In addition, BYD will use NVIDIA AI infrastructure for autonomous driving model training, and smart factory robots will also use the NVIDIA Isaac robotic system.

BYD and NVIDIA announced their cooperation in March last year to develop Dynasty and Ocean smart cars based on NVIDIA DRIVE, so today’s official announcement is expected to further expand their cooperation.

But in fact, BYD has not completely “bet” on Nvidia technology. According to a 2023 ADAS (Advanced Driving Assistance System) technology selection map of major automobile companies compiled by Counterpoint, BYD also has multiple technology options.

▲ Picture source market research agency Counterpoint

According to previous reports, Nvidia announced a new generation of “DRIVE Thor” computing platform in September 2022, dedicated to autonomous driving and assisted driving as well as a series of digital functions including in-car entertainment. DRIVE Thor’s first customer is JiKr, a subsidiary of the Chinese car company Geely.

The post BYD and Nvidia expand cooperation: Equipped with Drive Thor car-machine chip appeared first on TechGoing.

Yang Yuanqing introduced the product layout of Lenovo Car Computing in his speech. He pointed out that future smart cars will be more like super PCs on wheels, and the measurement of car performance standards has also changed from horsepower to computing power. Lenovo Car Computing’s domain control products. It will support smart cockpits, autonomous driving, smart screens, etc. Large models based on car scenes will also become smart companions to understand, help and accompany users.

It is noticed that during the event, Lenovo announced its automotive computing roadmap, which includes three new smart domain control products based on the NVIDIA DRIVE platform:

 Lenovo XH1: cabin-driving integrated central computing unit

 Lenovo AH1: L2++ ADAS Domain Controller

 Lenovo AD1: L4 autonomous driving domain controller

Nvidia founder and CEO Jensen Huang also appeared at the conference to promote Lenovo’s new domain controller products.

The post Lenovo Announces Vehicle Computing Roadmap: Join with Nvidia to launch domain controllers appeared first on TechGoing.

Sources familiar with the matter said that the three chips are based on NVIDIA H100 improved, NVIDIA is expected to be announced as soon as possible after November 16, the fastest domestic manufacturers will get samples in the next few days.

NVIDIA H100 Tensor Core GPU adopts the new Hopper architecture, based on the TSMC N4 process, integrated with 80 billion transistors. Compared to its predecessor, it delivers 9x faster training speeds for multi-expert (MoE) models.

Equipped with a fourth-generation Tensor Core and Transformer engine (FP8 accuracy), it also features highly scalable NVLink interconnectivity (up to 256 H100 GPUs, with 9x more bandwidth compared to the previous generation’s HDR Quantum InfiniBand network, with a bandwidth speed of 900GB/s), and more. (900GB/s bandwidth), among other features.

THIS IS A SPONSOR PROMOTION: >>>>>>>>>>>>>

Geekwills is an online shop that connects consumers with millions of products and brands around the world with the mission to empower them to live their best lives. Geekwills is committed to offering the most affordable quality products to enable consumers and sellers to fulfill their dreams in an inclusive environment.

The post NVIDIA working on AI chips HGX H20, L20 PCle and L2 PCle appeared first on TechGoing.

According to previous reports the currently revealed RTX 40 SUPER series graphics cards include the following three models:

 RTX 4080 SUPER: Powered by AD103-400 GPU with 10240 cores.

 RTX 4070 Ti SUPER: Powered by AD103-275/AD102-175 GPU with 8448 cores and 48 MB L2 cache.

 RTX 4070 SUPER: Powered by AD104-350 or AD103-175 GPU, with 7168 cores and 48 MB L2 cache.

CES 2024 will start on January 9, 2024. Intel, AMD, NVIDIA and various hardware manufacturers are expected to release new products during this period.

THIS IS A SPONSOR PROMOTION: >>>>>>>>>>>>>

Geekwills is an online shop that connects consumers with millions of products and brands around the world with the mission to empower them to live their best lives. Geekwills is committed to offering the most affordable quality products to enable consumers and sellers to fulfill their dreams in an inclusive environment.

The post Nvidia will hold a CES 2024 conference, expected to release the RTX 40 SUPER GPU appeared first on TechGoing.

According to the picture posted by the whistleblower @Zed__Wang, the packaging design of an RTX 4070 Ti SUPER graphics card has been exposed. It can be seen that this naming method is indeed strange. The tipster also complained that even the GTX 650 Ti Boost sounds much better than the RTX 4070 Ti SUPER.

On inquiry it is found that @Zed__Wang has a record of disclosing such designs before official release, and these revelations are usually accurate, so they are highly credible.

According to the specification information previously revealed by Kopite7kimi, the RTX 4070 Ti SUPER is an updated model of the existing Ti model. It has 8448 CUDA cores and uses AD102-175 or AD103-275 GPU. It is expected to maintain 285W power consumption and be equipped with 16GB GDDR6X video memory.

In addition, news broke that NVIDIA is expected to launch three graphics card products at CES 2024: RTX 4080 SUPER, 4070 Ti SUPER, and 4070 SUPER.

THIS IS A SPONSOR PROMOTION: >>>>>>>>>>>>>

Geekwills is an online shop that connects consumers with millions of products and brands around the world with the mission to empower them to live their best lives. Geekwills is committed to offering the most affordable quality products to enable consumers and sellers to fulfill their dreams in an inclusive environment.

The post Nvidia RTX 4070 Ti SUPER graphics card packaging design exposed appeared first on TechGoing.

It is learned from NVIDIA’s official website that the TGP power consumption of the public models of RTX 4080, RTX 4070 Ti and RTX 4070 are 320W, 285W and 200W respectively.

The following are the network transmission parameter specifications of the SUPER version of RTX 4070, RTX 4070 Ti and RTX 4080 graphics cards:

 RTX 4080 SUPER: Powered by AD103-400 GPU with 10240 cores.

 RTX 4070 Ti SUPER: Powered by AD103-275/AD102-175 GPU with 8448 cores and 48 MB L2 cache.

 RTX 4070 SUPER: Powered by AD104-350 or AD103-175 GPU, with 7168 cores and 48 MB L2 cache.

Three SUPER Edition graphics cards are expected to be announced at CES early next year.

THIS IS A SPONSOR PROMOTION: >>>>>>>>>>>>>

Geekwills is an online shop that connects consumers with millions of products and brands around the world with the mission to empower them to live their best lives. Geekwills is committed to offering the most affordable quality products to enable consumers and sellers to fulfill their dreams in an inclusive environment.

The post Nvidia’s new RTX 4070/4080 SUPER graphics card consume the same power as older models appeared first on TechGoing.

NVIDIA stated in a press release that its NVIDIA Omniverse now supports the DLSS 3.5 version of the generation ray reconstruction function, and RTX GPU users can use it in NVIDIA Studio for free.

NVIDIA creative director Sabour Amirazodi also showed off new projects through NVIDIA Studio, using powerful projectors to decorate his house with a very “magical” Halloween effect.

Note: Omniverse is a real-time 3D graphics collaboration platform created by Nvidia. It is already being used for applications in the visual effects and “digital twin” industrial simulation industries. Omniverse makes extensive use of a common scene description format.

Nvidia also said that RTX Video Super Resolution (VSR) will be available to users in the NVIDIA Studios driver version released tomorrow.

THIS IS A SPONSOR PROMOTION: >>>>>>>>>>>>>

Geekwills is an online shop that connects consumers with millions of products and brands around the world with the mission to empower them to live their best lives. Geekwills is committed to offering the most affordable quality products to enable consumers and sellers to fulfill their dreams in an inclusive environment.

The post Nvidia’s real-time 3D graphics collaboration platform Omniverse now supports DLSS 3.5 appeared first on TechGoing.

Among the many security vulnerabilities fixed this time, the one with the highest CVSS score is CVE-2023-31027, which is 8.2 points (out of 10 points, the higher the score, the more dangerous it is).

NVIDIA briefly introduced information about the vulnerability:

 The NVIDIA GPU graphics driver for Windows previously had a vulnerability that allowed low-privilege Windows users to escalate their privileges and gain higher privileges when administrators updated the GPU driver.

The update link address attached here. The graphics card models applicable to this update are as follows:

 NVIDIA GeForce GTX TITAN Z

 NVIDIA GeForce GTX TITAN Black

 NVIDIA GeForce GTX TITAN

 NVIDIA GeForce GTX 780 Ti

 NVIDIA GeForce GTX 780

 NVIDIA GeForce GTX 770

 NVIDIA GeForce GTX 760 Ti

 NVIDIA GeForce GTX 760

 NVIDIA GeForce GTX 760 (192-bit)

 NVIDIA GeForce GTX 760 Ti OEM

 NVIDIA GeForce GT 740

 NVIDIA GeForce GT 730

 NVIDIA GeForce GT 720

 NVIDIA GeForce GT 710

 NVIDIA GeForce GTX 690

 NVIDIA GeForce GTX 680

 NVIDIA GeForce GTX 670

 NVIDIA GeForce GTX 660 Ti

 NVIDIA GeForce GTX 660

 NVIDIA GeForce GTX 650 Ti Boost

 NVIDIA GeForce GTX 650 Ti

 NVIDIA GeForce GTX 650

 NVIDIA GeForce GTX 645

 NVIDIA GeForce GT 640

 NVIDIA GeForce GT 635

 NVIDIA GeForce GT 630

THIS IS A SPONSOR PROMOTION: >>>>>>>>>>>>>

Geekwills is an online shop that connects consumers with millions of products and brands around the world with the mission to empower them to live their best lives. Geekwills is committed to offering the most affordable quality products to enable consumers and sellers to fulfill their dreams in an inclusive environment.

The post Nvidia Releases 474.64 WHQL Graphics Driver, Fixes Many Security Issues appeared first on TechGoing.

The report said Foxconn is actively pursuing orders for B100 accelerator cards and plans to become the second supplier of B100 baseboards. However, unofficial sources say that NVIDIA is using Wistron to supply 100% of the substrates for the B100 accelerated card in the early stages of mass production due to a number of factors, including yield.

It is worth noting that Foxconn’s Honghe Technology is actively producing H100 products and is a strong contender for orders.

NVIDIA’s current suppliers of mainstream H100 series GPU modules and substrates are mainly Wistron Areson and Foxconn, and the rapid development of artificial intelligence has intensified the competition between assembly plants.

Wistron is the exclusive supplier of H100 substrates for NVIDIA’s DGX and HGX architectures, and also exclusively supplies motherboards and assembles AI servers for DGX. Wistron’s AI server-related products business continues to grow as shipments of H100 series AI servers based on NVIDIA’s DGX and HGX architectures steadily increase in the second half of the year.

THIS IS A SPONSOR PROMOTION: >>>>>>>>>>>>>

Geekwills is an online shop that connects consumers with millions of products and brands around the world with the mission to empower them to live their best lives. Geekwills is committed to offering the most affordable quality products to enable consumers and sellers to fulfill their dreams in an inclusive environment.

The post NVIDIA’s B100 accelerator card has entered the supply chain certification phase appeared first on TechGoing.

Modern chips are large-scale integrated circuits made up of hundreds of billions of transistors, and arranging them on tiny silicon wafers is one of the most difficult tasks in the tech industry, requiring tens of thousands of engineers to spend up to two years to complete.

The NVIDIA chip is so complex that it’s also at the heart of artificial intelligence technologies like ChatGPT.

This new research utilizes the big language models behind chatbots and data from NVIDIA’s 30-year archive of chip designs. One application uses the company’s long history of chip design to answer questions.

We’ve found that many senior designers spend a lot of time answering questions from junior designers,” said Bill Dally, NVIDIA’s chief scientist. Now we’re letting designers ask questions to chatbots, which saves senior designers a lot of time.”

The key finding of the study is that by adding a lot of company-specific data, even a regular chatbot can be more accurate than a senior chatbot. NVIDIA says this helps control system costs.

Another feature NVIDIA demonstrated was the use of artificial intelligence to generate code. Daley said engineers spend most of their time looking for possible problems in chips and using test tools to find out why.

The AI system can quickly generate scripts for test tools to test the designed chips.

Daley said, “The goal is not to automate processes or replace human roles, but to enhance the existing capabilities of employees and make them more efficient.”

THIS IS A SPONSOR PROMOTION: >>>>>>>>>>>>>

Geekwills is an online shop that connects consumers with millions of products and brands around the world with the mission to empower them to live their best lives. Geekwills is committed to offering the most affordable quality products to enable consumers and sellers to fulfill their dreams in an inclusive environment.

The post NVIDIA uses chatbots in the chip design process appeared first on TechGoing.