Performance Portability Study of Epistasis Detection using SYCL on NVIDIA GPU

被引:4
作者
Jin, Zheming [1 ]
Vetter, Jeffrey S. [1 ]
机构
[1] Oak Ridge Natl Lab, POB 2008, Oak Ridge, TN 37830 USA
来源
13TH ACM INTERNATIONAL CONFERENCE ON BIOINFORMATICS, COMPUTATIONAL BIOLOGY AND HEALTH INFORMATICS, BCB 2022 | 2022年
关键词
portability; programming model; GPU; epistasis;
D O I
10.1145/3535508.3545591
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We describe the experience of converting a CUDA implementation of a high-order epistasis detection algorithm to SYCL. The goals are for our work to be useful to application and compiler developers with a detailed description of migration paths between CUDA and SYCL. Evaluating the CUDA and SYCL applications on an NVIDIA V100 GPU, we find that the optimization of loop unrolling needs to be applied manually to the SYCL kernel for obtaining comparable performance. The performance of the SYCL group reduce function, an alternative to the CUDA warp-based reduction, depends on the problem and work group sizes. The 64-bit popcount operation implemented with tree of adders is slightly faster than the built-in popcount operation. When the number of OpenMP threads is four, the highest performance of the SYCL and CUDA applications are comparable.
引用
收藏
页数:8
相关论文
共 50 条
  • [31] Performance of epistasis detection methods in semi-simulated GWAS
    Chatelain, Clement
    Durand, Guillermo
    Thuillier, Vincent
    Auge, Franck
    BMC BIOINFORMATICS, 2018, 19
  • [32] Performance analysis of a parallel Monte Carlo code for simulating solar radiative transfer in cloudy atmospheres using CUDA-enabled NVIDIA GPU
    Russkova, Tatiana
    23RD INTERNATIONAL SYMPOSIUM ON ATMOSPHERIC AND OCEAN OPTICS: ATMOSPHERIC PHYSICS, 2017, 10466
  • [33] Epistasis Detection using Heterogeneous Bio-molecular Network
    Zhang, Huiling
    Wang, Jun
    Yu, Guoxian
    Cui, Lizhen
    Guo, Maozu
    2020 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE, 2020, : 194 - 199
  • [34] High-performance and Memory-saving Sparse General Matrix-Matrix Multiplication for NVIDIA Pascal GPU
    Nagasaka, Yusuke
    Nukada, Akira
    Matsuoka, Satoshi
    2017 46TH INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING (ICPP), 2017, : 101 - 110
  • [35] Parallel Botnet Detection System by Using GPU
    Hung, Che-Lun
    Wang, Hsiao-Hsi
    2014 IEEE/ACIS 13TH INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION SCIENCE (ICIS), 2014, : 65 - 70
  • [36] Portability Study of an OpenCL Algorithm for Automatic Target Detection in Hyperspectral Images
    Bernabe, Sergio
    Garcia, Carlos
    Igual, Francisco D.
    Botella, Guillermo
    Prieto-Matias, Manuel
    Plaza, Antonio
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2019, 57 (11): : 9499 - 9511
  • [37] Object Detection and Classification Using GPU Acceleration
    Prabhu, Shreyank
    Khopkar, Vishal
    Nivendkar, Swapnil
    Satpute, Omkar
    Jyotinagar, Varshapriya
    COMPUTATIONAL VISION AND BIO-INSPIRED COMPUTING, 2020, 1108 : 161 - 170
  • [38] Performance Improvement of Viewshed Analysis Using GPU
    Stojanovic, Natalija
    Stojanovic, Dragan
    2013 11TH INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS IN MODERN SATELLITE, CABLE AND BROADCASTING SERVICES (TELSIKS), VOLS 1 AND 2, 2013, : 397 - 400
  • [39] Performance of dynamic texture segmentation using GPU
    Francisco Gómez Fernández
    María Elena Buemi
    Juan Manuel Rodríguez
    Julio C. Jacobo-Berlles
    Journal of Real-Time Image Processing, 2016, 11 : 375 - 383
  • [40] GPU-accelerated molecular dynamics: State-of-art software performance and porting from Nvidia CUDA to AMD HIP
    Kondratyuk, Nikolay
    Nikolskiy, Vsevolod
    Pavlov, Daniil
    Stegailov, Vladimir
    INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS, 2021, 35 (04) : 312 - 324