Chinese semiconductor thread II

olalavn

Senior Member
Registered Member
If China can get Domestic EUV going with a complete domestic production of 3nm with EUV in just 2 years, it will blow the minds of the west. Right now, news articles only talk about SMEE kind of working on 28NM Lithography machine. Its also not widely shown to be used in Fabs yet. Its kind of a mystery. To go from that to having EUV in production Fab will be Sputnik level of Shock.
if DUV can use to produce process similar to 4-3nm with GAAfet technology, what do you think about it?
maybe in the future, the domestic DUV itself will use GAA technology
 

ansy1968

Brigadier
Registered Member
if DUV can use to produce process similar to 4-3nm with GAAfet technology, what do you think about it?
maybe in the future, the domestic DUV itself will use GAA technology
Coupled with a domestic EDA wallah!!!!! a self reliant domestic eco system.

Please, Log in or Register to view URLs content!

Please, Log in or Register to view URLs content!

Please, Log in or Register to view URLs content!

Please, Log in or Register to view URLs content!





9 hours ago — Xinhuazhang develops EDA tools compatible with Arm-based Huawei's Kunpeng and SPARCv9-based Phytium's FeiTeng processors.
 

measuredingabens

Junior Member
Registered Member
Please, Log in or Register to view URLs content!

Parallel photonic chip for nanosecond end-to-end image processing, transmission, and reconstruction

Abstract

Image processing, transmission, and reconstruction constitute a major proportion of information technology. The rapid expansion of ubiquitous edge devices and data centers has led to substantial demands on the bandwidth and efficiency of image processing, transmission, and reconstruction. The frequent conversion of serial signals between the optical and electrical domains, coupled with the gradual saturation of electronic processors, has become the bottleneck of end-to-end machine vision. Here, we present an optical parallel computational array chip (OPCA chip) for end-to-end processing, transmission, and reconstruction of optical intensity images. By proposing constructive and destructive computing modes on the large-bandwidth resonant optical channels, a parallel computational model is constructed to implement end-to-end optical neural network computing. The OPCA chip features a measured response time of 6 ns and an optical bandwidth of at least 160 nm. Optical image processing can be efficiently executed with minimal energy consumption and latency, liberated from the need for frequent optical–electronic and analog–digital conversions. The proposed optical computational sensor opens the door to extremely high-speed processing, transmission, and reconstruction of visible contents with nanoseconds response time and terahertz bandwidth.
 

measuredingabens

Junior Member
Registered Member
Please, Log in or Register to view URLs content!

In Optica, Optica Publishing Group’s journal for high-impact research, the researchers describe the new chip, which they call an optical parallel computational array (OPCA) chip. They show that the OPCA has a processing bandwidth of up to one hundred billion pixels and a response time of just 6 nanoseconds, which is about six orders of magnitude faster than current methods. They also used the chip to create an optical neural network that integrates image perception, computation and reconstruction.
 

tokenanalyst

Brigadier
Registered Member

Sugon: The company's high-end computers and other hardware facilities and platforms have passed verification and testing by multiple power grid ISVs and operation and maintenance companies​

Inspur stated on the investor interaction platform that the company's high-end computers and other hardware facilities and platforms have passed verification and testing by multiple power grid ISVs and operation and maintenance companies, and have been deployed in many power grid projects, facilitating applications such as smart grid inspections.
It is reported that the wave of big models will bring about an exponential growth in the number of parameters and data requirements. The intelligent computing industry has entered the fast lane of development. Sugon has been laying out in the field of intelligent computing for many years and is expected to inherit the industry's momentum:

1) AI servers: AI servers have significant advantages in the field of deep learning and are still the main force in the artificial intelligence market. The company has been fighting in the field of AI servers for many years and has launched the powerful Xmachine series. At present, the chips of the company's subsidiary Inspur Information are comparable to those of overseas leaders, and it is expected to restart the AI server product line through industrial linkage in the future;

2) Computing power services: The growth rate of model computing power exceeds Moore's Law, coupled with further sanctions from the United States, the computing power supply has shown a clear gap, and the demand for computing power leasing continues to increase. At present, Sugon has planned 7 5A-level intelligent computing centers, and the first-release layout is expected to benefit first;

3) Computing power scheduling: The computing power scheduling platform can realize the cross-regional and cross-application integration of computing power resources, dynamically allocate and optimize the use of computing power, and meet the definite needs in the context of the construction of a national integrated computing power network. Sugon currently has rich reserves in computing power scheduling.

In addition, Sugon launched the industry's first integrated computing service platform in 2021 (currently the platform has been upgraded to version 5.0). The number of users has exceeded 100,000, and the number of job submissions has exceeded 100 million. At the same time, the company has been deeply involved in the information high-speed rail test site-experimental supercomputing network led by the Institute of Computing Technology of the Chinese Academy of Sciences, and is expected to continue to benefit from the construction of the supercomputing Internet and the promotion of the national integrated computing network in the future.

Please, Log in or Register to view URLs content!
 
Top