There were rumors of a GTX 1060 3GB card, but the launch of the GTX 1060 featured a single 6GB model. Almost exactly one month later, nVidia has announced its 3GB GTX 1060 with 1152 CUDA Cores, down from 1280, and a halved framebuffer. The card will also run fewer TMUs as a result of disabling 1 SM, for a total of 9 simultaneous multiprocessors versus the 10 SMs on the GTX 1060 6GB. This brings down TMU count from 80 to 72 (with 8x texture map units per SM), making for marginally reduced power coupled with a greatly reduced framebuffer.
(Update: The card is already available on etailers, see here.)
In theory, this will most heavily impact 0.1% low and 1% low frame performance, as we showed in the AMD RX 480 8GB vs. 4GB comparison. Games which rely less upon Post FX and more heavily upon large resolution textures and maps (as in shadow, normal, specular – not as in levels) will most immediately show the difference. Assassin's Creed, Black Ops III (in some use cases), and Mirror's Edge Catalyst are poised to show the greatest differences between the two. NVidia has advertised an approximate 5% performance difference when looking at the GTX 1060 3GB vs. GTX 1060 6GB, but that number will almost certainly be blown out when looking at VRAM stressing titles.
Pascal has mobilized, officially launching in notebooks today. The GTX 1080, 1070, and 1060 full desktop GPUs will be available in Pascal notebooks, similar to the GTX 980 non-M launch from last year. Those earlier 980 laptops were a bit of an experiment, from what nVidia's laptop team told us, and led to wider implementation of the line-up for Pascal.
We had an opportunity to perform preliminary benchmarks using some of our usual test suite while at the London unveil event, including frametime analysis (1% / 0.1% lows) with Shadow of Mordor. Testing was conducted using the exact same settings as we use in our own benchmarks, and we used some of our own software to validate that results were clean.
Before getting to preliminary GTX 1080 & GTX 1070 notebook FPS benchmarks on the Clevo P775 and MSI GT62, we'll run through laptop overclocking, specification differences in the GTX 1070, and 120Hz display updates. Note also that we've got at least three notebooks on the way for testing, and will be publishing reviews through the month. Our own initial benchmarks are further down.
The theoretical end of AMD's Polaris desktop GPU line has just begun shipment, and that's in the form of the RX 460. Back at the pre-Computex press event, AMD informed us that the Polaris line would primarily consist of two GPUs on the Polaris architecture – Polaris 10 & 11 – and that three cards would ship on this platform. Two of the three have already shipped and been reviewed, including the ~$240 RX 480 8GB cards (review here) and ~$180-$200 RX 470 cards (review here). The next architecture will be Vega, in a position to potentially be the first consumer GPU to use HBM2.
Today, we're looking at Polaris 11 in the RX 460. The review sample received is Sapphire's RX 460 Nitro 4GB card, pre-overclocked to 1250MHz. The RX 460, like the 470, is a “partner card,” which means that no reference model will be sold by AMD for rebrand by its partners. AMD has set the MSRP to $110 for the RX 460, but partners will vary widely depending on VRAM capacity (2GB or 4GB), cooler design, pre-overclocks, and component selection. At time of writing, we did not have a list of AIB partner prices and cards available.
As always, we'll be reviewing the Sapphire RX 460 4GB with extensive thermal testing, FPS testing in Overwatch, DOTA2, GTA V, and more, and overclock testing. Be sure to check page 1 for our new PCB analysis and cooler discussion, alongside the in-depth architecture information.
We liked the RX 470 well enough, which, for our site, is certainly considerable praise; we tend to stick just with the numbers and leave most of the decision-making to the reader, but the RX 470 did receive some additional analysis. As we stated in the review, the RX 470 makes good sense as a card priced around $180, but not more than that. That's the key point: Our entire analysis was written on the assumption of a $180 video card, presently fielded only by PowerColor and its Red Devil RX 470. Exceeding the $180 mark on a 4GB 470 immediately invalidates the card, as it enter competition with AMD's own RX 480 4GB model (see: 4GB vs. 8GB VRAM benchmark). Granted, it's still far enough away from the RX 480 8GB & GTX 1060 that the 470 may exist in some isolation. For now, anyway.
But as seems to be the trend with both nVidia and AMD for this generation of graphics cards, the RX 470 has some pricing that at times seems almost silly. Take, for instance, the $220 XFX RX 470 RS Black Edition True OC card: it's $20 more than a 4GB RX 480, it's clocked to where we overclocked on our RX 470, and it will perform about 3-5% slower in AVG FPS than the RX 480 4GB reference card. And let's not start on the seemingly irrelevant $240 8GB RX 470 Nitro+, effectively an RX 480 8GB card (even in clock-rate) with four fewer CUs, fewer TMUs (from 144 to 128), and slower memory – though it does have a better cooling solution, to Sapphire's point.
AMD's RX 470 has been on our time table since May, when the pre-Computex press event informed us of a “mid-July” release. Well, it's mid-July – wait.
August 4th. It's August 4th. The RX 470 is available effective today, coinciding with embargo lift on reviews, and we've had time to thoroughly analyze the card's performance. The RX 470 is a partner card and will not be available as a reference model, though some partner cards may as well be reference models; they're using the reference RX 480 cooler, just with new colors, back-plates, or LEDs.
AMD has positioned its RX 470 in the sub-$200 market, listing its MSRP as $180. AIB partners will price their cards according to any custom coolers or pre-overclocks applied, though the floor has been set, more or less. That plants the 470 in a presently unchallenged market position: AMD's biggest current-gen competition in this price-range is its own RX 480 4GB card, the GTX 1060 being nVidia's lowest tier offering.
Before our deep-dive review on the Sapphire RX 470 Platinum, card architecture, thermal & endurance throttles, power, and FPS, let's run through the specs.
AMD's RX 480 Reference received our recommendation as a go-to for the $200-$300 market, but was immediately challenged by the release of the GTX 1060; the choice isn't so clear now, but both cards have appropriate use cases. Still, as with the Founders Edition card reviews, we recommended that our readers wait until AIB partner models of the RX 480 begin shipping, as the cooling performance will improve clock-rate stability on the Polaris 10 chip.
We finally received one of those AIB partner models. The MSI RX 480 Gaming X uses the Twin Frozr VI cooling solution – described in our Computex exclusive – and ships pre-overclocked to 1303MHz from ~1266MHz. The 8GB card's price should rest at $265, or $15 more than the reference RX 480 8GB ($250), and MSI will also be selling 4GB variants of the Gaming X. Our previous coverage of the RX 480 4GB vs. 8GB will help answer questions as to whether the lower capacity card is worth it.
AMD says the majority of its buyers prefer GPUs in the $100-$300 price-range, and as such, the company has shifted its launch away from “halo” products and toward that affordable segment. The focus for the RX 470 is on players sticking with 1080p, allowing the RX 480 to focus on the 1440p gamers.
The RX 470 uses the Polaris 10 GPU and has the same architecture as the RX 480, including compute pre-emption and asynchronous shaders, but is cut-down in stream processor count and clock-rate. The RX 470 will host 32 CUs, as opposed to the 36 CUs of the RX 480, and that puts us at 2048 stream processors. Knowing that each CU has 64 stream processors, none of this is actually new information yet – we'd already reported/calculated all this in our RX 480 review.
With no warning whatsoever, we received word tonight that nVidia's new version of the Titan X has been officially announced. The company likes to re-use names -- see: four products named "Shield" -- and has re-issued the "Titan X" badge for use on a new Pascal-powered GPU. The Titan X will be using GP102, a significantly denser chip than the GTX 1080's GP104-400 GPU.
GP102 is a 12B transistor chip with 11 TFLOPs of FP32 COMPUTE performance, 3584 CUDA cores clocked at 1.53GHz, and the card leverages 12GB of GDDR5X memory at 480GB/s memory bandwidth. We're assuming the Titan X's GDDR5X memory also operates at 10GHz, like its GTX 1080 predecessor.
Here's a thrown-together specs table. We are doing some calculations here (a ? denotes a specification that we've extracted, and one which is not confirmed). Unless nVidia is using an architecture more similar to the GP100 (detailed in great depth here), this should be fairly accurate.
Our thermal benchmarking has expanded to the point that the tests form our most comprehensive section of any review. For this content, we dig deep into endurance testing with nVidia's just-launched GeForce GTX 1060 Founders Edition card, comparing it to the MSI GTX 1060 Gaming X. The validation testing yields interesting results, particularly with regard to potential throttle points and dips in clock-rate. More on that in a bit.
Today marks the launch of the GTX 1060 ($250-$300), announced about ten days ago. The GTX 1060 fills the mid-range of the market as a 6GB solution on the 16nm FinFET process node debuted in Pascal, and that's done with GP106.
Our GTX 1060 Founders Edition & MSI 1060 Gaming X review looks at FPS (particularly vs. the 1070 and RX 480), Vulkan & Dx12 performance, thermals, noise, power, and overclocking results.
One of newest memory technologies on the market is HBM (High Bandwidth Memory), introduced on the R9 Fury X. HBM stacks 4 memory dies atop an interposer (packaged on the substrate) to get higher density modules, while also bringing down power consumption and reducing physical transaction distance. HBM is not located on the GPU die itself, but is on the GPU package – much closer than PCB-bound GDDR5/5X memory modules.