This generation's GPU battle is heating up. Beginning in May with the uber fast GeForce GTX 1080 aimed at 4K gamers, Nvidia's 16nm Pascal attack connected a few weeks after with the GTX 1070 delivering performance akin to a GTX 980 Ti for a heavily discounted price.

With the covers off Nvidia's latest cards, attending then turned to AMD's more than affordable offer, the Radeon RX 480. Naturally, at $200 to $240 the RX 480 wasn't taking on the $380 (currently $450) GTX 1070 and it certainly wasn't tangling with the $700 GTX 1080.

So leading upwardly to the RX 480's release it seemed like consumers would have an easy choice between AMD and Nvidia for the months to come: if you wanted an affordable sub-$300 graphics carte, AMD would be the obvious pick while folks spending more than than that would surely go for one of Nvidia's Pascal graphics cards.

However, as I was midway through writing the RX 480's review, Nvidia emailed us to confirm that a GTX 1060 was inbound and nosotros'd be notified of the release appointment at a after fourth dimension.

Nvidia soft-launched the GTX 1060 on July 7, at which fourth dimension information technology provided about of the GPU's specifications, showed off its Founders Edition graphics card and surprisingly fifty-fifty divulged pricing information.

This was no doubt a move to steal some of the RX 480'south thunder, in add-on to preliminary PCIe ability woes, timing couldn't have been worse for AMD. Thankfully the company swiftly addressed the RX 480'due south PCIe ability concerns and for that we commend them. AMD has also enjoyed some positive press thank you to its release of the Vulkan API for Doom which we'll look at in this review.

You could say that the battle between this generation'southward GPUs is just beginning. What we have is a $250 GTX 1060 ($300 for the Founders Edition) facing off confronting a $240 RX 480 8GB ($200 for the 4GB model) and this fight over the mid-range market should be groovy news for consumers.

The prices quoted above are in U.s.a. dollars and based on MSRPs set by AMD and Nvidia. Sadly, in that location are issues with those prices on both sides of the contend.

Availability appears to finally be picking up for Nvidia simply we have yet to see cards anywhere near its MSRP; meanwhile AMD'south lack of availability and partner cards is an outcome despite pricing aligning with its MSRP. Hopefully this will ameliorate soon only we almost expected this would happen afterwards such a long time on the 28nm process.

GP106 Upwardly Shut & Personal

The GeForce GTX 1080 and 1070 were built around the GP104 core, a 314mm2 die boasting an insane 7.2 billion transistor count. The GTX 1070 is of course a simplified version of the GTX 1080 despite featuring the aforementioned dice -- Nvidia simply disabled 5 of the SM units, effectively cutting the CUDA cadre count by 25%.

The new GTX 1060 is targeting a considerably lower price bespeak and therefore Nvidia has created what is a physically smaller GPU. At the middle of the GTX 1060 lies the newest Pascal GPU (codenamed GP106) which has a die measurement of just 200mm2, 36% smaller than the GP104.

Despite being much smaller, the GP106 supports all of the key Pascal architectural features, master among them being Simultaneous Multi-Projection (SMP).

All Pascal GPUs will accept the SMP Engine, which is located within the PolyMorph Engine at the end of the geometry pipeline and correct in front of the Raster Unit. With this characteristic, the GPU tin simultaneously map a single primitive on up to sixteen unlike projections from the same viewpoint.

Each project can be either mono or stereo. This features allows Pascal GPUs to accurately match the curved projection required for VR displays, the multiple project angles required for surround display setups, and other emerging display use cases. Nvidia says that in extreme cases, the SMP Engine can reduce the corporeality of required geometry work by up to 32x!

Unfortunately, this isn't something we are currently in a position to test but we do plan to carry out some in-depth VR benchmarking in the near time to come.

SLI? Not a take chances.

Both AMD and Nvidia have worked hard to reduce the bandwidth demands on the GPU for their latest generation Polaris and Pascal parts. For Nvidia this means implementing new 4:1 and eight:1 delta color pinch modes that provide more than options for compressing data to the GPU which the company claims can provide roughly xx% additional effective bandwidth to the GPU (the bodily amount will vary by game and scene) compared to their previous Maxwell based GPUs.

Whereas the GP104 can avowal as many equally 20 Streaming Multiprocessors (SMs) seen in the GTX 1080 the GTX 1060 has been outfitted with half that amount. Equally many of you will be aware, a Pascal SM comprise 128 CUDA cores, 256KB of register file chapters, a 96KB shared memory unit, 48KB of total L1 enshroud storage, and eight texture units. With 10 SMs, the GTX 1060 ships with a total of 1280 CUDA Cores and 80 Texture Units.

In curt, the core configuration has been reduced by 33% compared to the GTX 1070 and l% from the GTX 1080. Looking back to Maxwell, we see that the GTX 1060 features 25% more than cores than the GTX 960 but 23% fewer than the GTX 970. What's interesting here is that Nvidia is challenge GTX 980-like performance despite offering 38% fewer cores.

This is fabricated possible through the improved efficiency of Pascal. Nvidia says when developing the Pascal architecture, they were intensely focused on improving efficiency. Every unit within the GPU was scrubbed for ability, and disquisitional excursion paths were optimized to enable high clock speeds. The effect was their most efficient architecture yet capable of operating at frequencies previous unheard of for a GPU.

Whereas the GTX 980 operates at a boost clock of 1216MHz and the most extreme air-cooled overclocks only reached 1.4 to 1.5GHz, the GTX 1060 features a base clock operating speed of 1506MHz with an official boost clock speed of 1708MHz. Nvidia is suggesting overclocks of at least 2GHz on the GTX 1060 equally well so that volition be something to await at later in our review.

Feeding the GTX 1060 GPU data are six 32-chip retention controllers (192-bit total). Tied to each 32-scrap memory controller are eight ROP units and 256 KB of L2 cache. The total GP106 chip used in GTX 1060 ships with a full of 48 ROPs and 1536 KB of L2 cache. Coupled with 6GB of 8Gpbs GDDR5 retentiveness in that location is 192GB/southward of memory bandwidth bachelor. When compared to the GTX 1070 that's a 25% reduction in retentiveness bandwidth.

Finally, like the previous generation GTX 960, the new GTX 1060 is a 120w part and equally such only requires a single 6-pin PCIe connector. This means the TDP rating is twenty% slower than the RX 480 so Nvidia should avoid any PCIe power draw issues.

GTX 1060 Founders Edition

Available at release will be Nvidia's Founders Edition version of the GTX 1060, which of form comes at an incredible cost premium, this time some xx% more than the board partner cards despite having what is almost certainly going to exist an inferior cooler and board blueprint.

Moving by that issue, the card measures 250mm long and the PCB is actually only 175mm long while the libation overhangs by 75mm.

Although we don't concur with the price premium on the Founders Edition, we have to admit this is a nice reference card. I really liked the look of the GTX 1080 and 1070 Iron cards and the GTX 1060 FE has the same visual appeal. It's a loftier quality product and although information technology lacks a backplate the entire cooler has been constructed from alloys -- no plastic here.

Every bit always, we notice a blower style cooler that vents hot air out the rear of the chassis. The aluminum heatsink has been given a blackness pigment job and is clearly visible from the front. Information technology is worth zero that while the GTX 1060 should eat less ability than the RX 480, Nvidia has included a much larger heatsink so we expect the operating book to be low equally well as the thermals.

Any interesting blueprint choice of the GTX 1060 Founders Edition graphics card is the vi-pin PCIe power input placement. Ideally you want the power connector on elevation of the card toward the rear and that's exactly where you'll find it on this card. What's so odd then? Well, as mentioned earlier the libation overhangs the PCB by 75mm then yous would expect to discover the PCIe power connector at least 75mm from the end of the graphics card, just as it is on the RX 480.

Notwithstanding, Nvidia has removed the connector from the PCB and using old manner copper wires moved the connector off board to the rear of the carte. It is an obvious solution for peachy cable direction but not 1 we expected Nvidia to make, perhaps they are making some effort to justify that big price premium.

That said, onboard we find a very basic 3+1 phase power design. Despite that, Nvidia says there is a tremendous amount of headroom for overclocking. Their internal testing showed all boards are able to hitting speeds of 2GHz!

I really like the GTX 1060 Founders Edition's motorcar finished die cast aluminum body so it'll be interesting to see how board partner cards stack up. In fact, toward the end of this review I'll include a preview of the Gainward GTX 1060 GS card that we received just before the launch.