학술논문

13.6 A 16Gb 37Gb/s GDDR7 DRAM with PAM3-Optimized TRX Equalization and ZQ Calibration
Document Type
Conference
Source
2024 IEEE International Solid-State Circuits Conference (ISSCC) Solid-State Circuits Conference (ISSCC), 2024 IEEE International. 67:242-244 Feb, 2024
Subject
Bioengineering
Communication, Networking and Broadcast Technologies
Engineered Materials, Dielectrics and Plasmas
Photonics and Electrooptics
Robotics and Control Systems
Deep learning
Electric potential
Data centers
Random access memory
Crosstalk
Bandwidth
Voltage
Language
ISSN
2376-8606
Abstract
GDDR memory has consistently maintained a leading position in delivering high performance: necessary for applications such as artificial intelligence, deep learning, and data centers. However, achieving an elevated I/O bandwidth, beyond the latest 27Gb/s GDDR6 [1], presents significant challenges in ensuring a sufficient I/O link budget. One solution is using multi-level pulse amplitude modulation (PAM) signaling. In the GDDR7 I/O specification, single-ended PAM3 signaling is used to achieve higher data rates as it can transfer data more than 58% faster, compared to non-return-to-zero (NRZ) signaling. Furthermore, PAM3 offers a 50% larger voltage sensing margin than PAM4, which was adopted for GDDR6X [2]. Therefore, PAM3 exhibits a higher potential for bandwidth extension, given that single-ended signaling is vulnerable to random noise and crosstalk.