Bachelorarbeiten
Development of a PCB-Based Digital Microfluidics Platform
Beschreibung
Are you interested in hands-on experience in the emerging field of microfluidics? We are seeking a motivated student to join an innovative project focused on developing a PCB (Printed Circuit Board)-based digital microfluidics (DMF) platform. This project offers an excellent opportunity to apply your knowledge of hardware and PCB design while diving into the fascinating world of microfluidics.
About Digital Microfluidics (DMF):
Digital microfluidics (DMF) is a technology that allows precise manipulation of tiny droplets on a microscale using electrical fields. Unlike continuous-flow microfluidics, which relies on channels and pumps, DMF provides flexibility by enabling individual droplets to be moved, merged, split, or mixed on an open surface. This droplet-based control offers a powerful approach for various applications, from biomedical assays to chemical synthesis, with the benefit of reconfigurability and automation.
Project Scope:
In this project, you will focus on designing and implementing a DMF platform on a PCB. This involves:
-
Hardware Design and Integration: Designing a PCB layout to support electrode patterns necessary for droplet manipulation. The design must enable precise control of droplet movement across the platform, incorporating key components like driving electronics, electrode arrays, and control circuits.
-
Electronics and Control Systems: Developing and implementing a control system to power the electrodes, allowing selective activation for droplet control. You will have the opportunity to work with microcontrollers and control interfaces for automated droplet manipulation.
-
Testing and Optimization: Conducting experiments to validate the functionality of the DMF platform, evaluating parameters such as droplet speed, control accuracy, and system robustness. This includes troubleshooting and optimizing the system for reliable performance.
Requirements:
- Background in Hardware Design: Familiarity with PCB design is essential. Experience with software tools like Altium Designer, Eagle, or KiCad is highly preferred.
- Knowledge of Electronics Fundamentals: Understanding of microcontrollers, signal processing, and basic circuit design will be beneficial for the control system aspects of the project.
- Interest in Microfluidics or Biomedical Engineering: While prior experience in microfluidics is not required, an enthusiasm for learning about microfluidic systems and applications will be invaluable.
What You Will Gain:
- Practical experience in PCB design and hardware integration for microfluidic applications.
- Insight into the principles and applications of digital microfluidics.
- The opportunity to contribute to the development of cutting-edge technology with potential applications in diagnostics, biology, and chemistry.
If you are a proactive learner with a passion for electronics and an interest in microfluidics, we invite you to apply for this exciting project. This is a unique chance to apply your technical skills to an emerging area with broad interdisciplinary applications.
Kontakt
Yushen.Zhang+Project@TUM.de
Betreuer:
Web-Based Chip Design Platform Development
Beschreibung
This is an opportunity for students to join a project focused on further developing our existing web-based chip design platform. This project will involve identifying and resolving bugs, as well as enhancing the platform’s functionality.
Key Responsibilities:
- Further develop and improve the web-based chip design platform.
- Identify, troubleshoot, and resolve bugs and issues.
- Implement new features and improvements.
Requirements:
- Basic understanding of web programming (HTML, CSS, and JavaScript).
- Familiarity with the Vue.js framework or a willingness to learn it independently.
- Strong problem-solving skills and attention to detail.
- Ability to work collaboratively in a team environment.
Benefits:
- Gain hands-on experience in web development and chip design.
- Opportunity to work with cutting-edge technology.
- Enhance your problem-solving and programming skills.
- Collaborate with a dynamic and supportive team.
If you are interested in this exciting opportunity, please contact the email below for more details.
Voraussetzungen
Kontakt
Betreuer:
Acceleration of Artificial Netlist Generation
Beschreibung
Data-driven Methods are the dominant modeling approaches nowadays. Machine Learning approaches, like graph neural networks, are applied to classic EDA problems (e.g. power modeling [1]). To ensure transferability between different circuit designs, the models have to be trained on diverse datasets. This includes various circuit designs showing cifferent characteristical corners for measures, like timing or power dissipation.
The obstacle for academic research here is the lack of freely available circuits. There exist online collections, like OpenCores [2]. But it is questionable, if they support various design corners that make models robust. Here, the generation of artificial netlists can support. Frameworks for this target the automatic generation of random circuit designs with the only usecase to show realistic behavior to EDA tools. They do not have any other usable functionality. Although already used for classical EDA tools, artificial netlist generator (ANG) frameworks have been already developed especially for EDA targets [3].
As also large netlists need to be included in datasets, the performance of the ANG implementation itself need to be capable to generate netlists with large cell counts. The focus of this project should be to identify the time-consuming steps of an existing ANG implementation. Based on this analysis, the implementation should be modified for an acceleration of the generation run.
References:
[1] ZHANG, Yanqing; REN, Haoxing; KHAILANY, Brucek. GRANNITE: Graph neural network inference for transferable power estimation. In: 2020 57th ACM/IEEE Design Automation Conference (DAC). IEEE, 2020. S. 1-6.
[2] https://opencores.org/
[3] KIM, Daeyeon, et al. Construction of realistic place-and-route benchmarks for machine learning applications. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2022, 42. Jg., Nr. 6, S. 2030-2042.
Voraussetzungen
- interest in software development for electronic circuit design automation
- solid knowledge of digital circuit design
- very profound knowledge of C++
- ability to work independent
Kontakt
If you are interested in this topic, send me your application at:
philipp.fengler@tum.de
Betreuer:
Masterarbeiten
Design Automation for Digital Microfluidics (DMF) Chip Layout and Routing
Beschreibung
Project Overview:
Digital Microfluidics (DMF) is a versatile technology that enables the precise manipulation of tiny droplets on a chip through the application of electric fields. DMF has transformative applications in biological and chemical analysis, diagnostics, and microfluidic research by allowing for controlled movement, mixing, and splitting of fluid droplets on a surface. This technology is widely used in labs-on-a-chip, where samples and reagents can be handled and processed with minimal sample volume and maximum efficiency.
In this project, you’ll have the unique opportunity to build an automated DMF design program that will revolutionize the way researchers and engineers design DMF chips. The program will streamline the design process, allowing users to customize chip layouts based on specific requirements and generate optimized designs quickly.
Project Goals:
The primary objective is to create a program that can automatically design DMF chips based on user-defined parameters and generate a layout for electrodes and wiring routes to control pins. Here’s a breakdown of the project’s main goals:
-
User-Defined DMF Specifications:
Develop an intuitive interface that allows users to specify key design elements, including:- Electrode size and shape.
- Array size (number of electrodes in rows and columns).
- Layout constraints (e.g., spacing between electrodes, chip dimensions).
-
Automated Electrode Layout Generation:
Implement a backend that can process user input and automatically generate an array of electrodes according to the defined specifications. This will involve designing an efficient algorithm for arranging electrodes in a way that minimizes space while adhering to user preferences and technical constraints. -
Wire Routing Optimization:
Design and integrate an algorithm for automatic wire routing that connects each electrode to a control pin, ensuring minimal overlap and optimized routing paths. This step is critical for functional DMF chips, where clear and organized routing ensures reliable signal transmission and device performance. -
Exportable Design Files:
Enable users to export the generated design as a file that can be used in standard design software or directly implemented in DMF chip production. This feature allows the program to seamlessly fit into various design and manufacturing workflows.
Key Skills and Learning Outcomes:
By completing this project, students will gain valuable experience in:
- Algorithm Development and Optimization: Create algorithms for layout generation and wire routing that consider efficiency, space constraints, and functionality.
- Computer-Aided Design (CAD): Gain experience in translating user specifications into a tangible, manufacturable design.
- Microfluidics and DMF Technology: Acquire knowledge in DMF technology and its application in real-world research and industry settings.
- Software Development and User Interface Design: Build a user-friendly interface that allows for seamless input and output, making complex designs accessible even to non-specialists.
Ideal Candidate:
This project is ideal for students with an interest in microfluidics, computer-aided design, and automation. Students should have some experience in programming (Python, Java, or C++) and be comfortable with algorithmic problem-solving. Familiarity with CAD software, microfluidic systems, or electronic design automation (EDA) tools will be beneficial but is not required.
Outcome and Impact:
The completed project will provide a turnkey solution for DMF chip design that drastically reduces the time and complexity involved in chip layout and routing. This automated tool has the potential to become an invaluable resource in labs and industries focused on DMF, streamlining design processes and enabling rapid prototyping for research and commercial applications.
Are you ready to push the boundaries of automation and make a meaningful contribution to the field of microfluidics? Join us in designing a tool that will simplify DMF chip production and open doors to new possibilities in research and diagnostics!
Kontakt
Yushen.Zhang+Project@TUM.de
Betreuer:
Development of a PCB-Based Digital Microfluidics Platform
Beschreibung
Are you interested in hands-on experience in the emerging field of microfluidics? We are seeking a motivated student to join an innovative project focused on developing a PCB (Printed Circuit Board)-based digital microfluidics (DMF) platform. This project offers an excellent opportunity to apply your knowledge of hardware and PCB design while diving into the fascinating world of microfluidics.
About Digital Microfluidics (DMF):
Digital microfluidics (DMF) is a technology that allows precise manipulation of tiny droplets on a microscale using electrical fields. Unlike continuous-flow microfluidics, which relies on channels and pumps, DMF provides flexibility by enabling individual droplets to be moved, merged, split, or mixed on an open surface. This droplet-based control offers a powerful approach for various applications, from biomedical assays to chemical synthesis, with the benefit of reconfigurability and automation.
Project Scope:
In this project, you will focus on designing and implementing a DMF platform on a PCB. This involves:
-
Hardware Design and Integration: Designing a PCB layout to support electrode patterns necessary for droplet manipulation. The design must enable precise control of droplet movement across the platform, incorporating key components like driving electronics, electrode arrays, and control circuits.
-
Electronics and Control Systems: Developing and implementing a control system to power the electrodes, allowing selective activation for droplet control. You will have the opportunity to work with microcontrollers and control interfaces for automated droplet manipulation.
-
Testing and Optimization: Conducting experiments to validate the functionality of the DMF platform, evaluating parameters such as droplet speed, control accuracy, and system robustness. This includes troubleshooting and optimizing the system for reliable performance.
Requirements:
- Background in Hardware Design: Familiarity with PCB design is essential. Experience with software tools like Altium Designer, Eagle, or KiCad is highly preferred.
- Knowledge of Electronics Fundamentals: Understanding of microcontrollers, signal processing, and basic circuit design will be beneficial for the control system aspects of the project.
- Interest in Microfluidics or Biomedical Engineering: While prior experience in microfluidics is not required, an enthusiasm for learning about microfluidic systems and applications will be invaluable.
What You Will Gain:
- Practical experience in PCB design and hardware integration for microfluidic applications.
- Insight into the principles and applications of digital microfluidics.
- The opportunity to contribute to the development of cutting-edge technology with potential applications in diagnostics, biology, and chemistry.
If you are a proactive learner with a passion for electronics and an interest in microfluidics, we invite you to apply for this exciting project. This is a unique chance to apply your technical skills to an emerging area with broad interdisciplinary applications.
Kontakt
Yushen.Zhang+Project@TUM.de
Betreuer:
Web-Based Chip Design Platform Development
Beschreibung
This is an opportunity for students to join a project focused on further developing our existing web-based chip design platform. This project will involve identifying and resolving bugs, as well as enhancing the platform’s functionality.
Key Responsibilities:
- Further develop and improve the web-based chip design platform.
- Identify, troubleshoot, and resolve bugs and issues.
- Implement new features and improvements.
Requirements:
- Basic understanding of web programming (HTML, CSS, and JavaScript).
- Familiarity with the Vue.js framework or a willingness to learn it independently.
- Strong problem-solving skills and attention to detail.
- Ability to work collaboratively in a team environment.
Benefits:
- Gain hands-on experience in web development and chip design.
- Opportunity to work with cutting-edge technology.
- Enhance your problem-solving and programming skills.
- Collaborate with a dynamic and supportive team.
If you are interested in this exciting opportunity, please contact the email below for more details.
Voraussetzungen
Kontakt
Betreuer:
Fine-grained Exploration and Optimization of Deployment Parameters for Efficient Execution of Machine Learning Tasks on Microcontrollers
Beschreibung
Motivation
HW/SW Codesign, a technique that has been around for several decades, allows hardware designers
to take the target application into consideration and further enables software engineers to start
developing and testing firmware before actual hardware becomes available. This can drastically
reduce the time-to-market for new products and also comes with lower error rates compared to
conventional development cycles. Virtual prototyping is an important component in the typical
HW/SW-Codesign flow as software can be simulated at several abstraction layers (RTL-Level,
Instruction Level, Functional-Level) at early development stages, not only to find potential
hardware/software bugs but also to gain importation information regarding the expected
performance and efficiency metrics such as Runtime/Latency/Utilization.
Due to the increasing relevance of machine learning applications in our everyday lives, the co-
design and co-optimization on the hardware and models (HW/Model-Codesign) became more
popular, hence instead of the C/C++ code to be executed on the target device, the model
architecture and training aspects are aligned with the to be designed hardware or vice-versa.
However, due to the high complexity of nowadays machine learning frameworks and software
compilers, the deployment-related parameters also play a bigger role, which should be investigated
and exploited in the thesis.
Technical Background
The Embedded System Level (ESL) group at the EDA chair has a deep background in virtual
prototyping techniques. Recently, embedded machine learning became a highly exciting field of
research.
We are working primarily in an open-source software ecosystem. ETISS[1] is the instruction set
simulator that allows us to evaluate various embedded applications for different ISAs (nowadays
mainly RISC-V). Apache TVM[2] has been our ML deployment framework of choice for several
years now, especially due to its MicroTVM subproject. Our TinyML deployment and benchmarking
framework MLonMCU[3] is a powerful tool that enables us to evaluate different configurations of
tools fully automatically. However the actual candidates for evaluation need to be chosen manually,
which can lead to suboptimal results.
Task Description
In this project, an automated exploration for deployment parameters should be established. Further,
state-of-the-art optimization techniques must be utilized to find optimal sets of parameters in the
hyper-dimensional search space in an acceptable amount of time (no exhaustive search feasible).
The optimization should take multiple deployment metrics (for example, total runtime or memory
footprint) into account, yielding to a multi-objective optimization flow.
The to-be-implemented algorithms should build up on the existing tooling for prototyping and
benchmarking TinyML models developed at the EDA chair (ETISS & MLonMCU). If available,
existing libraries/packages for (hyper-parameter) optimization (for example, Optuna[4] or
XGBoost[5]) can be utilized.
First, a customizable objective function is required, which can be calculated, for example, based on
the weighted sum of relevant metrics determined using MLonMCU and should be later integrated
into the optimization algorithms.
To keep the complexity of the task low, the considered hardware and machine learning models can
be assumed as fixed. The workloads are further provided as already trained (and compressed)
models. The focus will thereby be solely on the deployment aspects of the machine learning
applications, which are mostly defined by the used machine learning and software compilers. The
search space grows in size heavily depending on the number of considered free variables, which can
be of different types (for example, categorical, discrete, sequential,…). Some examples are:
- Used data/kernel layout for convolution operations (NCHW, NHWC, HWIO, OHWI,…)
- Choice of kernel implementation (trivial, fallback, tuned, 3rd party kernel library, external,
accelerator,…)
- Compiler Flags (-O3/-Os/…, -fno-unroll,…)
It might turn out that some decisions might be helpful for some layers, while others would profit
from slightly or heavily different sets of parameters. Therefore, it should be possible to perform the
exploration on a per-layer fashion, which could yield even better results.
The optimization and exploration flow shall be visualized (for example Pareto plots) for the user
and executed in an efficient way to make sure of the available resources on our compute servers
(utilizing parallel processing and remote-execution features provided by MLonMCU)
Work Outline
1. Literature research
2. Setup toolset (MLonMCU → ETISS + TVM + muRISCV-NN)
3. Describe customizable objective/score functions for the optimization algorithm
4. Define search space(s) for deployment-parameter exploration
5. Develop automated exploration and optimization flow around the MLonMCU tool which
can take a batch of parameters and return the metrics used as inputs of the objective function
6. Investigate the potential of fine-grained (per-layer) optimization compared to a holistic (end-
to-end) approach
7. Optional: Introduce constraints (for example ROM footprint <1MB) to remove illegal
candidates from the search space (and potentially skip the time-consuming execution of
candidates)
8. Optional: Allow fast-estimation of deployment metrics by training a cost-model based on
the previous experiments.
References
[1] Mueller-Gritschneder, D., Devarajegowda, K., Dittrich, M., Ecker, W., Greim, M., & Schlichtmann, U. (2017, October). The
extendable translating instruction set simulator (ETISS) interlinked with an MDA framework for fast RISC prototyping. In
Proceedings of the 28th International Symposium on Rapid System Prototyping: Shortening the Path from Specification to Prototype
(pp. 79-84). GitHub: https://github.com/tum-ei-eda/etiss
[2] Chen, T., Moreau, T., Jiang, Z., Shen, H., Yan, E. Q., Wang, L., ... & Krishnamurthy, A. (2018). TVM: end-to-end optimization
stack for deep learning. arXiv preprint arXiv:1802.04799, 11(2018), 20. GitHub: https://github.com/apache/tvm
[3] van Kempen, P., Stahl, R., Mueller-Gritschneder, D., & Schlichtmann, U. (2023, September). MLonMCU: TinyML
Benchmarking with Fast Retargeting. In Proceedings of the 2023 Workshop on Compilers, Deployment, and Tooling for Edge AI (pp.
32-36). GitHub: https://github.com/tum-ei-eda/mlonmcu
[4] Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019, July). Optuna: A next-generation hyperparameter optimization
framework. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 2623-
2631). GitHub: https://github.com/optuna/optuna
[5] Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd
international conference on knowledge discovery and data mining (pp. 785-794). GitHub: https://github.com/dmlc/xgboost
Kontakt
Philipp van Kempen
Betreuer:
Hardware-based Memory Safety in RISC-V
Beschreibung
Memory safety bugs, e.g., buffer-over?ows or use-after-free, remain in the top ranks of security vulnerabilities. New hardware extensions such as the ARM Memory Tagging Extension help as mitigation, but are not yet available for all architectures. In this work, you will analyze and compare different methods to implement hardware-based memory safety approaches and their advantages/disadvantages. You will then implement hardware support for memory safety on RISC-V hardware.The work done in this thesis is part of the Chip Design Center Bayern Innovative that helps build an independent Chip Design infrastructure in Bavaria. In this project the Fraunhofer AISEC helps to develop secure RISC-V hardware and encourages publication of the ?nal results.
Voraussetzungen
The following list of prerequisites is not complete, but shall give you an idea what is expected.
- Experience in a hardware description language like VHDL/Verilog
- Basic knowledge of computer architectures and embedded systems programming
- Basic knowledge in C/C++ to use our instrumentation and evaluation framework
Kontakt
Please apply to:
Fraunhofer AISEC
Lichtenbergstraße 11
85748 München
Konrad Hohentanner
or via email: konrad.hohentanner@aisec.fraunhofer.de
Please attach your current grade report and CV to your application.
Betreuer:
Algorithm-based Error Detection for Hardware-Accelerated ANNs
Beschreibung
Artificial Neural Networks (ANNs) are being deployed increasingly in safety-critical scenes, e.g., automotive systems and their platforms. Various fault tolerance/detection methods can be adopted to ensure the computation of the ML networks' inferences is reliable. A state-of-the-art solution is redundancy, where a computation is made multiple times, and their respective results are compared. This can be achieved sequentially or concurrently, e.g., through lock-stepped processors. However, this redundancy method introduces a significant overhead to the system: The required multiplicity of computational demand - execution time or processing nodes. To mitigate this overhead, several Algorithm-based Error Detection (ABED) approaches can be taken; among these, the following should be considered in this work:
- Selective Hardening: Only the most vulnerable parts (layers) are duplicated.
- Checksums: Redundancy for linear operations can be achieved with checksums. It aims to mitigate the overhead by introducing redundancy into the algorithms, e.g., filter and input checksums for convolutions [1] and fully connected (dense) layers [2].
The goals of this project are:
- Integrate an existing ABED-enhanced ML compiler for an industrial ANN deployment flow,
- design an experimental evaluation to test the performance impacts of 1. and 2. for an industry HW/SW setup, and
- conduct statistical fault injection experiments [3] to measure error mitigation of 1. and 2.
Related Work:
[1] S. K. S. Hari, M. B. Sullivan, T. Tsai, and S. W. Keckler, "Making Convolutions Resilient Via Algorithm-Based Error Detection Techniques," in IEEE Transactions on Dependable and Secure Computing, vol. 19, no. 4, pp. 2546-2558, 1 July-Aug. 2022, doi: 10.1109/TDSC.2021.3063083.
[2] Kuang-Hua Huang and J. A. Abraham, "Algorithm-Based Fault Tolerance for Matrix Operations," in IEEE Transactions on Computers, vol. C-33, no. 6, pp. 518-528, June 1984, doi: 10.1109/TC.1984.1676475.
[3] R. Leveugle, A. Calvez, P. Maistri, and P. Vanhauwaert, "Statistical fault injection: Quantified error and confidence," 2009 Design, Automation & Test in Europe Conference & Exhibition, Nice, France, 2009, pp. 502-506, doi: 10.1109/DATE.2009.5090716.
Voraussetzungen
- Good understanding of Data Flow Graphs, Scheduling, etc.
- Good understanding of ANNs
- Good knowledge of Linux, (embedded) C/C++, Python
- Basic understanding of Compilers, preferably TVM and LLVM
This work will be conducted in cooperation with Infineon, Munich.
Kontakt
Please apply
johannes.geier@tum.de
Please attach your current transcript of records (grade report) and CV to your application.
Betreuer:
Cadence Internship position for AI ML assisted Functional Verification
Beschreibung
Kontakt
marion@cadence.com
Betreuer:
Interdisziplinäre Projekte
Design Automation for Digital Microfluidics (DMF) Chip Layout and Routing
Beschreibung
Project Overview:
Digital Microfluidics (DMF) is a versatile technology that enables the precise manipulation of tiny droplets on a chip through the application of electric fields. DMF has transformative applications in biological and chemical analysis, diagnostics, and microfluidic research by allowing for controlled movement, mixing, and splitting of fluid droplets on a surface. This technology is widely used in labs-on-a-chip, where samples and reagents can be handled and processed with minimal sample volume and maximum efficiency.
In this project, you’ll have the unique opportunity to build an automated DMF design program that will revolutionize the way researchers and engineers design DMF chips. The program will streamline the design process, allowing users to customize chip layouts based on specific requirements and generate optimized designs quickly.
Project Goals:
The primary objective is to create a program that can automatically design DMF chips based on user-defined parameters and generate a layout for electrodes and wiring routes to control pins. Here’s a breakdown of the project’s main goals:
-
User-Defined DMF Specifications:
Develop an intuitive interface that allows users to specify key design elements, including:- Electrode size and shape.
- Array size (number of electrodes in rows and columns).
- Layout constraints (e.g., spacing between electrodes, chip dimensions).
-
Automated Electrode Layout Generation:
Implement a backend that can process user input and automatically generate an array of electrodes according to the defined specifications. This will involve designing an efficient algorithm for arranging electrodes in a way that minimizes space while adhering to user preferences and technical constraints. -
Wire Routing Optimization:
Design and integrate an algorithm for automatic wire routing that connects each electrode to a control pin, ensuring minimal overlap and optimized routing paths. This step is critical for functional DMF chips, where clear and organized routing ensures reliable signal transmission and device performance. -
Exportable Design Files:
Enable users to export the generated design as a file that can be used in standard design software or directly implemented in DMF chip production. This feature allows the program to seamlessly fit into various design and manufacturing workflows.
Key Skills and Learning Outcomes:
By completing this project, students will gain valuable experience in:
- Algorithm Development and Optimization: Create algorithms for layout generation and wire routing that consider efficiency, space constraints, and functionality.
- Computer-Aided Design (CAD): Gain experience in translating user specifications into a tangible, manufacturable design.
- Microfluidics and DMF Technology: Acquire knowledge in DMF technology and its application in real-world research and industry settings.
- Software Development and User Interface Design: Build a user-friendly interface that allows for seamless input and output, making complex designs accessible even to non-specialists.
Ideal Candidate:
This project is ideal for students with an interest in microfluidics, computer-aided design, and automation. Students should have some experience in programming (Python, Java, or C++) and be comfortable with algorithmic problem-solving. Familiarity with CAD software, microfluidic systems, or electronic design automation (EDA) tools will be beneficial but is not required.
Outcome and Impact:
The completed project will provide a turnkey solution for DMF chip design that drastically reduces the time and complexity involved in chip layout and routing. This automated tool has the potential to become an invaluable resource in labs and industries focused on DMF, streamlining design processes and enabling rapid prototyping for research and commercial applications.
Are you ready to push the boundaries of automation and make a meaningful contribution to the field of microfluidics? Join us in designing a tool that will simplify DMF chip production and open doors to new possibilities in research and diagnostics!
Kontakt
Yushen.Zhang+Project@TUM.de
Betreuer:
Development of a PCB-Based Digital Microfluidics Platform
Beschreibung
Are you interested in hands-on experience in the emerging field of microfluidics? We are seeking a motivated student to join an innovative project focused on developing a PCB (Printed Circuit Board)-based digital microfluidics (DMF) platform. This project offers an excellent opportunity to apply your knowledge of hardware and PCB design while diving into the fascinating world of microfluidics.
About Digital Microfluidics (DMF):
Digital microfluidics (DMF) is a technology that allows precise manipulation of tiny droplets on a microscale using electrical fields. Unlike continuous-flow microfluidics, which relies on channels and pumps, DMF provides flexibility by enabling individual droplets to be moved, merged, split, or mixed on an open surface. This droplet-based control offers a powerful approach for various applications, from biomedical assays to chemical synthesis, with the benefit of reconfigurability and automation.
Project Scope:
In this project, you will focus on designing and implementing a DMF platform on a PCB. This involves:
-
Hardware Design and Integration: Designing a PCB layout to support electrode patterns necessary for droplet manipulation. The design must enable precise control of droplet movement across the platform, incorporating key components like driving electronics, electrode arrays, and control circuits.
-
Electronics and Control Systems: Developing and implementing a control system to power the electrodes, allowing selective activation for droplet control. You will have the opportunity to work with microcontrollers and control interfaces for automated droplet manipulation.
-
Testing and Optimization: Conducting experiments to validate the functionality of the DMF platform, evaluating parameters such as droplet speed, control accuracy, and system robustness. This includes troubleshooting and optimizing the system for reliable performance.
Requirements:
- Background in Hardware Design: Familiarity with PCB design is essential. Experience with software tools like Altium Designer, Eagle, or KiCad is highly preferred.
- Knowledge of Electronics Fundamentals: Understanding of microcontrollers, signal processing, and basic circuit design will be beneficial for the control system aspects of the project.
- Interest in Microfluidics or Biomedical Engineering: While prior experience in microfluidics is not required, an enthusiasm for learning about microfluidic systems and applications will be invaluable.
What You Will Gain:
- Practical experience in PCB design and hardware integration for microfluidic applications.
- Insight into the principles and applications of digital microfluidics.
- The opportunity to contribute to the development of cutting-edge technology with potential applications in diagnostics, biology, and chemistry.
If you are a proactive learner with a passion for electronics and an interest in microfluidics, we invite you to apply for this exciting project. This is a unique chance to apply your technical skills to an emerging area with broad interdisciplinary applications.
Kontakt
Yushen.Zhang+Project@TUM.de
Betreuer:
Web-Based Chip Design Platform Development
Beschreibung
This is an opportunity for students to join a project focused on further developing our existing web-based chip design platform. This project will involve identifying and resolving bugs, as well as enhancing the platform’s functionality.
Key Responsibilities:
- Further develop and improve the web-based chip design platform.
- Identify, troubleshoot, and resolve bugs and issues.
- Implement new features and improvements.
Requirements:
- Basic understanding of web programming (HTML, CSS, and JavaScript).
- Familiarity with the Vue.js framework or a willingness to learn it independently.
- Strong problem-solving skills and attention to detail.
- Ability to work collaboratively in a team environment.
Benefits:
- Gain hands-on experience in web development and chip design.
- Opportunity to work with cutting-edge technology.
- Enhance your problem-solving and programming skills.
- Collaborate with a dynamic and supportive team.
If you are interested in this exciting opportunity, please contact the email below for more details.
Voraussetzungen
Kontakt
Betreuer:
Vector Graphics Generation from XML Descriptions of Chip Modules
Beschreibung
Project Description
In this project, students will develop a Java program that reads an XML file describing various characteristics of a chip module and generates corresponding SVG graphics based on the provided descriptions. This project aims to enhance students’ understanding of XML parsing, SVG graphics creation, and Java programming. By the end of the project, students will have a functional tool that can visualize chip modules dynamically.
Objectives
- To understand and implement XML parsing in Java.
- To learn the basics of SVG graphics and how to generate them programmatically.
- To develop a Java application that integrates XML data with SVG output.
- To enhance problem-solving and programming skills in Java.
Prerequisites
Students should have the following skills and knowledge before starting this project:
- Basic Java Programming: Understanding of Java syntax, object-oriented programming concepts, and basic data structures.
- XML Basics: Familiarity with XML structure and how to read/write XML files.
- SVG Fundamentals: Basic knowledge of SVG (Scalable Vector Graphics) and its elements.
- Problem-Solving Skills: Ability to break down complex problems into manageable tasks and implement solutions.
Project Tasks
- XML Parsing: Write a Java program to read and parse the XML file containing chip module descriptions.
- SVG Generation: Develop methods to convert parsed XML data into SVG graphics.
- Integration: Combine XML parsing and SVG generation into a cohesive Java application.
- Testing and Debugging: Test the application with various XML files and debug any issues that arise.
- Documentation: Document the code and provide a user guide for the application.
Voraussetzungen
See above.
Kontakt
Yushen.Zhang+Project@cs.tum.edu
Betreuer:
Fine-grained Exploration and Optimization of Deployment Parameters for Efficient Execution of Machine Learning Tasks on Microcontrollers
Beschreibung
Motivation
HW/SW Codesign, a technique that has been around for several decades, allows hardware designers
to take the target application into consideration and further enables software engineers to start
developing and testing firmware before actual hardware becomes available. This can drastically
reduce the time-to-market for new products and also comes with lower error rates compared to
conventional development cycles. Virtual prototyping is an important component in the typical
HW/SW-Codesign flow as software can be simulated at several abstraction layers (RTL-Level,
Instruction Level, Functional-Level) at early development stages, not only to find potential
hardware/software bugs but also to gain importation information regarding the expected
performance and efficiency metrics such as Runtime/Latency/Utilization.
Due to the increasing relevance of machine learning applications in our everyday lives, the co-
design and co-optimization on the hardware and models (HW/Model-Codesign) became more
popular, hence instead of the C/C++ code to be executed on the target device, the model
architecture and training aspects are aligned with the to be designed hardware or vice-versa.
However, due to the high complexity of nowadays machine learning frameworks and software
compilers, the deployment-related parameters also play a bigger role, which should be investigated
and exploited in the thesis.
Technical Background
The Embedded System Level (ESL) group at the EDA chair has a deep background in virtual
prototyping techniques. Recently, embedded machine learning became a highly exciting field of
research.
We are working primarily in an open-source software ecosystem. ETISS[1] is the instruction set
simulator that allows us to evaluate various embedded applications for different ISAs (nowadays
mainly RISC-V). Apache TVM[2] has been our ML deployment framework of choice for several
years now, especially due to its MicroTVM subproject. Our TinyML deployment and benchmarking
framework MLonMCU[3] is a powerful tool that enables us to evaluate different configurations of
tools fully automatically. However the actual candidates for evaluation need to be chosen manually,
which can lead to suboptimal results.
Task Description
In this project, an automated exploration for deployment parameters should be established. Further,
state-of-the-art optimization techniques must be utilized to find optimal sets of parameters in the
hyper-dimensional search space in an acceptable amount of time (no exhaustive search feasible).
The optimization should take multiple deployment metrics (for example, total runtime or memory
footprint) into account, yielding to a multi-objective optimization flow.
The to-be-implemented algorithms should build up on the existing tooling for prototyping and
benchmarking TinyML models developed at the EDA chair (ETISS & MLonMCU). If available,
existing libraries/packages for (hyper-parameter) optimization (for example, Optuna[4] or
XGBoost[5]) can be utilized.
First, a customizable objective function is required, which can be calculated, for example, based on
the weighted sum of relevant metrics determined using MLonMCU and should be later integrated
into the optimization algorithms.
To keep the complexity of the task low, the considered hardware and machine learning models can
be assumed as fixed. The workloads are further provided as already trained (and compressed)
models. The focus will thereby be solely on the deployment aspects of the machine learning
applications, which are mostly defined by the used machine learning and software compilers. The
search space grows in size heavily depending on the number of considered free variables, which can
be of different types (for example, categorical, discrete, sequential,…). Some examples are:
- Used data/kernel layout for convolution operations (NCHW, NHWC, HWIO, OHWI,…)
- Choice of kernel implementation (trivial, fallback, tuned, 3rd party kernel library, external,
accelerator,…)
- Compiler Flags (-O3/-Os/…, -fno-unroll,…)
It might turn out that some decisions might be helpful for some layers, while others would profit
from slightly or heavily different sets of parameters. Therefore, it should be possible to perform the
exploration on a per-layer fashion, which could yield even better results.
The optimization and exploration flow shall be visualized (for example Pareto plots) for the user
and executed in an efficient way to make sure of the available resources on our compute servers
(utilizing parallel processing and remote-execution features provided by MLonMCU)
Work Outline
1. Literature research
2. Setup toolset (MLonMCU → ETISS + TVM + muRISCV-NN)
3. Describe customizable objective/score functions for the optimization algorithm
4. Define search space(s) for deployment-parameter exploration
5. Develop automated exploration and optimization flow around the MLonMCU tool which
can take a batch of parameters and return the metrics used as inputs of the objective function
6. Investigate the potential of fine-grained (per-layer) optimization compared to a holistic (end-
to-end) approach
7. Optional: Introduce constraints (for example ROM footprint <1MB) to remove illegal
candidates from the search space (and potentially skip the time-consuming execution of
candidates)
8. Optional: Allow fast-estimation of deployment metrics by training a cost-model based on
the previous experiments.
References
[1] Mueller-Gritschneder, D., Devarajegowda, K., Dittrich, M., Ecker, W., Greim, M., & Schlichtmann, U. (2017, October). The
extendable translating instruction set simulator (ETISS) interlinked with an MDA framework for fast RISC prototyping. In
Proceedings of the 28th International Symposium on Rapid System Prototyping: Shortening the Path from Specification to Prototype
(pp. 79-84). GitHub: https://github.com/tum-ei-eda/etiss
[2] Chen, T., Moreau, T., Jiang, Z., Shen, H., Yan, E. Q., Wang, L., ... & Krishnamurthy, A. (2018). TVM: end-to-end optimization
stack for deep learning. arXiv preprint arXiv:1802.04799, 11(2018), 20. GitHub: https://github.com/apache/tvm
[3] van Kempen, P., Stahl, R., Mueller-Gritschneder, D., & Schlichtmann, U. (2023, September). MLonMCU: TinyML
Benchmarking with Fast Retargeting. In Proceedings of the 2023 Workshop on Compilers, Deployment, and Tooling for Edge AI (pp.
32-36). GitHub: https://github.com/tum-ei-eda/mlonmcu
[4] Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019, July). Optuna: A next-generation hyperparameter optimization
framework. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 2623-
2631). GitHub: https://github.com/optuna/optuna
[5] Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd
international conference on knowledge discovery and data mining (pp. 785-794). GitHub: https://github.com/dmlc/xgboost
Kontakt
Philipp van Kempen
Betreuer:
Startup Microsystems: Innovate, Create, Compete – COSIMA Challenge
Microsystem, MEMS, Innovation, Creativity
This is a dynamic and hands-on internship designed to empower students to harness their creativity and technical skills to participate in the COSIMA (Competition of Students in Microsystems Applications) contest. This internship is not just an academic pursuit; it's a journey towards becoming an innovative entrepreneur in the realm of sensor and microsystem applications. At the end of this contest, you will be credited with the credits for FP/IP/IDP.
Beschreibung
Welcome to "Startup Microsystems: Innovate, Create, Compete – COSIMA Challenge," a dynamic and hands-on internship designed to empower students in harnessing their creativity and technical skills to participate in the COSIMA (Competition of Students in Microsystems Applications) contest. This internship is not just an academic pursuit; it's a journey towards becoming innovative entrepreneurs in the realm of sensor and microsystem applications.
COSIMA is a German national student competition.
Overview:
In this practical internship, students will delve into the world of microsystems, exploring their components, functionalities, and potential applications. The focus will be on fostering creativity and teamwork as students work collaboratively to conceive, design, and prototype innovative solutions using sensors and microsystems.
Key Features:
Creative Exploration: Unlike traditional courses and internships, this one offers the freedom to choose and define your own technical challenge. Students will be encouraged to think outside the box, identify real-world problems, and propose solutions that leverage microsystems to enhance human-technology interactions.
Hands-On Prototyping: The heart of the internship lies in turning ideas into reality. Students will actively engage in the prototyping process, developing functional prototypes of their innovative concepts. Emphasis will be placed on understanding the practical aspects of sensor integration, actuation, and control electronics.
COSIMA Contest Preparation: The internship will align with the COSIMA competition requirements, preparing students to present their prototypes on the competition day. Guidance will be provided on creating impactful presentations that showcase the ingenuity and practicality of their solutions.
Go International: The winners of COSIMA will qualify to take part in the international iCAN competition. Guidance and preparation for the iCAN will be provided.
Entrepreneurial Mindset: Drawing inspiration from successful startups that emerged from COSIMA, the internship will instill an entrepreneurial mindset. Students will learn about the essentials of founding a startup, from business planning to pitching their ideas.
Us in the past:
iCANX Wettbewerb 2024 (cosima-mems.de)
Das war COSIMA 2023 (cosima-mems.de)
Voraussetzungen
Intermediate German and English language proficiency is required.
Kontakt
Betreuer:
Forschungspraxis (Research Internships)
Design Automation for Digital Microfluidics (DMF) Chip Layout and Routing
Beschreibung
Project Overview:
Digital Microfluidics (DMF) is a versatile technology that enables the precise manipulation of tiny droplets on a chip through the application of electric fields. DMF has transformative applications in biological and chemical analysis, diagnostics, and microfluidic research by allowing for controlled movement, mixing, and splitting of fluid droplets on a surface. This technology is widely used in labs-on-a-chip, where samples and reagents can be handled and processed with minimal sample volume and maximum efficiency.
In this project, you’ll have the unique opportunity to build an automated DMF design program that will revolutionize the way researchers and engineers design DMF chips. The program will streamline the design process, allowing users to customize chip layouts based on specific requirements and generate optimized designs quickly.
Project Goals:
The primary objective is to create a program that can automatically design DMF chips based on user-defined parameters and generate a layout for electrodes and wiring routes to control pins. Here’s a breakdown of the project’s main goals:
-
User-Defined DMF Specifications:
Develop an intuitive interface that allows users to specify key design elements, including:- Electrode size and shape.
- Array size (number of electrodes in rows and columns).
- Layout constraints (e.g., spacing between electrodes, chip dimensions).
-
Automated Electrode Layout Generation:
Implement a backend that can process user input and automatically generate an array of electrodes according to the defined specifications. This will involve designing an efficient algorithm for arranging electrodes in a way that minimizes space while adhering to user preferences and technical constraints. -
Wire Routing Optimization:
Design and integrate an algorithm for automatic wire routing that connects each electrode to a control pin, ensuring minimal overlap and optimized routing paths. This step is critical for functional DMF chips, where clear and organized routing ensures reliable signal transmission and device performance. -
Exportable Design Files:
Enable users to export the generated design as a file that can be used in standard design software or directly implemented in DMF chip production. This feature allows the program to seamlessly fit into various design and manufacturing workflows.
Key Skills and Learning Outcomes:
By completing this project, students will gain valuable experience in:
- Algorithm Development and Optimization: Create algorithms for layout generation and wire routing that consider efficiency, space constraints, and functionality.
- Computer-Aided Design (CAD): Gain experience in translating user specifications into a tangible, manufacturable design.
- Microfluidics and DMF Technology: Acquire knowledge in DMF technology and its application in real-world research and industry settings.
- Software Development and User Interface Design: Build a user-friendly interface that allows for seamless input and output, making complex designs accessible even to non-specialists.
Ideal Candidate:
This project is ideal for students with an interest in microfluidics, computer-aided design, and automation. Students should have some experience in programming (Python, Java, or C++) and be comfortable with algorithmic problem-solving. Familiarity with CAD software, microfluidic systems, or electronic design automation (EDA) tools will be beneficial but is not required.
Outcome and Impact:
The completed project will provide a turnkey solution for DMF chip design that drastically reduces the time and complexity involved in chip layout and routing. This automated tool has the potential to become an invaluable resource in labs and industries focused on DMF, streamlining design processes and enabling rapid prototyping for research and commercial applications.
Are you ready to push the boundaries of automation and make a meaningful contribution to the field of microfluidics? Join us in designing a tool that will simplify DMF chip production and open doors to new possibilities in research and diagnostics!
Kontakt
Yushen.Zhang+Project@TUM.de
Betreuer:
Web-Based Chip Design Platform Development
Beschreibung
This is an opportunity for students to join a project focused on further developing our existing web-based chip design platform. This project will involve identifying and resolving bugs, as well as enhancing the platform’s functionality.
Key Responsibilities:
- Further develop and improve the web-based chip design platform.
- Identify, troubleshoot, and resolve bugs and issues.
- Implement new features and improvements.
Requirements:
- Basic understanding of web programming (HTML, CSS, and JavaScript).
- Familiarity with the Vue.js framework or a willingness to learn it independently.
- Strong problem-solving skills and attention to detail.
- Ability to work collaboratively in a team environment.
Benefits:
- Gain hands-on experience in web development and chip design.
- Opportunity to work with cutting-edge technology.
- Enhance your problem-solving and programming skills.
- Collaborate with a dynamic and supportive team.
If you are interested in this exciting opportunity, please contact the email below for more details.
Voraussetzungen
Kontakt
Betreuer:
Acceleration of Artificial Netlist Generation
Beschreibung
Data-driven Methods are the dominant modeling approaches nowadays. Machine Learning approaches, like graph neural networks, are applied to classic EDA problems (e.g. power modeling [1]). To ensure transferability between different circuit designs, the models have to be trained on diverse datasets. This includes various circuit designs showing cifferent characteristical corners for measures, like timing or power dissipation.
The obstacle for academic research here is the lack of freely available circuits. There exist online collections, like OpenCores [2]. But it is questionable, if they support various design corners that make models robust. Here, the generation of artificial netlists can support. Frameworks for this target the automatic generation of random circuit designs with the only usecase to show realistic behavior to EDA tools. They do not have any other usable functionality. Although already used for classical EDA tools, artificial netlist generator (ANG) frameworks have been already developed especially for EDA targets [3].
As also large netlists need to be included in datasets, the performance of the ANG implementation itself need to be capable to generate netlists with large cell counts. The focus of this project should be to identify the time-consuming steps of an existing ANG implementation. Based on this analysis, the implementation should be modified for an acceleration of the generation run.
References:
[1] ZHANG, Yanqing; REN, Haoxing; KHAILANY, Brucek. GRANNITE: Graph neural network inference for transferable power estimation. In: 2020 57th ACM/IEEE Design Automation Conference (DAC). IEEE, 2020. S. 1-6.
[2] https://opencores.org/
[3] KIM, Daeyeon, et al. Construction of realistic place-and-route benchmarks for machine learning applications. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2022, 42. Jg., Nr. 6, S. 2030-2042.
Voraussetzungen
- interest in software development for electronic circuit design automation
- solid knowledge of digital circuit design
- very profound knowledge of C++
- ability to work independent
Kontakt
If you are interested in this topic, send me your application at:
philipp.fengler@tum.de
Betreuer:
Vector Graphics Generation from XML Descriptions of Chip Modules
Beschreibung
Project Description
In this project, students will develop a Java program that reads an XML file describing various characteristics of a chip module and generates corresponding SVG graphics based on the provided descriptions. This project aims to enhance students’ understanding of XML parsing, SVG graphics creation, and Java programming. By the end of the project, students will have a functional tool that can visualize chip modules dynamically.
Objectives
- To understand and implement XML parsing in Java.
- To learn the basics of SVG graphics and how to generate them programmatically.
- To develop a Java application that integrates XML data with SVG output.
- To enhance problem-solving and programming skills in Java.
Prerequisites
Students should have the following skills and knowledge before starting this project:
- Basic Java Programming: Understanding of Java syntax, object-oriented programming concepts, and basic data structures.
- XML Basics: Familiarity with XML structure and how to read/write XML files.
- SVG Fundamentals: Basic knowledge of SVG (Scalable Vector Graphics) and its elements.
- Problem-Solving Skills: Ability to break down complex problems into manageable tasks and implement solutions.
Project Tasks
- XML Parsing: Write a Java program to read and parse the XML file containing chip module descriptions.
- SVG Generation: Develop methods to convert parsed XML data into SVG graphics.
- Integration: Combine XML parsing and SVG generation into a cohesive Java application.
- Testing and Debugging: Test the application with various XML files and debug any issues that arise.
- Documentation: Document the code and provide a user guide for the application.
Voraussetzungen
See above.
Kontakt
Yushen.Zhang+Project@cs.tum.edu
Betreuer:
Fine-grained Exploration and Optimization of Deployment Parameters for Efficient Execution of Machine Learning Tasks on Microcontrollers
Beschreibung
Motivation
HW/SW Codesign, a technique that has been around for several decades, allows hardware designers
to take the target application into consideration and further enables software engineers to start
developing and testing firmware before actual hardware becomes available. This can drastically
reduce the time-to-market for new products and also comes with lower error rates compared to
conventional development cycles. Virtual prototyping is an important component in the typical
HW/SW-Codesign flow as software can be simulated at several abstraction layers (RTL-Level,
Instruction Level, Functional-Level) at early development stages, not only to find potential
hardware/software bugs but also to gain importation information regarding the expected
performance and efficiency metrics such as Runtime/Latency/Utilization.
Due to the increasing relevance of machine learning applications in our everyday lives, the co-
design and co-optimization on the hardware and models (HW/Model-Codesign) became more
popular, hence instead of the C/C++ code to be executed on the target device, the model
architecture and training aspects are aligned with the to be designed hardware or vice-versa.
However, due to the high complexity of nowadays machine learning frameworks and software
compilers, the deployment-related parameters also play a bigger role, which should be investigated
and exploited in the thesis.
Technical Background
The Embedded System Level (ESL) group at the EDA chair has a deep background in virtual
prototyping techniques. Recently, embedded machine learning became a highly exciting field of
research.
We are working primarily in an open-source software ecosystem. ETISS[1] is the instruction set
simulator that allows us to evaluate various embedded applications for different ISAs (nowadays
mainly RISC-V). Apache TVM[2] has been our ML deployment framework of choice for several
years now, especially due to its MicroTVM subproject. Our TinyML deployment and benchmarking
framework MLonMCU[3] is a powerful tool that enables us to evaluate different configurations of
tools fully automatically. However the actual candidates for evaluation need to be chosen manually,
which can lead to suboptimal results.
Task Description
In this project, an automated exploration for deployment parameters should be established. Further,
state-of-the-art optimization techniques must be utilized to find optimal sets of parameters in the
hyper-dimensional search space in an acceptable amount of time (no exhaustive search feasible).
The optimization should take multiple deployment metrics (for example, total runtime or memory
footprint) into account, yielding to a multi-objective optimization flow.
The to-be-implemented algorithms should build up on the existing tooling for prototyping and
benchmarking TinyML models developed at the EDA chair (ETISS & MLonMCU). If available,
existing libraries/packages for (hyper-parameter) optimization (for example, Optuna[4] or
XGBoost[5]) can be utilized.
First, a customizable objective function is required, which can be calculated, for example, based on
the weighted sum of relevant metrics determined using MLonMCU and should be later integrated
into the optimization algorithms.
To keep the complexity of the task low, the considered hardware and machine learning models can
be assumed as fixed. The workloads are further provided as already trained (and compressed)
models. The focus will thereby be solely on the deployment aspects of the machine learning
applications, which are mostly defined by the used machine learning and software compilers. The
search space grows in size heavily depending on the number of considered free variables, which can
be of different types (for example, categorical, discrete, sequential,…). Some examples are:
- Used data/kernel layout for convolution operations (NCHW, NHWC, HWIO, OHWI,…)
- Choice of kernel implementation (trivial, fallback, tuned, 3rd party kernel library, external,
accelerator,…)
- Compiler Flags (-O3/-Os/…, -fno-unroll,…)
It might turn out that some decisions might be helpful for some layers, while others would profit
from slightly or heavily different sets of parameters. Therefore, it should be possible to perform the
exploration on a per-layer fashion, which could yield even better results.
The optimization and exploration flow shall be visualized (for example Pareto plots) for the user
and executed in an efficient way to make sure of the available resources on our compute servers
(utilizing parallel processing and remote-execution features provided by MLonMCU)
Work Outline
1. Literature research
2. Setup toolset (MLonMCU → ETISS + TVM + muRISCV-NN)
3. Describe customizable objective/score functions for the optimization algorithm
4. Define search space(s) for deployment-parameter exploration
5. Develop automated exploration and optimization flow around the MLonMCU tool which
can take a batch of parameters and return the metrics used as inputs of the objective function
6. Investigate the potential of fine-grained (per-layer) optimization compared to a holistic (end-
to-end) approach
7. Optional: Introduce constraints (for example ROM footprint <1MB) to remove illegal
candidates from the search space (and potentially skip the time-consuming execution of
candidates)
8. Optional: Allow fast-estimation of deployment metrics by training a cost-model based on
the previous experiments.
References
[1] Mueller-Gritschneder, D., Devarajegowda, K., Dittrich, M., Ecker, W., Greim, M., & Schlichtmann, U. (2017, October). The
extendable translating instruction set simulator (ETISS) interlinked with an MDA framework for fast RISC prototyping. In
Proceedings of the 28th International Symposium on Rapid System Prototyping: Shortening the Path from Specification to Prototype
(pp. 79-84). GitHub: https://github.com/tum-ei-eda/etiss
[2] Chen, T., Moreau, T., Jiang, Z., Shen, H., Yan, E. Q., Wang, L., ... & Krishnamurthy, A. (2018). TVM: end-to-end optimization
stack for deep learning. arXiv preprint arXiv:1802.04799, 11(2018), 20. GitHub: https://github.com/apache/tvm
[3] van Kempen, P., Stahl, R., Mueller-Gritschneder, D., & Schlichtmann, U. (2023, September). MLonMCU: TinyML
Benchmarking with Fast Retargeting. In Proceedings of the 2023 Workshop on Compilers, Deployment, and Tooling for Edge AI (pp.
32-36). GitHub: https://github.com/tum-ei-eda/mlonmcu
[4] Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019, July). Optuna: A next-generation hyperparameter optimization
framework. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 2623-
2631). GitHub: https://github.com/optuna/optuna
[5] Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd
international conference on knowledge discovery and data mining (pp. 785-794). GitHub: https://github.com/dmlc/xgboost
Kontakt
Philipp van Kempen
Betreuer:
Hardware-based Memory Safety in RISC-V
Beschreibung
Memory safety bugs, e.g., buffer-over?ows or use-after-free, remain in the top ranks of security vulnerabilities. New hardware extensions such as the ARM Memory Tagging Extension help as mitigation, but are not yet available for all architectures. In this work, you will analyze and compare different methods to implement hardware-based memory safety approaches and their advantages/disadvantages. You will then implement hardware support for memory safety on RISC-V hardware.The work done in this thesis is part of the Chip Design Center Bayern Innovative that helps build an independent Chip Design infrastructure in Bavaria. In this project the Fraunhofer AISEC helps to develop secure RISC-V hardware and encourages publication of the ?nal results.
Voraussetzungen
The following list of prerequisites is not complete, but shall give you an idea what is expected.
- Experience in a hardware description language like VHDL/Verilog
- Basic knowledge of computer architectures and embedded systems programming
- Basic knowledge in C/C++ to use our instrumentation and evaluation framework
Kontakt
Please apply to:
Fraunhofer AISEC
Lichtenbergstraße 11
85748 München
Konrad Hohentanner
or via email: konrad.hohentanner@aisec.fraunhofer.de
Please attach your current grade report and CV to your application.
Betreuer:
Algorithm-based Error Detection for Hardware-Accelerated ANNs
Beschreibung
Artificial Neural Networks (ANNs) are being deployed increasingly in safety-critical scenes, e.g., automotive systems and their platforms. Various fault tolerance/detection methods can be adopted to ensure the computation of the ML networks' inferences is reliable. A state-of-the-art solution is redundancy, where a computation is made multiple times, and their respective results are compared. This can be achieved sequentially or concurrently, e.g., through lock-stepped processors. However, this redundancy method introduces a significant overhead to the system: The required multiplicity of computational demand - execution time or processing nodes. To mitigate this overhead, several Algorithm-based Error Detection (ABED) approaches can be taken; among these, the following should be considered in this work:
- Selective Hardening: Only the most vulnerable parts (layers) are duplicated.
- Checksums: Redundancy for linear operations can be achieved with checksums. It aims to mitigate the overhead by introducing redundancy into the algorithms, e.g., filter and input checksums for convolutions [1] and fully connected (dense) layers [2].
The goals of this project are:
- Integrate an existing ABED-enhanced ML compiler for an industrial ANN deployment flow,
- design an experimental evaluation to test the performance impacts of 1. and 2. for an industry HW/SW setup, and
- conduct statistical fault injection experiments [3] to measure error mitigation of 1. and 2.
Related Work:
[1] S. K. S. Hari, M. B. Sullivan, T. Tsai, and S. W. Keckler, "Making Convolutions Resilient Via Algorithm-Based Error Detection Techniques," in IEEE Transactions on Dependable and Secure Computing, vol. 19, no. 4, pp. 2546-2558, 1 July-Aug. 2022, doi: 10.1109/TDSC.2021.3063083.
[2] Kuang-Hua Huang and J. A. Abraham, "Algorithm-Based Fault Tolerance for Matrix Operations," in IEEE Transactions on Computers, vol. C-33, no. 6, pp. 518-528, June 1984, doi: 10.1109/TC.1984.1676475.
[3] R. Leveugle, A. Calvez, P. Maistri, and P. Vanhauwaert, "Statistical fault injection: Quantified error and confidence," 2009 Design, Automation & Test in Europe Conference & Exhibition, Nice, France, 2009, pp. 502-506, doi: 10.1109/DATE.2009.5090716.
Voraussetzungen
- Good understanding of Data Flow Graphs, Scheduling, etc.
- Good understanding of ANNs
- Good knowledge of Linux, (embedded) C/C++, Python
- Basic understanding of Compilers, preferably TVM and LLVM
This work will be conducted in cooperation with Infineon, Munich.
Kontakt
Please apply
johannes.geier@tum.de
Please attach your current transcript of records (grade report) and CV to your application.
Betreuer:
Startup Microsystems: Innovate, Create, Compete – COSIMA Challenge
Microsystem, MEMS, Innovation, Creativity
This is a dynamic and hands-on internship designed to empower students to harness their creativity and technical skills to participate in the COSIMA (Competition of Students in Microsystems Applications) contest. This internship is not just an academic pursuit; it's a journey towards becoming an innovative entrepreneur in the realm of sensor and microsystem applications. At the end of this contest, you will be credited with the credits for FP/IP/IDP.
Beschreibung
Welcome to "Startup Microsystems: Innovate, Create, Compete – COSIMA Challenge," a dynamic and hands-on internship designed to empower students in harnessing their creativity and technical skills to participate in the COSIMA (Competition of Students in Microsystems Applications) contest. This internship is not just an academic pursuit; it's a journey towards becoming innovative entrepreneurs in the realm of sensor and microsystem applications.
COSIMA is a German national student competition.
Overview:
In this practical internship, students will delve into the world of microsystems, exploring their components, functionalities, and potential applications. The focus will be on fostering creativity and teamwork as students work collaboratively to conceive, design, and prototype innovative solutions using sensors and microsystems.
Key Features:
Creative Exploration: Unlike traditional courses and internships, this one offers the freedom to choose and define your own technical challenge. Students will be encouraged to think outside the box, identify real-world problems, and propose solutions that leverage microsystems to enhance human-technology interactions.
Hands-On Prototyping: The heart of the internship lies in turning ideas into reality. Students will actively engage in the prototyping process, developing functional prototypes of their innovative concepts. Emphasis will be placed on understanding the practical aspects of sensor integration, actuation, and control electronics.
COSIMA Contest Preparation: The internship will align with the COSIMA competition requirements, preparing students to present their prototypes on the competition day. Guidance will be provided on creating impactful presentations that showcase the ingenuity and practicality of their solutions.
Go International: The winners of COSIMA will qualify to take part in the international iCAN competition. Guidance and preparation for the iCAN will be provided.
Entrepreneurial Mindset: Drawing inspiration from successful startups that emerged from COSIMA, the internship will instill an entrepreneurial mindset. Students will learn about the essentials of founding a startup, from business planning to pitching their ideas.
Us in the past:
iCANX Wettbewerb 2024 (cosima-mems.de)
Das war COSIMA 2023 (cosima-mems.de)
Voraussetzungen
Intermediate German and English language proficiency is required.
Kontakt
Betreuer:
Ingenieurpraxis
Web-Based Chip Design Platform Development
Beschreibung
This is an opportunity for students to join a project focused on further developing our existing web-based chip design platform. This project will involve identifying and resolving bugs, as well as enhancing the platform’s functionality.
Key Responsibilities:
- Further develop and improve the web-based chip design platform.
- Identify, troubleshoot, and resolve bugs and issues.
- Implement new features and improvements.
Requirements:
- Basic understanding of web programming (HTML, CSS, and JavaScript).
- Familiarity with the Vue.js framework or a willingness to learn it independently.
- Strong problem-solving skills and attention to detail.
- Ability to work collaboratively in a team environment.
Benefits:
- Gain hands-on experience in web development and chip design.
- Opportunity to work with cutting-edge technology.
- Enhance your problem-solving and programming skills.
- Collaborate with a dynamic and supportive team.
If you are interested in this exciting opportunity, please contact the email below for more details.
Voraussetzungen
Kontakt
Betreuer:
Vector Graphics Generation from XML Descriptions of Chip Modules
Beschreibung
Project Description
In this project, students will develop a Java program that reads an XML file describing various characteristics of a chip module and generates corresponding SVG graphics based on the provided descriptions. This project aims to enhance students’ understanding of XML parsing, SVG graphics creation, and Java programming. By the end of the project, students will have a functional tool that can visualize chip modules dynamically.
Objectives
- To understand and implement XML parsing in Java.
- To learn the basics of SVG graphics and how to generate them programmatically.
- To develop a Java application that integrates XML data with SVG output.
- To enhance problem-solving and programming skills in Java.
Prerequisites
Students should have the following skills and knowledge before starting this project:
- Basic Java Programming: Understanding of Java syntax, object-oriented programming concepts, and basic data structures.
- XML Basics: Familiarity with XML structure and how to read/write XML files.
- SVG Fundamentals: Basic knowledge of SVG (Scalable Vector Graphics) and its elements.
- Problem-Solving Skills: Ability to break down complex problems into manageable tasks and implement solutions.
Project Tasks
- XML Parsing: Write a Java program to read and parse the XML file containing chip module descriptions.
- SVG Generation: Develop methods to convert parsed XML data into SVG graphics.
- Integration: Combine XML parsing and SVG generation into a cohesive Java application.
- Testing and Debugging: Test the application with various XML files and debug any issues that arise.
- Documentation: Document the code and provide a user guide for the application.
Voraussetzungen
See above.
Kontakt
Yushen.Zhang+Project@cs.tum.edu
Betreuer:
Startup Microsystems: Innovate, Create, Compete – COSIMA Challenge
Microsystem, MEMS, Innovation, Creativity
This is a dynamic and hands-on internship designed to empower students to harness their creativity and technical skills to participate in the COSIMA (Competition of Students in Microsystems Applications) contest. This internship is not just an academic pursuit; it's a journey towards becoming an innovative entrepreneur in the realm of sensor and microsystem applications. At the end of this contest, you will be credited with the credits for FP/IP/IDP.
Beschreibung
Welcome to "Startup Microsystems: Innovate, Create, Compete – COSIMA Challenge," a dynamic and hands-on internship designed to empower students in harnessing their creativity and technical skills to participate in the COSIMA (Competition of Students in Microsystems Applications) contest. This internship is not just an academic pursuit; it's a journey towards becoming innovative entrepreneurs in the realm of sensor and microsystem applications.
COSIMA is a German national student competition.
Overview:
In this practical internship, students will delve into the world of microsystems, exploring their components, functionalities, and potential applications. The focus will be on fostering creativity and teamwork as students work collaboratively to conceive, design, and prototype innovative solutions using sensors and microsystems.
Key Features:
Creative Exploration: Unlike traditional courses and internships, this one offers the freedom to choose and define your own technical challenge. Students will be encouraged to think outside the box, identify real-world problems, and propose solutions that leverage microsystems to enhance human-technology interactions.
Hands-On Prototyping: The heart of the internship lies in turning ideas into reality. Students will actively engage in the prototyping process, developing functional prototypes of their innovative concepts. Emphasis will be placed on understanding the practical aspects of sensor integration, actuation, and control electronics.
COSIMA Contest Preparation: The internship will align with the COSIMA competition requirements, preparing students to present their prototypes on the competition day. Guidance will be provided on creating impactful presentations that showcase the ingenuity and practicality of their solutions.
Go International: The winners of COSIMA will qualify to take part in the international iCAN competition. Guidance and preparation for the iCAN will be provided.
Entrepreneurial Mindset: Drawing inspiration from successful startups that emerged from COSIMA, the internship will instill an entrepreneurial mindset. Students will learn about the essentials of founding a startup, from business planning to pitching their ideas.
Us in the past:
iCANX Wettbewerb 2024 (cosima-mems.de)
Das war COSIMA 2023 (cosima-mems.de)
Voraussetzungen
Intermediate German and English language proficiency is required.
Kontakt
Betreuer:
Studentische Hilfskräfte
Fine-grained Exploration and Optimization of Deployment Parameters for Efficient Execution of Machine Learning Tasks on Microcontrollers
Beschreibung
Motivation
HW/SW Codesign, a technique that has been around for several decades, allows hardware designers
to take the target application into consideration and further enables software engineers to start
developing and testing firmware before actual hardware becomes available. This can drastically
reduce the time-to-market for new products and also comes with lower error rates compared to
conventional development cycles. Virtual prototyping is an important component in the typical
HW/SW-Codesign flow as software can be simulated at several abstraction layers (RTL-Level,
Instruction Level, Functional-Level) at early development stages, not only to find potential
hardware/software bugs but also to gain importation information regarding the expected
performance and efficiency metrics such as Runtime/Latency/Utilization.
Due to the increasing relevance of machine learning applications in our everyday lives, the co-
design and co-optimization on the hardware and models (HW/Model-Codesign) became more
popular, hence instead of the C/C++ code to be executed on the target device, the model
architecture and training aspects are aligned with the to be designed hardware or vice-versa.
However, due to the high complexity of nowadays machine learning frameworks and software
compilers, the deployment-related parameters also play a bigger role, which should be investigated
and exploited in the thesis.
Technical Background
The Embedded System Level (ESL) group at the EDA chair has a deep background in virtual
prototyping techniques. Recently, embedded machine learning became a highly exciting field of
research.
We are working primarily in an open-source software ecosystem. ETISS[1] is the instruction set
simulator that allows us to evaluate various embedded applications for different ISAs (nowadays
mainly RISC-V). Apache TVM[2] has been our ML deployment framework of choice for several
years now, especially due to its MicroTVM subproject. Our TinyML deployment and benchmarking
framework MLonMCU[3] is a powerful tool that enables us to evaluate different configurations of
tools fully automatically. However the actual candidates for evaluation need to be chosen manually,
which can lead to suboptimal results.
Task Description
In this project, an automated exploration for deployment parameters should be established. Further,
state-of-the-art optimization techniques must be utilized to find optimal sets of parameters in the
hyper-dimensional search space in an acceptable amount of time (no exhaustive search feasible).
The optimization should take multiple deployment metrics (for example, total runtime or memory
footprint) into account, yielding to a multi-objective optimization flow.
The to-be-implemented algorithms should build up on the existing tooling for prototyping and
benchmarking TinyML models developed at the EDA chair (ETISS & MLonMCU). If available,
existing libraries/packages for (hyper-parameter) optimization (for example, Optuna[4] or
XGBoost[5]) can be utilized.
First, a customizable objective function is required, which can be calculated, for example, based on
the weighted sum of relevant metrics determined using MLonMCU and should be later integrated
into the optimization algorithms.
To keep the complexity of the task low, the considered hardware and machine learning models can
be assumed as fixed. The workloads are further provided as already trained (and compressed)
models. The focus will thereby be solely on the deployment aspects of the machine learning
applications, which are mostly defined by the used machine learning and software compilers. The
search space grows in size heavily depending on the number of considered free variables, which can
be of different types (for example, categorical, discrete, sequential,…). Some examples are:
- Used data/kernel layout for convolution operations (NCHW, NHWC, HWIO, OHWI,…)
- Choice of kernel implementation (trivial, fallback, tuned, 3rd party kernel library, external,
accelerator,…)
- Compiler Flags (-O3/-Os/…, -fno-unroll,…)
It might turn out that some decisions might be helpful for some layers, while others would profit
from slightly or heavily different sets of parameters. Therefore, it should be possible to perform the
exploration on a per-layer fashion, which could yield even better results.
The optimization and exploration flow shall be visualized (for example Pareto plots) for the user
and executed in an efficient way to make sure of the available resources on our compute servers
(utilizing parallel processing and remote-execution features provided by MLonMCU)
Work Outline
1. Literature research
2. Setup toolset (MLonMCU → ETISS + TVM + muRISCV-NN)
3. Describe customizable objective/score functions for the optimization algorithm
4. Define search space(s) for deployment-parameter exploration
5. Develop automated exploration and optimization flow around the MLonMCU tool which
can take a batch of parameters and return the metrics used as inputs of the objective function
6. Investigate the potential of fine-grained (per-layer) optimization compared to a holistic (end-
to-end) approach
7. Optional: Introduce constraints (for example ROM footprint <1MB) to remove illegal
candidates from the search space (and potentially skip the time-consuming execution of
candidates)
8. Optional: Allow fast-estimation of deployment metrics by training a cost-model based on
the previous experiments.
References
[1] Mueller-Gritschneder, D., Devarajegowda, K., Dittrich, M., Ecker, W., Greim, M., & Schlichtmann, U. (2017, October). The
extendable translating instruction set simulator (ETISS) interlinked with an MDA framework for fast RISC prototyping. In
Proceedings of the 28th International Symposium on Rapid System Prototyping: Shortening the Path from Specification to Prototype
(pp. 79-84). GitHub: https://github.com/tum-ei-eda/etiss
[2] Chen, T., Moreau, T., Jiang, Z., Shen, H., Yan, E. Q., Wang, L., ... & Krishnamurthy, A. (2018). TVM: end-to-end optimization
stack for deep learning. arXiv preprint arXiv:1802.04799, 11(2018), 20. GitHub: https://github.com/apache/tvm
[3] van Kempen, P., Stahl, R., Mueller-Gritschneder, D., & Schlichtmann, U. (2023, September). MLonMCU: TinyML
Benchmarking with Fast Retargeting. In Proceedings of the 2023 Workshop on Compilers, Deployment, and Tooling for Edge AI (pp.
32-36). GitHub: https://github.com/tum-ei-eda/mlonmcu
[4] Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019, July). Optuna: A next-generation hyperparameter optimization
framework. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 2623-
2631). GitHub: https://github.com/optuna/optuna
[5] Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd
international conference on knowledge discovery and data mining (pp. 785-794). GitHub: https://github.com/dmlc/xgboost
Kontakt
Philipp van Kempen
Betreuer:
Cadence Internship position for AI ML assisted Functional Verification
Beschreibung
Kontakt
marion@cadence.com