Tensor program tuning is a non-convex objective optimization problem, to which search-
based approaches have proven to be effective. At the core of the search-based approaches …

Deep Neural Networks (DNNs) have shown excellent performance in a wide range of
machine learning applications. Knowing the latency of running a DNN model or tensor …

Tuning tensor program generation involves navigating a vast search space to find optimal
program transformations and measurements for a program on the target hardware. The …

Deep learning compilers with auto-tuners have the ability to generate high-performance
programs, particularly tensor programs on accelerators. However, the performance of these …

The requirement for deploying deep learning (DL) models efficiently has boosted the
research of DL compilers. Especially, the difficulty of generating optimized tensor programs …

AI applications powered by deep learning are increasingly running on edge devices.
Meanwhile, many real-world IoT applications demand multiple real-time tasks to run on the …

Many artificial intelligence models process input data of different lengths and resolutions,
making the shape of the tensors dynamic. The performance of these models depends on the …

Tensor program optimization on Deep Learning Accelerators (DLAs) is critical for efficient
model deployment. Although search-based Deep Learning Compilers (DLCs) have …

Real-time personalized applications require optimized on-device model adaptation to
deliver immediate responses. This paper introduces a hybrid architecture that effectively …