# A Benchmark Set of Highly-efficient CUDA and OpenCL Kernels and its Dynamic Autotuning with Kernel Tuning Toolkit

arXiv: https://arxiv.org/abs/1910.08498 · HTML: https://mlsanity.com/paper/1910.08498/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2019.

## Built on by (most cited first, 6 of 6)

- [BaCO: A Fast and Portable Bayesian Compiler Optimization Framework](https://mlsanity.com/paper/2212.11142/) (2022)
- [CATBench: A Compiler Autotuning Benchmarking Suite for Black-box Optimization](https://mlsanity.com/paper/2406.17811/) (2024)
- [Using hardware performance counters to speed up autotuning convergence on GPUs](https://mlsanity.com/paper/2102.05297/) (2021)
- [Searching CUDA code autotuning spaces with hardware performance counters: data from benchmarks running on various GPU architectures](https://mlsanity.com/paper/2102.05299/) (2021)
- [Tuning the Tuner: Introducing Hyperparameter Optimization for Auto-Tuning](https://mlsanity.com/paper/2509.26300/) (2025)
- [Automated Algorithm Design for Auto-Tuning Optimizers](https://mlsanity.com/paper/2510.17899/) (2025)

## Abstract (arXiv)

Autotuning of performance-relevant source-code parameters allows to automatically tune applications without hard coding optimizations and thus helps with keeping the performance portable. In this paper, we introduce a benchmark set of ten autotunable kernels for important computational problems implemented in OpenCL or CUDA. Using our Kernel Tuning Toolkit, we show that with autotuning most of the kernels reach near-peak performance on various GPUs and outperform baseline implementations on CPUs and Xeon Phis. Our evaluation also demonstrates that autotuning is key to performance portability. In addition to offline tuning, we also introduce dynamic autotuning of code optimization parameters during application runtime. With dynamic tuning, the Kernel Tuning Toolkit enables applications to re-tune performance-critical kernels at runtime whenever needed, for example, when input data changes. Although it is generally believed that autotuning spaces tend to be too large to be searched during application runtime, we show that it is not necessarily the case when tuning spaces are designed rationally. Many of our kernels reach near peak-performance with moderately sized tuning spaces that can be searched at runtime with acceptable overhead. Finally we demonstrate, how dynamic performance tuning can be integrated into a real-world application from cryo-electron microscopy domain.