AMD Announces Vega & Navi GPUs With HBM2 & Nextgen Memory - Coming In 2022 And 2022

AMD has just officially unveiled its RX 500 series "Vega" GPU architecture & RX 600 sries "Navi" GPU architecture. Coming in 2022 and 2022 Respectively. The company confirmed that Vega GPUs will feature 2d generation vertically stacked retention technology "HBM2". Which includes very significant power efficiency and operation improvements over the outset generation technology institute in the R9 Fury X. Navi GPUs will feature "nexgen" retentiveness. A yet unnamed vertically stacked high bandwidth memory technology to succeed HBM2.

Raja Koduri, caput of Radeon Technologies Group, just revealed the company'due south future GPU architectures all of which volition exist named after stars, star systems and galaxies. The company'due south head of the newly founded Radeon Technologies Grouping explained that the team is heading towards a new direction with a fresh look on all things graphics and in that location was a need to reflect this change of winds.

AMD Radeon Technologies Group Bids A Somber Farewell To Island Lawmaking Names And Begins Its Journey Into Space

One of the most heady things almost AMD's next generation Polaris graphics architecture is the highly anticipated move to the revolutionary FinFET process technology. Which is accompanied by a considerable engineering focus to push innovations on architectural efficiency.

AMD has consistently said that the Polaris graphics architecture will deliver a "historic" leap in performance per watt. This unprecedented comeback in performance per watt is where the naming convention stems from. This is because stars are the most efficient photon generators in the universe,. Which explains why engineers at the visitor plant it only plumbing equipment to telephone call their most power efficient graphics architecture to date "Polaris" after the brightest star that can be seen from globe'due south surface.

Excerpt from AMD's Official Polaris Press Release :
AMD'south Polaris architecture-based 14nm FinFET GPUs deliver a remarkable generational leap in power efficiency. Polaris-based GPUs are designed for fluid frame rates in graphics, gaming, VR and multimedia applications running on compelling small form-factor sparse and light computer designs.

"Our new Polaris architecture showcases pregnant advances in performance, ability efficiency and features," said Lisa Su, president and CEO, AMD. "2016 will exist a very exciting yr for Radeon fans driven by our Polaris architecture, Radeon Software Crimson Edition and a host of other innovations in the pipeline from our Radeon Technologies Group."

The Great Ambitions Of The Radeon Technologies Grouping

Raja Koduri, vice president and primary builder of the Radeon Technologies Group explained before that he holds a very ambitious goal of powering 90% of the earth'southward pixels. To achieve that efficiency goal is key and just as stars are the earth'southward most efficient photon generators, Koduri wants AMD graphics technology to be the earth'southward most efficient pixel generators.

One of the more notable changes that the Radeon Technologies Group is doing is giving its next gen graphics architectures unifying code names. Something the company hasn't washed consistently in the by, non in any official capacity anyhow. Raja explained earlier in the yr that this change will make things easier for anybody involved. Whether it be internally at AMD, journalists or fifty-fifty consumers. Raja confirmed that of the company'southward hereafter graphics architectures volition be given astronomical lawmaking names. Polaris beingness the first that will brainstorm Radeon Technologies Group's re-invigorated journey into infinite.

Raja Koduri, Senior Vice President and Main Architect, Radeon Technologies Group, speaking with Venturebeat.com :

We have some heady hardware announcements as well. This is designed for FinFET. Our guiding principle for the Polaris architecture was power efficiency. Nosotros accept the new naming scheme for our architectures. It'll exist based on galaxies, star systems, and stars. Yous'll see more of this coming in the future. Polaris is the get-go of our journey through space.

VB: Does the Polaris brand supervene upon the Radeon brand?

Koduri: Information technology'due south an architecture codename. It'll still be Radeon something something on the box. But we didn't accept a consistent architecture name similar our competitors do. Information technology was hard, because for people, including yourselves and some of the press and enthusiasts—This family of chips has this architecture and a similar grade of features. You can grouping them hands together.

[Exclusive] Greenland Has Been Known Every bit "Vega ten" Internally For Some Fourth dimension

2 months ago nosotros published an exclusive story explaining what Vega 10 was and what had happened to the Radeon flagship Greenland GPU. Today at Capsiacin - GDC 2022 - AMD has confirmed exactly what we had conveyed to yous in that study.

Vega is the brightest star in the Lyra constellation and the 2d brightest star in the northern hemisphere. Vega along with Arcturus and Sirius, is 1 of the most luminous stars shut to our earth's own dominicus. Vega has been extensively studied by astronomers and as such was described as "arguably the next most important star in the heaven afterwards the Sun". Furthermore, it was the northern pole star effectually 12,000 BCE.

Vega was the first star other than the Sun to be photographed and the showtime to have its spectrum recorded. Just perhaps the most significant fact of all about Vega is that it served as the baseline for calibrating the photometric brightness scale, and was one of the stars used to define the mean values for the UBV photometric arrangement.

This preface is important in underlining why the Vega lawmaking proper name bears a special meaning for AMD and why engineers chose to give it to their well-nigh powerful 14nm GPU to date. Greenland / Vega 10 will be the first GPU from the company to feature HBM2 - High Bandwidth Memory - Technology. All of this is role of company's strategy to deploy this extremely ability efficient and innovative memory standard in its high-cease graphics products start and eventually into mainstream GPUs and even APUs.

Vega RX 500 series GPUs Coming In 2022 With 2nd Generation - HBM2 - Stacked High Bandwidth Retentiveness

The Fiji GPU powering the R9 Fury series is AMD's largest always graphics processing unit. Information technology'due south also the world'due south simply and first to feature the 3D structured, two.5D stacked High Bandwidth Retention, . This standard was co-invented by AMD and SK Hynix, one of the world's largest memory makers. The advantages of vertically stacking dies are many. One of which is the enablement of significantly greater densities versus GDDR5. Also because HBM cubes occupy a lot less space than GDDR5 engineers can achieve tremendous area savings on the printed circuit board of whatsoever HBM graphics card. This allowed for the creation of world's fastest SFF half dozen inch graphics card, the 8 teraflops R9 Nano.

At that place are also other innovations that HBM leverages. One of which is packaging. Because it sits next to the GPU on an interposer, a very short distance away,  it allows engineers to create immensely wider memory busses with reduced latency and very depression ability requirements. The stop result translates to a memory standard that'southward very power efficient, very area efficient and very scalable and very fast.

Earlier this year the Robert Hallock, technical marketing atomic number 82 at the Radeon Technologies Grouping confirmed to us that while the visitor is still committed to the Loftier Bandwidth Memory technology it co-invented with SK Hynix and brought to the market place last twelvemonth, Polaris was designed to be compatible with both HBM/HBM2 and GDDR5 memory standards. Technical marketing lead Robert Hallock explained that the company has the flexibility to utilize either engineering as needs arise. This means that either memory technology tin exist employed where it makes sense.

AMD helped lead the development of HBM, was the first to bring HBM to market in GPUs, and plans to implement HBM/HBM2 in future graphics solutions.

At this time we accept just publicly demonstrated a GDDR5 configuration of the Polaris compages.It's important to understand that HBM isn't (currently) suitable for all GPU segments due to the electric current HBM price structure. In the mainstream GPU segment, GDDR5 remains an extremely cost-constructive, efficient and feasible retention technology.

HBM Is Essential Going Forrad

It'due south at present clear that the Radeon Technologies Group's plan is to introduce HBM2 applied science with it'south upcoming Vega graphics architecture, which will be launching next year. HBM2 is the second generation of the vertically stacked High Bandwidth Retentiveness standard that AMD introduced last yr with its flagship Radeon R9 Fury 10 graphics card, the R9 Fury and the R9 Nano.

Second generation High Bandwidth Memory is not only faster than the first generation but information technology also scales to capacities 8 times larger than HBM1. HBM2 feature 1GB per die and up to 8 Hi stacks for 8GB per cube. Which is eight times more than the highest capacity currently available per cube on HBM1. Additionally, HBM2 operates at twice the speed of HBM1 for double the retentivity bandwidth.

This means that engineers tin can equip the company's flagship Vega ten GPU with up to 32GB of super high speed HBM2 memory for a total of terabyte/southward of memory bandwidth. However nosotros'll have to wait until 2022 for the 14nm process engineering science and the HBM2 technology to mature enough for such a monstrous chip. Polaris graphics cards on the other hand are coming out this summer, before the back to schoolhouse season, on both desktops and gaming notebooks.

AMD Radeon Graphics Architectures

WCCFTech	Year	Consumer Production	GPU	Process	Transistors In Billions	Performance	Memory	Bandwidth
Southern Islands	2012	HD 7970 Ghz	Tahiti	28nm	4.iii	4.one TFLOPS	3GB GDDR5	264GB/s
Volcanic Islands	2013	R9 290X	Hawaii	28nm	vi.two	five.6 TFLOPS	4GB GDDR5	320GB/s
Caribbean Islands	2015	R9 Fury 10	Republic of the fiji islands	28nm	8.9	8.half dozen TFLOPS	4GB HBM1	512GB/s
POLARIS	2016	RX 480	Polaris 10	14nm	5.7	v.ii TFLOPS	8GB GDDR5	256 GB/s
VEGA	2017	RX Vega 64	Vega 10	14nm	12.5	thirteen TFLOPS	8GB HBM2	480GB/s
VEGA Refresh VEGA 2	2018 2022	TBA TBA	TBA Vega 20	12nm 7nm	12.5 TBA	TBA TBA	TBA 32GB HBM2	TBA one TB/south
NAVI	2019	TBA	Navi ten	7nm	TBA	TBA	Nextgen Memory	TBA

Source: https://wccftech.com/amd-unveils-polaris-vega-navi-graphics-architectures-hbm2/

Posted by: aguilarsals1979.blogspot.com

Share this post