Anonymized Network Sensing using C++26 std::execution on GPUs

2025-10-15

AI Summary

To address the challenges of complex GPU memory management and difficult workload portability in large-scale network traffic analysis, this paper proposes a multi-GPU anonymous network-aware computing framework built upon the C++26 `std::execution` asynchronous programming model. It pioneers the integration of Sender/Receiver semantics into network-aware graph computation, elevating GPUs to first-class execution entities and enabling cross-device composable asynchronous scheduling with fine-grained memory control. The framework constructs task chains using standardized execution policies, balancing developer productivity and peak performance. Evaluated on an 8-GPU NVIDIA A100 system, it achieves up to 55× speedup over a serial GraphBLAS baseline, significantly improving parallel efficiency and scalability. This work establishes a novel paradigm for real-time network analysis in high-density GPU environments.

Technology Category

• Machine Learning: Hardware-aware ML
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Large-scale network sensing plays a vital role in network traffic analysis and characterization. As network packet data grows increasingly large, parallel methods have become mainstream for network analytics. While effective, GPU-based implementations still face start-up challenges in host-device memory management and porting complex workloads on devices, among others. To mitigate these challenges, composable frameworks have emerged using modern C++ programming language, for efficiently deploying analytics tasks on GPUs. Specifically, the recent C++26 Senders model of asynchronous data operation chaining provides a simple interface for bulk pushing tasks to varied device execution contexts. Considering the prominence of contemporary dense-GPU platforms and vendor-leveraged software libraries, such a programming model consider GPUs as first-class execution resources (compared to traditional host-centric programming models), allowing convenient development of multi-GPU application workloads via expressive and standardized asynchronous semantics. In this paper, we discuss practical aspects of developing the Anonymized Network Sensing Graph Challenge on dense-GPU systems using the recently proposed C++26 Senders model. Adopting a generic and productive programming model does not necessarily impact the critical-path performance (as compared to low-level proprietary vendor-based programming models): our commodity library-based implementation achieves up to 55x performance improvements on 8x NVIDIA A100 GPUs as compared to the reference serial GraphBLAS baseline.

Problem

• Addresses GPU memory management challenges in network sensing
• Enables portable deployment of analytics on multi-GPU systems
• Achieves high performance using C++26 asynchronous execution model

Innovation

• Uses C++26 Senders model for asynchronous operations
• Leverages GPUs as first-class execution resources
• Achieves performance via composable library-based implementation