2
IEEE 802.11 MAC protocol has been the standard for Wireless LANs, and also adopted in many network simulation packages for wireless multi-hop ad hoc networks.MAC is defined to proper access to the channel and that is als...