1 / 16

Experiences Accelerating MATLAB Systems Biology Applications Myocyte

Experiences Accelerating MATLAB Systems Biology Applications Myocyte. Lukasz Szafaryn, Kevin Skadron, and Jeffrey J. Saucerman University of Virginia. Outline. MATLAB Optimizations to MATLAB GPU Acceleration with CUDA Applications (Heart Wall Tracking and Myocyte Simulation) Problem

grant-henry
Télécharger la présentation

Experiences Accelerating MATLAB Systems Biology Applications Myocyte

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Experiences Accelerating MATLAB Systems Biology ApplicationsMyocyte Lukasz Szafaryn, Kevin Skadron, and Jeffrey J. Saucerman University of Virginia

  2. Outline • MATLAB • Optimizations to MATLAB • GPU Acceleration with CUDA • Applications (Heart Wall Tracking and Myocyte Simulation) • Problem • Algorithm • Optimization and performance • Lessons • Conclusions • Future Research

  3. MATLAB • Convenient but inefficient programming language of choice for scientists - Interpreted language - Most of the existing code and libraries are single-threaded • MATLAB Parallel Toolbox - understanding of parallel programming • Jacket and GPUmat - large parallelism to justify overhead

  4. MATLAB contd. • Interpreted language optimized by JIT compiler – 2x slower than C • MATLAB Embedded Compiler has limited support – 1.2-1.4x slower than C • MEX Interface to link C code - translating to C - many functions written from scratch - no support for convenient OpenMP standard, need to use thread libraries

  5. Acceleration • Translation: - convert MATLAB to C • Parallelization: • C for multi-core CPU • CUDA for GPU Experimental Setup • CPU: 3.2 GHz quad-core Intel Core 2 Extreme • GPU: NVIDIA GeForce GTX 280 (PCIe 2.0) • MS Windows, MS C Compiler

  6. Acceleration with GPU (CUDA) CPU GPU C Program • Allocate GPU memory • Transfer inputs • Launch kernel • Return to CPU • Transfer results • Free GPU memory CUDA Kernel

  7. Myocyte SimulationApplication ODE Values / Next time step 35% ODE solver 65% Model evaluation 91 equations Initial Values • Models single cardiac myocyte and its electrical activity - determined to be a key aspect in the development of heart failure • Modeled by 91 Ordinary Differential Equations (ODEs) and 250 supporting equations

  8. Myocyte SimulationAlgorithm task-level parallelism (TLP) • Sequential nature of ODE solving does not allow processing of time steps in parallel • Speed-up from parallelizing model evaluation is limited by Amdahl's law • Mainly fine-grained TLP, no DLP, limited coarse-grained TLP by grouping equations 1 2 3 4 15 … time

  9. Myocyte SimulationPerformance of a Single Simulation 1.28x 1.52x 1.57x 2.23x 2.40x 2.19x 4.29x • Time reported for 10,000-point simulation (10s of simulated time)

  10. Myocyte SimulationPerformance of Multiple Simulations OpenMP constant ~3.6x speedup CUDA saturates at ~10.88x speedup • Time reported for 1000-point simulation (1.0s of simulated time) using a custom solver

  11. Porting Tradeoffs Convenience Performance • Developing modular code • replacing each MATLAB function with equivalent parallelized GPU function • common routines can be possibly reused in other applications • Hiding specific aspects of GPU programming inside each module • each module sets up its own GPU execution parameters • each module performs its own I/O with GPU transparently • Restructuring and combining code • writing code based on algorithm tasks rather than MATLAB statements • overlap parallel (often unrelated) tasks by executing them in the same kernel call • Exposing specific aspects of GPU programming • doing more work inside each GPU kernel call to fully exploit parallelism and avoid overhead • performing I/O with GPU manually to eliminate redundant data transfers

  12. Myocyte SimulationLessons • Typical MATLAB code written by a scientist has room for optimization – 2.0x • Conversion of the model to C was straightforward • More speedup possible by accelerating entire solver, not just the model evaluation • GPU can still provide best acceleration if its overhead is eliminated (heterogeneous chip), but… • Significant speedup is anticipated by offloading application to FPGA (well suited to fine-grained irregular parallelism)

  13. Conclusions • Limited availability of C libraries necessitates time consuming coding • Many systems biology applications (even those with limited parallelism) benefit from GPU • GPU overheads are significant (should be eliminated in new CPU-GPU architectures) • Real-time processing feasible in near future • Ultimately, acceleration of applications should be automated!

  14. Future Research • Automatic acceleration with the use of compiler - via use of architecture-specific libraries - via compiling for target architecture • Merging of workloads - based on resource needs - based on dependency • Acceleration with alternative architectures - well suited for fine-grained parallelism - esp. FPGA

  15. Acknowledgements • Funding provided by: • NSF grant IIS-0612049 • SRC grant 1607.001 • Equipment donated by NVIDIA

  16. Software Source code will be soon available at: http://lava.cs.virginia.edu/wiki/rodinia

More Related