This work presents MLIR, a novel approach to building reusable and extensible compiler
infrastructure. MLIR addresses software fragmentation, compilation for heterogeneous …

This work presents MLIR, a novel approach to building reusable and extensible compiler
infrastructure. MLIR aims to address software fragmentation, improve compilation for …

The KeOps library provides a fast and memory-efficient GPU support for tensors whose
entries are given by a mathematical formula, such as kernel and distance matrices. KeOps …

The performance bottlenecks of graph applications depend not only on the algorithm and
the underlying hardware, but also on the size and structure of the input graph. As a result …

High-performance kernel libraries are critical to exploiting accelerators and specialized
instructions in many applications. Because compilers are difficult to extend to support …

Achieving high performance for compute-intensive operators in machine learning (ML)
workloads is a crucial but challenging task. Many ML and system practitioners rely on …

Driven by deep learning, there has been a surge of specialized processors for matrix
multiplication, referred to as Tensor Core Units (TCUs). These TCUs are capable of …

Optimizing programs to run efficiently on modern parallel hardware is hard but crucial for
many applications. The predominantly used imperative languages-like C or OpenCL-force …

Tensor programs often need to process large tensors (vectors, matrices, or higher order
tensors) that require a specialized storage format for their memory layout. Several such …

Many graph problems can be solved using ordered parallel graph algorithms that achieve
significant speedup over their unordered counterparts by reducing redundant work. This …