A Synchronous 13.1 GHz Backside Resonant Clocking Mesh Implemented on a Graphics Core in an 18A Class Technology
This letter presents a global resonant clocking mesh architecture utilizing backside metal layers in an 18A class technology. Rotary traveling wave oscillators are implemented to provide synchronous low-skew, low-jitter, and 50% duty cycle clocks across a graphics core. To provide dynamic frequency and voltage scaling capabilities across a wide range of operating conditions, a high-speed fractional divider is designed. The proposed architecture is implemented on a 1.6 mm <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times $ </tex-math></inline-formula> 1.6 mm graphics core achieving FoMJ of 246 dB FoMT 190.3dBc/Hz.
Authors
- Anuradha Srinivasan
- Tanay Karnik (ORCID: https://orcid.org/0000-0003-0072-1492)
- Robert E. Orton
- Ragh Kuttappa (ORCID: https://orcid.org/0000-0003-1022-2187)
- Kailash Chandrashekar
- N. Hernández
- Vinayak Honkote
- Amreesh Rao
- Gaurav Kamalkar
- Eric Finley
- Chaitanya Sankuratri
- Faran Rafiq
Institutions
- Intel (United States) (US)
Publication Details
- Journal
- IEEE Solid-State Circuits Letters
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1109/lssc.2025.3552251
- Citations
- 2
- Primary Topic
- Advancements in PLL and VCO Technologies
- Type
- article
- Field-Weighted Citation Impact
- 1.46