How far can multicore SoC scaling go? Cavium's Octeon II
In network switching applications, multicore SoC architectures appear to be crossing a threshold between two paradigms. When multicore chips first appeared there was a clear distinction in the hardware between the control and data planes. One or a few general-purpose CPU cores sat in the control plane with their own caches and their own—usually AMBA—bus structure. A cluster of special-purpose processors sat in the data plane with their own buffers and interconnect scheme, and a bridge to the control-plane bus.
To read the full article, click here
Related Semiconductor IP
- SoC Security Platform / Hardware Root of Trust
- SPI to AHB-Lite Bridge
- Octal SPI Master/Slave Controller
- I2C and SPI Master/Slave Controller
- AHB/AXI4-Lite to AXI4-Stream Bridge
Related Blogs
- Will your multicore SoC hit the memory wall? Will the memory wall hit your SoC? Does it matter?
- Makimoto's Wave Revisited for Multicore SoC Design
- How to Build a Deadlock-Free Multi-cores SoC?
- ARM show new AMBA specs: think FPGAs and multicore