🚀 Medial just raised $500k in Pre-Series A. Tap to read the announcement. 🎉
Login

Back to feeds

Haran Naresh K

Stealth • 2m

Harnessing GPU Power with CUDA CUDA (Compute Unified Device Architecture) is a parallel computing platform by Nvidia that unleashes the power of GPUs for more than just graphics rendering. Initially developed in 2007, CUDA enables massive parallel processing, making it essential for tasks like deep learning, AI, and data science. By writing CUDA kernels in C++, developers can leverage thousands of GPU cores to process data efficiently. CUDA revolutionizes how large datasets are computed by using blocks and threads to optimize performance. Its impact is profound in AI research, making GPUs indispensable for training complex neural networks and advancing machine learning technologies.

1 replies4 likes
Replies (1)

More like this

Recommendations from Medial

Vasudha Chigurupati

Stealth • 9d

[This post has been deleted by the creator]

0 replies
Image Description
Image Description

Somen's 8D world

Stealth • 7m

new programming language Alart. **No Loops in this language. Bend Bend is a massively parallel, high-level programming language. that will do one week's job in 7 days with 7 computers Unlike low-level alternatives like CUDA and Metal, Bend has the

See More
9 replies10 likes
4

Kolkata Index

Stealth • 19d

West Bengal is set to launch a GPU as a service data center in Siliguri by Dec 2024, offering 160 petaflops of computational power. This initiative aims to boost research and development for startups and MSMEs in eastern India.

0 replies1 like
Image Description
Image Description

Inactive

Stealth • 6m

Could AI workload processing be the new crypto mining? Some companies think so, offering ways to earn by lending your GPU power for AI tasks, just like the old crypto mining days. Key points: - Services like Salad pay users to contribute their GP

See More
5 replies13 likes
Image Description
Image Description

Payal Manghnani

Stealth • 6m

Computing has come a long way with the introduction of NPUs, GPUs, and CPUs. Let's break it down in simple terms: 🧠 CPUs: They handle general instructions and system management. Think of them as the brain of your computer, evolving with more cores

See More
4 replies6 likes
Image Description

Rahul Gupta

Stealth • 6m

Your brain consumes 20 W of power. A single GPU consumes a kilowatt. A data center has tens of thousands of them, and is still not as powerful as your brain. Chew on that before you say AGI is imminent. ~ Pedro Domingos

2 replies14 likes

PRATHAM

 • 

Medial • 6m

NVIDIA is cashing in on the AI gold rush by selling shovels to tech giants ‼️ GPUs are essential in training complex neural networks, and NVIDIA's accelerate AI adoption worldwide. Their processors power 90% of supercomputers and are used by every m

See More
0 replies6 likes
1

Vaibhav Babruwan Shingde

Stealth • 10m

Let's Start With Today's Topic : How AI Chips Work , Uses , Companies Working On It? ° How AI Chips Work? •Large arrays of specialized processing cores for AI operations. •High-speed on-chip memory for storing AI models and data. •Fast interconn

See More
0 replies8 likes
Image Description
Image Description

Afifa

Stealth • 4m

NVIDIA- THE DOMINANT FORCE 1. NVIDIA is a leading force in AI and GPU technology. 2. Their GPUs, like the H100 Tensor Core, are critical for AI development, including training models like ChatGPT. 3. NVIDIA's stock has surpassed a $1 trillion ma

See More
2 replies6 likes
1

Golu

Stealth • 3m

AI has grown rapidly through advancements in machine learning, increased computational power, and vast data availability. These factors enable AI systems to learn complex patterns, improve decision-making, and automate tasks across industries, from h

See More
0 replies5 likes

Download the medial app to read full posts, comements and news.