Related papers: Autotuning GPU Kernels via Static and Predictive A…

Real-world experiments involve batched & delayed feedback, non-stationarity, multiple objectives & constraints, and (often some) personalization. Tailoring adaptive methods to address these challenges on a per-problem basis is infeasible,…

High-performance streams of (pseudo) random numbers are crucial for the efficient implementation for countless stochastic algorithms, most importantly, Monte Carlo simulations and molecular dynamics simulations with stochastic thermostats.…

In a heterogeneous, dynamic environment, like Grid, post-mortem analysis is of no use and data needs to be collected and analysed in real time. Novel techniques are also required for dynamically tuning the application's performance and…

Instrumenting programs for performing run-time checking of properties, such as regular shapes, is a common and useful technique that helps programmers detect incorrect program behaviors. This is specially true in dynamic languages such as…

In order to satisfy timing constraints, modern real-time applications require massively parallel accelerators such as General Purpose Graphic Processing Units (GPGPUs). Generation after generation, the number of computing clusters made…

Histograms are widely used in medical imaging, network intrusion detection, packet analysis and other stream-based high throughput applications. However, while porting such software stacks to the GPU, the computation of the histogram is a…

Machine learning techniques applied to software engineering tasks can be improved by hyperparameter optimization, i.e., automatic tools that find good settings for a learner's control parameters. We show that such hyperparameter…

Optimizing GPU kernels presents a significantly greater challenge for large language models (LLMs) than standard code generation tasks, as it requires understanding hardware architecture, parallel optimization strategies, and performance…

This paper describes in detail the bitonic sort algorithm,and implements the bitonic sort algorithm based on cuda architecture.At the same time,we conduct two effective optimization of implementation details according to the characteristics…

We present a new algorithm to quickly generate high-performance GPU implementations of complex imaging and vision pipelines, directly from high-level Halide algorithm code. It is fully automatic, requiring no schedule templates or…

Context: Data miners have been widely used in software engineering to, say, generate defect predictors from static code measures. Such static code defect predictors perform well compared to manual methods, and they are easy to use and…

Parameter-efficient tuning aims at updating only a small subset of parameters when adapting a pretrained model to downstream tasks. In this work, we introduce PASTA, in which we only modify the special token representations (e.g., [SEP] and…

In this paper, we study the parallelization of the dedispersion algorithm on many-core accelerators, including GPUs from AMD and NVIDIA, and the Intel Xeon Phi. An important contribution is the computational analysis of the algorithm, from…

Parallel computing can offer an enormous advantage regarding the performance for very large applications in almost any field: scientific computing, computer vision, databases, data mining, and economics. GPUs are high performance many-core…

GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong performance in general programming, large language models (LLMs) remain uncompetitive…

Constrained optimization problems arise frequently in classical machine learning. There exist frameworks addressing constrained optimization, for instance, CVXPY and GENO. However, in contrast to deep learning frameworks, GPU support is…

The Efficient Global Optimization (EGO) algorithm uses a conditional Gaus-sian Process (GP) to approximate an objective function known at a finite number of observation points and sequentially adds new points which maximize the Expected…

Modern GPUs are able to perform significantly more arithmetic operations than transfers of a single word to or from global memory. Hence, many GPU kernels are limited by memory bandwidth and cannot exploit the arithmetic power of GPUs.…

Efficient implementations of HPC applications for parallel architectures generally rely on external software packages (e.g., BLAS, LAPACK, CUDNN). While these libraries provide highly optimized routines for certain characteristics of inputs…

Designing and optimizing FPGA overlays is a complex and time-consuming process, often requiring multiple trial-and-error iterations to determine a suitable configuration. This paper presents an AI-driven approach to optimizing FPGA overlay…