13 citations · 40 across the 14 of their papers we have counts for
15 papers
Improving Inference Performance of Machine Learning with the Divide-and-Conquer Principle
Alex Kogan
Many popular machine learning models scale poorly when deployed on CPUs. In this paper we explore the reasons why and propose a simple, yet effective approach based on the well-kno…
Intra-process Caching and Reuse of Threads
Dave Dice, Alex Kogan
Creating and destroying threads on modern Linux systems incurs high latency, absent concurrency, and fails to scale as we increase concurrency. To address this concern we introduce…
Ready When You Are: Efficient Condition Variables via Delegated Condition Evaluation
Dave Dice, Alex Kogan
Multi-thread applications commonly utilize condition variables for communication between threads. Condition variables allow threads to block and wait until a certain condition hold…
Optimizing Inference Performance of Transformers on CPUs
Dave Dice, Alex Kogan
The Transformer architecture revolutionized the field of natural language processing (NLP). Transformers-based models (e.g., BERT) power many important Web services, such as search…
Compact Java Monitors
Dave Dice, Alex Kogan
For scope and context, the idea we'll describe below, Compact Java Monitors, is intended as a potential replacement implementation for the "synchronized" construct in the HotSpot J…
Hemlock : Compact and Scalable Mutual Exclusion
Dave Dice, Alex Kogan
We present Hemlock, a novel mutual exclusion locking algorithm that is extremely compact, requiring just one word per thread plus one word per lock, but which still provides local…