All Updates

All Updates

icon
Filter
Product updates
Google unveils sixth generation of TPU chips at I/O 2024 conference
Generative AI Infrastructure
May 14, 2024
This week:
Funding
Matr Foods raises EUR 20 million in debt funding to build mycelium meat factory
Plant-based Meat
Today
Last week:
M&A
Platform Science to acquire Trimble's global transportation telematics business units
Truck Industry Tech
Yesterday
Funding
Whatfix raises USD 100 million in Series E funding to expand business
EdTech: Corporate Learning
Yesterday
Product updates
Sky Mavis launches cross-game onboarding solution
Web3 Ecosystem
Sep 14, 2024
Funding
Bicara Therapeutics raises USD 315 million in IPO; plans to develop lead candidate ficerafusp alfa
Precision Medicine
Sep 13, 2024
Partnerships
Massive Bio and Foundation Medicine partner to improve cancer clinical trial enrollment
Precision Medicine
Sep 13, 2024
Partnerships
Moffitt Cancer Center partners with AstraZeneca to advance oncology cell therapies
Cell & Gene Therapy
Sep 13, 2024
Product updates
Quandela launches European quantum computer in North America
Quantum Computing
Sep 13, 2024
Partnerships
IonQ achieves high qubit gate fidelity on barium development platform
Quantum Computing
Sep 13, 2024
Partnerships
Massive Bio and Foundation Medicine partner to improve cancer clinical trial enrollment
Clinical Trial Technology
Sep 13, 2024
Generative AI Infrastructure

Generative AI Infrastructure

May 14, 2024

Google unveils sixth generation of TPU chips at I/O 2024 conference

Product updates

  • Google unveiled its next generation of Tensor Processing Units (TPU), Trillium, at its annual Google I/O developer conference. The TPUs are scheduled for release later this year.

  • Google's Trillium boasts several enhancements from the previous generation. This includes a 4.7x increase in compute performance per chip, wider matrix multiply units (MXUs), higher clock speed, and double the memory bandwidth. The new chips are also 67% more energy-efficient than the previous generation.

  • The chips uniquely carry the third generation of SparseCore, an accelerator specially designed for handling large-scale embeddings often found in advanced recommendation or ranking tasks. This enables Trillium TPUs to train models faster and serve them with lower latency.

Contact us

Gain access to all industry hubs, market maps, research tools, and more
Get a demo
arrow
menuarrow

By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.