Peter Michaleas
YOU?
Author Swipe
View article: Advancing AI Challenges for the United States Department of the Air Force
Advancing AI Challenges for the United States Department of the Air Force Open
The DAF-MIT AI Accelerator is a collaboration between the United States Department of the Air Force (DAF) and the Massachusetts Institute of Technology (MIT). This program pioneers fundamental advances in artificial intelligence (AI) to ex…
View article: Performance and Numerical Aspects of Decompositional Factorizations with FP64 Floating-Point Emulation in INT8
Performance and Numerical Aspects of Decompositional Factorizations with FP64 Floating-Point Emulation in INT8 Open
Mixing precisions for performance has been an ongoing trend as the modern hardware accelerators started including new, and mostly lower-precision, data formats. The advantage of using them is a great potential of performance gain and energ…
View article: GraphBLAS Mathematical Opportunities: Parallel Hypersparse, Matrix Based Graph Streaming, and Complex-Index Matrices
GraphBLAS Mathematical Opportunities: Parallel Hypersparse, Matrix Based Graph Streaming, and Complex-Index Matrices Open
The GraphBLAS high performance library standard has yielded capabilities beyond enabling graph algorithms to be readily expressed in the language of linear algebra. These GraphBLAS capabilities enable new performant ways of thinking about …
View article: Lincoln AI Computing Survey (LAICS) and Trends
Lincoln AI Computing Survey (LAICS) and Trends Open
In the past year, generative AI (GenAI) models have received a tremendous amount of attention, which in turn has increased attention to computing systems for training and inference for GenAI. Hence, an update to this survey is due. This pa…
View article: Easy Acceleration with Distributed Arrays
Easy Acceleration with Distributed Arrays Open
High level programming languages and GPU accelerators are powerful enablers for a wide range of applications. Achieving scalable vertical (within a compute node), horizontal (across compute nodes), and temporal (over different generations …
View article: DBOS Network Sensing: A Web Services Approach to Collaborative Awareness
DBOS Network Sensing: A Web Services Approach to Collaborative Awareness Open
DBOS (DataBase Operating System) is a novel capability that integrates web services, operating system functions, and database features to significantly reduce web-deployment effort while increasing resilience. Integration of high performan…
View article: Accelerating AI Development with Cyber Arenas
Accelerating AI Development with Cyber Arenas Open
AI development requires high fidelity testing environments to effectively transition from the laboratory to operations. The flexibility offered by cyber arenas presents a novel opportunity to test new artificial intelligence (AI) capabilit…
View article: GPU Sharing with Triples Mode
GPU Sharing with Triples Mode Open
There is a tremendous amount of interest in AI/ML technologies due to the proliferation of generative AI applications such as ChatGPT. This trend has significantly increased demand on GPUs, which are the workhorses for training AI models. …
View article: LLload: An Easy-to-Use HPC Utilization Tool
LLload: An Easy-to-Use HPC Utilization Tool Open
The increasing use and cost of high performance computing (HPC) requires new easy-to-use tools to enable HPC users and HPC systems engineers to transparently understand the utilization of resources. The MIT Lincoln Laboratory Supercomputin…
View article: Supercomputer 3D Digital Twin for User Focused Real-Time Monitoring
Supercomputer 3D Digital Twin for User Focused Real-Time Monitoring Open
Real-time supercomputing performance analysis is a critical aspect of evaluating and optimizing computational systems in a dynamic user environment. The operation of supercomputers produce vast quantities of analytic data from multiple sou…
View article: Hypersparse Traffic Matrices from Suricata Network Flows using GraphBLAS
Hypersparse Traffic Matrices from Suricata Network Flows using GraphBLAS Open
Hypersparse traffic matrices constructed from network packet source and destination addresses is a powerful tool for gaining insights into network traffic. SuiteSparse: GraphBLAS, an open source package or building, manipulating, and analy…
View article: HPC with Enhanced User Separation
HPC with Enhanced User Separation Open
HPC systems used for research run a wide variety of software and workflows. This software is often written or modified by users to meet the needs of their research projects, and rarely is built with security in mind. In this paper we explo…
View article: Anonymized Network Sensing Graph Challenge
Anonymized Network Sensing Graph Challenge Open
The MIT/IEEE/Amazon GraphChallenge encourages community approaches to developing new solutions for analyzing graphs and sparse data derived from social media, sensor feeds, and scientific data to discover relationships between events as th…
View article: What is Normal? A Big Data Observational Science Model of Anonymized Internet Traffic
What is Normal? A Big Data Observational Science Model of Anonymized Internet Traffic Open
Understanding what is normal is a key aspect of protecting a domain. Other domains invest heavily in observational science to develop models of normal behavior to better detect anomalies. Recent advances in high performance graph libraries…
View article: LLload: Simplifying Real-Time Job Monitoring for HPC Users
LLload: Simplifying Real-Time Job Monitoring for HPC Users Open
One of the more complex tasks for researchers using HPC systems is performance monitoring and tuning of their applications.Developing a practice of continuous performance improvement, both for speed-up and efficient use of resources is ess…
View article: LLload: Simplifying Real-Time Job Monitoring for HPC Users
LLload: Simplifying Real-Time Job Monitoring for HPC Users Open
One of the more complex tasks for researchers using HPC systems is performance monitoring and tuning of their applications. Developing a practice of continuous performance improvement, both for speed-up and efficient use of resources is es…
View article: Teaching Network Traffic Matrices in an Interactive Game Environment
Teaching Network Traffic Matrices in an Interactive Game Environment Open
Understanding what is normal is a key aspect of protecting a domain. Other domains invest heavily in observational science to develop models of normal behavior to better detect anomalies. Recent advances in high performance graph libraries…
View article: Teaching Network Traffic Matrices in an Interactive Game Environment
Teaching Network Traffic Matrices in an Interactive Game Environment Open
The Internet has become a critical domain for modern society that requires ongoing efforts for its improvement and protection. Network traffic matrices are a powerful tool for understanding and analyzing networks and are broadly taught in …
View article: Hypersparse Traffic Matrix Construction using GraphBLAS on a DPU
Hypersparse Traffic Matrix Construction using GraphBLAS on a DPU Open
Low-power small form factor data processing units (DPUs) enable offloading and acceleration of a broad range of networking and security services. DPUs have accelerated the transition to programmable networking by enabling the replacement o…
View article: Lincoln AI Computing Survey (LAICS) Update
Lincoln AI Computing Survey (LAICS) Update Open
This paper is an update of the survey of AI accelerators and processors from past four years, which is now called the Lincoln AI Computing Survey - LAICS (pronounced "lace"). As in past years, this paper collects and summarizes the current…
View article: Mapping of Internet "Coastlines" via Large Scale Anonymized Network Source Correlations
Mapping of Internet "Coastlines" via Large Scale Anonymized Network Source Correlations Open
Expanding the scientific tools available to protect computer networks can be aided by a deeper understanding of the underlying statistical distributions of network traffic and their potential geometric interpretations. Analyses of large sc…
View article: pPython Performance Study
pPython Performance Study Open
pPython seeks to provide a parallel capability that provides good speed-up without sacrificing the ease of programming in Python by implementing partitioned global array semantics (PGAS) on top of a simple file-based messaging library (Pyt…
View article: Focusing and Calibration of Large Scale Network Sensors using GraphBLAS Anonymized Hypersparse Matrices
Focusing and Calibration of Large Scale Network Sensors using GraphBLAS Anonymized Hypersparse Matrices Open
Defending community-owned cyber space requires community-based efforts. Large-scale network observations that uphold the highest regard for privacy are key to protecting our shared cyberspace. Deployment of the necessary network sensors re…
View article: Deployment of Real-Time Network Traffic Analysis using GraphBLAS Hypersparse Matrices and D4M Associative Arrays
Deployment of Real-Time Network Traffic Analysis using GraphBLAS Hypersparse Matrices and D4M Associative Arrays Open
Matrix/array analysis of networks can provide significant insight into their behavior and aid in their operation and protection. Prior work has demonstrated the analytic, performance, and compression capabilities of GraphBLAS (graphblas.or…
View article: AI and ML Accelerator Survey and Trends
AI and ML Accelerator Survey and Trends Open
This paper updates the survey of AI accelerators and processors from past three years. This paper collects and summarizes the current commercial accelerators that have been publicly announced with peak performance and power consumption num…
View article: Hypersparse Network Flow Analysis of Packets with GraphBLAS
Hypersparse Network Flow Analysis of Packets with GraphBLAS Open
Internet analysis is a major challenge due to the volume and rate of network traffic. In lieu of analyzing traffic as raw packets, network analysts often rely on compressed network flows (netflows) that contain the start time, stop time, s…
View article: Python Implementation of the Dynamic Distributed Dimensional Data Model
Python Implementation of the Dynamic Distributed Dimensional Data Model Open
Python has become a standard scientific computing language with fast-growing support of machine learning and data analysis modules, as well as an increasing usage of big data. The Dynamic Distributed Dimensional Data Model (D4M) offers a h…
View article: pPython for Parallel Python Programming
pPython for Parallel Python Programming Open
pPython seeks to provide a parallel capability that provides good speed-up without sacrificing the ease of programming in Python by implementing partitioned global array semantics (PGAS) on top of a simple file-based messaging library (Pyt…
View article: GraphBLAS on the Edge: Anonymized High Performance Streaming of Network Traffic
GraphBLAS on the Edge: Anonymized High Performance Streaming of Network Traffic Open
Long range detection is a cornerstone of defense in many operating domains (land, sea, undersea, air, space, ..,). In the cyber domain, long range detection requires the analysis of significant network traffic from a variety of observatori…
View article: New Phenomena in Large-Scale Internet Traffic
New Phenomena in Large-Scale Internet Traffic Open
The Internet is transforming our society, necessitating a quantitative understanding of Internet traffic. Our team collects and curates the largest publicly available Internet traffic data sets. An analysis of 50 billion packets using 10,0…