https://dasya.itu.dk/supervisor/p%C4%B1nar-tozun/ Recent content in Pınar Tözün on DASYA Hugo -- gohugo.io en-us © DASYA, IT University of Copenhagen Wed, 05 Aug 2026 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/current/pito-llm-agents/ Wed, 05 Aug 2026 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/current/pito-llm-agents/ This project would investigate the storage access patterns of LLM agents using open-source state-of-the-art inference frameworks such as vLLM and SGLang and workload traces such as the ones released by Mooncake, Alibaba, Swiss AI Initiative, etc. Depending on the size and duration of the project, it can also propose or implement optimizations for the storage access. This project would be suitable as a standalone project, a research project with an MSc thesis followup, or BSc thesis. https://dasya.itu.dk/for-students/proposals/current/pito-dgxspark/ Wed, 05 Aug 2026 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/current/pito-dgxspark/ This project investigates how running multiple deep learning tasks simultaneously (collocation) affects performance on resource-constrained edge devices, specifically the NVIDIA DGX Spark. Students will deploy and benchmark various model in isolated vs. different collocated scenarios, measure metrics such as GPU utilization, memory usage, training time, and analyze the trade-offs between throughput, fairness, and system efficiency. This project would be suitable as a BSc or MSc thesis. The workload can be adjusted based on the thesis and group size. https://dasya.itu.dk/for-students/proposals/current/pito-fdpsim-duckdb/ Wed, 05 Aug 2026 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/current/pito-fdpsim-duckdb/ Traditionally solid-state drives (SSDs) does not give the users the ability to control the data placement on the SSD. This often leads to suboptimal performance and lowers SSD lifetime, since SSDs internally don’t allow in-place updates. The updated disk pages are written elsewhere and the old versions have to be garbage collected. This poses problems if data with different lifetimes and update frequencies often gets written in the same region. https://dasya.itu.dk/for-students/proposals/current/pito-gpu-db-perf/ Wed, 05 Aug 2026 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/current/pito-gpu-db-perf/ This rise of hardware accelerators to meet the demand of AI workloads has also led to a variety of novel methods to leverage GPUs for traditional data analytics workloads. A key concern for any data-intensive system using GPUs is the efficiency of moving the data to the accelerator. In this project, we will investigate the performance of GPU databases and how they are impacted by the different kinds of data movement (CPU memory to GPU memory, SSD to GPU, etc. https://dasya.itu.dk/for-students/proposals/current/pito-llm-kvcache/ Wed, 05 Aug 2026 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/current/pito-llm-kvcache/ This project would investigate key-value(KV)-cache offloading in large language model (LLM) inference engines, with particular emphasis on data placement and storage efficiency. First, the project would use an emulator such as FEMU to characterize workload access patterns, including hot-key distributions, write intensity, and write amplification factor (WAF). Then, we would evaluate the potential of Flexible Data Placement (FDP) for improving data placement decisions on SSDs for KV-cache accesses. The project will use open source state-of-the-art KV-cache types such as LMCache or the ones implemented by the inference frameworks such as vLLM and SGLang. https://dasya.itu.dk/for-students/proposals/archive/pito-nas/ Tue, 30 Sep 2025 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-nas/ Designing neural networks that are both accurate and efficient has become an urgent challenge as the cost of deploying machine learning systems continues to grow. Traditional Neural Architecture Search (NAS) methods usually optimize for accuracy under constraints such as FLOPs, model size, or latency. However, in practice the lifecycle cost of a model is not only determined by training, but also by inference. While training is a one-off expense, inference is repeated continuously once a model is deployed, and depending on the number of queries served, it can become the dominant contributor to energy use and cost. https://dasya.itu.dk/for-students/proposals/archive/pito-ml-orion/ Thu, 24 Jul 2025 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-ml-orion/ This project investigates how running multiple deep learning training tasks simultaneously (collocation) affects performance on resource-constrained edge devices, specifically the NVIDIA Jetson Orion Nano. Students will deploy and benchmark various models (e.g., CNNs, Transformers) in isolated vs. different collocated scenarios, measure metrics such as GPU utilization, memory usage, training time, and analyze the trade-offs between throughput, fairness, and system efficiency. This project would be suitable as a BSc or MSc thesis. https://dasya.itu.dk/for-students/proposals/archive/pito-xnvme-duckdb/ Tue, 15 Jul 2025 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-xnvme-duckdb/ A recent MSc thesis project at ITU integrated xNVMe to DuckDB. DuckDB, like many popular database systems, rely on a syncronous IO backend and the POSIX filesystem interfaces for its ease of use. xNVMe, in contrast, allows a unified interface for alternative and more performant IO backends such as io-uring and spdk. Thus, integration of xNVMe into DuckDB offers interesting avenues for data analytics workloads run on DuckDB. The existing integration of xNVMe to DuckDB is preliminary. https://dasya.itu.dk/for-students/proposals/archive/pito-edge-benchmarking/ Tue, 15 Jul 2025 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-edge-benchmarking/ The work on running data-intensive applications on very powerful, expensive, and power-hungry server hardware is very popular thanks to the growing size of data centers and high-performance computing (HPC) platforms. However, with the rise of new generation internet of things (IoT) applications, the lower-power and lower-budget hardware devices that specifically target IoT, the edge platforms, embedded devices, etc. have also become quite powerful today offering non-negligible data processing capability. For example, NVIDIA Jetsons and Coral devices allow GPU- and TPU-acceleration of AI applications at the edge and come with hardware resources that can match the resources of a laptop. https://dasya.itu.dk/for-students/proposals/archive/pito-data-attribution/ Tue, 15 Jul 2025 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-data-attribution/ Deep convolutional networks are able to learn representation of images, scoring well in tasks such as image classification and object detection. During model training, these networks have the ability to process different input sizes without requiring changes to their architecture. In this project, we would like to investigate the effects that changing input sizes has on these kinds of models. We want to do this by investigating and using data attribution methods, as these techniques can help explain the effect of input data on the predictions of the model. https://dasya.itu.dk/for-students/proposals/archive/pito-data-selection/ Tue, 15 Jul 2025 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-data-selection/ Today’s foundation models are trained on vast amounts of data. The quality and size of this data has a huge impact on the accuracy of these models. Selecting the right amount and variety of data for a given task, however, is a resource-intensive process. In this project, which is part of a larger collaboration, we would like to expand our investigation of state-of-the-art data selection mechanisms from a hardware requirements and resource-efficiency perspective in addition to their impact on model accuracy. https://dasya.itu.dk/for-students/proposals/archive/pito-radt/ Tue, 15 Jul 2025 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-radt/ Observing how well machine learning systems utilize hardware resources is a crucial preliminary step to improve system performance and reduce hardware waste. To do such observations, one has to collect a lot of monitoring data on hardware behavior through experiments. In our group, we have recently built a framework to aid the management of such monitoring data efficiently, called Resource-Aware Data Systems Tracker. There is a variety of work to be done on this framework to improve it. https://dasya.itu.dk/for-students/proposals/archive/pito-gpu-db/ Tue, 15 Jul 2025 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-gpu-db/ This rise of hardware accelerators to meet the demand of AI workloads has also led to a variety of novel methods to leverage GPUs for traditional data analytics workloads. A key concern for any data-intensive system using GPUs is the efficiency of moving the data to the accelerator. In this project, we will investigate ways to improve data movement to GPUs by focusing on the steps of the data path and performance of different data movement options from the network or SSDs to GPUs such as GPUDirect or BaM [1]. https://dasya.itu.dk/for-students/proposals/archive/pito-tiny-resourcemanagement/ Tue, 15 Jul 2025 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-tiny-resourcemanagement/ Today many data sources are small low-powered and hardware-constrained devices such as mobile phones, wearable or self-driving smart platforms, etc. Edge computing is a broad term that refers to computations performed on such edge devices. It becomes increasingly important to enable techniques that get more value out of data at the edge rather than always sending the data to a remote and more powerful hardware device in the cloud for further data processing and training machine learning models. https://dasya.itu.dk/for-students/proposals/archive/pito-ml-scheduling/ Thu, 05 Jun 2025 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-ml-scheduling/ Workload collocation has been shown as an effective method to reduce the hardware requirements for certain deep learning (DL) training tasks. On the other hand, there hasn’t been many robust open-source implementations of schedulers that incorporate workload collocation on GPUs for DL. BLOX is a framework that aims at standardizing the way we implement deep learning schedulers. In this project, our goal is to investigate ways to integrate a collocation-aware scheduler in this framework. https://dasya.itu.dk/for-students/proposals/archive/pito-ml-checkpointing/ Thu, 05 Jun 2025 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-ml-checkpointing/ Deep learning training can run for hours or days, causing long queue times and poor quality of service (QoS) on shared clusters. Since schedulers can’t accurately predict training durations, they often wait for jobs to finish or time out, worsening the issue. Frameworks like TensorFlow and PyTorch support model checkpointing, but frequent checkpoints can slow training, while infrequent ones reduce effectiveness. Automating checkpointing could improve scheduler decisions and fairness. This project aims to (1) benchmark checkpointing overhead in TensorFlow and PyTorch, (2) identify optimal checkpointing frequencies, and (3) develop an automatic checkpointing module. https://dasya.itu.dk/for-students/proposals/archive/pito-ml-dataset/ Thu, 05 Jun 2025 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-ml-dataset/ This project focuses on extending an existing dataset for predicting GPU memory requirements during deep learning training by incorporating transformer-based models such as BERT, GPT, and their variants. The student will study the architecture of these models and develop training scripts to run them under controlled conditions. During training, key GPU metrics—including memory usage, utilization, and runtime characteristics—will be recorded. These observations will be used to build a richer dataset that links model specifications with their GPU resource needs. https://dasya.itu.dk/for-students/proposals/archive/pito-ml-gpu_utilization/ Thu, 05 Jun 2025 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-ml-gpu_utilization/ GPU offers massive computational power and parallelism through its Streaming Multiprocessors (SMs). Efficient GPU utilization is critical for maximizing performance and optimizing compute resource usage, which is measured using various metrics such as SMACT (SM Activity) and SMOCC (SM Occupancy), and DRAMA (DRAM Active). These metrics provide insight into how effectively the GPU’s SMs and memory are used during deep learning tasks. Currently, monitoring tools provide such metrics during runtime. This project aims to explore the concept of predicting GPU utilization metrics using deep learning models, trained on a large dataset of models executed on NVIDIA A100 40GB GPUs. https://dasya.itu.dk/for-students/proposals/archive/pito-edge-characterization/ Tue, 13 Aug 2024 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-edge-characterization/ The work on running data-intensive applications on very powerful, expensive, and power-hungry server hardware is very popular thanks to the growing size of data centers and high-performance computing (HPC) platforms. However, with the rise of new generation internet of things (IoT) applications, the lower-power and lower-budget hardware devices that specifically target IoT, the edge platforms, embedded devices, etc. have also become quite powerful today offering non-negligible data processing capability. For example, NVIDIA Jetsons and Coral devices allow GPU- and TPU-acceleration of AI applications at the edge and come with hardware resources that can match the resources of a laptop. https://dasya.itu.dk/for-students/proposals/archive/pito-fdp-duckdb/ Mon, 13 May 2024 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-fdp-duckdb/ Traditionally solid-state drives (SSDs) does not give the users the ability to control the data placement on the SSD. This often leads to suboptimal performance and lowers SSD lifetime, since SSDs internally don’t allow in-place updates. The updated disk pages are written elsewhere and the old versions have to be garbage collected. This poses problems if data with different lifetimes and update frequencies often gets written in the same region. https://dasya.itu.dk/for-students/proposals/archive/pito-tiny-modelupdates/ Mon, 13 May 2024 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-tiny-modelupdates/ One of the key challenges with enabling efficient machine learning on resource-constrained devices is keeping the machine learning models deployed on these devices up-to-date without frequent retraining. This requires exploring the impact of different model update mechanisms at the edge. This project would be suitable as a standalone project or BSc or MSc thesis at ITU during Fall 2024. If you are interested in resource-constrained hardware, benchmarking, and machine learning in general, this project would be a great fit for you. https://dasya.itu.dk/for-students/proposals/archive/pito-tiny-modelsizes/ Mon, 13 May 2024 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-tiny-modelsizes/ To enable efficient data processing and machine learning on resource-constrained devices has many challenges. One is fitting the models into the restrictive memory and compute resources of these devices. In this project, first, we would like to explore the landscape of foundational, generative-AI, language, etc. models with respect to their size and compute needs to understand what could be a fit to be deployed at the edge. Then, we would like to characterize the performance of some edge model deployments on a chosen edge device and building on the analysis in the first step. https://dasya.itu.dk/for-students/proposals/archive/pito-radtduckdb/ Thu, 23 Nov 2023 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/pito-radtduckdb/ Observing how well data-intensive systems utilize hardware resources is a crucial preliminary step to improve system performance and reduce hardware waste. To do such observations, one has to collect a lot of monitoring data on hardware behavior through experiments. In our group, we have recently built a framework to aid the management of such monitoring data efficiently, called Resource-Aware Data Systems Tracker. Currently, this framework uses Postgres data management system to keep the experimental data. https://dasya.itu.dk/for-students/proposals/archive/datapreprocessingpipelines/ Mon, 01 Aug 2022 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/datapreprocessingpipelines/ It is common to process data to clean it, filter it, restructure it, get metadata out of it, etc. before feeding the data into a data analysis or machine learning pipeline. There are many tools and libraries out there to aide with this process with different strengths and functionality (DALI, RAPIDS, HoloClean, DAPHNE, DuckDB, etc.). In this project, we would like to analyze pros/cons of some of these tools on a variety of hardware platforms and use cases. https://dasya.itu.dk/for-students/proposals/archive/diskaccesstracing/ Mon, 01 Aug 2022 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/diskaccesstracing/ In the past decade, data management community has focused on main-memory systems or main-memory-optimized systems. This focus has put the commodity memory hierarchy (DRAM and processor caches) into center when it comes to workload characterization studies. Today, with the evolution of persistent storage technologies such as NVRAM (persistent memory solution of Intel) and NVMe SSDs, data systems have access to orders of magnitude faster persistent storage than traditional hard disks. Recently developed data management systems (e. https://dasya.itu.dk/for-students/proposals/archive/profilingfordaphne/ Mon, 01 Aug 2022 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/profilingfordaphne/ DAPHNE is an EU project that aims at building a data system targeting integrated data analysis pipelines across data management and processing, high-performance computing (HPC), and machine learning (ML) training and scoring. The project had its first code release back in March. This project aims at adding a profiling infrastructure for DAPHNE codebase. If you are interested in learning about different profiling tools on CPUs (VTune, perf, etc.) or GPUs (nvidia-smi, dcgm, etc. https://dasya.itu.dk/for-students/proposals/archive/mlcollocation/ Mon, 01 Aug 2022 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/mlcollocation/ State-of-the-art machine learning models are known to be compute- and power-hungry. On the other hand, modern servers come equipped with really powerful CPU-GPU co-processors. Not all machine learning models are able to use all the available hardware resources on such servers. Workload collocation is a mechanism to increase hardware utilization when a single workload is not able to utilize all the resources on its own. While workload collocation has been heavily studied for traditional data-intensive applications such as relational databases or Spark, it has been largely unexplored for machine learning. https://dasya.itu.dk/for-students/proposals/archive/mlforhwutilestimation/ Sun, 01 May 2022 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/mlforhwutilestimation/ Today, there are many compute- and memory-hungry data-intensive workloads from big data analytics applications to deep learning. These workloads increasingly run on shared hardware resources, which requires building hardware resource managers that can both serve the needs of workloads and utilize hardware well. Predicting the resource utilization of applications can aid such resource managers while making scheduling decisions for those applications. In this project, we aim to investigate the effectiveness of different deep learning techniques for predicting hardware resource needs of applications. https://dasya.itu.dk/for-students/proposals/archive/ssdcharacterizationnew/ Tue, 20 Apr 2021 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/ssdcharacterizationnew/ NVMe SSDs are not a uniform class of devices. IO software stack is not uniform either. Understanding the performance characteristics of new-generation SSDs and the impact of the IO stack on their performance is crucial while determining how to design data-intensive systems. In this project, we would like to characterize the performance of a range of NVMe SSDs (e.g., Samsung Z-SSD, Intel Optane, etc.) using different libraries for submitting IOs (e. https://dasya.itu.dk/for-students/proposals/archive/workloadcharacterization/ Tue, 20 Apr 2021 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/workloadcharacterization/ A data science infrastructure orchestrates the execution of widely used machine learning frameworks (e.g., TensorFlow , PyTorch) on a heterogeneous set of processing units (e.g., CPU, GPU, TPU, FPGA) while powering an increasingly diverse and complex range of applications (e.g., fraud detection, healthcare, virtual assistance, automatic driving). Understanding the resource consumption characteristics of different data science workloads is a necessary step before designing effective hardware resource management in any data science infrastructure. https://dasya.itu.dk/for-students/proposals/archive/hashing/ Fri, 21 Aug 2020 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/hashing/ Hash-based authentication is an effective way of protecting passwords in software systems. Hashing obscures the original passwords, such that it cannot be recovered in case of a database breach. However, as demonstrated by our paper titled Hash-Based Authentication Revisited in the Age of High-Performance Computers, the practical security depends on which hashing algorithm is used as well as the complexity of the passwords. The main goal of this project is to do a study on which hashing-algorithms are the standard in current software systems as well as testing the cracking capacity of these hashing-algorithms on high-performance computers and home computers. https://dasya.itu.dk/for-students/proposals/archive/resourcemanager/ Wed, 20 May 2020 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/resourcemanager/ The variety and complexity of data-intensive applications and systems have been increasing drastically the past decade. Tasks from a SQL-based big data analytics request running on Apache Spark can be very different from tasks from deep learning training using TensorFlow framework. Nevertheless, these data-intensive applications increasingly run on shared hardware resources in data centers or high-performance computing (HPC) platforms. These hardware resources are also diverse today ranging from general-purpose CPUs to GPUs to programmable FPGAs. https://dasya.itu.dk/for-students/projects/archive/unitydots/ Wed, 20 May 2020 00:00:00 +0000 https://dasya.itu.dk/for-students/projects/archive/unitydots/ Improvements in modern processor hardware does not automatically enable more complex and higher quality games, animations, and virtual reality applications. A paradigm shift is necessary when it comes to how we develop these applications in order to exploit the resources of modern hardware (i.e., main memory, multicores) effectively. Unity Technologies has recently developed Data-Oriented Technology Stack (DOTS) specifically for this purpose. In this project, we want to benchmark and profile this novel game engine paradigm to measure its scalability on different types of multicore hardware (from servers to mobile platforms). https://dasya.itu.dk/for-students/projects/archive/ssdcharacterization/ Mon, 20 Apr 2020 00:00:00 +0000 https://dasya.itu.dk/for-students/projects/archive/ssdcharacterization/ SSDs are not a uniform class of devices. SSD landscape is quite diverse now with many new-gen much faster / customizable devices being available. Understand their performance characteristics is crucial while determining what their impact on data systems software stack should be. In this project, we would like to characterize the performance of a broad range of such SSDs (e.g., ZNS, Samsung Z-SSD, Samsung KV-SSD, Samsung Smart SSD, Intel Optane, etc. https://dasya.itu.dk/for-students/projects/archive/multitenant/ Sat, 01 Feb 2020 00:00:00 +0000 https://dasya.itu.dk/for-students/projects/archive/multitenant/ Building a task management system for multi-tenant cloud https://dasya.itu.dk/for-students/projects/archive/dpi/ Sat, 01 Feb 2020 00:00:00 +0000 https://dasya.itu.dk/for-students/projects/archive/dpi/ Intel’s oneAPI vs CPP https://dasya.itu.dk/for-students/projects/archive/iothtap/ Sat, 01 Feb 2020 00:00:00 +0000 https://dasya.itu.dk/for-students/projects/archive/iothtap/ How does commonly used time series systems handle an HTAP/IoT use-case? https://dasya.itu.dk/for-students/proposals/archive/efficient-os-level-context-switching-for-thread-migration/ Mon, 16 Dec 2019 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/efficient-os-level-context-switching-for-thread-migration/ Spreading the computation of similar concurrent tasks that have a large instruction footprint over multiple cores via thread migration is shown to improve the instruction cache utilization drastically since it allows instruction re-use across the concurrent tasks. However, thread migrations are costly due to the context switching overhead. To reduce this overhead, recent work mainly proposed techniques at the hardware-level. However, developing techniques at the level of the OS might be more effective in terms of the adoption of such thread migration mechanisms. https://dasya.itu.dk/for-students/proposals/archive/leveraging-heterogeneous-hardware/ Mon, 16 Dec 2019 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/leveraging-heterogeneous-hardware/ The computer architecture community is moving toward commoditization of hardware specialization instead of general purpose CPUs and more agile hardware development instead of years-long production cycles to enable faster, more energy-efficient, and more cost-effective hardware/software co-designs. This will lead to a disruption in the way we design and maintain the emerging data management systems as well. As the heterogeneity of hardware resources increase, it becomes essential for the data management systems to decide on the optimal design options based on the processor types they are running on. https://dasya.itu.dk/for-students/proposals/archive/micro-architectural-analysis-of-systemml/ Mon, 16 Dec 2019 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/micro-architectural-analysis-of-systemml/ Apache SystemML is an open-source platform to run machine learning tasks efficiently thanks to the hardware-conscious query compilation techniques it adopts. It can be run standalone or on top of Apache Spark. It is considered to be state-of-the-art when running machine learning tasks (i.e., in ACM SIGMOD 2017, there were ~5 papers that used SystemML as a comparison point). This project aims at understanding how efficiently SystemML utilizes the resources of commodity server hardware, and how this differs from some other widely used systems used to run machine learning (e. https://dasya.itu.dk/for-students/proposals/archive/what-is-htap/ Mon, 16 Dec 2019 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/what-is-htap/ The popularity of large-scale real-time analytics applications (real-time inventory/pricing, recommendations from mobile apps, fraud detection, risk analysis, IoT, etc.) keeps rising. These applications require distributed data management systems that can handle fast concurrent transactions (OLTP) and analytics on the recent data. Some of them even need running analytical queries (OLAP) as part of transactions. Efficient processing of individual transactional and analytical requests, however, leads to different optimizations and architectural decisions while building a data management system. https://dasya.itu.dk/for-students/proposals/archive/workload-characterization-for-big-data-management/ Mon, 16 Dec 2019 00:00:00 +0000 https://dasya.itu.dk/for-students/proposals/archive/workload-characterization-for-big-data-management/ The Transaction Processing Performance Council (TPC) is a non-profit IT organization founded to define database benchmarks and disseminate objective, verifiable performance data to the industry. TPC has standardized several new benchmarks (e.g., TPCx-HS and TPCx-BB), in recent years. Older popular benchmarks, like TPC-C (representing high-performance transaction processing) and TPC-H (representing traditional analytical processing), are not suitable to explain the behavior of the emerging big data applications (with heavy ingest rates and complex analytical queries involving machine learning) on modern hardware. https://dasya.itu.dk/for-students/projects/archive/speechrecognition/ Sun, 15 Dec 2019 00:00:00 +0000 https://dasya.itu.dk/for-students/projects/archive/speechrecognition/ Investigating the behavior of acoustic model training via deep learning on co-processors of different price groups https://dasya.itu.dk/for-students/projects/archive/htaptpcch/ Sat, 01 Jun 2019 00:00:00 +0000 https://dasya.itu.dk/for-students/projects/archive/htaptpcch/ Investigating what an HTAP benchmark needs https://dasya.itu.dk/for-students/projects/archive/speechrecognitionpre/ Sat, 01 Jun 2019 00:00:00 +0000 https://dasya.itu.dk/for-students/projects/archive/speechrecognitionpre/ How do we implement and efficiently train a centralized deep learning system converting speech to text in a scalable manner?