8304

Parallelizing LINQ Program for GPGPU

Pritesh Agrawal
Department of Computer Science and Engineering, Indian Institute of Technology, Kanpur
Indian Institute of Technology, 2012
@article{agrawal2012parallelizing,

   title={Parallelizing LINQ Program for GPGPU},

   author={Agrawal, P.},

   year={2012}

}

Source Source   

1209

views

Recent technologies have brought parallel infrastructure to general users. Nowa-days parallel infrastructure is available in PC’s and personal laptops. Now single core machines have became history. Even multi-core technologies are replaced by GPGPUs when it comes to high performance computing because GPGPUs are giv-ing many cores at low cost. Sequential programs of the past are unable to efficiently utilize this parallel architecture. An application which run parallel has lesser running time than sequential application. Writing parallel programs manually is a difficult task. So we can not expect domain experts to write parallel programs. We can create an automatic parallelizing compiler to convert a sequential code to parallel code. Domain experts can use this kind of compiler to convert their sequential code to parallel code to utilize parallel infrastructure. In this work, we have proposed a tool which will convert a sequential code to parallel code. Here for sequential code we took LINQ programming language and for parallel architecture we took CUDA. LINQ is a query language developed by Microsoft to query data in .NET Languages and CUDA is an architecture developed by NVIDIA to use GPUs. Our proposed parallelizing compiler will automatically convert a LINQ code to an equivalent CUDA code. Microsoft has also developed a compiler to parallelize LINQ operators but it is only for multi-cores and not for GPGPUs. In our work we are parallelizing these LINQ operators in GPGPUs using CUDA.
VN:F [1.9.22_1171]
Rating: 0.0/5 (0 votes cast)

* * *

* * *

TwitterAPIExchange Object
(
    [oauth_access_token:TwitterAPIExchange:private] => 301967669-yDz6MrfyJFFsH1DVvrw5Xb9phx2d0DSOFuLehBGh
    [oauth_access_token_secret:TwitterAPIExchange:private] => o29ji3VLVmB6jASMqY8G7QZDCrdFmoTvCDNNUlb7s
    [consumer_key:TwitterAPIExchange:private] => TdQb63pho0ak9VevwMWpEgXAE
    [consumer_secret:TwitterAPIExchange:private] => Uq4rWz7nUnH1y6ab6uQ9xMk0KLcDrmckneEMdlq6G5E0jlQCFx
    [postfields:TwitterAPIExchange:private] => 
    [getfield:TwitterAPIExchange:private] => ?cursor=-1&screen_name=hgpu&skip_status=true&include_user_entities=false
    [oauth:protected] => Array
        (
            [oauth_consumer_key] => TdQb63pho0ak9VevwMWpEgXAE
            [oauth_nonce] => 1474899416
            [oauth_signature_method] => HMAC-SHA1
            [oauth_token] => 301967669-yDz6MrfyJFFsH1DVvrw5Xb9phx2d0DSOFuLehBGh
            [oauth_timestamp] => 1474899416
            [oauth_version] => 1.0
            [cursor] => -1
            [screen_name] => hgpu
            [skip_status] => true
            [include_user_entities] => false
            [oauth_signature] => 5ai+23n6Spngq1VQ+kioTrSs2IA=
        )

    [url] => https://api.twitter.com/1.1/users/show.json
)
Follow us on Facebook
Follow us on Twitter

HGPU group

1997 peoples are following HGPU @twitter

HGPU group © 2010-2016 hgpu.org

All rights belong to the respective authors

Contact us: