Dataset

This dataset was created by E4CRYPT3D

Released under CC0: Public Domain

Contents

Techpowerup datasets

Dataset consists of two datasets, cpus and gpus scraped using Python scrapy from https://www.techpowerup.com/.

CPU Dataset

The CPU dataset contains information about various CPU models and their specifications. The dataset includes the following columns:

• Name: The name of the CPU model.
• Codename: The codename used by the manufacturer for the CPU model.
• Cores: The number of cores in the CPU.
• Clock: The base clock speed of the CPU, measured in GHz.
• Socket: The socket type that the CPU is compatible with.
• Process: The manufacturing process used to create the CPU, measured in nanometers.
• L3 Cache: The size of the L3 cache in the CPU, measured in MB.
• TDP: The thermal design power of the CPU, measured in watts.
• Released: The release date of the CPU.

GPU Dataset

The GPU dataset contains information about various GPU models and their specifications. The dataset includes the following columns:

• Product_Name: The name of the GPU model.
• GPU_Chip: The GPU Chip that is used in the GPU Model
• Released: The release date of the GPU.
• Bus: The bus width of the GPU.
• Memory: The memory capacity of the GPU, measured in GB.
• GPU_clock: The base clock speed of the GPU, measured in MHz.
• Memory_clock: The memory clock speed of the GPU, measured in MHz.
• Shaders_TMUs_ROPs: The number of shaders, texture mapping units, and raster operations pipelines in the GPU.

Both of the datasets are useful for comparing the performance and features of different CPU and GPU models. They can be used for a variety of applications such as gaming, content creation, AI, Machine learning, and more. It could be used by researchers to study the evolution of the technology in a specific period of time and make predictions for future advancements. It could also be used by professionals in the tech industry, to make informed decisions when choosing components for a build or a system.

The code for the scraper can be found here

Dataset

This dataset was created by gpulab

Contents

This dataset contains the latest prices and historical lowest prices for various GPU models from Nvidia, AMD, and Intel as of 2024. Sourced from Tom's Hardware, this data is useful for analyzing price trends and studying the cost dynamics of computer hardware.

Context

In early August 2020, Kaggle announced a "floating quota for GPU hours" in Notebooks. Previously, we had 30 GPU hours per week. Those were the dark times. Over the following 2 months, the quotas varied between 36 and a whopping 43 hours. I have been keeping track of the weekly changes, because why not? I will continue to update this amazing dataset. You're welcome.

Content

This dataset documents all weekly GPU quotas since August 8th 2020. This will sound more impressive once more than a few months have passed. Hopefully.

Quotas are being updated and reset every week on midnight CET from Friday to Saturday.

Column Description

The dataset contains an impressive two columns: date, which is the start date, and gpu_hours, which is not the start date.

Acknowledgements

Banner and vignette photo by Christian Wiediger on Unsplash.

Dataset

This dataset was created by Cyber Deep

Released under MIT

Contents

Dataset

This dataset was created by Meenal Saini

Released under MIT

Contents

Dataset Overview Introduction Provide a brief introduction about the dataset. Example: "This dataset contains historical stock price data for NVIDIA Corporation, a leading technology company specializing in GPUs, AI, and computer hardware. The data spans [specific date range] and includes key metrics like opening price, closing price, trading volume, and more."

Data Source Mention where you got the data (if applicable). Example:

Data extracted from [source, e.g., Yahoo Finance, official NVIDIA reports]. Ensure no proprietary or confidential data is included. Why Use This Dataset? Highlight the potential applications:

Financial trend analysis Predictive modeling using machine learning Stock price forecasting with time-series models Insights into market behavior

Related Dataset: GPU Benchmarks Compilation

Context

A Graphics Card is nothing more than another processor that is specially design and made to handle graphics. These are referred to as a Graphics Processing Unit (GPU). Adding one of these to your computer will take the load of processing graphics away from your CPU, allowing your CPU to handle other tasks. Due to the detail and sheer amount of graphics in modern games, a GPU is a must to play these games smoothly.

Content

When choosing a GPU, it’s important to take note of individual specs and to also make sure that the other components in your build are compatible.

• Bus Interface
• Memory Size (VRAM)
• Memory Bus Width
• Memory Type
• GPU Clock Speed
• Memory Clock Speed
• Unified Shaders
• Texture Mapping Units
• Render Output Units
• and more!

Acknowledgements

Web scraped from TechPowerUp, sourced from NVIDIA, AMD and Intel official websites

If you enjoyed this dataset, here's some similar datasets you may like 😎

Dataset

This dataset was created by sewonghwang

Released under CC0: Public Domain

Contents

This dataset is just for personal, non-commercial purposes.

Overview

This dataset provides a comprehensive record of NVIDIA Corporation's (NVDA) daily stock prices over the last five years. NVIDIA, a prominent technology company known for its graphics processing units (GPUs), has experienced significant market activity, making its stock price data valuable for financial analysis, trading strategies, and market trend studies.

Data Fields

The dataset includes the following columns:

1. Date: The trading date (YYYY-MM-DD format).
2. Open: The price of the stock at market opening.
3. High: The highest price of the stock during the trading day.
4. Low: The lowest price of the stock during the trading day.
5. Close: The price of the stock at market close.
6. Adj Close: The adjusted closing price, accounting for dividends and stock splits.
7. Volume: The number of shares traded on that day.

Time Period

• Start Date: Five years prior from the current date (for example, if today's date is 2024-05-23, the dataset starts from 2019-05-23).
• End Date: The most recent trading day available in the dataset.

Data Source

The data is typically sourced from reliable financial database Yahoo Finance. It is crucial to ensure data accuracy and completeness for effective analysis.

Usage

This dataset can be used for: - Historical Analysis: Studying NVIDIA's stock performance over time. - Technical Analysis: Applying various technical indicators and chart patterns. - Machine Learning: Training models for stock price prediction. - Market Research: Understanding market trends and investor behavior. - Investment Strategies: Backtesting trading strategies to assess their performance.

Example Applications

• Trend Analysis: Identifying bullish or bearish trends in NVIDIA's stock price.
• Volatility Analysis: Measuring the stock's volatility and assessing risk.
• Correlation Studies: Examining the relationship between NVIDIA's stock price and other market variables.
• Event Impact Analysis: Analyzing the impact of company announcements, earnings reports, or macroeconomic events on the stock price.

Note

It is important to handle the data responsibly, considering market hours, holidays, and any corporate actions like stock splits or dividends that might affect the stock price. Adjustments for these factors are usually reflected in the "Adj Close" column to provide a more accurate historical comparison.

This dataset is ideal for analysts, investors, researchers, and students interested in financial markets, particularly in understanding the dynamics of a leading technology company's stock over a significant period.

Dataset

This dataset was created by Lostgold Player

Contents

Dataset

This dataset was created by ck

Contents

Dataset

This dataset was created by ZhiweiJiang

Released under CC0: Public Domain

Contents

Dataset

This dataset was created by Pranav Hari

Released under Community Data License Agreement - Sharing - Version 1.0

Contents

This dataset provides comprehensive daily stock price data for NVIDIA Corporation (NVDA) and five key companies that play a crucial role in NVIDIA's success through manufacturing and research collaborations. The companies included are:

• TSMC (TSM): NVIDIA's primary chip manufacturer, responsible for producing its cutting-edge GPUs.
• Samsung Electronics (005930.KS): A major partner in NVIDIA’s chip fabrication, providing advanced semiconductor manufacturing services that contribute to NVIDIA’s GPU production capacity and diversification.
• ASML (ASML): Supplies the lithography equipment used in the advanced manufacturing of NVIDIA’s chips. ASML’s EUV technology is critical for creating NVIDIA’s high-performance GPUs.
• Synopsys (SNPS): Provides critical electronic design automation (EDA) tools used in the development of NVIDIA’s complex semiconductors, enabling accurate design and efficient production.
• Cadence Design Systems (CDNS): A key partner in providing design and simulation tools for NVIDIA’s chip development process, essential for the growing complexity of NVIDIA’s architectures.

The dataset includes daily price data for each company, such as opening price, closing price, highest price, lowest price, and trading volume. This collection is ideal for financial analysis, stock market predictions, and understanding how these key affiliated companies contribute to NVIDIA’s business and technological innovations.

This dataset enables researchers, analysts, and traders to explore the relationship between NVIDIA’s performance and the companies that are integral to its manufacturing processes and research projects, particularly in semiconductor fabrication and design.

The released trace contains a hybrid of training and inference jobs running state-of-the-art ML algorithms. It is collected from a large production cluster with over 6,500 GPUs (on ~1800 machines) in Alibaba PAI (Platform for Artificial Intelligence), spanning the July and August of 2020. We also include a Jupyter notebook that parses the trace and highlights some of the main characteristics (see section 3 Demo of Data Analysis).

We also present a characterization study of the trace in a paper, "MLaaS in the Wild: Workload Analysis and Scheduling in Large-Scale Heterogeneous GPU Clusters", published in NSDI ’22.

https://github.com/alibaba/clusterdata/tree/master/cluster-trace-gpu-v2020

Dataset

This dataset was created by Alao David I.

Contents

Dataset

This dataset was created by tkm2261

Contents

Dataset

This dataset was created by MarMohMM

Contents