This document summarizes a PhD student's presentation on their research into taming deep software variability. The key points are:
1. The PhD aims to identify new external factors that influence software performance, measure their effects, and reuse performance models across workloads.
2. Current work is analyzing input sensitivity in video compression software, and grouping inputs by similar performance profiles.
3. Ideas discussed include specializing software for specific workloads using feature importance analysis to remove unnecessary code.
SPLC 2021 - The Interplay of Compile-time and Run-time Options for Performan...Luc Lesoil
Many software projects are configurable through compile-time options (e.g. using ./configure) and also through run-time options (e.g. command-line parameters, fed to the software at the execution).
Several works have studied how to predict the effect of run-time options on performance.
However it is unclear how these prediction models generalize when the software is built with different values of compile-time options.
For instance, is the best run-time configuration always the best w.r.t. the chosen compilation options?
In this paper, we investigate the effect of compile-time options on the performance distributions of 5 software systems.
We prove there can exist an interplay between the compile-time and the execution levels, by exhibiting a case where different compilation options significantly alter the performance distributions of a software system.
VaMoS 2021 - Deep Software Variability: Towards Handling Cross-Layer Configur...Luc Lesoil
Configuring software is a powerful mean to reach functional and performance goals of a system. However, many layers (hardware, operating system, input data, etc), themselves subject to variability, can alter performances of software configurations. For instance, configurations' options of the x264 video encoder may have very different effects on x264's encoding time when used with different input videos, depending on the hardware on which it is executed. In this vision paper, we coin the term deep software variability to refer to the interaction of all external layers modifying the behavior or non-functional properties of a software. Deep software variability challenges practitioners and researchers: the combinatorial explosion of possible executing environments complicates the understanding, the configuration, the maintenance, the debug, and the test of configurable systems. There are also opportunities: harnessing all variability layers (and not only the software layer) can lead to more efficient systems and configuration knowledge that truly generalizes to any usage and context.
VaMoS 2022 - Transfer Learning across Distinct Software SystemsLuc Lesoil
Many research studies predict the performance of configurable software using machine learning techniques, thus requiring large amounts of data. Transfer learning aims to reduce the amount of data needed to train these models and has been successfully applied on different executing environments (hardware) or software versions. In this paper we investigate for the first time the idea of applying transfer learning between distinct configurable systems. We design a study involving two video encoders (namely x264 and x265) coming from different code bases. Our results are encouraging since transfer learning outperforms traditional learning for two performance properties (out of three). We discuss the open challenges to overcome for a more general application.
Transfer Learning for Performance Analysis of Configurable Systems:A Causal ...Pooyan Jamshidi
Modern systems (e.g., deep neural networks, big data analytics, and compilers) are highly configurable, which means they expose different performance behavior under different configurations. The fundamental challenge is that one cannot simply measure all configurations due to the sheer size of the configuration space. Transfer learning has been used to reduce the measurement efforts by transferring knowledge about performance behavior of systems across environments. Previously, research has shown that statistical models are indeed transferable across environments. In this work, we investigate identifiability and transportability of causal effects and statistical relations in highly-configurable systems. Our causal analysis agrees with previous exploratory analysis~\cite{Jamshidi17} and confirms that the causal effects of configuration options can be carried over across environments with high confidence. We expect that the ability to carry over causal relations will enable effective performance analysis of highly-configurable systems.
Escape the Walls of PaaS: Unlock the Power & Flexibility of DigitalOcean App ...DigitalOcean
Watch this Tech Talk: https://do.co/video_pdougherty
With DigitalOcean App Platform, you get out-of-the-box support for several programming languages and application frameworks. For those languages and frameworks that DigitalOcean doesn’t currently support, learn how you can utilize the Dockerfile mechanism and still benefit from a fully managed PaaS experience.
About the Presenter
Phil Dougherty is a Senior Product Manager at DigitalOcean focused on Kubernetes, container registry, and PaaS. With over 15 years of professional experience in data centers, networking, security, and automation, he has seen the evolution of scale out hosting platforms go from homegrown shell scripts on dedicated servers to multi-cloud micro service based architectures running on Kubernetes. In his free time he likes to ride motorcycles both on and off road, travel, and spend time in the great outdoors.
New to DigitalOcean? Get US $100 in credit when you sign up: https://do.co/deploytoday
To learn more about DigitalOcean: https://www.digitalocean.com/
Follow us on Twitter: https://twitter.com/digitalocean
Like us on Facebook: https://www.facebook.com/DigitalOcean
Follow us on Instagram: https://www.instagram.com/thedigitalocean/
We're hiring: http://do.co/careers
OpenCV DNN moduleとOur methodのruntimeを比較したスライドで、13th Annual International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services(MOBIQUITOUS)(http://mobiquitous.org/2016/show/home) のworkshopで発表したスライドの一部になっています。画像認識部分の詳細は省略しました。
SPLC 2021 - The Interplay of Compile-time and Run-time Options for Performan...Luc Lesoil
Many software projects are configurable through compile-time options (e.g. using ./configure) and also through run-time options (e.g. command-line parameters, fed to the software at the execution).
Several works have studied how to predict the effect of run-time options on performance.
However it is unclear how these prediction models generalize when the software is built with different values of compile-time options.
For instance, is the best run-time configuration always the best w.r.t. the chosen compilation options?
In this paper, we investigate the effect of compile-time options on the performance distributions of 5 software systems.
We prove there can exist an interplay between the compile-time and the execution levels, by exhibiting a case where different compilation options significantly alter the performance distributions of a software system.
VaMoS 2021 - Deep Software Variability: Towards Handling Cross-Layer Configur...Luc Lesoil
Configuring software is a powerful mean to reach functional and performance goals of a system. However, many layers (hardware, operating system, input data, etc), themselves subject to variability, can alter performances of software configurations. For instance, configurations' options of the x264 video encoder may have very different effects on x264's encoding time when used with different input videos, depending on the hardware on which it is executed. In this vision paper, we coin the term deep software variability to refer to the interaction of all external layers modifying the behavior or non-functional properties of a software. Deep software variability challenges practitioners and researchers: the combinatorial explosion of possible executing environments complicates the understanding, the configuration, the maintenance, the debug, and the test of configurable systems. There are also opportunities: harnessing all variability layers (and not only the software layer) can lead to more efficient systems and configuration knowledge that truly generalizes to any usage and context.
VaMoS 2022 - Transfer Learning across Distinct Software SystemsLuc Lesoil
Many research studies predict the performance of configurable software using machine learning techniques, thus requiring large amounts of data. Transfer learning aims to reduce the amount of data needed to train these models and has been successfully applied on different executing environments (hardware) or software versions. In this paper we investigate for the first time the idea of applying transfer learning between distinct configurable systems. We design a study involving two video encoders (namely x264 and x265) coming from different code bases. Our results are encouraging since transfer learning outperforms traditional learning for two performance properties (out of three). We discuss the open challenges to overcome for a more general application.
Transfer Learning for Performance Analysis of Configurable Systems:A Causal ...Pooyan Jamshidi
Modern systems (e.g., deep neural networks, big data analytics, and compilers) are highly configurable, which means they expose different performance behavior under different configurations. The fundamental challenge is that one cannot simply measure all configurations due to the sheer size of the configuration space. Transfer learning has been used to reduce the measurement efforts by transferring knowledge about performance behavior of systems across environments. Previously, research has shown that statistical models are indeed transferable across environments. In this work, we investigate identifiability and transportability of causal effects and statistical relations in highly-configurable systems. Our causal analysis agrees with previous exploratory analysis~\cite{Jamshidi17} and confirms that the causal effects of configuration options can be carried over across environments with high confidence. We expect that the ability to carry over causal relations will enable effective performance analysis of highly-configurable systems.
Escape the Walls of PaaS: Unlock the Power & Flexibility of DigitalOcean App ...DigitalOcean
Watch this Tech Talk: https://do.co/video_pdougherty
With DigitalOcean App Platform, you get out-of-the-box support for several programming languages and application frameworks. For those languages and frameworks that DigitalOcean doesn’t currently support, learn how you can utilize the Dockerfile mechanism and still benefit from a fully managed PaaS experience.
About the Presenter
Phil Dougherty is a Senior Product Manager at DigitalOcean focused on Kubernetes, container registry, and PaaS. With over 15 years of professional experience in data centers, networking, security, and automation, he has seen the evolution of scale out hosting platforms go from homegrown shell scripts on dedicated servers to multi-cloud micro service based architectures running on Kubernetes. In his free time he likes to ride motorcycles both on and off road, travel, and spend time in the great outdoors.
New to DigitalOcean? Get US $100 in credit when you sign up: https://do.co/deploytoday
To learn more about DigitalOcean: https://www.digitalocean.com/
Follow us on Twitter: https://twitter.com/digitalocean
Like us on Facebook: https://www.facebook.com/DigitalOcean
Follow us on Instagram: https://www.instagram.com/thedigitalocean/
We're hiring: http://do.co/careers
OpenCV DNN moduleとOur methodのruntimeを比較したスライドで、13th Annual International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services(MOBIQUITOUS)(http://mobiquitous.org/2016/show/home) のworkshopで発表したスライドの一部になっています。画像認識部分の詳細は省略しました。
Gain a deeper understanding of how to debug and profile your content running with IL2CPP. In depth examples demonstrate how to diagnose problems and improve performance.
Koichi Hirai, Fujitsu
Post-K use Arm based super computer. But there are not too many Arm based servers for HPC.
Therefore we think to need to build Arm HPC Ecosystem until Post-K release.
In this presentation, we describe our collaboration efforts to build the Arm HPC Ecosystem.
Tutorial on Point Cloud Compression and standardisationRufael Mekuria
Tutorial on Point Cloud Compression and standardisation given at IEEE VCIP 2017 in december. I provide the techniques for point cloud compression and the designed quality metrics and codecs in my PhD at CWI. I detail the standardisation activity on point cloud compression that I started in 2014 and that started in 2017 involving all mobile device makers like Apple, Huawei, Sony, Samsung and Nokia.
In 2014, users simply expect more from web apps, developers expect less complexity.
This presentation explains, why Meteor is the next generation platform that delievers a better user experience with less development effort and shows the three main traits that help evolve programming from the dinosaur stage to the modern web.
HC-4012, Complex Network Clustering Using GPU-based Parallel Non-negative Mat...AMD Developer Central
Presentation HC-4012, Complex Network Clustering Using GPU-based Parallel Non-negative Matrix Factorization, by Huming Zhu at the AMD Developer Summit (APU13) November 11-13, 2013.
Recorded video here:
http://on-demand.gputechconf.com/siggraph/2017/video/sig1757-tristan-lorach-vkFX-effective-approach-for-vulkan-api.html
Vulkan is a complex low-level API, full of structures and dedicated objects. Using it may be tedious and often leads to complicated source code. We propose here a way to define and use Vulkan components in a convenient and readable way. Then we will show how this infrastructure allows to introduce and use higher concepts, such as Techniques, Passes; and even how to instantiate resources, render-targets right from within the effect, making it self-sufficient and consistent as a general description. The overall purpose of this open-source project is to improve and enhance the use of Vulkan API, while keeping its strength and flexibility. This project can run in two different ways: either as a compiler generating C++ code for you; or at runtime, to load effects and use them right away.
vkFx comes from a former project called nvFx, presented few years ago. While nvFx was intended to be Generic (OpenGL & D3D compliant), vkFx is Vulkan-specific: so the project is thin and doesn’t break important paradigms that Vulkan requires to stay powerful.
Presentation & discussion around low-level graphics APIs. This was a quickly made presentation that I put together for a discussion with Intel and fellow ISVs, thought it could be worth sharing
"Industrial Internet IoT bootcamp" meetup, 11-5-2015 hosted by GE Digital at HackerDojo. Discussing topics ranging from IoT architecture to connectivity and protocols, cyber security, data science and industrial UX design.
Gain a deeper understanding of how to debug and profile your content running with IL2CPP. In depth examples demonstrate how to diagnose problems and improve performance.
Koichi Hirai, Fujitsu
Post-K use Arm based super computer. But there are not too many Arm based servers for HPC.
Therefore we think to need to build Arm HPC Ecosystem until Post-K release.
In this presentation, we describe our collaboration efforts to build the Arm HPC Ecosystem.
Tutorial on Point Cloud Compression and standardisationRufael Mekuria
Tutorial on Point Cloud Compression and standardisation given at IEEE VCIP 2017 in december. I provide the techniques for point cloud compression and the designed quality metrics and codecs in my PhD at CWI. I detail the standardisation activity on point cloud compression that I started in 2014 and that started in 2017 involving all mobile device makers like Apple, Huawei, Sony, Samsung and Nokia.
In 2014, users simply expect more from web apps, developers expect less complexity.
This presentation explains, why Meteor is the next generation platform that delievers a better user experience with less development effort and shows the three main traits that help evolve programming from the dinosaur stage to the modern web.
HC-4012, Complex Network Clustering Using GPU-based Parallel Non-negative Mat...AMD Developer Central
Presentation HC-4012, Complex Network Clustering Using GPU-based Parallel Non-negative Matrix Factorization, by Huming Zhu at the AMD Developer Summit (APU13) November 11-13, 2013.
Recorded video here:
http://on-demand.gputechconf.com/siggraph/2017/video/sig1757-tristan-lorach-vkFX-effective-approach-for-vulkan-api.html
Vulkan is a complex low-level API, full of structures and dedicated objects. Using it may be tedious and often leads to complicated source code. We propose here a way to define and use Vulkan components in a convenient and readable way. Then we will show how this infrastructure allows to introduce and use higher concepts, such as Techniques, Passes; and even how to instantiate resources, render-targets right from within the effect, making it self-sufficient and consistent as a general description. The overall purpose of this open-source project is to improve and enhance the use of Vulkan API, while keeping its strength and flexibility. This project can run in two different ways: either as a compiler generating C++ code for you; or at runtime, to load effects and use them right away.
vkFx comes from a former project called nvFx, presented few years ago. While nvFx was intended to be Generic (OpenGL & D3D compliant), vkFx is Vulkan-specific: so the project is thin and doesn’t break important paradigms that Vulkan requires to stay powerful.
Presentation & discussion around low-level graphics APIs. This was a quickly made presentation that I put together for a discussion with Intel and fellow ISVs, thought it could be worth sharing
"Industrial Internet IoT bootcamp" meetup, 11-5-2015 hosted by GE Digital at HackerDojo. Discussing topics ranging from IoT architecture to connectivity and protocols, cyber security, data science and industrial UX design.
The Evolution of Agile - Continuous Delivery - Extending Agile out to Product...Burns Sheehan
Burns Sheehan held a highly successful Agile event, "The Evolution of Agile" on Januray 25th 2012. View the presentation given by on of the speakers, Ifor Evans "The Evolution of Agile - Continuous Delivery - Extending Agile out to Production".
In our tests, we found that the HP Z8 tower with Intel Xeon Gold 6226R processors completed three sample media and entertainment tasks in up to 44 percent less time than the Apple Mac Pro with Intel Xeon W-3275M processor, while adding only 11 percent to the purchase price.
Cloud Native Debugging in Production - Dig Deep into your agentsShai Almog
Talk given at HashiTalks 2022 by Shai Almog:
Learn how continuous observability helps us go beyond the limits of AMS, Logs and other observability tools. Solve real world problems at scale in production in polyglot highly distributed environments such as Nomad, K8S etc. with this free solution.
Android and OSGi Can They Work Together - BJ Hargrave & Neil Bartlettmfrancis
OSGi DevCon 2008
"Android is so hot right now!" But what about OSGi? Google's recently announced Android mobile phone platform has everyone all abuzz. It has a VM for applications but it is not a "proper" Java VM and does not have a standard JRE. What does this mean for running the OSGi Service Platform along with bundles on Android? This talk will explore the OSGi on Android topic and give feedback on the speaker's efforts to get OSGi implementations up and running on the Android SDK.
Cloud Based Video Production and EditingPaul Richards
As the, Chief Streaming Officer, here at PTZOptics I get to live stream and play with technology all the time and it has become a dream come true! The industry is chock-full of interesting people and the technology is moving so quickly there is always something new to work on. One of the most rewarding parts of my job is fielding questions from the comments on our YouTube videos.
I recently received a question about cloud based video production. It turns out we have three live interviews on the horizon dedicated to the topic:
-October 21st with NewTek (Hopefully CEO Andrew Cross but no promises :)
-October 28th with Jon Landman of Teradeck (Tentative)
-November 11th with Mark Gilbert CTO of Gallery SIENNA
-December 9th with Philippe Laurent CEO of GoEasyLive.
The Question from Donnie Campbell was: “I understand that there is device specific software to convert video to RTMP (i.e. VMIX, Wirecast, Wirecast go) but is there a cloud based option where I could stream regular video to a cloud based server to do this conversion?”
Traditionally, video production has always been handled on-site, compressed and then streamed. I would bet that 99% of all live video production is still done this way, primarily because of bandwidth restrictions and costs. The major breakthrough announced at NAB from NewTek this year, allows for ultra low latency IP video streaming over a LAN (Local Area Network). The technology NewTek has named “NDI” (Network Device Interface) was released in April of 2016, and is already in the hands of over 1 million video production users (source #1). Watch our live recording about “NewTek NDI Playbook” to learn more about how this technology is being integrated in almost every major market vertical!
While streaming video on the LAN is good, ideally we want to stream anywhere which is where Mark Gilbert from Gallery SIENNA says he can help us. Gilbert says “We are soon to launch our revolutionary NDI.Cloud global IP video service and I wondered if there was any common interest with PTZOptics.” Our team obviously responded saying that if NDI.Cloud allows NDI equipped facilities to seamless integrate with other NDI facilities over wide area networks and the public internet we would definitely be interested! Before you get to excited though Gilbert explained,”We are currently in a closed beta, and we would love to share more… Yesterday we demonstrated a low latency live NDI stream over NDI.Cloud from Mumbai to NewYork (12,500KM) (Source #2).
This got me thinking… If the entire video conferencing industry moved to the cloud why couldn’t video production? The cloud offers a lot of benefits to users, the biggest being low initial investment costs. The best cloud based services make life simpler for end users with a low monthly payment and a “wow this just works” style of delivery. In the video conferencing industry SaaS has been crushing the traditional pay-up-front hardware solutions year after year.
Droidcon 2011: Gingerbread and honeycomb, Markus Junginger, GreenrobotDroidcon Berlin
Gingerbread and Honeycomb
Markus Junginger, greenrobots
Google is developing Android rapidly: Since the release of the Android 1.0 SDK two and a half years ago, Honeycomb is the 9th (!) release of the SDK. Having catched up with its competition in previous releases, Android begins to innovate with new APIs like Near-Field-Communication (NFC). This session keeps developers up-to-date with the new APIs introduced in Android 2.3 Gingerbread and Android 3.0 Honeycomb. Developers will learn how to use state-of-the-art features while maintaining compatibility with devices running older versions of the OS.
Besides NFC, performance is probably the most important advancement in Gingerbread: Android 2.3 got a new parallel garbage collection, an improved JIT compiler and lots of new NDK features for high performance native apps. Also, the SIP API may trigger a new breed of IP telephony apps.
Honeycomb is perceived as the first “tablet version” of Android. One of the most important features are Activity fragments, which become the new building blocks for apps that target both smartphone and tablet screens. Nevertheless, tablets are just one aspect to Android 3.0. For example, developers can now speed up the UI dramatically by activating hardware accelerated rendering. The GPU is also the central part of the new animation framework and the Renderscript engine allowing 3D content and high performance shaders. Together with multicore CPU support, Honeycomb sets the stage for next-generation apps that exploit the desktop-like processing power.
The new APIs in 2.3 and 3.0 are a plentiful resource for developers to make their Android apps unique. This is the session you need to get started!
Hardening Your CI/CD Pipelines with GitOps and Continuous SecurityWeaveworks
Join us for a webinar on how to secure your CI/CD pipeline for Kubernetes with GitOps best practices and continuous runtime protection. As modern developers and DevOps teams are embarking on a quest for speed and reliability through automated CI/CD pipelines for Kubernetes, enterprises still need to ensure security and regulatory compliance.
Together with Deepfence, the Weaveworks team will explain and demonstrate how GitOps continuous delivery pipelines, combined with continuous security observability, improves the overall security of your development workflow - from Git to production.
In this webinar we will demonstrate:
Deepfence container scanning
Git-to-Kubernetes using FluxCD
Deepfence continuous runtime security
Slides for talk given at IWMW 1999 held at Goldsmiths College on 7-9 September 1999.
See http://www.ukoln.ac.uk/web-focus/events/workshops/webmaster-sep1999/materials/multimedia/
Continuous Integration to Shift Left Testing Across the Enterprise StackDevOps.com
With the move to agile DevOps, automated testing is a critical function to ensure high quality in continuous deployments.
In this session, learn how to start testing earlier and often to ensure quality in your codebase. Join Architect Suman Gopinath and Offering Manager Korinne Alpers to talk about shifting-left in the development cycle, starting with unit testing as a key aspect of continuous integration. You'll view a demo of the latest zUnit unit testing tooling for CICS Db2 applications, as well as hear best practices and tales from the testing trenches.
This presentation explores a brief idea about the structural and functional attributes of nucleotides, the structure and function of genetic materials along with the impact of UV rays and pH upon them.
The ability to recreate computational results with minimal effort and actionable metrics provides a solid foundation for scientific research and software development. When people can replicate an analysis at the touch of a button using open-source software, open data, and methods to assess and compare proposals, it significantly eases verification of results, engagement with a diverse range of contributors, and progress. However, we have yet to fully achieve this; there are still many sociotechnical frictions.
Inspired by David Donoho's vision, this talk aims to revisit the three crucial pillars of frictionless reproducibility (data sharing, code sharing, and competitive challenges) with the perspective of deep software variability.
Our observation is that multiple layers — hardware, operating systems, third-party libraries, software versions, input data, compile-time options, and parameters — are subject to variability that exacerbates frictions but is also essential for achieving robust, generalizable results and fostering innovation. I will first review the literature, providing evidence of how the complex variability interactions across these layers affect qualitative and quantitative software properties, thereby complicating the reproduction and replication of scientific studies in various fields.
I will then present some software engineering and AI techniques that can support the strategic exploration of variability spaces. These include the use of abstractions and models (e.g., feature models), sampling strategies (e.g., uniform, random), cost-effective measurements (e.g., incremental build of software configurations), and dimensionality reduction methods (e.g., transfer learning, feature selection, software debloating).
I will finally argue that deep variability is both the problem and solution of frictionless reproducibility, calling the software science community to develop new methods and tools to manage variability and foster reproducibility in software systems.
Exposé invité Journées Nationales du GDR GPL 2024
Professional air quality monitoring systems provide immediate, on-site data for analysis, compliance, and decision-making.
Monitor common gases, weather parameters, particulates.
Seminar of U.V. Spectroscopy by SAMIR PANDASAMIR PANDA
Spectroscopy is a branch of science dealing the study of interaction of electromagnetic radiation with matter.
Ultraviolet-visible spectroscopy refers to absorption spectroscopy or reflect spectroscopy in the UV-VIS spectral region.
Ultraviolet-visible spectroscopy is an analytical method that can measure the amount of light received by the analyte.
Slide 1: Title Slide
Extrachromosomal Inheritance
Slide 2: Introduction to Extrachromosomal Inheritance
Definition: Extrachromosomal inheritance refers to the transmission of genetic material that is not found within the nucleus.
Key Components: Involves genes located in mitochondria, chloroplasts, and plasmids.
Slide 3: Mitochondrial Inheritance
Mitochondria: Organelles responsible for energy production.
Mitochondrial DNA (mtDNA): Circular DNA molecule found in mitochondria.
Inheritance Pattern: Maternally inherited, meaning it is passed from mothers to all their offspring.
Diseases: Examples include Leber’s hereditary optic neuropathy (LHON) and mitochondrial myopathy.
Slide 4: Chloroplast Inheritance
Chloroplasts: Organelles responsible for photosynthesis in plants.
Chloroplast DNA (cpDNA): Circular DNA molecule found in chloroplasts.
Inheritance Pattern: Often maternally inherited in most plants, but can vary in some species.
Examples: Variegation in plants, where leaf color patterns are determined by chloroplast DNA.
Slide 5: Plasmid Inheritance
Plasmids: Small, circular DNA molecules found in bacteria and some eukaryotes.
Features: Can carry antibiotic resistance genes and can be transferred between cells through processes like conjugation.
Significance: Important in biotechnology for gene cloning and genetic engineering.
Slide 6: Mechanisms of Extrachromosomal Inheritance
Non-Mendelian Patterns: Do not follow Mendel’s laws of inheritance.
Cytoplasmic Segregation: During cell division, organelles like mitochondria and chloroplasts are randomly distributed to daughter cells.
Heteroplasmy: Presence of more than one type of organellar genome within a cell, leading to variation in expression.
Slide 7: Examples of Extrachromosomal Inheritance
Four O’clock Plant (Mirabilis jalapa): Shows variegated leaves due to different cpDNA in leaf cells.
Petite Mutants in Yeast: Result from mutations in mitochondrial DNA affecting respiration.
Slide 8: Importance of Extrachromosomal Inheritance
Evolution: Provides insight into the evolution of eukaryotic cells.
Medicine: Understanding mitochondrial inheritance helps in diagnosing and treating mitochondrial diseases.
Agriculture: Chloroplast inheritance can be used in plant breeding and genetic modification.
Slide 9: Recent Research and Advances
Gene Editing: Techniques like CRISPR-Cas9 are being used to edit mitochondrial and chloroplast DNA.
Therapies: Development of mitochondrial replacement therapy (MRT) for preventing mitochondrial diseases.
Slide 10: Conclusion
Summary: Extrachromosomal inheritance involves the transmission of genetic material outside the nucleus and plays a crucial role in genetics, medicine, and biotechnology.
Future Directions: Continued research and technological advancements hold promise for new treatments and applications.
Slide 11: Questions and Discussion
Invite Audience: Open the floor for any questions or further discussion on the topic.
29. Research questions
Identify new variability f
actors
Which variability f
actors
are the most influential?
Can we reuse perf
ormance models
trained on another workload?
31. On a concrete example ?
Software
0.152.2854
--no-cabac –-ref 1
–-no-mbtree
32. On a concrete example ?
Software Input Data
0.152.2854
--no-cabac –-ref 1
–-no-mbtree
High complexity
Action scene
33. On a concrete example ?
Software Input Data
0.152.2854
7.5.0
--no-cabac –-ref 1
–-no-mbtree
–-disable-asm
-On
High complexity
Action scene
Compiler
34. On a concrete example ?
Software Input Data
0.152.2854
7.5.0
--no-cabac –-ref 1
–-no-mbtree
–-disable-asm
-On
High complexity
Action scene
Compiler Operating
System
18.04
LTS
GENERIC_CMOS_UPDATE
BH1750
35. On a concrete example ?
Software Input Data
0.152.2854
7.5.0
--no-cabac –-ref 1
–-no-mbtree
–-disable-asm
-On
High complexity
Action scene
Compiler
Hardware
Operating
System
18.04
LTS
GENERIC_CMOS_UPDATE
BH1750
Dell latitude 7400
36. On a concrete example ?
Software Input Data
0.152.2854
7.5.0
--no-cabac –-ref 1
–-no-mbtree
–-disable-asm
-On
High complexity
Action scene
Compiler
Hardware
Operating
System
18.04
LTS
What if ?
GCC 7.5.0 GCC 7.3.0
→ GCC 7.3.0
Ubuntu Fedora
→ GCC 7.3.0
We enable mbtree
GENERIC_CMOS_UPDATE
BH1750
Dell latitude 7400
37. On a concrete example ?
Software Input Data
0.152.2854
7.5.0
--no-cabac –-ref 1
–-no-mbtree
–-disable-asm
-On
High complexity
Action scene
Compiler
Hardware
Operating
System
18.04
LTS
What if ?
GCC 7.5.0 GCC 7.3.0
→ GCC 7.3.0
Ubuntu Fedora
→ GCC 7.3.0
We enable mbtree
GENERIC_CMOS_UPDATE
BH1750
Dell latitude 7400
Here we go !
39. 1. PhD subject - T
o sum up ?
Identify new external variability f
actors
40. 1. PhD subject - T
o sum up ?
Identify new external variability f
actors
Measure their eff
ects on software
41. 1. PhD subject - T
o sum up ?
Identify new external variability f
actors
Measure their eff
ects on software
Reuse perf
ormance models across workloads
50. Motivation : why video compression?
x264 commits : devs are aware of input sensitivity
51. Motivation : why video compression?
x264 commits : devs are aware of input sensitivity
x264 f
eatures : devs created a f
eature f
or special input videos
57. Dataset
[1]
Wang, Y., Inguva, S., & Adsumilli, B. (2019 1, September). Youtube ugc dataset for video compression research.
In 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP) (pp. 1-5). IEEE.
Youtube UGC Dataset [1]
58. Dataset
[1]
Wang, Y., Inguva, S., & Adsumilli, B. (2019 1, September). Youtube ugc dataset for video compression research.
In 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP) (pp. 1-5). IEEE.
1300+ short videos
Youtube UGC Dataset [1]
59. Dataset
[1]
Wang, Y., Inguva, S., & Adsumilli, B. (2019 1, September). Youtube ugc dataset for video compression research.
In 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP) (pp. 1-5). IEEE.
1300+ short videos
Diff
erent resolutions (360p 2160p)
→ GCC 7.3.0
Youtube UGC Dataset [1]
60. Dataset
[1]
Wang, Y., Inguva, S., & Adsumilli, B. (2019 1, September). Youtube ugc dataset for video compression research.
In 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP) (pp. 1-5). IEEE.
1300+ short videos
Diff
erent resolutions (360p 2160p)
→ GCC 7.3.0
Diff
erent categories
Youtube UGC Dataset [1]
61. Dataset
[1]
Wang, Y., Inguva, S., & Adsumilli, B. (2019 1, September). Youtube ugc dataset for video compression research.
In 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP) (pp. 1-5). IEEE.
1300+ short videos
Diff
erent resolutions (360p 2160p)
→ GCC 7.3.0
Diff
erent categories
Video properties
Spatial/Temporal/Chunk complexity
Quality score
Youtube UGC Dataset [1]
62. Dataset
[1]
Wang, Y., Inguva, S., & Adsumilli, B. (2019 1, September). Youtube ugc dataset for video compression research.
In 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP) (pp. 1-5). IEEE.
https://media.withyoutube.com/
1300+ short videos
Diff
erent resolutions (360p 2160p)
→ GCC 7.3.0
Diff
erent categories
Video properties
Spatial/Temporal/Chunk complexity
Quality score
Youtube UGC Dataset [1]
70. Results (1)
Perf
ormances change with input videos.
Feature positive
→ GCC 7.3.0 & negative eff
ects depending on inputs
Perf
ormance correlations can be low or negative between inputs
71. Results (1)
Perf
ormances change with input videos.
Feature positive
→ GCC 7.3.0 & negative eff
ects depending on inputs
Perf
ormance correlations can be low or negative between inputs
Group together videos having the same “encoding profile”
74. Results (2)
Include input properties in the model
Specialize x264 f
or a new video
without measuring any new configuration
75. Results (2)
Include input properties in the model
Specialize x264 f
or a new video
without measuring any new configuration
Reduce the variability of the inputs
78. 2. Current work - T
o sum up ?
Input sensitivity matters
Group inputs by perf
ormance
& find discriminant (cheap) properties
79. 2. Current work - T
o sum up ?
Input sensitivity matters
Group inputs by perf
ormance
& find discriminant (cheap) properties
Include input properties in the model
82. 3. Ideas & Discussion
Specialize the code f
or a workload
83. 3. Ideas & Discussion
Specialize the code f
or a workload
Use f
eature importances to remove useless parts of code
84. 3. Ideas & Discussion
Specialize the code f
or a workload
Use f
eature importances to remove useless parts of code
branch selection choose the best branch
→ GCC 7.3.0