Apple completes its ARM lineup with 5nm, 134billion transistor M2 Ultra
By Nick Flaherty, eeNews Europe (June 5, 2023)
Apple has completed its range of ARM-based chips with the M2 Ultra, its largest to date with 134bn transistors.
As previously suggested, the M2 Ultra uses Apple’s UltraFusion interconnect and silicon interposer to combine two of the M2 Max die with a unified memory architecture. This has 10,000 signals, providing over 2.5TB/s of low-latency interprocessor bandwidth to support up to 192GB of memory capacity, 50 percent more than M1 Ultra, with 800GB/s of memory bandwidth, twice that of M2 Max.
![]() |
E-mail This Article | ![]() |
![]() |
Printer-Friendly Page |
Related News
- Sondrel completes a multi-billion transistor chip design at 5nm
- Ultra Accelerator Link Consortium (UALink) Welcomes Alibaba, Apple and Synopsys to Board of Directors
- C-DAC partners with MosChip and Socionext for design of HPC Processor AUM based on Arm architecture
- intoPIX unveils new FastTicoRAW & FastTicoXS codecs for Apple silicon and makes the switch to ARM-based technology simple
- ADTechnology to launch its 5nm A53-based Platform, ADP500 based on Samsung Foundry
Breaking News
- Agile Analog appoints CEO to drive growth
- Numem Appoints Former Intel Executives to Leadership Team
- Optimized SAR ADCs, Sigma-Delta ADCs, DACs, and Audio CODECs for IoT, MCU, SoC, and Consumer Applications
- Enabled on makeChip and powered by Racyics, the SpiNNaker2 chip forms the core of the newly launched SpiNNcould supercomputer!
- Semidynamics Announces Cervell™ All-in-One RISC-V NPU Delivering Scalable AI Compute for Edge and Datacenter Applications
Most Popular
- Keysight EDA and Intel Foundry Collaborate on EMIB-T Silicon Bridge Technology for Next-Generation AI and Data Center Solutions
- IC'Alps joins Intel Foundry Accelerator program as Value Chain Alliance (VCA) and Design Services Alliance (DSA) partner
- Intel Foundry Gathers Customers and Partners, Outlines Priorities
- Weebit Nano and DB HiTek to demonstrate chips integrating Weebit ReRAM at PCIM 2025
- Semidynamics Announces Cervell™ All-in-One RISC-V NPU Delivering Scalable AI Compute for Edge and Datacenter Applications