Logo
  • 1. Introduction
  • 2. Floating Point
  • 3. Dot Product: An Accuracy Example
  • 4. CUDA and Floating Point
  • 5. Considerations for a Heterogeneous World
  • 6. Concrete Recommendations
  • 7. Acknowledgements
  • 8. References
  • 9. Notices
Floating Point and IEEE 754
  • »
  • Contents
  • v12.9 | PDF | Archive  

Contents

White paper covering the most common issues related to NVIDIA GPUs.

  • 1. Introduction
  • 2. Floating Point
    • 2.1. Formats
    • 2.2. Operations and Accuracy
    • 2.3. The Fused Multiply-Add (FMA)
  • 3. Dot Product: An Accuracy Example
    • 3.1. Example Algorithms
    • 3.2. Comparison
  • 4. CUDA and Floating Point
    • 4.1. Compute Capability 2.0 and Above
    • 4.2. Rounding Modes
    • 4.3. Controlling Fused Multiply-add
    • 4.4. Compiler Flags
    • 4.5. Differences from x86
  • 5. Considerations for a Heterogeneous World
    • 5.1. Mathematical Function Accuracy
    • 5.2. x87 and SSE
    • 5.3. Core Counts
    • 5.4. Verifying GPU Results
  • 6. Concrete Recommendations
  • 7. Acknowledgements
  • 8. References
  • 9. Notices
    • 9.1. Notice
    • 9.2. OpenCL
    • 9.3. Trademarks

Privacy Policy | Manage My Privacy | Do Not Sell or Share My Data | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © 2011-2025, NVIDIA Corporation & affiliates. All rights reserved.

Last updated on Apr 18, 2025.