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

by   Filip Petrovič, et al.

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.


page 1

page 2

page 3

page 4


Kernel Launcher: C++ Library for Optimal-Performance Portable CUDA Applications

Graphic Processing Units (GPUs) have become ubiquitous in scientific com...

Searching CUDA code autotuning spaces with hardware performance counters: data from benchmarks running on various GPU architectures

We have developed several autotuning benchmarks in CUDA that take into a...

Multiverse: Easy Conversion of Runtime Systems into OS Kernels via Automatic Hybridization

The hybrid runtime (HRT) model offers a path towards high performance an...

KASR: A Reliable and Practical Approach to Attack Surface Reduction of Commodity OS Kernels

Commodity OS kernels have broad attack surfaces due to the large code ba...

Pushing the Limits of Online Auto-tuning: Machine Code Optimization in Short-Running Kernels

We propose an online auto-tuning approach for computing kernels. Differe...

A Reliable and Practical Approach to Kernel Attack Surface Reduction of Commodity OS

Commodity OS kernels are known to have broad attack surfaces due to the ...

Automated Parallel Kernel Extraction from Dynamic Application Traces

Modern program runtime is dominated by segments of repeating code called...

Please sign up or login with your details

Forgot password? Click here to reset