Priority Filt: A Way to Increase Network Reliability on Chip against Soft Error by Considering Multiple Bit Upset
Author(s):
Article Type:
Research/Original Article (دارای رتبه معتبر)
Abstract:
One of the most important challenges that threaten the reliability of network-based chips is soft errors. These problems occur mainly in buffers of on the chip networks. The shrinking size of the technology has also increased the likelihood of converting single-event upset errors set to multi-event upsets, so it is predicted that by 2021 most soft errors of the multi-event reversal type will occur. Many different methods of avoiding and tolerating soft errors do not have the ability to deal with multi-event events due to different patterns. On the other hand, the rate of crosstalk fault is increasing. The purpose of this paper is to provide a method that, while improving the tolerance of single-event reversal events in buffers, is also able to tolerate multi-event upsets. The proposed method that is called Priority Flit is based on the different importance of tailer and data flits. In the other words, the fault tolerance method against soft errors in tailor and data is different. The second one is leafing and the second one is based on crosstalk avoidance and Hamming code. Results show improvements in the terms of hardware and performance with respect to the state-of-the-art mechanism.
Keywords:
Language:
Persian
Published:
Intelligent Systems in Electrical Engineering, Volume:12 Issue: 3, 2021
Pages:
19 to 32
magiran.com/p2333404
دانلود و مطالعه متن این مقاله با یکی از روشهای زیر امکان پذیر است:
اشتراک شخصی
با عضویت و پرداخت آنلاین حق اشتراک یکساله به مبلغ 1,390,000ريال میتوانید 70 عنوان مطلب دانلود کنید!
اشتراک سازمانی
به کتابخانه دانشگاه یا محل کار خود پیشنهاد کنید تا اشتراک سازمانی این پایگاه را برای دسترسی نامحدود همه کاربران به متن مطالب تهیه نمایند!
توجه!
- حق عضویت دریافتی صرف حمایت از نشریات عضو و نگهداری، تکمیل و توسعه مگیران میشود.
- پرداخت حق اشتراک و دانلود مقالات اجازه بازنشر آن در سایر رسانههای چاپی و دیجیتال را به کاربر نمیدهد.
In order to view content subscription is required
Personal subscription
Subscribe magiran.com for 70 € euros via PayPal and download 70 articles during a year.
Organization subscription
Please contact us to subscribe your university or library for unlimited access!