NumCIL: Numeric operations in the common intermediate language

K. Skovhede; B. Vinter

doi:10.4156/jnit.vol4.issue1.2

NumCIL: Numeric operations in the common intermediate language

K. Skovhede, B. Vinter

eScience

3 Citations (Scopus)

Abstract

As multicore processors are now the standard for high performance machines, scientists must develop complex programs to fully utilize the processing power. In this article we present NumCIL, a new framework for expressing scientific and financial algorithms. By using n-dimensional arrays, a scientist can write sequential code without knowledge of parallel constructs. The library is a CIL library and can thus be used from languages as diverse as IronPython, F# and C#. As the ndimensional arrays are compatible with numpy ndarrays, it is possible to run some existing numpy programs unmodified on NumCIL. The NumCIL library can run entirely in CIL or offload computation to an external library. We compare NumCIL to numpy and show that the implementation is able to perform on par with numpy for a variety of problems taken from imaging, physics and financial computing domains.

Original language	English
Journal	Journal of Next Generation Information Technology
Volume	4
Issue number	1
Pages (from-to)	9-18
Number of pages	10
ISSN	2092-8637
DOIs	https://doi.org/10.4156/jnit.vol4.issue1.2
Publication status	Published - 1 Feb 2013

Access to Document

10.4156/jnit.vol4.issue1.2

Cite this

@article{d0729f3012304ea391fbb29d568c9c11,

title = "NumCIL: Numeric operations in the common intermediate language",

abstract = "As multicore processors are now the standard for high performance machines, scientists must develop complex programs to fully utilize the processing power. In this article we present NumCIL, a new framework for expressing scientific and financial algorithms. By using n-dimensional arrays, a scientist can write sequential code without knowledge of parallel constructs. The library is a CIL library and can thus be used from languages as diverse as IronPython, F# and C#. As the ndimensional arrays are compatible with numpy ndarrays, it is possible to run some existing numpy programs unmodified on NumCIL. The NumCIL library can run entirely in CIL or offload computation to an external library. We compare NumCIL to numpy and show that the implementation is able to perform on par with numpy for a variety of problems taken from imaging, physics and financial computing domains.",

author = "K. Skovhede and B. Vinter",

year = "2013",

month = feb,

day = "1",

doi = "10.4156/jnit.vol4.issue1.2",

language = "English",

volume = "4",

pages = "9--18",

journal = "Journal of Next Generation Information Technology",

issn = "2092-8637",

publisher = "Advanced Institutes of Convergence Information Technology",

number = "1",

}

TY - JOUR

T1 - NumCIL

T2 - Numeric operations in the common intermediate language

AU - Skovhede, K.

AU - Vinter, B.

PY - 2013/2/1

Y1 - 2013/2/1

N2 - As multicore processors are now the standard for high performance machines, scientists must develop complex programs to fully utilize the processing power. In this article we present NumCIL, a new framework for expressing scientific and financial algorithms. By using n-dimensional arrays, a scientist can write sequential code without knowledge of parallel constructs. The library is a CIL library and can thus be used from languages as diverse as IronPython, F# and C#. As the ndimensional arrays are compatible with numpy ndarrays, it is possible to run some existing numpy programs unmodified on NumCIL. The NumCIL library can run entirely in CIL or offload computation to an external library. We compare NumCIL to numpy and show that the implementation is able to perform on par with numpy for a variety of problems taken from imaging, physics and financial computing domains.

AB - As multicore processors are now the standard for high performance machines, scientists must develop complex programs to fully utilize the processing power. In this article we present NumCIL, a new framework for expressing scientific and financial algorithms. By using n-dimensional arrays, a scientist can write sequential code without knowledge of parallel constructs. The library is a CIL library and can thus be used from languages as diverse as IronPython, F# and C#. As the ndimensional arrays are compatible with numpy ndarrays, it is possible to run some existing numpy programs unmodified on NumCIL. The NumCIL library can run entirely in CIL or offload computation to an external library. We compare NumCIL to numpy and show that the implementation is able to perform on par with numpy for a variety of problems taken from imaging, physics and financial computing domains.

UR - http://www.scopus.com/inward/record.url?scp=84875241683&partnerID=8YFLogxK

U2 - 10.4156/jnit.vol4.issue1.2

DO - 10.4156/jnit.vol4.issue1.2

M3 - Journal article

AN - SCOPUS:84875241683

SN - 2092-8637

VL - 4

SP - 9

EP - 18

JO - Journal of Next Generation Information Technology

JF - Journal of Next Generation Information Technology

IS - 1

ER -

NumCIL: Numeric operations in the common intermediate language

Abstract

Access to Document

Other files and links

Fingerprint

Cite this