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:
Partnerships
Geographic expansion
Lemonade partners with Homesite to expand home insurance services
InsurTech: Personal Lines
Jun 14, 2024
Funding
BayaniPay raises USD 3 million in seed funding to expand payment solutions
Neobanks
Jun 14, 2024
Partnerships
Carbonfuture and Swiss Re partner for long-term carbon removal through biochar
Carbon Management Software
Jun 13, 2024
Funding
Sidekick raises GBP 8.5 million in seed and debt funding to support expansion
Retail Trading Infrastructure
Jun 13, 2024
Partnerships
Climatiq and Epicor partner to reduce CO2 emissions in supply chains
Carbon Management Software
Jun 13, 2024
Product updates
EHang's pilotless eVTOL aircraft concludes first flight launch in Saudi Arabia
Passenger eVTOL Aircraft
Jun 13, 2024
Partnerships
Skyports partners with Unified Aviation to accelerate global network release
Passenger eVTOL Aircraft
Jun 13, 2024
Partnerships
Industry news
USSF chooses Blue Origin, SpaceX, and ULA for ~USD 5.6 billion Pentagon launch contracts
Space Travel and Exploration Tech
Jun 13, 2024
Funding
AnyCreek raises USD 1.8 million in seed funding to enhance platform and expand into new markets
Travel Tech
Jun 13, 2024
Funding
Zeta Labs raises USD 2.9 million in pre-seed funding to develop autonomous AI agent
Generative AI Applications
Jun 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.