Abstract: Summary form only given. In this tutorial, I will give an overview of current approaches to compiler-directed power and energy mangement. I will discuss several promising compiler ...

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

The evolution of artificial intelligence (AI) models and hardware accelerators has brought about unique challenges for compilers. These challenges stem from the constantly evolving architecture of AI ...

This RFC proposes the creation of a new community-driven documentation platform for https://compilers.wiki, with the goal of providing a centralized and up-to-date resource for information about ...

With the recent popularity of neural networks comes the need for efficient serving of inference workloads. A neural network inference workload can be represented as a computational graph with nodes as ...

A family of C, C++ and FORTRAN compilers for PCs from Sybase Waterloo, a division of Sybase. Originally produced by Watcom International Corporation, Waterloo, Ontario, Watcom compilers have been ...