An in-depth look at Google’s first Tensor Processing Unit (TPU)

Linking pages

Modular: AIâs compute fragmentation: what matrix multiplication teaches us https://www.modular.com/blog/ais-compute-fragmentation-what-matrix-multiplication-teaches-us 44 comments
Introducing Trillium, sixth-generation TPUs | Google Cloud Blog https://cloud.google.com/blog/products/compute/introducing-trillium-6th-gen-tpus/ 6 comments
The Economics of Large Language Models - Sunyan’s Substack https://sunyan.substack.com/p/the-economics-of-large-language-models 1 comment
Google AI Infrastructure Supremacy: Systems Matter More Than Microarchitecture https://www.semianalysis.com/p/google-ai-infrastructure-supremacy 1 comment
Google AI Infrastructure Supremacy: Systems Matter More Than Microarchitecture https://www.semianalysis.com/p/google-ai-infrastructure-supremacy?post_id=114314781&publication_id=329241 1 comment
TelaMalloc: Efficient On-Chip Memory Allocation for Production Machine Learning Accelerators https://www.micahlerner.com/2023/04/16/telamalloc-efficient-on-chip-memory-allocation-for-production-machine-learning-accelerators.html 1 comment
TelaMalloc: Efficient On-Chip Memory Allocation for Production Machine Learning Accelerators https://www.micahlerner.com/2023/06/06/telamalloc-efficient-on-chip-memory-allocation-for-production-machine-learning-accelerators.html 0 comments
AI 101: GPU vs. TPU vs. NPU https://www.backblaze.com/blog/ai-101-gpu-vs-tpu-vs-npu/ 0 comments
Understanding the Software Stack in Quantum Computing https://minimumviableparagraph.com/20240514-understanding-software-stack-quantum-computing 0 comments
Chip Odyssey 2006: The Start of the Modern Chip Era - EE Times https://www.eetimes.com/chip-odyssey-2006-the-start-of-the-modern-chip-era/ 0 comments

Linked pages

Google supercharges machine learning tasks with TPU custom chip | Google Cloud Blog https://cloudplatform.googleblog.com/2016/05/Google-supercharges-machine-learning-tasks-with-custom-chip.html 279 comments
A Neural Network Playground http://playground.tensorflow.org/#activation=tanh&batchSize=10&dataset=circle&regDataset=reg-plane&learningRate=0.03&regularizationRate=0&noise=0&networkShape=4,2&seed=0.44309&showTestData=false&discretize=false&percTrainData=50&x=true&y=true&xTimesY=false&xSquared=false&ySquared=false&cosX=false&sinX=false&cosY=false&sinY=false&collectStats=false&problem=classification&initZero=false&hideText=false 236 comments
First In-Depth Look at Google’s TPU Architecture https://www.nextplatform.com/2017/04/05/first-depth-look-googles-tpu-architecture/ 86 comments
Quantifying the performance of the TPU, our first machine learning chip | Google Cloud Blog https://cloudplatform.googleblog.com/2017/04/quantifying-the-performance-of-the-TPU-our-first-machine-learning-chip.html 27 comments
Sigmoid function - Wikipedia https://en.wikipedia.org/wiki/Sigmoid_function 6 comments
Application-specific integrated circuit - Wikipedia http://en.wikipedia.org/wiki/Application-specific_integrated_circuit 5 comments
Long short-term memory - Wikipedia https://en.wikipedia.org/wiki/Long_short-term_memory 4 comments
[1704.04760] In-Datacenter Performance Analysis of a Tensor Processing Unit https://arxiv.org/abs/1704.04760 0 comments
Systolic array - Wikipedia https://en.wikipedia.org/wiki/Systolic_array 0 comments
https://cloud.google.com/blog/big-data/2016/07/understanding-neural-networks-with-tensorflow-playground 0 comments
Digits is revolutionizing accounting with Google Cloud ML | Google Cloud Blog https://cloud.google.com/blog/products/ai-machine-learning/digits-is-revolutionizing-accounting-with-google-cloud-ml 0 comments