Radeon Technologies Group

[Jorge-Vieira]

AMD GPU Roadmap: Capsaicin Names Upcoming Architectures

Some Hints as to What Comes Next

On March 14 at the Capsaicin event at GDC AMD disclosed their roadmap for GPU architectures through 2018. There were two new names in attendance as well as some hints at what technology will be implemented in these products. It was only one slide, but some interesting information can be inferred from what we have seen and what was said in the event and afterwards during interviews.
Polaris the the next generation of GCN products from AMD that have been shown off for the past few months. Previously in December and at CES we saw the Polaris 11 GPU on display. Very little is known about this product except that it is small and extremely power efficient. Last night we saw the Polaris 10 being run and we only know that it is competitive with current mainstream performance and is larger than the Polaris 11. These products are purportedly based on Samsung/GLOBALFOUNDRIES 14nm LPP.

The source of near endless speculation online.
In the slide AMD showed it listed Polaris as having 2.5X the performance per watt over the previous 28 nm products in AMD’s lineup. This is impressive, but not terribly surprising. AMD and NVIDIA both skipped the 20 nm planar node because it just did not offer up the type of performance and scaling to make sense economically. Simply put, the expense was not worth the results in terms of die size improvements and more importantly power scaling. 20 nm planar just could not offer the type of performance overall that GPU manufacturers could achieve with 2nd and 3rd generation 28nm processes.
What was missing from the slide is mention that Polaris will integrate either HMB1 or HBM2. Vega, the architecture after Polaris, does in fact list HBM2 as the memory technology it will be packaged with. It promises another tick up in terms of performance per watt, but that is going to come more from aggressive design optimizations and likely improvements on FinFET process technologies. Vega will be a 2017 product.
Beyond that we see Navi. It again boasts an improvement in perf per watt as well as the inclusion of a new memory technology behind HBM. Current conjecture is that this could be HMC (hybrid memory cube). I am not entirely certain of that particular conjecture as it does not necessarily improve upon the advantages of current generation HBM and upcoming HBM2 implementations. Navi will not show up until 2018 at the earliest. This *could* be a 10 nm part, but considering the struggle that the industry has had getting to 14/16nm FinFET I am not holding my breath.
AMD provided few details about these products other than what we see here. From here on out is conjecture based upon industry trends, analysis of known roadmaps, and the limitations of the process and memory technologies that are already well known.
Click here to read the rest about AMD's upcoming roadmap!
HBM1 is Limited in Next Gen Parts
I cannot discount the use of HBM1 technologies in certain higher end products to be used by AMD and NVIDIA, but it does appear to have too many limitations when considering these next gen parts. The biggest limitation is the 4GB of total memory that the technology currently supports. HBM2 increases this up to 32 GB, but that technology is nowhere near ready for introduction. Samsung has already started producing HBM2 parts, but quantities are unknown. SK Hynix, one of the primary partners with AMD for developing HBM, is not starting mass production of HBM2 until Q3 of this year.

The interposer and stacked memory allows high bandwidth, low latency communication with onboard memory. HBM1 is limited to 4GB though.
Power savings and PCB space are big positives for HBM, but when we consider overall bandwidth it is not that much greater than other high end GDDR-5 implementations such as the GTX 980 Ti. The FuryX features around 500 GB/sec of bandwidth while the GTX 980 Ti is not that far behind with 336 GB/sec. When we look at overall video card performance between these competing products, the differences are not that great. Everyone loves bandwidth, but it is seemingly not the limiting factor in high end implementations right now. HBM2 might expose this as a myth as it provides 1 TB/sec of bandwidth in its full implementation, but we are still many months away from having enough HBM2 memory to satisfy demand for a consumer level product.
All indications point to GDDR-5 and GDDR-5X as being the primary memory types that we will see in the next generation parts. 4GB just is not enough for these upcoming cards so HBM1 is right out. 8 GB is going to be the baseline for products ranging from $300 and up. HBM2 is not going to be available until much later this year. When we look at the situation, GDDR-5 and 5X are the only options to provide the required memory capacity. AMD and NVIDIA have relatively large caches as well as significant design expertise in memory controllers so as to offset bandwidth losses by going with GDDR-5/X
This is not to say that we may see a couple of SKUs utilize HBM1, but it is unlikely given the overall attitude towards 4 GB cards in the performance marketplace. It is also not impossible that AMD may implement a hybrid HBM system that utilizes the memory as a fast access, large cache while utilizing a larger volume of memory using GDDR-5 off the interposer. This is a much larger jump in supposition as compared to earlier statements, but it is not an impossible scenario. 2 GB of HBM using a 2048 bit connection would be a lower power, lower latency pool of memory that would enhance the performance of any GPU in most circumstances, assuming the work was done to truly optimize that configuration in drivers and hardware.

Interposer for more than Memory
The latest 14/16nm FF processes are… interesting. They are very power efficient and can clock to good speeds. What seems to be the issue is that they do not seem truly optimized for big designs. From what we have gathered, neither Polaris 10 or 11 are all that big. There seems to be no “big” GPU like what we initially saw with the previous 28 nm parts. Throughout the Capsaicin event, and in Ryan’s interview with Raja posted afterwards, we keep hearing about how smaller dies are the way to go moving forward. While we will eventually seeing larger and larger products come to market in the years ahead, it seems that right now there are some real physical and economic limits when it comes to die size.

Fiji was the first AMD GPU to integrate HBM memory into the mix. The interposer is about the max size as one can get without "stitching".
We must also consider that this is a decision based on AMD’s economic reasoning rather than real physical limitations. It could very well be that NVIDIA comes around with a monstrous sized GPU based on TSMC’s 16nm process. The rumored 17 billion transistor GPU could be a single piece of silicon that approaches 500+ mm square. This is just a rumor though. So far we have seen relatively small products being produced on these new, cutting edge processes. Even Intel has limited the size of their 14 nm products up to this point, but that will change with the 14nm Xeons make it to market. Still, we are 1.5+ years into Intel making 14 nm parts and we are just now seeing larger sized products about to be released. AMD could be risk averse with Samsung/GLOBALFOUNDRIES while NVIDIA may be in a position to gamble on a larger initial product on TSMC’s process.
Raja stated in his presentation and interview that they need to move beyond CrossFire. This to me means that they are working on a more seamless implementation of multiple chips rendering a single workload more effectively. The Radeon Pro Duo still follows the more traditional CrossFire route by utilizing xDMA over the PLX bridge chip located on the PCB. This gives relatively low latency access to the other GPU over a pretty wide interfaced (PCI-E 3.0 x16). It is a good solution, but it is not perfect.
Given the hints that we have received, it appears as though AMD might be implementing a multi-chip solution utilizing an interposer to provide very high speed and wide bus width connections between graphics chips. Interposers are not just for memory solutions, but have been shown in the past by companies like Altera to integrate individual dies on a single high-speed substrate to act as a single chip. The original idea behind that was to utilize different ASICs fabricated on process technologies that are more effective for the work rather than try to design everything onto a single die and process technology.

Ask a simple question, receive a simple answer. This in no way proves that AMD is going this route, simply that it is a possibility.
The lead in here is that there seems to be a good chance that AMD will integrate multiple chips on an interposer that allows high speed communication between the GPUs. It may also allow some extra flexibility in memory access either on the interposer in the form of a cache, or by splitting available memory channels between the two chips while communicating with external to the interposer memory. There are other more exotic potential configurations here, but from a high level this solution could work.
AMD has developed the interposer technology for years, they have good relations with the suppliers and those providing the packaging technology. But it is a logical jump to expect a multi-GPU solution using an interposer to provide communication effectively between chips, thereby moving away from the traditional CrossFire implementation that we have today. I wouldn’t mortgage my house and bet that this will be the implementation that we end up seeing, but considering what we know so far, it is certainly not beyond the realm of possibility. By utilizing many smaller dies AMD achieves better overall yields, less single-chip complexity that speeds development and fabrication, and a scalable solution that allows products to be addressed to different markets quickly.
I could be very wrong of course. Next to the Navi chip is “Scalability” which could very well relate to what I described above. I could be two generations of chips too early with this interposer speculation. AMD could be just playing it safe by introducing smaller GPUs for the budget and midrange market, and leave Fiji and Hawaii for the higher end products for the time being. Eventually AMD would have to address the high end of the market with a bigger Polaris chip, but so far we have only seen mention of the two smaller products with 10 and 11. Looking at the evidence around us, a larger GPU on 14nm is a greater undertaking than what we have seen in the past.

This could be AMD's top card for some time, if my conjecture is correct.
Needless to say, it has been many years since we have seen a process node jump like the one we will be experiencing this summer. 28nm held its own for a long time, but we are finally jumping to a new node that promises far more density and power efficiency. When we combine this with design work that has been honed by having to rely on a single process node for many years, we can expect to see very efficient and fast parts. Just how fast will depend on how big the chips can get, but for now we believe that we have at least the budget and midrange covered with Polaris 11 and 10 respectively. It also makes some sense as well that a larger GPU is not relatively close by the release of the Radeon Pro Duo card which leverages the previous generation Fiji chip to power. While that card is aimed at the pro market and those willing to spend $1500 on a single card, it is going to be the top end AMD card for the near future.
I can barely wait for June to roll around so we can finally see these chips integrated into products for mass consumption.

Noticia:
http://www.pcper.com/reviews/Graphic...-Architectures


Fica aqui a analise do Josh ao evento da AMD/Radeon Group na GDC 2016, onde ele fala do que se pode passar nas proximas gerações, a utilização ou não de alguns tipos de memória, tamanhos dos chips associados a custos de produção, fala também como na proxima geração Polaris e aquilo que a nVidia pode ou não apresentar como sendo melhor, mais caro ou mais poderoso que o Polaris.

[Jorge-Vieira]

AMD might sell GPU technology to Intel

Intel gets AMD inside

The dark satanic rumour mill has manufactured a hell on earth yarn that AMD is about to sell its GPU technology to Intel.

The rumour was started by Bloomberg, If true then Intel will license GPU patents from AMD and replace a $1.5 billion deal that Intel has with Nvidia. That deal will end on March 17, 2017.
Chipzilla is starting to lose interest in Nvidia because it is licensing terms are rather inflexible. AMD is seen as being more flexible.
Of course this does not mean that Intel will start producing AMD GPUs it is more likely that AMD tech will be under the bonnet of Intel’s integrated graphics. From AMD’s perspective this will not damage it too much because
Intel’s integrated graphics just replace the lower end of the market which is pretty much dead anyway.
It is all rumour and speculation, but as a story it does make some sense. If it plays out the way we think than AMD will not lose much other than bolstering the street cred of its rival’s integrated graphics. Nvidia will pay the price for not doing what Intel tells it and everyone will be happy.
AMD does need something anyway to make up for the ground it is losing to Nvidia. If Zen does not save it, it will need all the help it can get.

Noticia:
http://www.fudzilla.com/news/graphic...wop-with-intel


Não sei se será verdade ou mais uma especulação.
Mas o que eu sempre disse é que a criação do Radeon Group era uma forma de AMD se libertar e poder fazer certos e determinados negocios com a divisão dos GPUs.
Se isto se concretizar, penso que a AMD só sai a ganhar, sendo a Intel o maior fabricante de processadores e cada um desses processadores com um GPU dedicado AMD é assim no minimo algo para o estranho, rivais de sempre e agora unidos pelos GPUs.
Por outro lado, esta noticia pode até não fazer sentido nenhum porque é sabido o esforço que a Intel tem feito para melhorar a sua componente grafica presente nos CPUs.













Intel Reportedly in Talks For A Cross-Licensing Deal With AMD for its GPU IP – Contract with Nvidia Expires in Q1 2017

Something pretty interesting has been happening in the GPU IP industry as of late. Intel introduced its brand new Devil’s Canyon NUC with AMD XConncect technology and it has already previously stated its plans to adopt FreeSync in upcoming iGPUs. With the cross-licensing agreement it has from Nvidia set to expire in Q1 2017 – whispers are starting (via Seeking Alpha) that the silicon giant may be seeking a partnership with AMD this time around.

Intel reportedly in talks to license AMD’s GPU IP

Intel currently has a cross-licensing agreement with Nvidia which allows it to use its GPU intellectual property in its own homemade iGPUs. This particular deal, which will expire in Q1 2017 is the source of approximately 66 Million Dollars per quarter for Nvidia Corporation (or approximately $264 Million per fiscal year) since it gets a piece of the pie for every iGPU Intel ships. According to rumblings from Bloomberg (via Seeking Alpha) however, Intel is now in talks with AMD to take over from Q1 2017. This isn’t something confirmed and the report isn’t even present on Bloomberg’s website – but it has all the markings of a plausible event.
Intel supports AMD FreeSync and AMD XConnect Technology

Intel has been venturing into AMD territory for quite a while now. It pledged support for the AMD powered FreeSync technology (aka VESA A Sync) over Nvidia’s proprietary G-Sync for its future processors and also recently released its flagship Skull Canyon NUC with support for AMD XConnect tech. All these point towards a fondness for the mostly open source nature of the red silicon maker. While there is no word on the exact dollar figures of this particular deal it is quite possible that AMD is willing to offer a sweeter deal than Nvidia.
Currently, the most powerful iGPU Intel has is the Iris Pro 580 (approximately equal to a desktop GTX 750) which is insanely powerful for an integrated GPU. If this deal with AMD is successful however, than we might actually see it shifting to something very similar to a GCN based architecture depending on what kind of licensing they are able to achieve.
Advertisements

Implications of a cross licensing deal with AMD

FBR & Co.’s Christopher Rolland, who has a Market Perform rating on shares of AMD, sees the potential appeal of AMD’s technology in Intel’s data center server chips, but he also sees a bargaining chip against Nvidia:

For Intel, a potential deal would enable the company to boost the graphics performance in their own chips, or perhaps to use high performance GPUs in areas of data center. While less likely a motivation for Intel, such a deal may also give them IP ammunition just in case NVIDIA decided to renew litigation once their cross-licensing agreement expires in early 2017. via Barrons

There could be several caveats associated with this idea however, one of the primary ones being that Nvidia holds the IP of some key GPU technologies that are employed in modern GPUs. Shifting over to AMD might actually require Intel to have a cross licensing agreement with both companies. Then again, Nvidia was not able to enforce its patents in the Nvidia v Samsung case, which is a very big precedent in the industrial world – so it could easily end up happening with or without Nvidia’s consent.
As far as financial outlooks go – according to Barrons, investors of Nvidia aren’t expecting this deal to be renewed after the royalty ‘cliff’ in 2017. In fact if it ends up being renewed, this will be something that will exceed analyst expectations. AMD on the other hand could stand to benefit greatly from an agreement like this. Not only could ~50 Million dollars make the difference between being in profit (at Net Income) but it could help solidify its RTG momentum that has been such a resounding success so far.

Noticia:
http://wccftech.com/intel-talks-cros...#ixzz43HRAa3tu

[Jorge-Vieira]

AMD has not given up on mobile GPU

But only in the right circumstances

Raja Koduri, senior vice president and chief architect of AMD's Radeon Technologies Group has said that the outift is open to making a graphics processor for mobile devices but only in select circumstances.

AMD flogged its mobile graphics division in 2009 to Qualcomm, which uses the technology in a mobile GPU called Adreno, an anagram of Radeon. It was a classic own goal because the mobile market was just starting to take off.
However according to ITworld Koduri said it 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.
AMD could make one as part of a large custom chip deal, potentially worth millions of dollars. To do that of course it would need a mobile partner willing to take a gamble. The sort of thing that AMD would do is like it did for Microsoft’s Xbox or PlayStation 4.
There is nothing to stop AMD breaking down its GPUs into smaller cores and tweaking them so they use less power. They should be able to manage 4K video.
However AMD would have to look at Nvidia’s GPUs which are seen as too power hungry to do much good. Its biggest rival is Imagination, with its Mali graphics used in Samsung's Galaxy handsets.
A mobile AMD chip might enable some radical technology improvements which might make a partner more interested. However it is also unlikely that anyone is going to take up Koduri’s offer.

Noticia:
http://www.fudzilla.com/news/graphic...-on-mobile-gpu

[Enzo]

AMD a crescer. O gigante vermelho esta a acordar?

[Jorge-Vieira]

O gigante vermelho nunca esteve adormecido, provavelmente até esteve ou começa a ficar evidente agora que esteve ou está algum tempo à frente no tempo e na visão das coisas.

[Pedro_1]

Os gpu´s são muito bons, o problema sempre foi porem as placas a trabalhar ao potencial máximo, quer fosse pela api em si que negava quaisquer vantagens de uma arquitetura mais versátil que è o gcn, bem como títulos que carregam porcarias desnecessárias proprietárias que não só desgraçam a performance do jogo em placas amd, como a parte engraçada è que trazem também problemas às suas próprias placas, ou pelo menos causam dores de cabeça extra de como otimizar os requisitos de processamento de um determinado titulo em certas arquiteturas.

Gameworks è muito giro mas está visto que trás mais problemas do que trás soluções. Existem sempre alternativas a efeitos, falo no caso do physx por exemplo que não è preciso uma placa nvidia para nada com um código restrito. Ninguém quer saber desta porcaria proprietária para nada ainda para mais quando há motores de física tão bons ou melhores que isto que fazem na verdade um trabalho bom.

Dou como exemplo o planetside 2 que houve uma altura que chegaram a por os efeitos physx de alguma forma a correr no engine do jogo propriamente dito, lembro-me que o jogo corria tremendamente bem com todos os efeitos xpto no ecrã e não era preciso placas nvidia para nada.

Uns meses mais tarde acabaram com isso, disseram nos fóruns que causava muitos problemas e instabilidades bla bla bla......uma tremenda peta. Lá foi a nvidia que viu que não conseguia por aquilo a trabalhar como deve ser para eles e lá devem ter decidido acabar com a festa não só para eles como para todos os jogadores. Um jogo que anunciado desde inicio com physx e petas de que tudo ia ficar bonito e giro....só peta, hoje planetside 2 o physx è apenas uma miragem.

Voltando à amd, temos já vários exemplos de que o dx12 sempre parece mais promissor e com menos intrujices, o ultimo exemplo è o hitman que corre bem nas amd´s, dou também como exemplo a gtx 980 que se dizia ser um milhão de % melhor que 290x/390x e mais uma vez só petas. Ambas otimizadas lutam taco a taco sem tretas pelo meio.

Já vi esta fotografia em vários sítios, lembro-me quando a 780 ti saiu se dizia ser amazing e ser muitooooooo melhor que uma 290x e afins, e com o tempo acabamos por descobrir que não, que ambas otimizadas lutam a peito.

Tava aqui agora o dia todo a relatar petas e intrujices de marketing e afins. Enfim.

Vou mas è tomar o pequeno almoço que até me falta memoria de muitas outras coisas.

[Enzo]

Isto faz-me lembrar os carros. Antigamente era motor contra motor. Agora é electronica. Quando a electronica falha...

[Jorge-Vieira]

AMD's Capsaicin event sees the company focused on VR, next-gen GPUs

GDC 2016 - AMD was all systems go at its Capsaicin event during the Game Developers Conference, unveiling its new dual-GPU video card, the Radeon Pro Duo. The company also talked about its massive commitment to VR, DirectX 12, its next-gen Polaris architecture, and more.






AMD was super confident during this event, where it had a fair amount of hands to play in its battle with NVIDIA. The laser-focused commitment to VR has me excited, as I believe that being a VR-focused company this early on, will only benefit Radeon Technologies Group, and AMD. The company has made partnerships with both Oculus and HTC, for the Rift and Vive, respectively. The company has gone all-in with VR to the point of having its own APU inside of a headset, partnering with Sulon for the Sulon Q headset.

With HDR-enabled TVs and video cards thanks to its next-gen Polaris card, the company had working 14nm at the show. The Radeon Pro Duo was on stage being used during the demonstration, requiring 3 x 8-pin PCIe power connectors to power the dual-GPU video card, rocking 8GB of HBM (4GB per Fiji GPU).


The company also talked about its next-gen cards, with Polaris noting a 2.5x performance-per-watt gain over 28nm GPUs, but AMD also teased Vega for 2017 and Navi for 2018. Vega looks like the big release from AMD, as it has HBM2 noted in the roadmap, while Polaris doesn't. I asked AMD if this meant Polaris wouldn't have HBM2, and that AMD would have HBM2 used on a video card when Vega arrives. But, AMD reiterated it would have a HBM2-based card in 2016.



All in all, AMD hosted an excellent event - which was both informative and casual. Lisa Su, the CEO of AMD, came out on stage and used an air cannon to fire t-shirts into the crowd... I mean, come on - that's pretty cool, right?

Noticia:
http://www.tweaktown.com/news/51163/...pus/index.html

[Jorge-Vieira]

Could Intel License Radeon Graphics IP Or Just Acquire AMD’s RTG?

It has been suggested for quite some time that Intel could/should take advantage of AMD's struggling situation to make an acquisition, or at least take advantage of licensing some of its technologies. The latter thought has ramped-up again in the rumor mill, and while there's no clear path that Intel might take, it's being said that the Santa Clara company is heavily weighing its options.
A decade ago, it would have been quite a historic event to see Intel work with AMD in any major way, but the landscape has shifted, and with AMD in need of more revenue streams, it now makes more sense perhaps that the companies could work together. Does that mean Intel's looking to craft its own graphics solutions that use AMD IP? It sounds bizarre, but it could happen, even if it's just in the high-end workstation or server space. Intel might not be that interested in acquiring IP for use in its IGP products, but that's just one product silo to consider in the bigger picture.
image: http://hothardware.com/ContentImages...phics_Card.jpg

Intel already throws its support behind AMD's XConnect external GPU product The key thing to bear in mind here is that this rumor explicitly involves AMD's graphics technologies, not CPU IP. This points to at least a few ideas of what could come of this connection, even if they still sound a little outlandish.
Making this all the more interesting, Intel currently has an IP partnership with NVIDIA, which is set to expire in 2017. That brings significant revenue to NVIDIA year after year, so this proposed AMD deal could definitely affect that as well. In fact, if the Intel/NVIDIA contract isn't renewed, and AMD moves on in, it could benefit AMD regardless, even if it's worth less than what NVIDIA participates in currently.
If you still think it's nutty to picture Intel and AMD working together, picture this: just this past week, we saw Intel throw its weight behind AMD's Xconnect external GPU solution, which utilizes its Thunderbolt 3.0 protocol. It almost seems like Intel is getting a little cozy with AMD, and it can't help but make us wonder if the idea of an all-out acquisition of the Radeon Technology Group could happen. Again, outlandish, but with the industry changing as it is, you learn not to be surprised by much these days.
The future for AMD could be very interesting, and could also potentially include a nice boost to AMD's pocketbook.

Noticia:
http://hothardware.com/news/could-in...JMypKc3IdOP.99



Dinheiro não será problema se a Intel quiser comprar o Radeon Group, como já o tinha referido, a criação desta nova divisão deve ser para vender a curto médio prazo e assim a AMD recupera grande parte do investimento feito no desastroso negocio da compra da ATI em 2006.
Por outro já nada espanta, pela segunda vez, a AMD/Radeon Group utiliza uma máquina Intel (primeira vez na apresentação do Quatum Project, segunda vez agora na GDC 2016 na apresentação da Radeon Pro Duo) para demonstração dos seus produtos.
Pelo lado da AMD/Radeon Group um licensiamento (sem compra) à Intel, seria dinheiro em caixa todos os anos a entrar e com fartura e talvez seja este o cenário mais provável, caso a Intel não renove com a nVidia.

[Zavtekirou]

Boa tarde,

Voto em a Intel comprar a Radeon Group! A AMD precisa de dinheiro como de pão para a boca! E a Intel tem de sobra. Além de que seria muito mais competitivo para a Nvidia ter pela frente a Intel que a AMD no mercado daa gráficas dedicadas.

Cumprimento.

[Enzo]

Boa tarde,

Voto em a Intel comprar a Radeon Group! A AMD precisa de dinheiro como de pão para a boca! E a Intel tem de sobra. Além de que seria muito mais competitivo para a Nvidia ter pela frente a Intel que a AMD no mercado daa gráficas dedicadas.

Cumprimento.

Discordo plenamente. De monopolistas estou eu farto. Preferia que fosse a Samsung a alinhar na compra da Radeon e manter a Nvidia e a Intel na corrida. E se possivel, mandarem vir mais um, Matrox, Apple, qualquer um desses com muito nome e/ou guito.

[Zavtekirou]

Boa tarde,

Mas monopólio existe agora. Com a Intel pela frente duvido que a Nvidia tivesse tanto mercado como tem agora com a AMD.

Cumprimentos.

[Enzo]

Claro que existe. A AMD deixou-se ficar pelo caminho, tendo tudo para manter pelo menos 60% do mercado.
Agora que parecem estar de volta, vamos ver as falhas que vão mandar e as coisas boas que vao conseguir trazer, e o que é que isso vai mudar ao panorama actual. Depois de tanto tempo de seca e falhas, ainda acredito.

[Jorge-Vieira]

Claro que existe. A AMD deixou-se ficar pelo caminho, tendo tudo para manter pelo menos 60% do mercado.
Agora que parecem estar de volta, vamos ver as falhas que vão mandar e as coisas boas que vao conseguir trazer, e o que é que isso vai mudar ao panorama actual. Depois de tanto tempo de seca e falhas, ainda acredito.

Se há uma coisa que tem ficado evidente desde a criação do Radeon Group, é que primeiro que nós, são os próprios responsáveis que acreditam num novo regresso e em força. Basta ver o Raja Koduri a falar, basta ver toda a abertura e mudança que houve em comunicação e, basta ver o ultimo livestream para se acreditar que mais que ninguém é os próprios que acreditam que podem trazer coisas boas e acima tudo grandes planos para o futuro, algo que não se via no tempo apenas da AMD.
Acredito também que esta mudança seja para tornar o Radeon Group rentável e apetecível para um futuro negocio, esperando que este negocio não caia em maos de uma empresa monopolista, mas de uma que saiba potenciar o que a AMD tem de bom.

Na nossa perspectiva, é bom que a AMD/Radeon Group voltem ao patamar de onde nunca deveriam ter saído (por culpa apenas deles), por muito que gostemos mais de um ou de outro, o monopolio da nVidia é por demais evidente e mau para o consumidor, graficas "com defeito", graficas overpriced, tecnologias proprietárias, capanços a nível de drivers e outras coisas mais.

[Enzo]

Para alem do registo que querem impor para obtermos as drivers...
Gosto imenso de ambas, mas acho a Nvidia mais capitalista e monopolista que a AMD. Portanto, sou 55%vermelho e 45 verde.