Integrating Novel Packaging Technologies for Large Scale Computer Systems

Author(s):  
James Mitchell ◽  
John Cunningham ◽  
Ashok V. Krishnamoorthy ◽  
Robert Drost ◽  
Ron Ho

Proximity Communication (PxC) enables VLSI chips placed face-to-face to communicate using close-field capacitive coupling. In a 90 nm standard CMOS technology, using the packaging techniques described in this paper, PxC provides chip-to-chip latency of 2.5 ns at 4 Gb/s per channel with less than 2.5 mW/Gb/s, an areal bandwidth density of 0.83 Tb/s/mm2, and a BER less than 10−15. At a system level, the benefits of PxC scale directly with the number of chips that can be packaged together, because PxC enables designers to aggregate multiple chips that perform as a single large piece of silicon. The chips can also be heterogeneous to provide an optimized mix of process technology and functionality, such as integrating DRAM chips, NAND flash memory, and CMOS processor chips. In this paper we describe packaging advances and technology prototypes that enable PxC and provide its system-level benefits.

Micromachines ◽  
2021 ◽  
Vol 12 (8) ◽  
pp. 879
Author(s):  
Ruiquan He ◽  
Haihua Hu ◽  
Chunru Xiong ◽  
Guojun Han

The multilevel per cell technology and continued scaling down process technology significantly improves the storage density of NAND flash memory but also brings about a challenge in that data reliability degrades due to the serious noise. To ensure the data reliability, many noise mitigation technologies have been proposed. However, they only mitigate one of the noises of the NAND flash memory channel. In this paper, we consider all the main noises and present a novel neural network-assisted error correction (ANNAEC) scheme to increase the reliability of multi-level cell (MLC) NAND flash memory. To avoid using retention time as an input parameter of the neural network, we propose a relative log-likelihood ratio (LLR) to estimate the actual LLR. Then, we transform the bit detection into a clustering problem and propose to employ a neural network to learn the error characteristics of the NAND flash memory channel. Therefore, the trained neural network has optimized performances of bit error detection. Simulation results show that our proposed scheme can significantly improve the performance of the bit error detection and increase the endurance of NAND flash memory.


2012 ◽  
Vol 47 (1) ◽  
pp. 75-84 ◽  
Author(s):  
Koichi Fukuda ◽  
Yoshihisa Watanabe ◽  
Eiichi Makino ◽  
Koichi Kawakami ◽  
Jumpei Sato ◽  
...  

Author(s):  
Kazushige Kanda ◽  
Masaru Koyanagi ◽  
Toshio Yamamura ◽  
Koji Hosono ◽  
Masahiro Yoshihara ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document