All about AI Accelerators: GPU, TPU, Dataflow, Near-Memory, Optical, Neuromorphic & more (w/ Author)

Subscribers:
284,000
Published on ● Video Link: https://www.youtube.com/watch?v=VQoyypYTz2U



Duration: 1:02:35
65,912 views
1,553


#ai #gpu #tpu

This video is an interview with Adi Fuchs, author of a series called "AI Accelerators", and an expert in modern AI acceleration technology.
Accelerators like GPUs and TPUs are an integral part of today's AI landscape. Deep Neural Network training can be sped up by orders of magnitudes by making good use of these specialized pieces of hardware. However, GPUs and TPUs are only the beginning of a vast landscape of emerging technologies and companies that build accelerators for the next generation of AI models. In this interview, we go over many aspects of building hardware for AI, including why GPUs have been so successful, what the most promising approaches look like, how they work, and what the main challenges are.

OUTLINE:
0:00 - Intro
5:10 - What does it mean to make hardware for AI?
8:20 - Why were GPUs so successful?
16:25 - What is "dark silicon"?
20:00 - Beyond GPUs: How can we get even faster AI compute?
28:00 - A look at today's accelerator landscape
30:00 - Systolic Arrays and VLIW
35:30 - Reconfigurable dataflow hardware
40:50 - The failure of Wave Computing
42:30 - What is near-memory compute?
46:50 - Optical and Neuromorphic Computing
49:50 - Hardware as enabler and limiter
55:20 - Everything old is new again
1:00:00 - Where to go to dive deeper?

Read the full blog series here:
Part I: https://medium.com/@adi.fu7/ai-accelerators-part-i-intro-822c2cdb4ca4
Part II: https://medium.com/@adi.fu7/ai-accelerators-part-ii-transistors-and-pizza-or-why-do-we-need-accelerators-75738642fdaa
Part III: https://medium.com/@adi.fu7/ai-accelerators-part-iii-architectural-foundations-3f1f73d61f1f
Part IV: https://medium.com/@adi.fu7/ai-accelerators-part-iv-the-very-rich-landscape-17481be80917
Part V: https://medium.com/@adi.fu7/ai-accelerators-part-v-final-thoughts-94eae9dbfafb

Links:
Merch: http://store.ykilcher.com
TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
Discord: https://discord.gg/4H8xxDF
BitChute: https://www.bitchute.com/channel/yannic-kilcher
LinkedIn: https://www.linkedin.com/in/ykilcher
BiliBili: https://space.bilibili.com/2017636191

If you want to support me, the best thing to do is to share out the content :)

If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this):
SubscribeStar: https://www.subscribestar.com/yannickilcher
Patreon: https://www.patreon.com/yannickilcher
Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq
Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2
Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m
Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n




Other Videos By Yannic Kilcher


2022-03-08Spurious normativity enhances learning of compliance and enforcement behavior in artificial agents
2022-03-06First Author Interview: AI & formal math (Formal Mathematics Statement Curriculum Learning)
2022-03-05OpenAI tackles Math - Formal Mathematics Statement Curriculum Learning (Paper Explained)
2022-03-04[ML News] DeepMind controls fusion | Yann LeCun's JEPA architecture | US: AI can't copyright its art
2022-03-02AlphaCode - with the authors!
2022-03-01Competition-Level Code Generation with AlphaCode (Paper Review)
2022-02-28Can Wikipedia Help Offline Reinforcement Learning? (Author Interview)
2022-02-26Can Wikipedia Help Offline Reinforcement Learning? (Paper Explained)
2022-02-23[ML Olds] Meta Research Supercluster | OpenAI GPT-Instruct | Google LaMDA | Drones fight Pigeons
2022-02-21Listening to You! - Channel Update (Author Interviews)
2022-02-20All about AI Accelerators: GPU, TPU, Dataflow, Near-Memory, Optical, Neuromorphic & more (w/ Author)
2022-02-18[ML News] Uber: Deep Learning for ETA | MuZero Video Compression | Block-NeRF | EfficientNet-X
2022-02-17CM3: A Causal Masked Multimodal Model of the Internet (Paper Explained w/ Author Interview)
2022-02-16AI against Censorship: Genetic Algorithms, The Geneva Project, ML in Security, and more!
2022-02-15HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning (w/ Author)
2022-02-10[ML News] DeepMind AlphaCode | OpenAI math prover | Meta battles harmful content with AI
2022-02-08Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents (+Author)
2022-02-07OpenAI Embeddings (and Controversy?!)
2022-02-06Unsupervised Brain Models - How does Deep Learning inform Neuroscience? (w/ Patrick Mineault)
2022-02-04GPT-NeoX-20B - Open-Source huge language model by EleutherAI (Interview w/ co-founder Connor Leahy)
2022-01-29Predicting the rules behind - Deep Symbolic Regression for Recurrent Sequences (w/ author interview)



Tags:
deep learning
machine learning
arxiv
explained
neural networks
ai
artificial intelligence
paper
gpu
tpu
ipu
wave computing
dataflow
near memory compute
ai accelerators
deep learning hardware
sambanova
cerebras
graphcore
mythic
optical computing
lightmatter
groq
why are gpus so fast
why does deep learning need gpus
do i need a gpu for deep learning
transformers hardware
hardware matrix multiplication
fast deep learning
machine learning hardware