OpenMP to GPGPU: a compiler framework for automatic translation and optimization
By Seyong Lee, Seung-Jai Min, Rudolf Eigenmann. ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming, 2009
514 citations recorded by the source corpus.
Subfields: Computer Networks and Communications, Hardware and Architecture
View Paper: https://www.semanticscholar.org/paper/271be72b0c57686a3e77d0f794ef08db1b39a28f
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Networks and Communications
- Timothy G. Rogers
- Mike O'Connor
- Francky Catthoor
- Tor M. Aamodt
- Jingfei Kong
- Ping Xiang
- Yi Yang
- Huiyang Zhou
In Hardware and Architecture
- Albert Cohen
- Timothy G. Rogers
- José Ignacio Gómez
- Francky Catthoor
- Christian Tenllado
- Juan Carlos Juega
- Mike O'Connor
- Tor M. Aamodt
Citations in the corpus
- A GPGPU compiler for memory optimization and parallelism management (2010, methodology): “One interesting way to automatically generate GPGPU programs is to translate OpenMP programs to CUDA programs [9].”
- Polyhedral parallel code generation for CUDA (2013, methodology): “In parallel, in the OpenMPC project, the Cetus compiler framework was used to translate OpenMP to CUDA [Lee et al. 2009]; unlike current polyhedral compilers, it can handle dynamic, data-dependent control flow.”
- Cache-Conscious Wavefront Scheduling (2012, background): “Intra-wavefront locality is a combination of intra-thread locality [27] (where data is private to a single scalar thread) and inter-thread locality where data is shared among scalar threads in the same wavefront.”