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
EKORE raises EUR 1.3 million (~ USD 1 million) in seed funding to strengthen platform
Digital Twin
Dec 20, 2024
Funding
Culina Health raises USD 7.9 million in Series A funding to expand offerings and expand team
Functional Nutrition
Dec 19, 2024
FDA approval
ViGeneron receives IND clearance for VG801 gene therapy
Cell & Gene Therapy
Dec 19, 2024
Product updates
Reflex Aerospace ships first commercial satellite SIGI
Next-gen Satellites
Dec 19, 2024
Partnerships
Vast partners with SpaceX for two private astronaut missions to ISS
Space Travel and Exploration Tech
Dec 19, 2024
Management news
Carbios appoints Philippe Pouletty as interim CEO amid plant delay
Waste Recovery & Management Tech
Dec 19, 2024
Funding
BlueQubit raises USD 10 million in seed funding to develop quantum platform
Quantum Computing
Dec 19, 2024
FDA approval
Arbor Biotechnologies receives FDA clearance for ABO-101 IND application
Human Gene Editing
Dec 19, 2024
Funding
Partnerships
Personalis partners with Merck and Moderna for cancer therapy development and investment
Precision Medicine
Dec 19, 2024
Partnerships
COTA partners with Guardant Health to develop clinicogenomic data solutions for cancer research
Precision Medicine
Dec 19, 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.