Sciweavers

25 search results - page 5 / 5
» CGiS, a new Language for Data-parallel GPU Programming
Sort
View
178
Voted
PPOPP
2009
ACM
16 years 4 months ago
OpenMP to GPGPU: a compiler framework for automatic translation and optimization
GPGPUs have recently emerged as powerful vehicles for generalpurpose high-performance computing. Although a new Compute Unified Device Architecture (CUDA) programming model from N...
Seyong Lee, Seung-Jai Min, Rudolf Eigenmann
129
Voted
PDP
2008
IEEE
15 years 10 months ago
A Transformation Framework for Communicating Multiprocessor-Tasks
Parallel programming models based on a mixture of task and data parallelism have shown to be successful in addressing the increasing communication overhead of distributed memory p...
Jörg Dümmler, Thomas Rauber, Gudula R&uu...
136
Voted
ICS
2004
Tsinghua U.
15 years 9 months ago
Evaluating support for global address space languages on the Cray X1
The Cray X1 was recently introduced as the first in a new line of parallel systems to combine high-bandwidth vector processing with an MPP system architecture. Alongside capabili...
Christian Bell, Wei-Yu Chen, Dan Bonachea, Katheri...
140
Voted
ICS
2009
Tsinghua U.
15 years 10 months ago
High-performance CUDA kernel execution on FPGAs
In this work, we propose a new FPGA design flow that combines the CUDA programming model from Nvidia with the state of the art high-level synthesis tool AutoPilot from AutoESL, to...
Alexandros Papakonstantinou, Karthik Gururaj, John...
145
Voted
PLDI
2011
ACM
14 years 6 months ago
The tao of parallelism in algorithms
For more than thirty years, the parallel programming community has used the dependence graph as the main abstraction for reasoning about and exploiting parallelism in “regular...
Keshav Pingali, Donald Nguyen, Milind Kulkarni, Ma...