Gaussian processes are widely used in machine learning domains but remain computationally demanding, limiting their efficient scalability across emerging hardware platforms. The GPRat library addresses these challenges using the HPX asynchronous many-task runtime system. In this work, we extend GPRat to enable portability across multiple hardware architectures and evaluate its performance on representative x86-64, ARM, and RISC-V chips. We conduct node-level strong scaling and problem size scaling benchmarks for Gaussian process prediction and hyperparameter optimization to assess single-core performance, parallel scalability, and architectural efficiency. Our results show that while the x86-64 Zen 2 chip achieves a 58% single-core performance advantage over the ARM-based Fujitsu A64FX, superior parallel scaling allows the 48-core ARM chip to outperform the 64-core Zen 2 by 9% at full node utilization. The evaluated SOPHON SG2042 RISC-V chip exhibits substantially lower performance and weaker scalability, with single-core performance lagging by up to a factor of 14 and large-scale parallel workloads showing slowdowns of up to a factor of 24. For problem size scaling, ARM and x86-64 systems demonstrate comparable performance within 23%. These findings highlight the growing competitiveness of purpose-built ARM chips. Furthermore, they underscore the importance of wide-register vectorization support and improvements to the memory subsystem for upcoming RISC-V platforms, especially when targeted by many-task runtimes.

翻译：摘要：高斯过程广泛用于机器学习领域，但其计算密集性限制了其在新兴硬件平台上高效扩展的潜力。GPRat库利用HPX异步多任务运行时系统解决了这些挑战。本研究扩展GPRat以支持跨多种硬件架构的可移植性，并评估其在代表性x86-64、ARM和RISC-V芯片上的性能。我们针对高斯过程预测与超参数优化开展了节点级强扩展与问题规模扩展基准测试，以评估单核性能、并行可扩展性及架构效率。结果显示，尽管x86-64 Zen 2芯片单核性能比基于ARM的Fujitsu A64FX高出58%，但48核ARM芯片凭借优异的并行扩展能力，在满节点利用率下性能反超64核Zen 2芯片9%。经评估的SOPHON SG2042 RISC-V芯片性能显著较低且可扩展性较弱，其单核性能差距最高达14倍，大规模并行工作负载的减速比最高达24倍。在问题规模扩展方面，ARM与x86-64系统性能差异在23%以内。这些发现凸显了专用ARM芯片日益增强的竞争力，同时强调了宽寄存器向量化支持与内存子系统改进对即将推出的RISC-V平台的重要性，尤其当面向多任务运行时系统时。