Putting power forward
Steve Pimpis, AMP Group
EDN (October 06, 2016)
Introduction
Designers of advanced computing systems are no longer able to consider the power supply as a “black box” that can be plugged in at the end of the project. Giving due consideration to power design at an early stage is essential given the growing complexity of server boards, demands for greater power and efficiency, and the need to plan for multiple product generations. On the other hand, engineers also need flexible power solutions in order to respond to system design changes and adopt a platform approach to the power design, which can help streamline future development. The ability to easily configure, control and monitor power delivery functions is a valuable characteristic enabled by digitally configurable power modules.
Pressure on power design
High-performance computer boards such as data-center servers present increasingly complex routing and component-placement challenges as designers seek to maximize data-processing and storage capabilities in the minimum possible area to comply with the standard rack dimensions. With a mix of advanced processors, ASICs and FPGAs that feature large numbers of I/Os and multiple power domains, the PCB can incorporate 20 layers or more for timing-critical high-speed signal traces and power distribution.
To read the full article, click here
Related Semiconductor IP
- 64-bit, RISC-V, ultra-high performance processors
- 64-bit, RISC-V, performance and data computation processors
- 32-bit, RISC-V, deeply embedded processors
- Verification IP for eUSB 2 v2 and USB 2.0
- AFDX 1G Switch IP
Related Articles
- Integrated Low Power Verification Suite: The way forward for SoC use-case Verification
- Market Focus: DSP makers' forward spin on the market
- Putting the D Back into Design for Test
- Comparing Current and Emerging CDMA Forward Link PHYs
Latest Articles
- Design and Development of a Neuromorphic Silicon Suite: PVT Sensing, Stochastic LIF Inference, On-Chip STDP Learning, and Crossbar Programming
- LLM4RTL: Tool-Assisted LLM for RTL Generation
- Towards Delta Aware Training: Efficient DNN Weight Storage for Resource-Constrained FPGAs
- CHERI-D: Secure and efficient inline object ID for CHERI temporal memory safety
- AIA: A 16nm Multicore SoC for Approximate Inference Acceleration Exploiting Non-normalized Knuth-Yao Sampling and Inter-Core Register Sharing