It has been a long time that computer architecture and systems are optimized for efficient
execution of machine learning (ML) models. Now, it is time to reconsider the relationship …

In node classification tasks, graph convolutional neural networks (GCNs) have
demonstrated competitive performance over traditional methods on diverse graph data …

Abstract Machine learning (ML) is increasingly seen as a viable approach for building
compiler optimization heuristics, but many ML methods cannot replicate even the simplest of …

Past research has proposed numerous hardware prefetching techniques, most of which rely
on exploiting one specific type of program context information (eg, program counter …

Detecting semantically similar functions--a crucial analysis capability with broad real-world
security usages including vulnerability detection, malware lineage, and forensics--requires …

Program execution speed critically depends on increasing cache hits, as cache hits are
orders of magnitude faster than misses. To increase cache hits, we focus on the problem of …

Edge TPUs are a domain of accelerators for low-power, edge devices and are widely used
in various Google products such as Coral and Pixel devices. In this paper, we first discuss …

Graph neural networks (GNNs) have emerged as a powerful tool for learning software
engineering tasks including code completion, bug finding, and program repair. They benefit …

Analytical hardware performance models yield swift estimation of desired hardware
performance metrics. However, developing these analytical models for modern processors …

A significant effort has been made to train neural networks that replicate algorithmic
reasoning, but they often fail to learn the abstract concepts underlying these algorithms. This …