AMD Reveals Polaris 10 and 11 Market Positioning

While we’ve pretty much confirmed that GP104 will replace the current Maxwell chips with the new GTX 1080 and 1070, things are less clear from AMD. We got some clarification yesterday from the release of a new roadmap that appeared to show Polaris 10 replacing current Fiji cards. With a new statement as part of their Q1 earnings release, AMD is shedding a bit more light on where they see Polaris 11 fitting in.

“AMD demonstrated its “Polaris” 10 and 11 next-generation GPUs, with Polaris 11 targeting the notebook market and “Polaris” 10 aimed at the mainstream desktop and high-end gaming notebook segment. “Polaris” architecture-based GPUs are expected to deliver a 2x performance per watt improvement over current generation products and are designed for intensive workloads including 4K video playback and virtual reality (VR).”

From the statement, we can see that Polaris 11 is meant for mainstream desktop and high-end gaming notebook segment. To me, this suggests that Polaris 10 will be branded 480 and 480X which has been the mainstream segment. With at 2304 stream processors, this would make for a good 390X replacement and once you consider the significant improvements GCN 4.0 brings, it would be competitive with Fury. Polaris 11 seems to be targeting the low power segment with notebooks and like x70/x70X which have historically been the top end notebook cards.

If our speculation is correct, this means AMD is transitioning to a release schedule similar to Nvidia. The mainstream chip with Polaris 10 would come in first with a slight improvement over the current Fiji flagships. A few months later, in early 2017, we will see Vega with HBM2 come in as a true upgrade over Fury X. Starting off, it looks like GP104 and Polaris 10 will battle it out quite equally so it will be interesting to see how it all plays out.

AMD Graphics Roadmap Reveals Fiji Replacement

One of the biggest concerns about Polaris 10 has been whether or not it will be a true replacement for Fury X. With the latest leaks out, most of the information points to about 100W TDP with 2304 shaders and clock speeds around 1050Mhz. Compared to Nvidia’s Pascal GP104, this doesn’t sound very competitive, leading to concerns that Nvidia would dominate the high-end. With the release today of AMD’s more detailed roadmap, our concerns have been laid to rest.

The new official roadmap offers a bit more detail than the one AMD showed back at Capsaicin. The new one offers more detail around Polaris 10 and 11, with both chips working to replace the entire Fury and 300 series lineup. This means the top Polaris 11 chip will offer enough performance to at least match, if not exceed Fury X. This should be competitive enough against GP104. If the 2304 shader report is true, AMD has truly revamped GCN 4.0 into something that is significantly superior to GCN 1.0 while cutting power consumption at the same time.

The layout for Polaris compared to the current lineup also suggests there will be no rebrands for the 400 series. It suggests that Polaris 10 will go from about 490X to 480 while Polaris 11 will fill in 470X down to at least 460. With how well small die low power Polaris 11 has done, rebrands don’t really make any sense. Finally, Vega will drop in 2017 with HBM2 and not in late 2016 as some have hoped.

With the improvements AMD has done, I am really looking forward to what Polaris and GCN 4.0 will bring to the graphics landscape.

AMD May Launch Polaris R9 470 and R9 480 at Computex

Polaris 10 and 11 have long been tagged as releasing at Computex later this year. As we know from AMD directly, Polaris 10 will be the flagship chip while Polaris 11 will fill in the gap below. Previously, the expectation has been that Polaris 10 would do battle against GP104/GTX 1080 when that card launched. Now it seems that the card won’t be as high performing as we’ve come to expect.

According to the source, Polaris 10 won’t be the R9 490 and 490X we’ve come to expect as the GP104 challenger. Instead, the approximately 2304 core GPU (up to 2560) will be branded as the R9 480 or 480X. This is largely based on the clock speeds which have been reported as between 800-1050Mhz and the TDP of 110-135W. It’s hard to see how a 125W GPU will match the approx 250W GP104 that Nvidia will launch. Polaris 11 has also had its TDP leaked at 50W which is actually a bit higher than expected.

There is still some hope though as this information is reportedly from last month that has finally leaked out. This means AMD could have tweaked the TDP and clock speeds higher since then, perhaps to around 1200Mhz and 150W+ TDP. AMD has also introduced massive tweaks to GCN to achieve greater efficiency along with the move to 14nm. Nvidia may also have chosen to reintroduce FP64 compute units to Pascal GeForce which could take as much as 30% of the TDP, putting the GP104 at a real 200W worth of gaming performance. Either way, the battle between AMD and Nvidia will be heating up at Computex.

AMD Polaris Project F GPU Revealed

With Polaris only months away, more details about what Polaris 10 and 11 will look like are coming out. According to an ex-AMD employee profile on LinkedIn, a dGPU codenamed Project F is set to be built on GlobalFounrdies and Samsung 14nm LPP process. What’s more, the Project F GPU will be 232mm2, making the chips similar in size to the 232mmof Pitcairn and Curacao from the 28nm generation of GCN.

At 232mm2, Project F is a relatively small chip for a new process. This should give AMD a low-risk option to evaluate the 2nd generation 14nm process from GlobalFounrdies and Samsung focused on performance. With the use of the new process, the number of transistors will grow massively due to the increased transistor density over 28nm. This should let Project F to pack in at least 4-5 million transistors, putting it at least into the R9 380 and 380X (359mm2) performance range before considering any architectural improvements.

Finally, by using 14nm, Project F is most likely the GPU that AMD showed off back at CES that severely trounced the GTX 950 in performance per watt. With the larger die size, it stands to reason that the demo unit was likely underclocked a bit or not allowed to turbo, letting it be much more efficient. Even at full power, AMD likely has a card that will be much more efficient than Maxwell while offering significantly improved performance over the last generation at a similar cost.

AMD Polaris Will use HBM2 and GDDR5

Ever since HBM1 was revealed and launched with Fury X, many have been looking forwards to what HBM2 would bring along in 2016. While HBM1 brought large power savings and a major boost in memory bandwidth, it was largely limited to a relatively low 4GB capacity. HBM2, however, is set to provide a boost in capacity and bandwidth by increasing the number of stackable dies. We’re now getting reports that AMD’s upcoming Polaris chips will utilize HBM2.

As a major revamp of the GCN architecture, a Polaris flagship GPU would be the natural product to debut HBM2. A flagship GPU much more powerful than current generation chips due to the new architecture and process node would likely require more memory bandwidth to feed it and a high memory capacity as it would be meant for VR and 4K gaming. Being the largest chip in the lineup, the flagship would also benefit from the major power savings, helping offset its core power consumption. The confirmation of HBM2 also suggests that we will be getting high-end Polaris chips this year.

At the same time, AMD is also confirming that they will continue to use GDDR5 and likely GDDR5X as well. At CES, AMD showed off a low powered Polaris chip using GDDR5 that was able to provide the same performance as Nvidia’s GTX 950 but with a significantly lower power consumption. With such a leap in efficiency, the HBM2 chips will likely be light years ahead of current cards in terms of efficiency if GDDR5 already shows such massive gains.

AMD Polaris GPUs Spotted Shipping

When AMD unveiled their new Polaris architecture last week, details about the timeline were a bit scarce. Other than previous confirms about a mid -2016 launch for one of the Polaris cards, AMD had been mum about when Polaris would actually arrive. Now information has surfaced about Polaris shipments has been spotted. According to a shipment tracking site, 4 Polaris cards have already been shipped around, with the earliest from Jan 2015.

The more recent models were the C981 and C980 which shipped in late December and early January. Valued at 47,578 and 40,790 INR respectively, these should fall into the product lineup around the R9 390/390X. Surprisingly, the earliest Polaris shipment, the 913, was in January 2015, nearly a year ago. this means AMD has had working Polaris silicon for nearly a year. A 924 was also shipped in August. Given their reported value, these 2 chips will likely be mid-tier about where the R7 370 and R9 380 fall.

If AMD had Polaris working for them for nearly a year, it suggests that  a launch may come sooner than expected. This bolstered by the fact that AMD already has development advanced enough to show off a working demo at CES. Whatever the case, Polaris is fast approaching and will likely launch within 6 months.

AMD Polaris GPU Architecture Offically Unveiled

First leaked yesterday, we’re now able to bring you the full AMD presentation on their upcoming Polaris GPU architecture. Set to ship mid-2016, Polaris will be using a 14/16nm FinFET process and bring massive power consumption and efficiency improvements. According to RTG SVP Raja Koduri, AMD says the massive potential that would come out of moving to FinFETs and a lower process node at the same time and decided to design a new architecture just for that.

Not surprisingly, the biggest focus is on the efficiency side of things. AMD is claiming a historic leap in performance per watt that any Radeon GPU has ever seen. The key to this is the new compute units for Polaris, or GCN 4.0. While we can expect much remains similar to past GCN revisions, the new release will be adding more parts to make the chip more efficient. A more efficient hardware scheduler, primitive discard accelerator and improved memory compression are expected to help as well. While HBM(2) will help reduce power consumption, GDDR5X models will be launched first.

To show off their improved efficiency, AMD showed off working Polaris silicon with presumably GDDR5X. Facing off against a GTX 950 in an identical system, the Polaris part managed to pull 1.65x less power from the wall as a whole. Using only 86W total compared to the 140W on the Nvidia card. This was while both cards were running Star Wars Battlefront at 1080p 60fps. Even if some of the gains are coming from the FinFETs and die shrink, that is still pretty impressive as AMD has been lagging behind on this front. The demo GPU was made using Globalfoundries 14nm FinFET process fo what it’s worth but expect some 16nm parts from TSMC as well.

Just as AMD has done with previous GCN releases, Polaris will also see other parts of the modular system upgraded. These include the Command Processor, Geometry Processor, Multimedia Cores, Display Engine, L2 Cache and Memory Controller. For the Multimedia Cores, the biggest additions are support for 4K HEVC (h.265) encoding and decoding at 60 FPS which should be welcome as well as AMD continues to push HDR. On the connectivity side, DisplayPort 1.3, and, at long last, HDMI 2.0a are supported.

For AMD, 2016 will be a critical year as both their GPU and CPU get a major architectural overhaul at the same time they get a major process upgrade. If executed well, this may finally pull AMD out of it’s slow decline and bring the firmly back into the black. Whether that happens remains to be seen.

AMD Polaris Next-Gen GPU Details Leaked

Despite the Polaris launch still some time away, AMD is set to start releasing details for their upcoming graphics architecture. According to the leak, AMD will be revealing some key details to their post-GCN plans tomorrow. The biggest takeaway so far from Polaris is that AMD is moving onto their GCN 4.0 or 4th generation Graphics Core Next. This will be the first AMD GPUs to be manufactured using FinFETs and on a 14/16nm process.

AMD has stuck with the basic building blocks of GCN since it’s initial debut with Tahiti in early 2012. That was GCN 1.0 and further revisions came via GCN 1.1 in 2013 and 2015 with GCN 1.2. While AMD tends to use GCN 2.0 and GCN 3.0 when referring to the 2013 and 2015 releases, those updates haven’t been that drastic, and not quite deserving a full point bump. This time around, it looks like AMD is releasing something that is more deserving for jumping a full 1.0.

The key part of the update is undoubtedly the new GCN 4.0 units. While the leak details are a bit scant, AMD is planning on the introduction of the FinFETs to dramatically improve performance and efficiency. Other updated units include the Command Processor, Geometry Processor, Multimedia Cores, Display Engine, L2 Cache and Memory Controller. These updates should tie into helping AMD improve on their front end, increased compatibility with DX12/Vulcan, increased video decoding/encoding support, a greater colour space and better memory performance.

With AMD willing to start sharing some Polaris details with us, one can hope that these new chips will start launching soon. As the event happens, we will be sure to bring you more up to date and accurate information.

Images Courtesy of Videocardz