Automatic code generation for GPUs in llc

被引：0
作者：
Ruyman Reyes
Francisco de Sande
机构：
[1] Universidad de La Laguna,Departamento de Estadística, I.O. y Computación
来源：
The Journal of Supercomputing | 2011年 / 58卷
关键词：
GPU computing; CUDA; llc; OpenMP; Compiler;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
llc is a C-based language where parallelism is expressed using compiler directives. In this paper, we present a new backend of an llc compiler that produces code for GPUs. We have also implemented a software architecture that eases the development of new backends. Our design represents an intermediate layer between a high-level parallel language and different hardware architectures.
引用
收藏
页码：349 / 356
页数：7
相关论文
共 20 条
  • [1] Brodtkorb AR(2010)State-of-the-art in heterogeneous computing Sci Program 18 1-33
  • [2] Dyken C(2003)llc: a parallel skeletal language Parallel Process Lett 13 437-448
  • [3] Hagen TR(2006)Basic skeletons in llc Parallel Comput 32 491-506
  • [4] Hjelmervik JM(2008)A closer look at GPUs Commun ACM 51 50-57
  • [5] Storaasli OO(2008)Scalable parallel programming with CUDA Queue 6 40-53
  • [6] Dorta AJ(2007)A survey of general-purpose computation on graphics hardware Comput Graph Forum 26 80-113
  • [7] González JA(undefined)undefined undefined undefined undefined-undefined
  • [8] Rodríguez C(undefined)undefined undefined undefined undefined-undefined
  • [9] de Sande F(undefined)undefined undefined undefined undefined-undefined
  • [10] Dorta AJ(undefined)undefined undefined undefined undefined-undefined
12