More Like this

1. High-Performance GPU-to-CPU Transpilation and Optimization via High-Level Parallel Constructs

   https://doi.org/10.1145/3572848.3577475  

   Moses, William S; Ivanov, Ivan R; Domke, Jens; Endo, Toshio; Doerfert, Johannes; Zinenko, Oleksandr (February 2023, ACM)

   NA (Ed.)

   While parallelism remains the main source of performance,architectural implementations and programming modelschange with each new hardware generation, often leadingto costly application re-engineering. Most tools for perfor-mance portability require manual and costly application port-ing to yet another programming model.We propose an alternative approach that automaticallytranslates programs written in one programming model(CUDA), into another (CPU threads) based on Polygeist/MLIR.Our approach includes a representation of parallel constructsthat allows conventional compiler transformations to ap-ply transparently and without modification a nd enablesparallelism-specific optimizations. We evaluate our frame-work by transpiling and optimizing the CUDA Rodinia bench-mark suite for a multi-core CPU and achieve a 58% geomeanspeedup over handwritten OpenMP code. Further, we showhow CUDA kernels from PyTorch can efficiently run andscale on the CPU-only Supercomputer Fugaku without userintervention. Our PyTorch compatibility layer making use oftranspiled CUDA PyTorch kernels outperforms the PyTorchCPU native backend by 2.7×. 

   more » « less
2. Differentiable Compound Optics and Processing Pipeline Optimization for End-to-end Camera Design

   https://doi.org/10.1145/3446791  

   Tseng, Ethan; Mosleh, Ali; Mannan, Fahim; St-Arnaud, Karl; Sharma, Avinash; Peng, Yifan; Braun, Alexander; Nowrouzezahrai, Derek; Lalonde, Jean-François; Heide, Felix (June 2021, ACM Transactions on Graphics)

   null (Ed.)

   Most modern commodity imaging systems we use directly for photography—or indirectly rely on for downstream applications—employ optical systems of multiple lenses that must balance deviations from perfect optics, manufacturing constraints, tolerances, cost, and footprint. Although optical designs often have complex interactions with downstream image processing or analysis tasks, today’s compound optics are designed in isolation from these interactions. Existing optical design tools aim to minimize optical aberrations, such as deviations from Gauss’ linear model of optics, instead of application-specific losses, precluding joint optimization with hardware image signal processing (ISP) and highly parameterized neural network processing. In this article, we propose an optimization method for compound optics that lifts these limitations. We optimize entire lens systems jointly with hardware and software image processing pipelines, downstream neural network processing, and application-specific end-to-end losses. To this end, we propose a learned, differentiable forward model for compound optics and an alternating proximal optimization method that handles function compositions with highly varying parameter dimensions for optics, hardware ISP, and neural nets. Our method integrates seamlessly atop existing optical design tools, such as Zemax . We can thus assess our method across many camera system designs and end-to-end applications. We validate our approach in an automotive camera optics setting—together with hardware ISP post processing and detection—outperforming classical optics designs for automotive object detection and traffic light state detection. For human viewing tasks, we optimize optics and processing pipelines for dynamic outdoor scenarios and dynamic low-light imaging. We outperform existing compartmentalized design or fine-tuning methods qualitatively and quantitatively, across all domain-specific applications tested. 

   more » « less
3. DeepFlow: A Cross-Stack Pathfinding Framework for Distributed AI Systems

   https://doi.org/10.1145/3635867  

   Ardalani, Newsha; Pal, Saptadeep; Gupta, Puneet (December 2023, ACM Transactions on Design Automation of Electronic Systems)

   Over the past decade, machine learning model complexity has grown at an extraordinary rate, as has the scale of the systems training such large models. However there is an alarmingly low hardware utilization (5-20%) in large scale AI systems. The low system utilization is a cumulative effect of minor losses across different layers of the stack, exacerbated by the disconnect between engineers designing different layers spanning across different industries. To address this challenge, in this work we designed a cross-stack performance modelling and design space exploration framework. First, we introduce CrossFlow, a novel framework that enables cross-layer analysis all the way from the technology layer to the algorithmic layer. Next, we introduce DeepFlow (built on top of CrossFlow using machine learning techniques) to automate the design space exploration and co-optimization across different layers of the stack. We have validated CrossFlow’s accuracy with distributed training on real commercial hardware and showcase several DeepFlow case studies demonstrating pitfalls of not optimizing across the technology-hardware-software stack for what is likely, the most important workload driving large development investments in all aspects of computing stack. 

   more » « less
4. Optical calibration and distortion correction for a volumetric augmented reality display

   https://doi.org/10.1117/12.2544954  

   Rathinavel, Kishore; Wang, Hanpeng; Fuchs, Henry (February 2020, Emerging Digital Micromirror Device Based Systems and Applications XII, Photonics West 2020.)

   We develop optical calibration and distortion correction for a recently developed DMD-based volumetric aug- mented reality display. The display is capable of displaying imagery over a large volume — composed of 280 depth planes over a large depth-range (15 cm to 400 cm) and 40 degrees field-of-view. An unintended property of this display is that the field-of-view of the depth planes changes slightly over depth. This can cause distortions, perceptual errors for the perspective depth cue, and reduce the image quality slightly. To address these issues, we develop an optical calibration method and a distortion correction as a post-processing step to our rendering pipeline. 

   more » « less
5. Generalized Laplacian Positional Encoding for Graph Representation Learning

   Maskey, Sohir; Parviz, Ali; Thiessen; Maximilian; Stärk, Hannes; Sadikaj, Ylli; Maron, Haggai (December 2022, NeurIPS Workshop on Symmetry and Geometry in Neural Representations)

   Graph neural networks (GNNs) are the primary tool for processing graph-structured data. Unfortunately, the most commonly used GNNs, called Message Passing Neural Networks (MPNNs) suffer from several fundamental limitations. To overcome these limitations, recent works have adapted the idea of positional encodings to graph data. This paper draws inspiration from the recent success of Laplacian-based positional encoding and defines a novel family of positional encoding schemes for graphs. We accomplish this by generalizing the optimization problem that defines the Laplace embedding to more general dissimilarity functions rather than the 2-norm used in the original formulation. This family of positional encodings is then instantiated by considering p-norms. We discuss a method for calculating these positional encoding schemes, implement it in PyTorch and demonstrate how the resulting positional encoding captures different properties of the graph. Furthermore, we demonstrate that this novel family of positional encodings can improve the expressive power of MPNNs. Lastly, we present preliminary experimental results. 

   more » « less