CUDPP Documentation

rel_gems3-2

Introduction

CUDPP is the CUDA Data Parallel Primitives Library. CUDPP is a library of data-parallel algorithm primitives such as parallel-prefix-sum ("scan"), parallel sorting and parallel reduction. Primitives such as these are important building blocks for a wide variety of data-parallel algorithms, including sorting, stream compaction, and building data structures such as trees and summed-area tables.

Homepage

Homepage for CUDPP: http://www.gpgpu.org/developer/cudpp/

Announcements and discussion of CUDPP are hosted on the CUDPP Google Group.

Getting Started with CUDPP

You may want to start by browsing the CUDPP public interface. For information on building CUDPP, see Building CUDPP.

The "apps" subdirectory included with CUDPP has a few source code samples that use CUDPP:

• simpleCUDPP, a simple example of using cudppScan()
• satGL, an example of using cudppMultiScan() to generate a summed-area-table of a scene rendered in real time. The SAT is then used to simulate depth of field.
• cudpp_testrig, a comprehensive test application for all the functionality of CUDPP

We have also provided a code walkthrough of the simpleCUDPP example.

Release Notes

For specific release details see the Change Log.

Note:

This release (rel_gems3-2) should be considered beta code. This release was made to support the GPU Gems 3 article "Parallel Prefix Sum (Scan) with CUDA" (see references). Because this is beta code, the interfaces in the CUDPP library may change in a future release. In fact, some of the interfaces will change (for the better). To see some discussion about what will change, see the todo page.

This release (rel_gems3) has been tested on 32-bit Windows XP and 64-bit Redhat Enterprise Linux 5 (RHEL 5 x86_64). We expect the code to compile and work correctly on other linux flavors, but it has not yet been tested.

CUDA

CUDPP is implemented in NVIDIA CUDA. It requires the CUDA Toolkit version 1.0 or later. Please see the NVIDIA CUDA homepage to download CUDA as well as the CUDA Programming Guide and CUDA SDK, which includes many CUDA code examples.

Design Goals

Design goals for CUDPP include:

• Performance. We aim to provide best-of-class performance for our primitives. We welcome suggestions and contributions that will improve our performance. We also want to provide primitives that can be easily benchmarked, and compared against other implementations on GPUs and other processors.
• Modularity. We want our primitives to be easily included in other applications. To that end we have made the following design decisions:
  • CUDPP is provided as a library that can link against other applications.
  • CUDPP calls run on the GPU on GPU data. Thus they can be used as standalone calls on the GPU (with programmers initializing GPU data and performing copies back and forth) and, more importantly, as GPU components in larger CPU/GPU applications.
  • CUDPP is implemented as 4 layers:
    1. The Public Interface is the external library interface, which is the intended entry point for most applications. The public interface calls into the Application-Level API.
    2. The Application-Level API comprises functions callable from CPU code. These functions execute code jointly on the CPU and the GPU by calling into the Kernel-Level API below them.
    3. The Kernel-Level API comprises functions that run entirely on the GPU across an entire grid of thread blocks. These functions may call into the CTA-Level API below them.
    4. The CTA-Level API comprises functions that run entirely on the GPU within a single Cooperative Thread Array (CTA, aka Thread block). These are low-level functions implementing core data-parallel algorithms, typically by processing data within shared (CUDA __shared__) memory.

Programmers may use any of the lower three CUDPP layers in their own programs by building the source directly into their application. However, the typical usage of CUDPP is to link to the library and invoke functions in the CUDPP Public Interface, as in the simpleCUDPP, satGL, and cudpp_testrig application examples included in the CUDPP distribution.

In the future, if and when CUDA supports building device-level libraries, we hope to enhance CUDPP to ease the use of CUDPP internal algorithms at all levels.

Use Cases

We expect the normal use of CUDPP will be in one of two ways:

1. Linking the CUDPP library against another application.
2. Running our "test" application, cudpp_testrig, that exercises CUDPP functionality.

References

The following publications describe work incorporated in CUDPP.

• Mark Harris, Shubhabrata Sengupta, and John D. Owens. "Parallel Prefix Sum (Scan) with CUDA". In Hubert Nguyen, editor, GPU Gems 3, chapter 39, pages 851–876. Addison Wesley, August 2007. http://graphics.idav.ucdavis.edu/publications/print_pub?pub_id=916
• Shubhabrata Sengupta, Mark Harris, Yao Zhang, and John D. Owens. "Scan Primitives for GPU Computing". In Graphics Hardware 2007, pages 97–106, August 2007. http://graphics.idav.ucdavis.edu/publications/print_pub?pub_id=915

Credits

CUDPP Developers

• Mark Harris, NVIDIA Ltd.
• John D. Owens, University of California, Davis
• Shubho Sengupta, University of California, Davis
• Yao Zhang, University of California, Davis
• Andrew Davidson, Louisiana State University

Other CUDPP Contributors

• Nadatur Satish, University of California, Berkeley

Acknowledgments

Thanks to Jim Ahrens, Ian Buck, Guy Blelloch, Jeff Bolz, Jeff Inman, Eric Lengyel, David Luebke, Pat McCormick, and Richard Vuduc for their contributions during the development of this library.

Thanks also to our funding agencies:

• Department of Energy Early Career Principal Investigator Award DE-FG02-04ER25609
• SciDAC Institute for Ultrascale Visualization (http://www.iusv.org/)
• Los Alamos National Laboratory
• National Science Foundation (grant 0541448)
• Generous hardware donations from NVIDIA

CUDPP Copyright and Software License

CUDPP is copyright The Regents of the University of California, Davis campus and NVIDIA Corporation. The license is a modified version of the BSD license, designed to encourage reuse of this software in other projects, both commercial and non-commercial. For details, please see the CUDPP License page.

---