Processador AMD Ryzen / Threadripper

Exatamente se eles conseguirem no zen a diferença que se conseguiu do phenom para o phenom 2 era ouro sobre azul... E finalmente punham pressão sobre os preços da Intel também


Vamos ver, Espero que sim, ou melhor esperamos nós, e que meta muita pressão quer na Nvidia e Intel, mas duvido, devido a estas situações, espero muito estar enganado. uso Intel e Nvidia mas os preços ui já começa a chatear lol... principalmente em relação a evolução nos CPU's
 
AMD Contracts TSMC To Produce Zen At 16nm Amidst Concerns Over 14nm Woes At Globalfoundries

AMD has allegedly decided to delegate the responsibility of producing its hotly anticipated Zen CPU chips to TSMC on its 16nm FinFET process. This development has allegedly unfolded amidst AMD fears of Globalfoundries’ slow 14nm FinFET yield and capacity progress. And while these claims do seem plausible I should still provide a note of caution as this is very much a rumor at this moment in time and as such was tagged accordingly.


Globalfoundries was famously responsible for the delays to AMD’s last round of make-or-break product launches. Which included AMD’s first ever mainstream APU code named Llanno and its first high performance Bulldozer based server and desktop FX chips. These first gen 3000 series APUs and FX 8100 series CPUs were supposed to land in Q1 2011 but were delayed to Q4 2011 as a result of multiple challenges that Gloablfoundries’ faced in bringing its 32nm SOI manufacturing process to full operation.

AMD Has Been Very Coy When Going On Record About Whether Globalfoundries or TSMC Will Produce Zen
Analysts and journalists have repeatedly asked AMD on various occasions about whether Zen will be manufactured at TSMC or Globalfoundries. I can recall two or three occasions off the top of my head of when this occurred and the answer was always the same. Zen will feature FinFET technology, both TSMC and Globalfoundries are partners of AMD and that was that. It’s becoming much clearer now why AMD chose not to commit to any one of the two early on.

Globalfoundries has reportedly suffered a setback recently as a result of its owner, the government of Abu Dhabi, deciding to cut back on expenses after oil prices crashed, which have so far shown no signs of bouncing back. As such GloFo is reportedly attempting to retool its 28nm equipment for 14nm production. This retooling however has been considerably slow and is the reason behind the recent delays in bringing volumes and yields up to snuff by the pure-play foundry.

TSMC has undoubtedly faced its fair share of setbacks but it has successfully managed to iron out most of the kinks and its 16FF+ high performance process is set for volume production this quarter. NVIDIA confirmed that it will partner with TSMC to produce its next generation Pascal GPUs next year. This past August Digitimes confirmed that TSMC will in fact be making chips for AMD on the 16FF+ process. And as AMD GPUs have historically always been made at TSMC it’s safe to assume that AMD’s next generation Arctic Islands will also be produced at TSMC.

Finalmente deram um chuto na GF se se confirmar. Pena que não tenham apostado na Samsung mas assim ficam com um processo que está definitivamente atrás da Intel.
 
A AMD anda com uma streak de sorte.......
Mas até podem andar uns tempos com os 16nm da TSMC e quando a GF tiver os 14nm em condições, podem avançar para este.
 

Interessante. No papel é algo bastante diferente do Bulldozer.
A nível de virgula flutuante já não existe uma unidade por cada dois cores e sim um por core, dois 256 bit pipes. Talvez suporte 512 AVX.
A nível de inteiros é parecido por core, mas faltam os detalhes. Os detalhes podem fazer toda a diferença, mas o Bulldozer não era mau nesses aspecto.
Falta saber muita coisa. Por exemplo a performance das caches, que no Bulldozer eram péssimas.

Visto de cima, não é muito diferente do Skylake, mas não quer dizer que venha a ter a mesma performance. Os detalhes fazem as diferenças.
Veremos no que dá.
 
Deduzo que eles se tenham baseado na mesma informação que o "Dresdenboy", um upstream patch para o GCC

Here are some quotes of the patch file:

+;; Decoders unit has 4 decoders and all of them can decode fast path
+;; and vector type instructions.
+;; Integer unit 4 ALU pipes.
+;; 2 AGU pipes.
+;; Floating point unit 4 FP pipes.
+ 32, /* size of l1 cache. */
+ 512, /* size of l2 cache. */
Excerpt:
  • 4 wide decoders
  • 4 integer ALUs
  • 2 AGUs (for 2R 1W L1 cache according to a LinkedIn profile)
  • 4 FP pipelines

dew7k7.jpg


http://dresdenboy.blogspot.pt/
 
Ao menos parecem ter aprendido com os erros no desenho desta arquitectura.
Mas a performance e eficiência no final têm que chegar bem perto dos Intel senão não conseguem competir no mercado de servidores.
 
O Bulldozer para servidores (integer mais importante), até não era mau em performance, mas nesse mercado a performance/watt é ainda mais importante. Com o novo processo (infelizmente 16nm e não os 14nm) devem melhorar bastante o consumo.
 
Sim, em certas coisas o BD safava-se... Mas não quero entrar no Hypetrain da AMD, porque já fui "papado" com o BD e agora com as FURY (apenas devido ao seu posicionamento monetário, são boas gráficas, mas um pouco mais baixo em preço não fazia mal)
 
AMD’s next generation x86 and ARM high performance cores code named “Zen” and “K12” have reportedly taped out according to the linkedin profile of an AMD design engineer. Coincidentally AMD’s President and CEO Lisa Su had also announced at the company’s Q3 earnings call that the company’s design teams have successfully taped out several FinFET designs at multiple foundries in Q3 2015.



We reported in July that AMD had taped out two FinFET designs in Q2 2015. AMD then followed up in Q3 by taping out several other FinFET products at more than one foundry. AMD’s CEO did not go into detail with regards to which designs taped out on which specific process node or at which foundry. However AMD’s established foundry partners for FinFET products include TSMC with its 16FF+ process and Globalfoundries with its 14LPP process. So it’s a safe bet that these are the foundries Su was referring to, with Samsung standing in as a potential third player and a second source to Globalfoundries. Since Samsung and Globalfoundries have partnered on 14nm FinFET LPE and LPP, AMD could chose to go with either one.

AMD Q3 2015 Earnings Teleconference
Harlan Sur – JPMorgan – Analyst
Great, thanks for taking my question. So, Lisa, you gave us a relatively brief update on Zen. If you could just give us an update on Zen from a (technical difficulty) perspective? It’s a new core architecture, a new process technology. I think you taped out a couple of chips last quarter.
Any feedback on the performance or the yield metrics that gives the team confidence on the broad rollout of the different product families starting next year?

Lisa Su – Advanced Micro Devices, Inc. – President, CEO
Yes, so, Harlan, let me couch it this way. So as we stated in the financial analyst day, we had a target of 40% IPC performance of Zen over our previous generation. We believe we are on track for that.
Relative to process technology, we have taped out multiple products to multiple fabs in FinFET and we believe that they’re also on track in terms of overall ramp. So we continue to focus on both of those aspects, both the architecture and the process technology, but so far, so good.

AMD Zen And K12 High Performance X86 And ARM CPU Cores Taped Out
According to the profile of an AMD design engineer spotted by Matthias Waldhauer AKA Dresdenboy on Linkedin, both Zen and K12 have already taped out. You’ll find a screengrab of the relative information below.


What We Know So Far About AMD’s Zen Microarchitecture
We first broke the news about AMD’s next generation high performance core back in September of last year. At which point AMD’s then CEO Rory Read revealed the code name for the company’s upcoming high performance x86 CPU microarchitecture. Prior to that revelation we only had knowledge of Zen’s sister ARMv8 core code named K12.


As of late AMD has been slightly more generous in providing detail about its brand new inception. Back in May AMD announced that it was preparing an entirely new line-up of FX CPUs and a brand new platform ‘AM4″. We learned that the new family of FX processors code named “Summit Ridge” would feature an entirely new socket and an updated feature set including DDR4 memory support. And more importantly we learned that the new platform would feature mainstream CPUs with “high core counts” – rumored to be up to eight cores – and “SMT” support.

Two months later we learned that AMD was also working on a monstrous High Performance Computing APU with 16 Zen cores and a huge integrated GPU in addition to stacked High Bandwidth Memory. We also learned that AMD is planning to introduce high performance server CPUs with up to 32 Zen CPU cores. Hearing about all of those different SKUs is jolly exciting but it was also quite frustrating as we had no idea what to expect from Zen. That is until AMD revealed a whopper at its Financial Analyst Day earlier this year, which is that Zen will have a 40% instruction per clock improvement over its predecessor “Excavator”.

Advertisements
AMD’s Zen CPU Core Coming in 2016 – Features FinFET Process, SMT And New Cache System
Zen will be AMD’s successor to the Bulldoze family of cores. It will be the first ever CPU core from the company to adopt simultaneous multithreading. It’s also the company’s first entirely new CPU core design following the Bulldozer family of cores which debuted in 2011 and was the company’s first ever design to feature clustered multithreading .


In addition to SMT, Zen also features a new high-bandwidth low latency cache system. A vital improvement over the previous generation of cores. Since subpar cache performance was one of the primary pitfalls of AMD’s Bulldozer CPU microarchitecture. The new CPU core is designed for and will be manufactured on an advanced FinFET process. Which would allow the CPU core to scale from low power mobile applications to high performance desktop and enterprise markets.

Zen To Feature A 40% Instructions Per Clock Improvement Over Excavator
Mark Papermaster, AMD’s Chief Technology Officer revealed that the company plans to introduce a huge IPC improvement with Zen over AMD’s latest generation “Excavator” x86 core. A 40% increase in IPC would represent the largest jump in IPC ever for the company, an improvement which Mark Papermaster claimed he had not seen “anywhere in the industry”.


Papermaster also made it a point to highlight that this 40% performance improvement figure is independent from the manufacturing process. So it’s a permanent architectural performance improvement that will always be present regardless of the process node.



Zen will be featured in AMD’s enthusiast CPU product line in 2016. Lisa Su confirmed that the new CPU architecture will be arriving to desktop FX CPUs first and to servers second. Succeeding Zen will be Zen+ cores. Which will feature evolutionary improvement over Zen. The company will introduce a new socket in 2016 dubbed AM4 that will house products spanning from high performance CPUs to mainstream APUs based on Zen and next generation FinFET GCN based GPUs.



The new family of high performance FX CPUs which appeared in previous leaks as “Summit Ridge” will feature SMT CPUs with high core counts and DDR4 memory support. The platform will be based on the new AM4 socket and a new yet undisclosed chipset. Unconfirmed leaks indicate that Summit Ridge will feature CPUs with up to 8 Zen cores and 12MB of L2 and L3 cache, but that is yet to be confirmed.


Read more: http://wccftech.com/amd-zen-k12-taped/#ixzz3p0kNb9nh

http://wccftech.com/amd-zen-k12-taped/
 
Só pelas aterações reveladas, dá para antever que vão haver ganhos consideráveis de performance.
Depois a mudança para 16-14nm vai actualizar bastante os consumos.

Resumindo, deve ser tudo uma questão de posicionamento e preço.

Espero que a amd viva muitos mais anos.
Pensar na possibilidade de um dia querer um cpu e só haver intel, ou uma gráfica e só haver nvidia, é aterrador para a carteira...
 
Vai haver am4.

É suposto ser um novo socket compatilhado para cpus e apus, com ddr4, e claro, deve-se esperar que tenha todos os buses/interfaces actualizados e melhor integrados.
 
Back
Topo