I am a PhD candidate at Northwestern University with a B.S.
in Computer Engineering and Computer Science from Rose-Hulman
Institute of Technology.
I study compilers, specifically looking into new intermediate
representations and abstractions.
My research aims to broaden the optimization space of compilers
through intermediate representations that grant empowering degrees of freedom
through strong guarantees.
I am broadly interested in static analysis, runtime system
co-design, programming languages, and memory models.
Tommy McMichen, Nathan Greiner, Peter Zhong,
Federico Sossai, Atmn Patel, and Simone Campanoni
CGO 2024
Collection-oriented programming is a mainstay in many fields of computer science and its application.
However modern, general-purpose compilers are entirely blind to their usage within programs.
By prematurely lowering collections to their memory layout in libraries and compiler front ends, ambiguous memory behavior is presented to the compiler.
Compilers are left to glean conservative information via costly and conservative analysis results.
All of this culminates in data collections being a barrier to optimization for the compiler.
We introduce MemOIR, an SSA form for data collections, objects and their fields.
At its core, MemOIR decouples the memory used to store data from the memory used to logically organize data.
We use MemOIR to explore novel static analyses and transformations of collections at the element-level.
Getting a Handle on Unmanaged Memory
The paper is available
here.
The artifact is available
here.
Nick Wanninger, Tommy McMichen, Simone Campanoni, and Peter Dinda
ASPLOS 2024
The inability to relocate objects in unmanaged languages brings with it a menagerie of problems.
Perhaps the most impactful is memory fragmentation, which has long plagued applications such as databases and web servers.
These issues either fester or require Herculean programmer effort to address on a per-application basis because, in general, heap objects cannot be moved in unmanaged languages.
In this work, we bridge this gap between unmanaged and managed languages through the use of handles, a level of indirection allowing heap object movement.
Handles open the door to seamlessly employ runtime features from managed languages in existing, unmodified code written in unmanaged languages.
We describe a new compiler and runtime system, Alaska, which automatically transforms pointer-based code to utilize handles, with optimizations to reduce performance impact.
A codesigned runtime system manages this level of indirection and exploits heap object movement via an extensible service interface.
We evaluate one such service, which eliminates fragmentation on the heap via compaction, reducing memory usage by up to 40% in Redis.
Program State Element Characterization
The paper is available
here.
The source code is available on
GitHub.
For more information, see the
ACM DL.
Enrico Armenio Deiana, Brian Suchy, Michael Wilkins,
Brian Homerding, Tommy McMichen, Katarzyna Dunajewski,
Peter Dinda, Nikos Hardavellas, and Simone Campanoni
CGO 2023
Program State Element Characterization (PSEC) enables developers to more easily use modern language abstractions like OpenMP and C++ smart pointers.
To accomplish this, PSEC provides a characterization of program state elements within a given code region.
Today this process must be performed manually with no dedicated tool support.
We implement PSEC in the CARMOT tool.
Using CARMOT, developers are able to achieve parallel speedups that match those of hand-tuned OpenMP directives and avoid memory leaks with C++ smart pointers.
We hope that PSEC and CARMOT empower developers to fully utilize the rich, expanding ecosystem of modern programming language abstractions.
Angelo Matni, Enrico Armenio Deiana, Yian Su, Lukas Gross, Souradip Ghosh, Sotiris Apostolakis,
Ziyang
Xu, Zujun Tan, Ishita Chaturvedi, Brian Homerding, Tommy McMichen, David I. August, and
Simone
Campanoni
CGO 2022
NOELLE provides abstractions to help build advanced code analyses and transformations on top of the
production quality LLVM compiler.
NOELLE has been used to accelerate a diverse set of research prototypes, with a powerful
automatically
parallelizing compiler built upon it.
It is available open source on github to help accelerate your compiler research.
Fine-Grained Acceleration using Runtime Integrated Custom Execution (RICE)
The paper is available
here.
For more information, see the
ACM DL.
Leela Pakanati, John T. McMichen, and Zachary Estrada
CASES 2019
Runtime Integrated Custom Execution (RICE) relocates traditional peripheral reconfigurable
acceleration devices into the pipeline of the processor. This relocation unlocks fine-grained
acceleration previously impeded by communication overhead to a peripheral
accelerator. Preliminary simulation results on a subset of the PARSEC benchmark suite shows
promise for RICE in HPC applications. This was published in a 'work-in-progress' paper track.
Senior design project to improve the performance and efficiency of biologically-accurate neuron
simulations using the Hodgkin-Huxley model and a LUT accelerator approach. Designed and developed
novel parallel architecture to allow for parallel variable time-step integrators (VITAMIN), which
achieved strong scaling on multi-core machines. Minimized hardware area usage of LUT accelerator,
with
similar execution time performance. Implemented software improvements to improve execution time
performance.
