Radeon Technologies Group

[Zavtekirou]

Boa tarde,

O problema da Radeon Group é que cada vez mais as gráficas dedicadas são um mercado de nicho. Cada vez mais as gráficas dos SoC chegam e bastam para as necessidades da grande maioria das pessoas. Por isso mesmo que retornem a ter uma boa quota de mercado nas gráficas dedicadas não esperem que estas venham a ser o salva vidas financeiro da AMD.

Cumprimentos.

[Jorge-Vieira]

AMD is Willing To Make ’14nm FinFET’ GCN Based Mobile GPUs For The Right Customer

AMD is still open to making GPUs for the mobile market according to a statement by Raja Koduri (via ITWorld). The company sold off its mobile division to Qualcomm back in 2009, which uses the technology to make Adreno GPUs, but AMD has stated that if it is offered a particularly lucrative licensing agreement or custom chip deal – it will be willing to offer its services in the low-power GPU department.

AMD is ready to design low-power GCN GPUs for the mobile sector if it gets the right offer

AMD’s GPU architecture has a very modular design philosophy. Built rather like legos, AMD’s GPU architecture can be modified at will to various power/performance scenarios – something that allows it to be incredibly flexible in terms of custom deals and agreements. Qualcomm built on its original mobile division to create Adreno GPUs (which is an anagram for Radeon by the way) and while it is doing pretty darn well, AMD wouldn’t say no to an offer to make a custom chip solution in the mobile market.

The company is open to making a graphics processor for mobile devices based on its Radeon product line, but only in select circumstances, said Raja Koduri, senior vice president and chief architect of AMD’s Radeon Technologies Group.
Advertisements

AMD could make a mobile GPU as part of a partnership or a licensing deal, but otherwise has no active plans to build an end product for mobile devices, Koduri said this week (via ITWorld).

AMD’s forays into the custom chip world has already yielded promising results. Having already shipped over 50 Million customized solutions (APUS) for the Xbox One and PS4, it is looking out for any deal that can boost its revenue streams. The red chip maker has access to cutting edge GPU technology as well as an incredibly refined power efficiency philosophy – both of which are ideal characteristics of a mobile GPU with a low power draw. This is in contrast to Nvidia – which has so far, focused more on performance rather than power efficiency (something that started to change with Maxwell and should be perfected by the arrival of Pascal on FinFET).
AMD recently unveiled its Polaris architecture which offers a 2.5 times increase in performance per watt over the 28nm base line of the last generation. Keep in mind however, that Qualcomm has already shifted over to 14nm FinFETs with the Adreno 530 GPU (which boasts support for Vulkan API) so any increase in performance will have to be through architectural gains. AMD is probably the only company in the world right now that can offer a better GPU package than Qualcomm for mobility purposes.
However, as stated by Raja Koduri, they have no plans to do so unless and until they get a specialized offer. This involves the likes of a partnership agreement or long term custom chip agreement, both of which are relatively unlikely in the mobile GPU arena. Still, AMD’s architecture has a few inherent strengths that could be desirable to a big mobile player in the future – but until that happens, AMD will keep the door open for prospective customers.

Noticia:
http://wccftech.com/amd-willing-14nm-gcn-mobile-gpu-right-customer/#ixzz43Ss5y9BV


Agora é o próprio Raja Koduri que abre as portas a um eventual negocio com os chips Radeon, por isso o Radeon Group está apostar em fazer dinheiro em caixa.

[Enzo]

Boa tarde,

O problema da Radeon Group é que cada vez mais as gráficas dedicadas são um mercado de nicho. Cada vez mais as gráficas dos SoC chegam e bastam para as necessidades da grande maioria das pessoas. Por isso mesmo que retornem a ter uma boa quota de mercado nas gráficas dedicadas não esperem que estas venham a ser o salva vidas financeiro da AMD.

Cumprimentos.

Têm de começar por algum lado.
Além de que alguem falou aqui recentemente precisamente o contrário: "a AMD quis os APUs, quando é um nicho de mercado"
Por mim, APUs serve para lols rockets leagues e afins. AAA games, é gráfica à macho!

[Zavtekirou]

Boa tarde,

O futuro serão os SoC. A evolução que tem tido prova isso mesmo. Não me surpreenderá o dia em que um SoC terá mais capacidade que a maioria das gráficas dedicadas. Hoje em dia já se equiparam a gráficas mid-end, por isso mesmo se vê para onde a indústria caminha.

As gráficas dedicadas acabarão por ficar para servidores e coisas do género.

Cumprimentos.

[Jorge-Vieira]

Têm de começar por algum lado.
Além de que alguem falou aqui recentemente precisamente o contrário: "a AMD quis os APUs, quando é um nicho de mercado"
Por mim, APUs serve para lols rockets leagues e afins. AAA games, é gráfica à macho!

Enzo, os APUs não é um nicho de mercado, todas as consolas (PS 4 e X1) têm um APU e a AMD tem feito bom dinheiro com isso.
Só é um nicho de mercado se te referires à parte PC.

[Enzo]

Sim, precisamente.
Até eu próprio disse que a NX iria fazer com que a AMD fizesse o pleno

Kystic, acho estranho se isso vier a acontecer. Penso que isso era eliminar um mercado gigantesco sem necessidade.
Aumentem é a potencia das graficas dedicadas para que haja mais diferenca entre elas e mercados distintos para elas.

[Jorge-Vieira]

Sim, isso é evidente.
A nVidia não está virada para as consolas e, neste momento nem precisa.

[Zavtekirou]

Boa noite,

A Nvidia já chegou ao ponto de começar a ter dispositivos seus e tudo. Há um mundo de diferença entre a AMD e a Nvidia. Sinceramente acho que a Nvidia já nem encara a AMD como competição a sério. A Intel o mesmo nos processadores.

Neste momento a AMD tem de lutar em duas frentes contra adversários diferentes mas igualmente muito maiores, com muito mais recursos e que ocupam fatias maioritárias do mercado. Tarefa muito complicada. Acho que a AMD acabará por ser comprada, mas como é americana não vejo o governo a permitir que seja a Samsung a fazer tal compra. Daí que tenha de ser uma empresa americana também.

Cumprimentos.

[Enzo]

Eu acredito. Agora, é esperar para ver.

[Jorge-Vieira]

AMD Open to Making Mobile GPUs

Looking back, AMD missed a big opportunity to get into the mobile phone and tablet market. According to Raja Koduri, SVP for RTG, AMD may be contemplating getting back into the mobile graphics market, provided the circumstances are right.
Originally a part of ATI, the mobile graphics division, Imageon was acquired by AMD along with the parent company. After running into severe financial hardship, AMD decided to sell the mobile division off to Qualcomm which renamed it Adreno, an anagram of Radeon. Combined with their custom ARM CPUs, Qualcomm has managed to become the largest mobile SoC vendor, putting Adreno into millions of devices. The only other major competitors are Imagination and Mali from ARM itself.
By considering the mobile GPU market if the right customer comes by, AMD is opening yet another market for them to enter. Right now, Adreno is still largely based on the VLIW architecture that ATI and AMD left in 2011. GCN, on the other hand, is a more complex and advanced architecture with arguably better performance per watt. With the rise of GPU based compute being used in gaming, GCN may be a potent force in tablets.
Seeking more custom chip customers makes sense of AMD given that their consoles deals are helping keep the firm afloat as other sources of revenue are dropping. There is a large measure of risk however as Nvidia has demonstrated with their flagging Tegra lineup. By securing a customer first, AMD can pass on the risk and run a much safer course. Perhaps, the next PSP or DS will be running GCN.

Noticia:
http://www.eteknix.com/amd-open-to-making-mobile-gpus/


Mais uma noticia que dá conta da vontade da AMD/Radeon Group entrar no mercado móvel e, na minha opinião acho que o devem fazer, a arquitetura GCN é multifacetada, poderosa e se chegar a dispositivos móveis poderemos ver ainda maiores aumentos de performance.

[Enzo]

Acho que é mais uma forma de fazerem guito, nem mercado que promete não abrandar assim tão cedo. Qualquer dia vemos telemoveis AMD por ai.

[Zavtekirou]

Boa noite,

No mercado móvel não há espaço para gráficas móveis dedicadas, é tudo SoC. A AMD se quer entrar no mercado móvel é com APU's em SoC. Mas mesmo assim já entra bem atrasada. A Intel que é a Intel entrou atrasada também e não tem muita percentagem de mercado fará a AMD coitada.

Cumprimentos.

[Jorge-Vieira]

AMD’s Vega 10 GPU Expected To Feature 4096 GCN 4.0 Stream Processors – Flagship Chip of Graphic IP v9.0 Generation

AMD unveiled their next generation Polaris, Vega and Navi graphics architectures at Capsaicin 2016. The event highlighted the upcoming generation of graphics architecture which will feature the latest iteration of the GCN cores available at the time of their launch. While AMD’s upcoming generation of Polaris graphics cards is going to give Radeon a boost in the performance per watt department, the generation after that, codenamed Vega, is going to take performance to a whole new level.

The latest AMD GPU Architecture Roadmap was showcased at Capsaicin 2016.

AMD’s Vega 10 GPU Features 4096 GCN 4.0 Stream Processors, Flagship GPUBased on the Vega Architecture, 14nm FinFET Process

The latest details on AMD’s upcoming generation of graphics architecture comes straight from Videocardz (via 3DCenter). The sources managed to find some very critical details on AMD’s upcoming Vega GPU which has also been known as Greenland. The decision to name AMD GPUs after stars rather than Islands happened after the Radeon Technology Group was formed which is being led by Raja Koduri. Under his leadership, the team at RTG presented their first roadmap to the audience at Capsaicin 2016.
According to the LinkedIn profile of Yu Zheng who is the manager of research and development at AMD, the upcoming Greenland GPU at its peak capacity, will feature 4096 stream processors. These are not the current generation stream processors but utilize the advancements made in the IP v9.0 generation of graphics SOCs under development by AMD. It is also noted that this chip is the “Leading Chip” of the first graphic IP v9.0 chip generation. You can see the image to the profile and listed details below:

The Linkedin Profile of an AMD employee has revealed the specs of AMD’s flagship Vega GPU.

Following the same approach as NVIDIA who put forward a roadmap for their upcoming GPUs, we got to see two new products, Vega and Navi. We know very well that AMD’s Polaris architecture currently comprises of two chips. The Polaris 10 is the high-end graphics core which was demoed at Capsaicin while the Polaris 11 is the entry level graphics core which was demoed back at CES 2016. Both chips are based on the 14nm FinFET architecture from Global Foundries and are expected to feature up to 2.5x the performance per watt compared to the currently available GCN revision.

Radeon Pro Duo is just the beginning, expect more HBM GPUs from AMD and NVIDIA in 2016-2017.

Specifications of both Polaris 10 and Polaris 11 chips are leaking for a while now. The latest ones are quite juicy so do give them a look. The more surprising bit about the Capsaicin 2016 event was that the Polaris GPU wasn’t going to use HBM2, the latest update to the HBM2 roadmap. AMD sighted the price of HBM2 DRAM chips as the issue right now. That’s where Vega comes in.
READ [UPDATED] AMD Responds To Cease And Desist Letter From Asetek

GPU Family	AMD Polaris	AMD Vega	NVIDIA Pascal

GPU Family	AMD Polaris	AMD Vega	NVIDIA Pascal
Flagship GPU	Polaris 10	Vega 10	NVIDIA GP100/GP200
GPU Process	GloFo 14nm FinFET	GloFo 14nm FinFET	TSMC 16nm FinFET
GPU Transistors	TBC	15-18 Billion	~17 Billion
HBM Memory (Consumers)	GDDR5/X	HBM2	Up to 16 GB (SK Hynix/Samsung) HBM2
HBM Memory (Dual-Chip Professional/ HPC)	GDDR5/X or HBM	HBM2	32 GB (SK Hynix/Samsung) HBM2
HBM2 Bandwidth	512 GB/s	1 TB/s (Peak)	1 TB/s (Peak)
Graphics Architecture	GCN 4.0 (Polaris)	GCN 4.0 (Vega)	Next-CUDA (Compute Oriented)
Successor of (GPU)	Fiji (Radeon 300)	Polaris 10 (Radeon 400)	GM200 (Maxwell)
Launch	2016	2017	2016-2017

AMD’s Vega GPU Will Be a Compute Beast, FirePro and HPC APUs With High Amount of FP64 Compute Expected in 2017

In the past, we have had many details pop up on a rumored Greenland GPU. We saw it mentioned in FirePro slides, HPC APU slides, even as the fastest GCN based GPU. We now know that Greenland is in fact the Vega GPU and not just any Vega GPU, the flagship Vega 10 GPU. The whole reason that Vega has been shown as the only HBM2 graphics part leads us to believe that it will not be aimed at just Radeon graphics cards but at the HPC market.
Advertisements

AMD Vega 10 Will Be Compute Monster With 4096 SPs and HBM2 On Board.

Knowing how NVIDIA will deploy their HBM2 Pascal GPUs on HPC front this year, AMD will tackle those and take a slice at HPC with their own modern day, double precision compute graphics cores. The Vega 10 GPU with next generation of HBM2 memory will be aiming at the heart of HPC computing in FirePro cards and HPC APUs. This might also prompt AMD to release a next generation successor to the Radeon Pro Duo with unprecedented amounts of TFLOPs and more power aimed at developers.
As mentioned before, the Vega 10 GPU is expected to feature as much as 32 GB of HBM2 VRAM along with 18 billion transistors crammed underneath its die that is manufactured on the latest 14nm process node. This will make Vega a true professional offering but that doesn’t mean the card won’t be built for gamers. As always, AMD will pay just as much attention to the PC gaming market as the high-performance market. AMD will have range of new graphics card that will deploy the Vega GPU architecture that enhance upon the performance and architecture of Polaris.
READ NVIDIA GeForce GTX 980 Ti With GM200 GPU Possibly Arriving in Q2 2015 - Custom Variants Get Greenlight

AMD Polaris and Vega Will Have Key Architecture Differences, Polaris is More Close To Fiji Than Vega

Since this article is about Vega, we might just as well let you know about some key details dug up by PCTuning Forums which reveals that the Polaris architecture, while being an updated architecture compared to Fiji is still more close to it. The While Vega 10 is part of the Graphics IP v9.0 architecture, Polaris is still part of the IP v8.0 family which is the same as current Fiji graphics cards. Following are the different architecture blocks and their respective revision number as compiled by the forum members:

Table Courtesy/Credits: PCTuning Forums

• GMC – Graphics Memory Controller
• IH – Interrupt Handler
• SMC– System Management Controller
• DCE – Display Controller Engine
• GFX – Graphics IP Revision
• SDMA – System Direct Memory Access
• UVD – Unified Video Decoder
• VCE – Video Coding Engine

Using the same LinkedIn profile we mentioned above, we came to know that AMD’s Fiji is part of the graphics IP v8.0 family, the same family which Polaris chips (Ellesmere and Baffin) have also showed up to be a part of. Vega on the other hand is mentioned to be part of the Graphics IP v9.0 family which seems to be more modern than current generation of graphics processors from AMD. Although this is just speculation at the moment and AMD have shown slides that detail the new Polaris architecture having several new graphics blocks embedded with in it.

AMD Polaris is (Graphics IP v8.0) and Vega is (Graphics IP v9.0)

That along with the fact that AMD is getting up to 2.5x performance per watt enhancements out of their core which is something that just a process revision can’t offer so it is very clear that architecture changes are made by AMD in their upcoming Polaris graphics cards. It is fine to have some hardware blocks on Polaris to be same as GCN 3.0 architecture which is also a fine tuned version of their GCN architecture. It’s really getting interesting with all the leaks surrounding Polaris and Vega, we expect to hear more in the months ahead.

Noticia:
http://wccftech.com/amd-vega-10-4096-stream-processors/#ixzz445mEzv7P



A ser verdade o que aqui está descrtio, temos o chip Vega com 4096 Stream Processors, que é a mesma quantidade presente nas actuais Fury X, acho que seria expectável um aumento considerável para estas unidades (isto se área do chip for identica), tendo em conta o menor processo de fabrico. Por isso espero que isto não seja uma Fury X 2 apenas com HBM 2.0, mas sim algo mais evoluido.
Outro pormenor, é que o Vega fará parte de uma nova serie de placas graficas, dado que a noticia dá o Vega como sucessor das proximas R9 400.













AMD's next-gen Vega 10 GPU should rock 4096 GCN 4.0 cores and HBM2

AMD laid out its GPU architecture roadmap through to 2019 at its huge Capsaicin event during the Game Developers Conference, but now we're hearing rumbles on its exciting new Vega GPU - due out in 2017.






Vega will reportedly rock a huge 4096 stream processors based on the Greenland GPU, with improvements in the way of the GCN 4.0 architecture, which are included in the IP v9.0 generation of graphics chips under development from AMD.

We should expect Vega 10 to be AMD's flagship product from the Greenland GPU era - rocking somewhere between 15-18 billion transistors, and the exciting new HBM2 technology which offers up to 1TB/sec of memory bandwidth. Vega looks like it'll be fighting against NVIDIA's compute-powerful GP100 (the Pascal-based successor to the GTX Titan X and GTX 980 Ti) - as Vega is the only HBM2-powered card on AMD's roadmap for 2017.


This brings us to the question of "what will Polaris be, if Vega features HBM2" - and the answer is Polaris is closer to the Fiji architecture, with massive power savings thanks to the 14nm FinFET process. Vega on the other hand, is AMD's huge answer to a successor to Fiji - and something that will fight off the GP100 beast from NVIDIA.

We will be at NVIDIA's GPU Technology Conference next week, so expect us to deliver some great GPU content in just over a week's time!

Noticia:
http://www.tweaktown.com/news/51294/...bm2/index.html














AMD Greenland/Vega may be Fiji Replacement at 4096 GCN Shaders

This year, both AMD and Nvidia will be launching their new Polaris and Pascal based GPUs. Unfortunately, it looks like the flagship chips won’t be arriving till next year. Set to arrive in early 2017, Vega, also known as Greenland, is to be the flagship replacement for Fiji. According to information 3DCenter dug up, Vega will feature 4096 GCN shaders, the same amount as Fiji currently has.
With Polaris and Vega, there are suggestions that AMD has managed to improve GCN 4.0’s performance by 30% compared to current GCN offerings. This alone should allow a significant performance increase over the Fury X. Fiji was also limited due to the design of GCN being unoptimized for massive chips with too many shaders and if AMD has managed to fix this, Vega will perform better than expected.
Furthermore, Vega will utilize HBM2 which will finally remove the 4GB cap faced by HBM GPUs as well as reduce latency. The use of 14nm as well and other Polaris improvements will also allow for a cooler and less power hungry die. We can also expect Vega to come in at a die size similar to Hawaii rather than Fiji, with a true Fiji size successor to come later on in the process cycle.

Noticia:
http://www.eteknix.com/amd-greenland...6-gcn-shaders/

[Jorge-Vieira]

AMD Pledges to Take On NVIDIA’s Turing With 7nm Radeon GPUs in 2019

We’re nearing the end of what has been quite the wild year for graphics. Initially plagued by an exceedingly frustrating inflation of GPU prices caused by the crypto bubble which had only tapered off to end on an equally frustrating note of a very expensive NVIDIA RTX Turing product lineup.
Well, the crypto bubble has burst, the graphics channel is oversaturated with unsold GPU inventory and we’re on the cusp of an entirely new generation of graphics products based on TSMC’s leading edge 7nm FinFET process. Suffice to say, 2019 is shaping up to be the polar opposite of what 2018 has been for the discrete graphics market.

SPONSORED CONTENT
Transfer your debt to a card with 0% interest until 2020
By CompareCards


With 7nm At Hand, AMD is Getting Ready to Tango With NVIDIA’s Turing

At least that’s what CEO Dr. Lisa Su wants us to believe. Take a listen to what she had to say last week when asked about how the company plans to compete with NVIDIA’s new ray tracing focused Turing graphics architecture.

AMD CEO Lisa Su – Nov 27, 2018 – 22nd Annual Credit Suisse Technology, Media & Telecom Conference
“We believe, we will be very competitive overall and that includes the high-end of the GPU market. Obviously there are new products out there from our competition. We will have our set of new products as well and we will be right there in the mix”
“As it relates to ray tracing in particular I think it’s an important technology, but as with all important technologies it takes time to really have the ecosystem adopt [it]. And we’re working very closely with the ecosystem on both hardware and software solutions and expect that ray tracing will be an important element especially as it gets more into the mainstream, frankly, of the market.”
– Transcripted by Wccftech.com

This builds on Dr. Su’s comments at an interview with Barron’s a month prior where she asserted that AMD will be “competitive in high-end graphics,” and that AMD is “making high-performing quality products and building a solid long-term foundation.”

Noticia completa:
https://wccftech.com/amd-pledges-to-...-gpus-in-2019/

Pelo menos vontade de fazer mais e melhor existe, a ver se em 2019 temos efetivamente novos GPUs da AMD capazes de competir com a nVidia em todos os segmentos de mercado, nós consumidores agradeciamos.

[Enzo]

Gosto! Estou à espera dessas novidades. A grande diferença é que a Nvidia nunca adormeceu como a Intel, por isso vai dar bem mais luta.