Strategies for protecting intellectual property when using CUDA applications on graphics processing units

Recent advances in the massively parallel computational abilities of graphical processing units (GPUs) have increased their use for general purpose computation, as companies look to take advantage of big data processing techniques. This has given rise to the potential for malicious software targeting GPUs, which is of interest to forensic investigators examining the operation of software. The ability to carry out reverse-engineering of software is of great importance within the security and forensics elds, particularly when investigating malicious software or carrying out forensic analysis following a successful security breach. Due to the complexity of the Nvidia CUDA (Compute Uni ed Device Architecture) framework, it is not clear how best to approach the reverse engineering of a piece of CUDA software. We carry out a review of the di erent binary output formats which may be encountered from the CUDA compiler, and their implications on reverse engineering. We then demonstrate the process of carrying out disassembly of an example CUDA application, to establish the various techniques available to forensic investigators carrying out black-box disassembly and reverse engineering of CUDA binaries. We show that the Nvidia compiler, using default settings, leaks useful information. Finally, we demonstrate techniques to better protect intellectual property in CUDA algorithm implementations from reverse engineering.

Dynamically balanced and plausible trajectory planning for human-like characters

International audience

Evolution of mylonitic microfabrics (EMM), a computer application for educational purposes

`Evolution of mylonitic microfabrics' (EMM) is an interactive Filemaker Pro 3.0 application that documents a series of see-through deformation experiments on polycrystalline norcamphor. The application comprises computer animations, graphics and text explanations designed to give students and researchers insight into the interaction and dynamic nature of small-scale, mylonitic processes like intracrystalline glide, dynamic recrystallization and strain localization (microshearing). EMM shows how mylonitic steady state is achieved at different strain rates and temperatures. First, rotational mechanisms like glide-induced vorticity, subgrain rotation recrystallization and rigid-body rotation bring grains' crystal lattices into orientations that are favorable for intracrystalline glide. In a second stage, selective elimination of grains whose lattices are poorly oriented for glide involves grain boundary migration. This strengthens the texture. Temperature and strain rate affect both the relative activity of different strain accommodation mechanisms and the rate of microfabric change. Steady-state microfabrics are characterized by stable texture, grain size and shape-preferred orientations of grains and domains. This involves the cyclical generation and elimination of dynamically recrystallized grains and microshear zones.

A three-dimensional representation method for noisy point clouds based on growing self-organizing maps accelerated on GPUs

The research described in this thesis was motivated by the need of a robust model capable of representing 3D data obtained with 3D sensors, which are inherently noisy. In addition, time constraints have to be considered as these sensors are capable of providing a 3D data stream in real time. This thesis proposed the use of Self-Organizing Maps (SOMs) as a 3D representation model. In particular, we proposed the use of the Growing Neural Gas (GNG) network, which has been successfully used for clustering, pattern recognition and topology representation of multi-dimensional data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models, without considering time constraints. It is proposed a hardware implementation leveraging the computing power of modern GPUs, which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). The proposed methods were applied to different problem and applications in the area of computer vision such as the recognition and localization of objects, visual surveillance or 3D reconstruction.

A comparative study of navigation meshes

International audience

Architectural-Physical Co-Design of 3D CPUs with Micro-Fluidic Cooling

The performance, energy efficiency and cost improvements due to traditional technology scaling have begun to slow down and present diminishing returns. Underlying reasons for this trend include fundamental physical limits of transistor scaling, the growing significance of quantum effects as transistors shrink, and a growing mismatch between transistors and interconnects regarding size, speed and power. Continued Moore's Law scaling will not come from technology scaling alone, and must involve improvements to design tools and development of new disruptive technologies such as 3D integration. 3D integration presents potential improvements to interconnect power and delay by translating the routing problem into a third dimension, and facilitates transistor density scaling independent of technology node. Furthermore, 3D IC technology opens up a new architectural design space of heterogeneously-integrated high-bandwidth CPUs. Vertical integration promises to provide the CPU architectures of the future by integrating high performance processors with on-chip high-bandwidth memory systems and highly connected network-on-chip structures. Such techniques can overcome the well-known CPU performance bottlenecks referred to as memory and communication wall. However the promising improvements to performance and energy efficiency offered by 3D CPUs does not come without cost, both in the financial investments to develop the technology, and the increased complexity of design. Two main limitations to 3D IC technology have been heat removal and TSV reliability. Transistor stacking creates increases in power density, current density and thermal resistance in air cooled packages. Furthermore the technology introduces vertical through silicon vias (TSVs) that create new points of failure in the chip and require development of new BEOL technologies. Although these issues can be controlled to some extent using thermal-reliability aware physical and architectural 3D design techniques, high performance embedded cooling schemes, such as micro-fluidic (MF) cooling, are fundamentally necessary to unlock the true potential of 3D ICs. A new paradigm is being put forth which integrates the computational, electrical, physical, thermal and reliability views of a system. The unification of these diverse aspects of integrated circuits is called Co-Design. Independent design and optimization of each aspect leads to sub-optimal designs due to a lack of understanding of cross-domain interactions and their impacts on the feasibility region of the architectural design space. Co-Design enables optimization across layers with a multi-domain view and thus unlocks new high-performance and energy efficient configurations. Although the co-design paradigm is becoming increasingly necessary in all fields of IC design, it is even more critical in 3D ICs where, as we show, the inter-layer coupling and higher degree of connectivity between components exacerbates the interdependence between architectural parameters, physical design parameters and the multitude of metrics of interest to the designer (i.e. power, performance, temperature and reliability). In this dissertation we present a framework for multi-domain co-simulation and co-optimization of 3D CPU architectures with both air and MF cooling solutions. Finally we propose an approach for design space exploration and modeling within the new Co-Design paradigm, and discuss the possible avenues for improvement of this work in the future.

Physical Design Methodologies for Low Power and Reliable 3D ICs

As the semiconductor industry struggles to maintain its momentum down the path following the Moore's Law, three dimensional integrated circuit (3D IC) technology has emerged as a promising solution to achieve higher integration density, better performance, and lower power consumption. However, despite its significant improvement in electrical performance, 3D IC presents several serious physical design challenges. In this dissertation, we investigate physical design methodologies for 3D ICs with primary focus on two areas: low power 3D clock tree design, and reliability degradation modeling and management. Clock trees are essential parts for digital system which dissipate a large amount of power due to high capacitive loads. The majority of existing 3D clock tree designs focus on minimizing the total wire length, which produces sub-optimal results for power optimization. In this dissertation, we formulate a 3D clock tree design flow which directly optimizes for clock power. Besides, we also investigate the design methodology for clock gating a 3D clock tree, which uses shutdown gates to selectively turn off unnecessary clock activities. Different from the common assumption in 2D ICs that shutdown gates are cheap thus can be applied at every clock node, shutdown gates in 3D ICs introduce additional control TSVs, which compete with clock TSVs for placement resources. We explore the design methodologies to produce the optimal allocation and placement for clock and control TSVs so that the clock power is minimized. We show that the proposed synthesis flow saves significant clock power while accounting for available TSV placement area. Vertical integration also brings new reliability challenges including TSV's electromigration (EM) and several other reliability loss mechanisms caused by TSV-induced stress. These reliability loss models involve complex inter-dependencies between electrical and thermal conditions, which have not been investigated in the past. In this dissertation we set up an electrical/thermal/reliability co-simulation framework to capture the transient of reliability loss in 3D ICs. We further derive and validate an analytical reliability objective function that can be integrated into the 3D placement design flow. The reliability aware placement scheme enables co-design and co-optimization of both the electrical and reliability property, thus improves both the circuit's performance and its lifetime. Our electrical/reliability co-design scheme avoids unnecessary design cycles or application of ad-hoc fixes that lead to sub-optimal performance. Vertical integration also enables stacking DRAM on top of CPU, providing high bandwidth and short latency. However, non-uniform voltage fluctuation and local thermal hotspot in CPU layers are coupled into DRAM layers, causing a non-uniform bit-cell leakage (thereby bit flip) distribution. We propose a performance-power-resilience simulation framework to capture DRAM soft error in 3D multi-core CPU systems. In addition, a dynamic resilience management (DRM) scheme is investigated, which adaptively tunes CPU's operating points to adjust DRAM's voltage noise and thermal condition during runtime. The DRM uses dynamic frequency scaling to achieve a resilience borrow-in strategy, which effectively enhances DRAM's resilience without sacrificing performance. The proposed physical design methodologies should act as important building blocks for 3D ICs and push 3D ICs toward mainstream acceptance in the near future.

Variations développementales chez les poissons hybrides clonaux Chrosomus eos-neogaeus : transgressions phénotypiques en 3D

Le succès écologique des organismes dépend principalement de leur phénotype. Une composante important du phénotype est la morphologie fonctionnelle car elle influence la performance d’un organisme donné dans un milieu donné et donc reflète son écologie. Des disparités dans la morphologie fonctionnelle ou dans le développement entre espèces peuvent donc mener à des différences écologiques. Ce projet évalue le rôle des mécanismes de variation morphologique dans la production de différences écologiques entre espèces au sein des poissons hybrides du complexe Chrosomus eos-neogaeus. En utilisant la microtomodensitométrie à rayons X et la morphométrie géométrique 3D, la forme des éléments des mâchoires est décrite pour comparer la variation morphologique et les différences développementales entre les membres du complexe C. eos neogaeus. Les hybrides présentent autant de variation phénotypique que les espèces parentales et présentent des phénotypes nouveaux, dit transgressifs. Les hybrides présentent aussi des différences marquées avec les espèces parentales dans leur allométrie et dans leur intégration phénotypique. Finalement, ceux-ci semblent être plastiques et en mesure de modifier leur phénotype pour occuper plusieurs environnements. L’entièreté de ces résultats suggère que des changements dans le développement des hybrides entraînent une différenciation phénotypique et écologique avec les espèces parentales.

POSE ESTIMATION AND 3D RECONSTRUCTION USING SENSOR FUSION

A camera maps 3-dimensional (3D) world space to a 2-dimensional (2D) image space. In the process it loses the depth information, i.e., the distance from the camera focal point to the imaged objects. It is impossible to recover this information from a single image. However, by using two or more images from different viewing angles this information can be recovered, which in turn can be used to obtain the pose (position and orientation) of the camera. Using this pose, a 3D reconstruction of imaged objects in the world can be computed. Numerous algorithms have been proposed and implemented to solve the above problem; these algorithms are commonly called Structure from Motion (SfM). State-of-the-art SfM techniques have been shown to give promising results. However, unlike a Global Positioning System (GPS) or an Inertial Measurement Unit (IMU) which directly give the position and orientation respectively, the camera system estimates it after implementing SfM as mentioned above. This makes the pose obtained from a camera highly sensitive to the images captured and other effects, such as low lighting conditions, poor focus or improper viewing angles. In some applications, for example, an Unmanned Aerial Vehicle (UAV) inspecting a bridge or a robot mapping an environment using Simultaneous Localization and Mapping (SLAM), it is often difficult to capture images with ideal conditions. This report examines the use of SfM methods in such applications and the role of combining multiple sensors, viz., sensor fusion, to achieve more accurate and usable position and reconstruction information. This project investigates the role of sensor fusion in accurately estimating the pose of a camera for the application of 3D reconstruction of a scene. The first set of experiments is conducted in a motion capture room. These results are assumed as ground truth in order to evaluate the strengths and weaknesses of each sensor and to map their coordinate systems. Then a number of scenarios are targeted where SfM fails. The pose estimates obtained from SfM are replaced by those obtained from other sensors and the 3D reconstruction is completed. Quantitative and qualitative comparisons are made between the 3D reconstruction obtained by using only a camera versus that obtained by using the camera along with a LIDAR and/or an IMU. Additionally, the project also works towards the performance issue faced while handling large data sets of high-resolution images by implementing the system on the Superior high performance computing cluster at Michigan Technological University.

Through Wafer 3D Vertical Micro-Coaxial Probe for High Frequency Material Characterization and Millimeter Wave Packaging Systems

This work presents the development of an in-plane vertical micro-coaxial probe using bulk micromachining technique for high frequency material characterization. The coaxial probe was fabricated in a silicon substrate by standard photolithography and a deep reactive ion etching (DRIE) technique. The through-hole structure in the form of a coaxial probe was etched and metalized with a diluted silver paste. A co-planar waveguide configuration was integrated with the design to characterize the probe. The electrical and RF characteristics of the coaxial probe were determined by simulating the probe design in Ansoft’s High Frequency Structure Simulator (HFSS). The reflection coefficient and transducer gain performance of the probe was measured up to 65 GHz using a vector network analyzer (VNA). The probe demonstrated excellent results over a wide frequency band, indicating its ability to integrate with millimeter wave packaging systems as well as characterize unknown materials at high frequencies. The probe was then placed in contact with 3 materials where their unknown permittivities were determined. To accomplish this, the coaxial probe was placed in contact with the material under test and electromagnetic waves were directed to the surface using the VNA, where its reflection coefficient was then determined over a wide frequency band from dc-to -65GHz. Next, the permittivity of each material was deduced from its measured reflection coefficients using a cross ratio invariance coding technique. The permittivity results obtained when measuring the reflection coefficient data were compared to simulated permittivity results and agreed well. These results validate the use of the micro-coaxial probe to characterize the permittivity of unknown materials at high frequencies up to 65GHz.

Dynamic Image Precompensation for Improving Visual Performance of Computer Users with Ocular Aberrations

With the progress of computer technology, computers are expected to be more intelligent in the interaction with humans, presenting information according to the user's psychological and physiological characteristics. However, computer users with visual problems may encounter difficulties on the perception of icons, menus, and other graphical information displayed on the screen, limiting the efficiency of their interaction with computers. In this dissertation, a personalized and dynamic image precompensation method was developed to improve the visual performance of the computer users with ocular aberrations. The precompensation was applied on the graphical targets before presenting them on the screen, aiming to counteract the visual blurring caused by the ocular aberration of the user's eye. A complete and systematic modeling approach to describe the retinal image formation of the computer user was presented, taking advantage of modeling tools, such as Zernike polynomials, wavefront aberration, Point Spread Function and Modulation Transfer Function. The ocular aberration of the computer user was originally measured by a wavefront aberrometer, as a reference for the precompensation model. The dynamic precompensation was generated based on the resized aberration, with the real-time pupil diameter monitored. The potential visual benefit of the dynamic precompensation method was explored through software simulation, with the aberration data from a real human subject. An "artificial eye'' experiment was conducted by simulating the human eye with a high-definition camera, providing objective evaluation to the image quality after precompensation. In addition, an empirical evaluation with 20 human participants was also designed and implemented, involving image recognition tests performed under a more realistic viewing environment of computer use. The statistical analysis results of the empirical experiment confirmed the effectiveness of the dynamic precompensation method, by showing significant improvement on the recognition accuracy. The merit and necessity of the dynamic precompensation were also substantiated by comparing it with the static precompensation. The visual benefit of the dynamic precompensation was further confirmed by the subjective assessments collected from the evaluation participants.

Variations développementales chez les poissons hybrides clonaux Chrosomus eos-neogaeus : transgressions phénotypiques en 3D

Le succès écologique des organismes dépend principalement de leur phénotype. Une composante important du phénotype est la morphologie fonctionnelle car elle influence la performance d’un organisme donné dans un milieu donné et donc reflète son écologie. Des disparités dans la morphologie fonctionnelle ou dans le développement entre espèces peuvent donc mener à des différences écologiques. Ce projet évalue le rôle des mécanismes de variation morphologique dans la production de différences écologiques entre espèces au sein des poissons hybrides du complexe Chrosomus eos-neogaeus. En utilisant la microtomodensitométrie à rayons X et la morphométrie géométrique 3D, la forme des éléments des mâchoires est décrite pour comparer la variation morphologique et les différences développementales entre les membres du complexe C. eos neogaeus. Les hybrides présentent autant de variation phénotypique que les espèces parentales et présentent des phénotypes nouveaux, dit transgressifs. Les hybrides présentent aussi des différences marquées avec les espèces parentales dans leur allométrie et dans leur intégration phénotypique. Finalement, ceux-ci semblent être plastiques et en mesure de modifier leur phénotype pour occuper plusieurs environnements. L’entièreté de ces résultats suggère que des changements dans le développement des hybrides entraînent une différenciation phénotypique et écologique avec les espèces parentales.

Studio e Realizzazione del Modello RVE (Representative Volume Element) per componenti polimerici realizzati in stampa 3D FDM

A fianco ai metodi più tradizionali, fin ora utilizzati, le tecnologie additive hanno subito negli ultimi anni una notevole evoluzione nella produzione di componenti. Esse permettono un ampio di range di applicazioni utilizzando materiali differenti in base al settore di applicazione. In particolare, la stampa 3D FDM (Fused Deposition Modeling) rappresenta uno dei processi tecnologici additivi più diffusi ed economicamente più competitivi. Gli attuali metodi di analisi agli elementi finiti (FEM) e le tecnologie CAE (Computer-Aided Engineering) non sono in grado di studiare modelli 3D di componenti stampati, dal momento che il risultato finale dipende dai parametri di processo e ambientali. Per questo motivo, è necessario uno studio approfondito della meso struttura del componente stampato per estendere l’analisi FEM anche a questa tipologia di componenti. Lo scopo del lavoro proposto è di creare un elemento omogeneo che rappresenti accuratamente il comportamento di un componente realizzato in stampa 3D FDM, questo avviene attraverso la definizione e l’analisi di un volume rappresentativo (RVE). Attraverso la tecnica dell’omogeneizzazione, il volume definito riassume le principali caratteristiche meccaniche della struttura stampata, permettendo nuove analisi e ottimizzazioni. Questo approccio permette di realizzare delle analisi FEM sui componenti da stampare e di predire le proprietà meccaniche dei componenti a partire da determinati parametri di stampa, permettendo così alla tecnologia FDM di diventare sempre di più uno dei principali processi industriali a basso costo.

Understanding 3D structures from sketches

Sketches are a unique way to communicate: drawing a simple sketch does not require any training, sketches convey information that is hard to describe with words, they are powerful enough to represent almost any concept, and nowadays, it is possible to draw directly from mobile devices. Motivated from the unique characteristics of sketches and fascinated by the human ability to imagine 3D objects from drawings, this thesis focuses on automatically associating geometric information to sketches. The main research directions of the thesis can be summarized as obtaining geometric information from freehand scene sketches to improve 2D sketch-based tasks and investigating Vision-Language models to overcome 3D sketch-based tasks limitations. The first part of the thesis concerns geometric information prediction from scene sketches improving scene sketch to image generation and unlocking new creativity effects. The thesis proceeds showing a study conducted on the Vision-Language models embedding space considering sketches, line renderings and RGB renderings of 3D shape to overcome the use of supervised datasets for 3D sketch-based tasks, that are limited and hard to acquire. Following the obtained observations and results, Vision-Language models are applied to Sketch Based Shape Retrieval without the need of training on supervised datasets. We then analyze the use of Vision-Language models for sketch based 3D reconstruction in an unsupervised manner. In the final chapter we report the results obtained in an additional project carried during the PhD, which has lead to the development of a framework to learn an embedding space of neural networks that can be navigated to get ready-to-use models with desired characteristics.

An Embedded In-Cabin Lightweight High-Performance 3D Gaze Estimation System

Gaze estimation has gained interest in recent years for being an important cue to obtain information about the internal cognitive state of humans. Regardless of whether it is the 3D gaze vector or the point of gaze (PoG), gaze estimation has been applied in various fields, such as: human robot interaction, augmented reality, medicine, aviation and automotive. In the latter field, as part of Advanced Driver-Assistance Systems (ADAS), it allows the development of cutting-edge systems capable of mitigating road accidents by monitoring driver distraction. Gaze estimation can be also used to enhance the driving experience, for instance, autonomous driving. It also can improve comfort with augmented reality components capable of being commanded by the driver's eyes. Although, several high-performance real-time inference works already exist, just a few are capable of working with only a RGB camera on computationally constrained devices, such as a microcontroller. This work aims to develop a low-cost, efficient and high-performance embedded system capable of estimating the driver's gaze using deep learning and a RGB camera. The proposed system has achieved near-SOTA performances with about 90% less memory footprint. The capabilities to generalize in unseen environments have been evaluated through a live demonstration, where high performance and near real-time inference were obtained using a webcam and a Raspberry Pi4.