-
- News
- Books
Featured Books
- pcb007 Magazine
Latest Issues
Current IssueThe Growing Industry
In this issue of PCB007 Magazine, we talk with leading economic experts, advocacy specialists in Washington, D.C., and PCB company leadership to get a well-rounded picture of what’s happening in the industry today. Don’t miss it.
The Sustainability Issue
Sustainability is one of the most widely used terms in business today, especially for electronics and manufacturing but what does it mean to you? We explore the environmental, business, and economic impacts.
The Fabricator’s Guide to IPC APEX EXPO
This issue previews many of the important events taking place at this year's show and highlights some changes and opportunities. So, buckle up. We are counting down to IPC APEX EXPO 2024.
- Articles
- Columns
Search Console
- Links
- Events
||| MENU - pcb007 Magazine
CES Press Day: NVIDIA, Samsung, and Intel
January 11, 2019 | Dan Feinberg, Technology Editor, I-Connect007Estimated reading time: 8 minutes
Three major companies—NVIDIA, Samsung, and Intel—had lengthy, interesting presentations on CES press day, and each had with their own agenda.
NVIDIA
The first company was NVIDIA with CEO and Founder Jensen Huang making the presentation. The presentation started with a quick update on NVIDIA’s autonomous driving, which has been a major focus for them over the past few years. In fact, the NVIDIA booth has been and will be in the automotive area again this year.
We were soon informed, however, that this year’s presentation would focus totally on computer graphics and gaming. NVIDIA’s lengthy presentation felt like Jensen Huang talking through demo after demo, showing the capabilities of their new generation of graphics processing units (GPUs) and doing what no other can do yet by showing ray tracing at its absolute best. The demos were live—not videos—and they were gorgeous and impressive, brimming with vibrant, lifelike reflections with exquisite details. They were more lifelike than real life. More impressive was the fact that according to Huang—who told us at the very end—they were all powered by an RTX 2060 (accompanied by an Intel Core i9-9900X CPU and 32 GB of RAM) performing ray tracing in real time.
These demonstrations were not done with the top-of-the-line RTX 2080Ti, as we all assumed. They showed the performance possible with the just-announced RTX 2060. The 2060 is priced at less than half of the top end 2080.
If anything will make NVIDIA’s sales of the new generation GPU take off, it will be the amazing performance and high value of the 2060 based on its announced price and demonstrated performance. NVIDIA says that it is DLSS, which gets the credit. DLSS is essentially an AI-powered way to improve visuals. It can take a lower-res image, and using AI, learn what pixels need to be added to show real-life reflections. Thus, this improves what is on the screen while achieving higher frame rates with a middle of the range—albeit latest generation—GPU.
Showing a live demo of Battlefield V at 1440-p resolution, the system reached nearly 70 FPS with RTX off. With ray tracing enabled, performance dropped to about 55 FPS. But when they turned on DLSS, performance bounced back to where it was with ray tracing disabled. In addition to the low price of $399, NVIDIA will be giving free copies of some top games with an RTX GPU purchase.
The card will offer 52 teraflops of Tensor Core processing power, can handle 5 Gigarays per second, and features a 6-GB frame buffer. Historically, the GTX xx60 series has been the entry-level version of the GeForce series, although they have always performed well for the price, providing good value. The RTX 2060 per NVIDIA will offer somewhere between 1.4 and two times the performance benefit over its last generation GTX 1060. That makes it faster than the last generation GTX 1070Ti cards, which were one level higher.
There were other announcements such as the soon-to-be-available series of notebooks using portable versions of the new GTX generation. Also, there are some very high-end monitors available that take advantage of the next-generation NVIDIA sync, but the focus for most of us as we left the arena was that NVIDIA showed off ray tracing and amazed us while doing so. Further, they did it with a fairly priced middle-of-the-road next-generation CPU that he had just announced. Oh yes, and how did Huang describe this impressive device? He called it cute.
Page 1 of 3
Suggested Items
TSMC Celebrates 30th North America Technology Symposium
04/29/2024 | TSMCTSMC unveiled its newest semiconductor process, advanced packaging, and 3D IC technologies for powering the next generation of AI innovations with silicon leadership at the Company’s 2024 North America Technology Symposium.
CACI Awarded $1.3 Billion Task Order to Provide Communications and Information Technology Expertise
04/26/2024 | CACI International Inc.CACI International Inc announced that it has been awarded a five-year task order worth a total estimated value of $1.3 billion to provide communications and information technology expertise to U.S. European Command (USEUCOM) and U.S. Africa Command (USAFRICOM).
Intel Gaudi, Xeon and AI PC Accelerate Meta Llama 3 GenAI Workloads
04/22/2024 | Intel CorporationMeta launched Meta Llama 3, its next-generation large language model (LLM). Effective on launch day, Intel has validated its AI product portfolio for the first Llama 3 8B and 70B models across Intel® Gaudi® accelerators, Intel® Xeon® processors, Intel® Core™ Ultra processors and Intel® Arc™ graphics.
Cadence Unveils Palladium Z3 and Protium X3 Systems
04/18/2024 | Cadence Design SystemsThe Palladium Z3 and Protium X3 systems offer increased capacity, and scale from job sizes of 16 million gates up to 48 billion gates, so the largest SoCs can be tested as a whole rather than just partial models, ensuring proper functionality and performance.
IDTechEx Explores the Role of 3D Cu-Cu Hybrid Bonding in Powering Future HPC and AI Products
04/18/2024 | PRNewswireSemiconductor packaging has evolved from traditional 1D PCB levels to cutting-edge 3D hybrid bonding at the wafer level, achieving interconnecting pitches as small as single micrometers and over 1000 GB/s bandwidth. Key parameters, including Power, Performance, Area, and Cost, are crucial considerations