Fast and efficient automatic memory management for GPUs using compiler-assisted runtime coherence scheme

Parallel Architectures and Compilation Techniques - Conference Proceedings, PACT

Volumn , Issue , 2012, Pages 33-42

  Pai, Sreepathi ^a   Govindarajan, R ^a   Thazhuthaveetil, Matthew J ^a  

^a INDIAN INSTITUTE OF SCIENCE   (India)

Author keywords

Automatic; Data transfers; GPU; Memory management; Software coherence

Indexed keywords

AUTOMATIC; AUTOMATIC MEMORY MANAGEMENT; BENCHMARK SUITES; COMPILER ANALYSIS; COMPILER-ASSISTED; ERROR PRONES; GPU; MANUAL MEMORY-MANAGEMENT; MEMORY MANAGEMENT; MEMORY MANAGER; PERFORMANCE POTENTIALS; RODINIA; RUNTIMES;

DATA TRANSFER; PARALLEL ARCHITECTURES;

PROGRAM COMPILERS;

EID: 84867509022     PISSN: 1089795X     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1145/2370816.2370824     Document Type: Conference Paper

References (21)

1. M. M. Baskaran, U. Bondhugula, et al. Automatic data movement and computation mapping for multi-level parallel architectures with explicitly managed memories. In PPoPP, 2008.
2. B. L. Chamberlain, D. Callahan, and H. P. Zima. Parallel programmability and the Chapel language. International Journal of High Performance Computing Applications, 21:291-312, 2007.
3. P. Charles, C. Grothoff, V. Saraswat, et al. X10: An object-oriented approach to non-uniform cluster computing. In OOPSLA, 2005.
4. S. Che, M. Boyer, J. Meng, et al. Rodinia: A benchmark suite for heterogeneous computing. In IISWC, 2009.
5. A. E. Eichenberger, K. O'Brien, et al. Optimizing compiler for the CELL processor. In PACT, 2005.
6. I. Gelado, J. E. Stone, et al. An asymmetric distributed shared memory model for heterogeneous parallel systems. In ASPLOS, 2010.
7. I. Gelado et al. GMAC: Global Memory for Accelerators (version 0.0.20). URL http://code.google.com/p/adsm/.
8. T. B. Jablin, P. Prabhu, et al. Automatic CPU-GPU communication management and optimization. In PLDI, 2011.
9. T. B. Jablin, J. A. Jablin, et al. Dynamically Managed Data for CPU-GPU architectures. In CGO, March 2012.
10. Khronos. OpenCL: The open standard for parallel programming of heterogeneous systems. URL http://www.khronos.org/opencl.
11. S. Lee and R. Eigenmann. OpenMPC: Extended OpenMP programming and tuning for GPUs. In SC, 2010.
12. S. Lee, S.-J. Min, and R. Eigenmann. OpenMP to GPGPU: a compiler framework for automatic translation and optimization. In PPoPP, 2009.
13. V. W. Lee, C. Kim, et al. Debunking the 100X GPU vs. CPU myth: an evaluation of throughput computing on CPU and GPU. In ISCA, 2010.
14. NVIDIA. CUDA: Compute Unified Device Architecture. URL http://developer.nvidia.com/cuda.
15. NVIDIA. NVIDIA CUDA C Programming Guide version 4.0. 2011.
16. G. Paoloni. How to benchmark code execution times on Intel IA-32 and IA-64 instruction set architectures. 2010.
17. B. Saha, X. Zhou, et al. Programming model for a heterogeneous x86 platform. In PLDI, 2009.
18. L. Seiler, D. Carmean, et al. Larrabee: A many-core x86 architecture for visual computing. ACM Trans. Graph., 27(3), 2008.
19. A. Sidelnik, B. L. Chamberlain, M. J. Garzaran, and D. Padua. Using the High Productivity Language Chapel to target GPGPU architectures. Technical report, UIUC Dept. of Computer Science, 2011.
20. TOP500.org. The Top 500. URL http://www.top500.org/.
21. x10 lang.org. X10 2.1 cuda. URL http://docs.codehaus.org/display/ XTENLANG/X10+2.1+CUDA.