Original Link: http://www.anandtech.com/show/6140/nvidia-announces-keplerbased-quadro-k5000-secondgeneration-maximus
NVIDIA Announces Kepler-Based Quadro K5000 & Second-Generation Maximusby Ryan Smith on August 7, 2012 10:00 AM EST
Since the initial launch of NVIDIA’s unusual chip stack for Kepler in late March, there has been quite a bit of speculation on how NVIDIA would flesh out their compute and professional products lines. Typically NVIDIA would launch a high-end GPU first (e.g. GF100), and use that to build their high-end consumer, professional, and compute products. Kepler of course threw a wrench into that pattern when the mid-tier GK104 became the first Kepler GPU to be launched.
The first half of that speculation came to rest in May, when NVIDIA has announced their high-end Kepler GPU, GK110, and Tesla products based on both GK104 and GK110. NVIDIA’s solution to the unusual Kepler launch situation was to launch a specialized Tesla card based on GK104 in the summer, and then launch the more traditional GK110 based Tesla late in the year. This allowed NVIDIA to get Tesla K10 cards in the hands of some customers right away (primarily those with workloads suitable for GK104), rather than making all of their customers wait for Tesla K20 at the end of the year.
Meanwhile the second half of that speculation comes to an end today with the announcement of NVIDIA’s first Kepler-based Quadro card, the Quadro K5000.
|Quadro K5000||Quadro 6000||Quadro 5000|
|Memory Clock||5.4GHz GDDR5||3GHz GDDR5||3GHz GDDR5|
|Memory Bus Width||256-bit||384-bit||320-bit|
|FP64||1/24 FP32||1/2 FP32||1/2 FP32|
|Manufacturing Process||TSMC 28nm||TSMC 40nm||TSMC 40nm|
The Quadro K5000 is the Kepler-based successor to NVIDIA’s existing Fermi-based Quadro 5000 video card. Based on the same GK104 GPU as NVIDIA’s Tesla K10 and GeForce GTX 680, the card is in many ways the near-obligatory workstation version of NVIDIA’s existing consumer products. Based on the theoretical performance numbers provided by NVIDIA, Quadro K5000 uses a fully enabled GK104 GPU clocked at around 700MHz core, and is paired with 4GB of VRAM operating at 5.4GHz. Meanwhile NVIDIA has the max power consumption of the card listed at an incredibly low 122W, which given the low core clockspeed of the card indicates that NVIDIA was able to significantly reduce GK104’s power consumption by reducing its clockspeed by such a large degree.
For NVIDIA the Quadro K5000 is the most significant new Quadro card in quite some time and is this way for many of the same reasons that the GeForce GTX 680 was a major card for NVIDIA’s consumer graphics division. The jump to TSMC’s 28nm process along with the Kepler architecture has greatly improved NVIDIA’s power efficiency, with NVIDIA’s graphics performance increasing while at the same time their power consumption has been greatly reduced.
Meanwhile Quadro K5000 also brings with it all of the major Kepler family features that we first saw with the GeForce GTX 680, including support for DisplayPort 1.2, 4 display controllers per GPU, PCI-Express 3.0 support, the NVENC H.264 video encoder, and even bindless textures. The additional display functionality in particular will likely have the greatest impact for Quadro users, especially those who are intending to drive 4k monitors or who are already driving 3+ monitors by using multiple Quadro cards. This also means that NVIDIA can now support up to 16 monitors off of a single system by using 4 Quadro K5000 cards, with the ability to keep them genlocked using Quadro Sync functionality.
As for matters of performance, Intel Sandy Bridge-E workstation owners will be happy to hear that PCI-Express 3.0 should also make its presence felt. Unlike the GeForce 600 series NVIDIA will be enabling PCIe 3.0 for qualified SNB-E workstations, which will improve performance in situations where the PCIe bus is the bottleneck.
Meanwhile we expect that NVIDIA’s bindless texture feature to finally get some real attention with the K5000, after having been largely ignored on their consumer cards. Because bindless textures are currently only available via OpenGL and because OpenGL has a much greater presence in the professional market as opposed to the consumer market, there should be enough interest on the software side for this functionality to be put to meaningful use.
Wrapping things up, professional users looking to pick up a Quadro K5000 will want to pay close attention to their wallets and their calendars. Quadro K5000 is set to ship individually in October for $2249, or together with the Tesla K20 as part of second generation Maximus systems in December.
Finally, as with the Tesla K10 there’s the question of what to make of NVIDIA releasing a professional product based on what is otherwise a mid-range GPU. GK104’s strengths and weaknesses haven’t changed – it’s still strong at graphics and picky about compute performance – but unlike Tesla K10 NVIDIA doesn’t necessarily need strong compute performance here as the Quadro line is first and foremost for professional graphics. Still, compared to the Quadro 5000 it replaces the K5000 is losing quite a bit of double-precision compute performance along with some ECC memory protection (GK104 lacks ECC for its caches), so NVIDIA has clearly had to make some trade-offs to get a Kepler Quadro card released in October of this year as opposed to next year when more GK110 GPUs become available. Thankfully for NVIDIA they don’t necessarily need strong compute performance from their Quadro cards so long as they have Maximus.
Second Generation Maximus
NVIDIA’s second announcement of the day directly ties into the Quadro announcement, which is the announcement of NVIDIA’s second generation Maximus technology. Strictly speaking this isn’t a new technology in and of itself – it’s the same concept of using a Quadro card and a Tesla card together in a single system and is based on the same software – but for marketing purposes NVIDIA is going to be separating Maximus based on the generation of the video cards involved.
From here on NVIDIA’s first generation Maximus technology will refer to pairing together Fermi cards, e.g. Quadro 6000 paired with a Tesla 2075. Second generation Maximus on the other hand will refer to pairing together Kepler cards, specially a Quadro K5000 with a Tesla K20.
The significance of this announcement isn’t in the branding itself, but rather what it represents for NVIDIA. Because NVIDIA is not launching a GK110 Quadro card (or at least not yet) Maximus’s importance in NVIDIA’s ecosystem has been greatly elevated virtually overnight. For the Fermi generation all of NVIDIA’s high-end Quadro cards were capable of both high performance rendering and high performance compute, with the Quadro 6000 in particular being a superset of both the Quadro and Tesla families by offering NVIDIA’s best graphics performance combined with their best compute performance. Maximus improved the experience by offloading compute onto a Tesla card – and thereby bypassing the performance penalty of frequently context switching – but Maximus wasn’t strictly necessary for high performance compute with Quadro.
Second generation Maximus on the other hand sees Maximus become essential to compute performance. Because of GK104’s limited compute performance, Quadro K5000 cannot achieve high compute performance on its own; at best it’s a great graphics product and a decent single-precision compute product. Instead Quadro K5000 needs to be paired with a GK110 Tesla card in order to achieve both high graphics performance and high compute performance. Second generation Maximus in turn is the technology and branding glue that brings all of this together.
As we mentioned in our quick look at the Quadro K5000, NVIDIA going this route isn’t particularly surprising given the fact that GK104 is such a strong performer at graphics tasks and is far more available than GK110, but it means that NVIDIA is now very reliant on Maximus in all situations that call for a Quadro video card with strong compute performance. It also means that NVIDIA is at the mercy of application developers to a certain extent as developers need to specifically accommodate Maximus. To NVIDIA’s credit the number of programs supporting Maximus has more than tripled in the last year, but that’s still a far cry from the hundreds of applications professionals typically use.
For this reason we wouldn’t be shocked to eventually see a GK110 Quadro card, but until that time this is NVIDIA’s flagship graphics + compute solution.