Search Results - "Moses, William S."

Polygeist: Raising C to Polyhedral MLIR by Moses, William S., Chelini, Lorenzo, Zhao, Ruizhe, Zinenko, Oleksandr

“…We present Polygeist, a new compilation flow that connects the MLIR compiler infrastructure to cutting edge polyhedral optimization tools. It consists of a C…”
Get full text

Retargeting and Respecializing GPU Workloads for Performance Portability by Ivanov, Ivan R., Zinenko, Oleksandr, Domke, Jens, Endo, Toshio, Moses, William S.

“…In order to come close to peak performance, accelerators like GPUs require significant architecture-specific tuning that understand the availability of shared…”
Get full text

Enabling Transformers to Understand Low-Level Programs by Guo, Zifan Carl, Moses, William S.

“…Unlike prior approaches to machine learning, Transformer models can first be trained on a large corpus of unlabeled data with a generic objective and then on a…”
Get full text

Reverse-Mode Automatic Differentiation and Optimization of GPU Kernels via Enzyme by Moses, William S., Churavy, Valentin, Paehler, Ludger, Huckelheim, Jan, Narayanan, Sri Hari Krishna, Schanen, Michel, Doerfert, Johannes

“…Computing derivatives is key to many algorithms in scientific computing and machine learning such as optimization, uncertainty quantification, and stability…”
Get full text

Scalable Automatic Differentiation of Multiple Parallel Paradigms through Compiler Augmentation by Moses, William S., Narayanan, Sri Hari Krishna, Paehler, Ludger, Churavy, Valentin, Schanen, Michel, Huckelheim, Jan, Doerfert, Johannes, Hovland, Paul

“…Derivatives are key to numerous science, engineering, and machine learning applications. While existing tools generate derivatives of programs in a single…”
Get full text

The Quantum Tortoise and the Classical Hare: A simple framework for understanding which problems quantum computing will accelerate (and which it will not) by Choi, Sukwoong, Moses, William S, Thompson, Neil

“…Quantum computing promises transformational gains for solving some problems, but little to none for others. For anyone hoping to use quantum computers now or…”
Get full text

Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients by Moses, William S, Churavy, Valentin

“…Applying differentiable programming techniques and machine learning algorithms to foreign programs requires developers to either rewrite their code in a…”
Get full text

Extracting Incentives from Black-Box Decisions by Shavit, Yonadav, Moses, William S

“…An algorithmic decision-maker incentivizes people to act in certain ways to receive better decisions. These incentives can dramatically influence subjects'…”
Get full text

The MLIR Transform Dialect. Your compiler is more powerful than you think by Lücke, Martin Paul, Zinenko, Oleksandr, Moses, William S, Steuwer, Michel, Cohen, Albert

“…To take full advantage of a specific hardware target, performance engineers need to gain control on compilers in order to leverage their domain knowledge about…”
Get full text

Input-Gen: Guided Generation of Stateful Inputs for Testing, Tuning, and Training by Ivanov, Ivan R, Meyer, Joachim, Grossman, Aiden, Moses, William S, Doerfert, Johannes

“…The size and complexity of software applications is increasing at an accelerating pace. Source code repositories (along with their dependencies) require vast…”
Get full text

High-Performance GPU-to-CPU Transpilation and Optimization via High-Level Parallel Constructs by Moses, William S, Ivanov, Ivan R, Domke, Jens, Endo, Toshio, Doerfert, Johannes, Zinenko, Oleksandr

“…While parallelism remains the main source of performance, architectural implementations and programming models change with each new hardware generation, often…”
Get full text

Computational Complexity of Arranging Music by Moses, William S, Demaine, Erik D

“…This paper proves that arrangement of music is NP-hard when subject to various constraints: avoiding musical dissonance, limiting how many notes can be played…”
Get full text

Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions by Vasilache, Nicolas, Zinenko, Oleksandr, Theodoridis, Theodoros, Goyal, Priya, DeVito, Zachary, Moses, William S, Verdoolaege, Sven, Adams, Andrew, Cohen, Albert

“…Deep learning models with convolutional and recurrent networks are now ubiquitous and analyze massive amounts of audio, image, video, text and graph data, with…”
Get full text