Abstract | ||
---|---|---|
NVIDIA’s new architecture, Kepler improves GPU’s performance significantly with the new streaming multiprocessor SMX. Along with the performance, NVIDIA has also introduced many new technologies such as direct parallelism, hyper-Q and GPU Direct with RDMA. Apart from other usual GPUs, NVIDIA also released another Kepler ‘GeForce’ GPU named GTX Titan. GeForce GTX Titan is not only good for gaming but also good for high performance computing with CUDA. Nevertheless, it is remarkably cheaper than Kepler Tesla GPUs. We investigate the performance of GTX Titan and find out how to optimize a CUDA code appropriately for it. Meanwhile, Intel has launched its new many integrated core (MIC) system, Xeon Phi. A Xeon Phi coprocessor could provide similar performance with NVIDIA Kepler GPUs theoretically but, in reality, it turns out that its performance is significantly inferior to GTX Titan. |
Year | DOI | Venue |
---|---|---|
2013 | 10.22323/1.187.0423 | CoRR |
Field | DocType | Volume |
Supercomputer,CUDA,Xeon Phi,Computer science,Parallel computing,Multiprocessing,Remote direct memory access,Titan (rocket family),Kepler,Coprocessor | Journal | abs/1311.0590 |
ISSN | Citations | PageRank |
PoS (LATTICE 2013) 423 | 3 | 0.88 |
References | Authors | |
1 | 9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hwancheol Jeong | 1 | 11 | 2.73 |
Weonjong Lee | 2 | 11 | 3.07 |
Jeonghwan Pak | 3 | 5 | 1.45 |
Kwang-jong Choi | 4 | 3 | 0.88 |
Sang-Hyun Park | 5 | 149 | 26.55 |
Jun-sik Yoo | 6 | 3 | 0.88 |
Joo Hwan Kim | 7 | 3 | 0.88 |
Joungjin Lee | 8 | 3 | 0.88 |
Young Woo Lee | 9 | 9 | 5.76 |