Intel SAE

Dynamic Binary Instrumentation of OS Kernel, Driver and BIOS

We introduce the Intel® Simulation and Analysis Engine (Intel® SAE) --- a framework for full-system instruction-level instrumentation of "ring 0" (privileged) and "ring 3" (user-level) code behavior on x86 platforms. When plugged-in to a Wind River® Simics Virtual Platform, Intel® SAE boots native operating systems (e.g. Linux and Windows, as well as Android), running unmodified binaries while facilitating flexible and customizable instruction-level instrumentation of everything executing on the CPU, i.e. BIOS, kernel, drivers and all kernel and user-space processes. Beyond its ability to instrument a single system, Intel SAE is capable of distributed node-to-node multi-system simulation and instrumentation, useful for analysis of enterprise-scale workloads, such as CloudSuite, Hadoop, Memcached etc.

You can download and read about SAE in greater detail here (click me) !

If you use SAE, please cite SAE using the following BibTeX entry:
@inproceedings{Chachmon:2016:SAE:2925426.2926293,
author = {Chachmon, Nadav and Richins, Daniel and Cohn, Robert and Christensson, Magnus and Cui, Wenzhi and Reddi, Vijay Janapa},
title = {Simulation and Analysis Engine for Scale-Out Workloads},
booktitle = {Proceedings of the 2016 International Conference on Supercomputing},
series = {ICS '16},
year = {2016},
isbn = {978-1-4503-4361-9},
location = {Istanbul, Turkey},
pages = {22:1--22:13},
articleno = {22},
numpages = {13},
url = {http://doi.acm.org/10.1145/2925426.2926293},
doi = {10.1145/2925426.2926293},
acmid = {2926293},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {Analysis, JIT, big data, full-system, instrumentation, multicore, multisystem, scale-out, transparency},
}

Organizers

	Vijay Janapa Reddi is an Assistant Professor in the Department of Electrical and Computer Engineering at The University of Texas at Austin. His research interests include system architecture and software design and implementation to address performance, power, and reliability issues in mobile and high-performance computing systems. He is the co-author of widely used tools, e.g., the Pin user-space dynamic binary instrumentation engine and the GPUWattch power modeling simulation framework. He is the recipient of the NAE Gilbreth Lectureship Award, Intel Early Career Award, PLDI Most Influential Paper Award, and has received Best Paper and Top Picks awards in Computer Architecture. Beyond his research activities, Vijay is very passionate about STEM education, particularly involving computer science education starting at an early age. He is responsible for the Hands-On Computer Science (HaCS) curriculum that teaches computer science to 6th graders in the Austin Independent School District (AISD) through Arduino-based hands-on projects. AISD ties directly into the heart of the public education system in Austin--Texas. Vijay received his Ph.D. in Computer Science from Harvard University. He can be contacted at vj@ece.utexas.edu.
	Nadav Chachmon is a senior software engineer at Intel. Nadav worked on areas of processor & systemsoftware architecture, functional & cycle accurate simulation technologies and dynamic binary instrumentation & translation technologies. Nadav has worked as Intel ® SAE instrumentation framework architect and on the product’s performance. He is the recipient of the Intel Achievement Award for development and productization of pin dynamic binary instrumentation framework and of Intel SW Quality Award for the development of Intel ® SAE as part of a virtualplatform. He received his B.Sc in Computer Engineering from TechnionMachon Technologi Le' Israel. He can be contacted at nadav.chachmon@intel.com.
	Magnus Christensson is an engineering manager / engineer at Intel. A founding employee of Virtutech that was acquired into Intel in 2010, Magnus has 15+ years of experience on virtual platform solutions and applications. Magnus designed and implemented the cross-platform binary translation engine in Simics, and continues to work primarily on performance and scalability aspects of the Simics simulator. He received his M.Sc. in Computer Science from Royal Institute of Technology, Stockholm, Sweden. He can be contacted at magnus.christensson@intel.com.
	Daniel Richins is a Ph.D. student in the department of Electrical and Computer Engineering at The University of Texas at Austin. Daniel previously worked at Marvell Semiconductor, where he worked on CPU performance simulation. His current research is centered around big data and understanding distributed workloads from a microarchitectural perspective. He can be contacted at <first letter of first name> <last name> (at) utexas (dot) edu.
	Wenzhi Cui is a Ph.D. student in the department of Computer Science at The University of Texas at Austin. His current research focuses on exploring the design trade-offs for high-performance scripting languages, e.g., Python, Javascript, and Julia. He is interested in developing hardware and runtime techniques to improve scripting language implementations. He can be contacted at wc8348 (at) utexas (dot) edu.