Intel: Return to the discrete graphics market: Xe GPU development is progressing well

Today’s news, Intel announced that it will return to the discrete graphics market after a 20-year hiatus, confirming that the development of Xe GPU is progressing smoothly.

It is reported that in the company's recent financial report, Intel stated that its low-power GPU codenamed DG1 has already begun shipments, and may appear on PC products for the market this holiday (may refer to Christmas).

However, Intel also admitted frankly that the chip is still in the early testing stage, and according to the market, it will have to wait for a while, but the overall project progress and chip test performance are satisfactory to the team.

It is reported that Intel divides the GPU (Xe) product line into four categories, namely low power consumption (LP), high-performance gaming (HPG), high-performance (HP) and high-performance computing (HPC), which correspond to each Class users.

According to sources, the aforementioned code-named DG1 belongs to Intel's low-power product line, based on Intel's 10nm SuperFin process to create 96 EU (execution unit, equivalent to 8 shaders) GPU. Judging from the previously exposed benchmark data, the product has a frequency of up to 1.5GHz and is equipped with 3GB of video memory.

In addition, Bob Swan also said that DG1 will only appear in branded desktops in the early days, and will appear in the systems of multiple OEMs later in the fourth quarter.

Comments

What are the areas of Intel Xeon E3, E5, E7 processors

Xeon E3 is a single-socket processor series for workstations and entry-level servers, Xeon E5 is a processor series for high-end workstations and servers, and Xeon E7 is a processor series for mission-critical and data centers. The following is a detailed introduction: 1. Xeon and Core are similar to Intel's processor series, and Xeon processors are mainly used for professional-grade and server products, similar to Core i3, i5, i7 three series. 2. The Xeon E3 processor is mainly for low-end servers and microservers, generally used for website hosting and cloud services, designed to handle a large number of light network transactions or cloud transactions, such as used in search queries and social networks The effect of the web page. 3. The Xeon E5 is mainly used for entry-level dual-socket servers, high-performance dual-socket and quad-socket servers, and is currently the most widely used mainstream server processor. 4. Xeon E7 is Intel's highest performance server proce...

Apple's self-developed computer processor, bid farewell to Intel CPU

American Apple announced on June 22 that it will install a self-developed CPU (central processing unit) on the personal computer "Mac". Since adopting Intel CPU in 2006, Apple will replace it after about 15 years. In addition to reducing the power consumption of the computer using the new CPU, it is also easy to collaborate with the iPhone. Apple held its annual developer conference "WWDC" online on June 22 and announced the news at the conference. Apple CEO Tim Cook (Reuters), who attended the online annual developer conference "WWDC", first put self-developed CPUs on some new Mac products that will be launched before the end of 2020. After that, it took about 2 years to change the CPU of all models to its own products. Apple has joined hands with ARM Holdings, which provides semiconductor design support, and the production is expected to be entrusted to Taiwan Semiconductor Manufacturing (TSMC, TSMC). Apple Chief Executive Officer (CEO) Tim Cook s...

Intel showcases smart edge and energy-efficient performance research results at 2020 VLSI seminar

At this week's 2020 VLSI Technology and Circuits Symposium, Intel will introduce a series of research results and technical perspectives on the transformation of computing caused by the growing data distributed on cores, edges, and endpoints. CTO Mike Mayberry will deliver a keynote speech entitled "Future Computing: How Data Transformation Reshapes VLSI", emphasizing the importance of transitioning from hardware/program-centric computing to data/information-centric computing. "There is a huge amount of data flow on the distributed edge, network and cloud infrastructure, which requires high energy efficiency and powerful processing near the location where the data is generated, but this processing is often constrained by bandwidth, memory and power resources The Intel Research Institute highlighted several new methods for improving computing efficiency at the VLSI seminar. These methods show the broad prospects of various application fields, including robotics, aug...

server-Intel

Search This Blog