In recent years, researchers have proposed a number of automated tools t...
Compiler backends should be automatically generated from hardware design...
We present egglog, a fixpoint reasoning system that unifies Datalog and
...
Library learning compresses a given corpus of programs by extracting com...
Satisfiability Modulo Theory (SMT) solvers and equality saturation engin...
Specialized accelerators are increasingly used to meet the power-perform...
Many compilers, synthesizers, and theorem provers rely on rewrite rules ...
We present a new approach to e-matching based on relational join; in
par...
Past work on optimizing fabrication plans given a carpentry design can
p...
Past work on optimizing fabrication plans given a carpentry design can
p...
Tensor kernels in machine learning (ML) often correspond to pure mathema...
Checkpointing enables training deep learning models under restricted mem...
Modern deep neural networks increasingly make use of features such as dy...
An e-graph efficiently represents a congruence relation over many
expres...
An E-graph is a data structure that can efficiently encode the congruenc...
Development of formal proofs of correctness of programs can increase act...
A core problem in hardware-software codesign is in the sheer size of the...
Recent program synthesis techniques help users customize CAD models(e.g....
Computational fabrication is increasingly popular among end-users and ma...
Frameworks for writing, compiling, and optimizing deep learning (DL) mod...
Frameworks for writing, compiling, and optimizing deep learning (DL) mod...
Machine learning powers diverse services in industry including search,
t...
Designing and debugging distributed systems is notoriously difficult. Th...
Recent renewed interest in optimizing and analyzing floating-point progr...
Floating point arithmetic plays a central role in science, engineering, ...