AMD Raven Ridge APUs May Combine Zen and Polaris With HBM

One of the first applications that came to mind with HBM was pairing it up with an AMD APU. Proven to work as VRAM with the Fiji GPUs last year, HBM also has possible applications to act as a high-speed cache for other applications where density is important. While we’ve known that AMD has been planning APUs with HBM, the latest report points to Raven Ridge, the 2017  series of APUs that follow Bristol Ridge, to have HBM.

According to the source, Raven Ridge will utilize AMD’s upcoming Zen CPU cores likely paired with Polaris GCN iGPU. With 14nmLPP and Polaris, AMD can stuff a much larger iGPU with their APUs without worrying too much about extra costs or ballooning die size. However, even with the current generation of APUs, the iGPU is bottlenecked at the high-end, something even DDR4 won’t fully solve.

In order to keep growing APU GPU performance, AMD also needs to increase the memory bandwidth. One way, of course, is to use eDRAM as Intel has done with notable success. That, however, is expensive, leading to the top SKUs costing near $400. In comes HBM to the rescue at a relatively lower cost, allowing a large yet budget friendly cache pool to help reduce bandwidth constraints. To produce this, AMD has tapped Amkor, the same firm that worked on Fiji interposers to package Raven Ridge.

With at least, 1GB HBM buffer, the APU will be very well fed, allowing for the iGPU to grow to at least R7 370 performance levels before running out of steam. AMD is also probably working on HMC to supplant HBM in the future as well. If AMD manages to pull this off, Raven Ridge will be the most potent APUs yet, securing the crown against Intel.

Intel Seeks AMD GPU Patent Licensing

After Samsung and Nvidia had their recent legal spat, more light has been shed on the world of GPU patents and licensing.  While Intel holds their own wealth of patents, no doubt some concerning GPUs, Nvidia and AMD, being GPU firms, also hold more important patents as well. With Intel’s cross-licensing deal with Nvidia set to expire in Q1 2017, the chip giant is reportedly in negotiations with AMD to strike up a patent deal.

Being one of the big two GPU designers, AMD probably has many important and critical GPU patents. Add in their experience with APUs and iGPUs, there is probably quite a lot there that Intel needs. With the Nvidia deal expiring, Intel probably sees a chance to get a better deal while getting some new patents as well. Approaching AMD also makes sense as being the smaller of the two GPU makers, AMD may be willing to share their patents for less. It’s also a way to inject some cash into AMD and keep it afloat to stave off anti-trust lawsuits.

AMD also has a lot to offer with the upcoming generation. The GPU designer’s GCN architecture is ahead of Nvidia’s when it comes to DX12 and Asynchronous Compute and that could be one area Intel is looking towards. Intel may also be forced into cross-licencing due to the fact with some many patents out there, there have to be some they are violating. The biggest question will be if AMD will consider allowing their more important and revolutionary patents to be licensed.

With the Nvidia deal being worth $66 million a quarter or $264 million a year, AMD has the chance to squeeze out a good amount of cash from Intel. Even though $264 million wouldn’t have been enough to put AMD in the black for 2015, it wouldn’t have hurt to have the extra cash.

Intel Claims iGPUs Faster than 80% of Discrete GPUs

One of the common complaints against Intel every time they launch a new generation of CPUs is the amount of die space used for the iGPU. Since Sandy Bridge, Intel has significantly improved their iGPU while CPU performance hasn’t moved much. This has all been worth it though as Intel is claiming once again that casual and even mainstream gamers don’t need a discrete graphics card anymore. In fact, according to Intel, iGPUs are now faster than 80% of discrete cards.

Of course, Intel is only claiming those numbers since the new Skylake Iris Pro HD 580 is a massive 50% leap up in performance over past iGPUs, placing it near the likes of the GTX 750 and R 250X. While these cards may be capable of 1080p at medium settings, any CPU with the 580 is likely outside a casual or mainstream gamer’s budget. The more tame HD 530 that most users have is unlikely to be useful for anything higher than 720p low/medium in any mainstream games. That makes it safe to say that the 750 and 250X are probably faster than 100% of iGPUs.

Nevertheless, iGPUs have become much more relevant than in the past. AMD has their own line of APUs and both firms undoubtedly want users to choose them not just based on CPU performance but for the iGPU as well. Even with all the talk, the move to 4K and VR and ever more demanding games at 1080p will likely move gaming out of reach for iGPUs once again.

AMD Zen APU with Insane Memory Bandwidth Spotted

Ever since Llano launched back in 2011, AMD has been pushing their APUs as being the next big thing. Combining a powerful CPU and GPU on one die, the APU allows even budget users to enjoy strong graphics to play games or use it for compute. In 2016, AMD is looking to combine their new Zen CPU architecture with their Polaris based graphics and it looks like something revolutionary will happen. According to a leaked paper, AMD may be planning a multi-core Zen APU coupled with a massive iGPU and an HBM cache with 128GB/s of bandwidth

For AMD, APUs have stayed strong even as their CPU line faltered, with their iGPU beating out Intel solutions. This changed though with Intel’s Iris Pro graphics that came with an eDRAM cache, with the high-speed cache helping put Intel neck and neck with AMD’s top APUs. The only bright side for AMD is that Intel’s chips have cost significantly more than AMD’s offerings. With the launch of a competitive CPU architecture in Zen, a new GPU architecture in Polaris and a large HBM cache, AMD has a chance to surge past Intel in this critical segment.

At a peak of 128GB/s, the HBM cache performs similarly to that of the memory of graphics cards like the GTX 760 and 960. If AMD adds in a high-performance iGPU, the APU has the chance to match or even exceed $150 graphics cards. With this APU, AMD is truly bringing gaming to the masses. Maybe in 2016, we may finally see AMD APUs powering Apple products.

Intel Prepping Skull Canyon Enthusiast NUC

With the increasing relevance of mobile and smaller form factors, Intel has been focusing a lot of their attention on this segment. According to leaked internal documentation, Intel is readying a new enthusiast-oriented NUC or Next Unit of Computing. Dubbed Skull Canyon, the new system will feature a Skylake based CPU paired with a potent Iris Pro iGPU in the tiny form factor.

Set to arrive in Q1 2016, Skull Canyon is expected to be the fastest NUC Intel has ever made yet. With the top end Iris Pro 580 graphics (GT4), this little NUC will offer potent graphics capability that should surpass most HTPCs. The iGPU will feature 576 ALUs, in 72 EUs, in a total 9 subslices. Paired with 128MB of eDRAM, this should allow for performance near GTX 750 or R7 370 levels. You can read more about our analysis of Skylake’s new graphics architecture here.

Given our experience with past NUCs, this should be paired with a dual-core i7 U series processor with Turbo Boost and Hyper-Threading. This should give the iGPU plenty of juice to ramp up clock speeds. However, with the enthusiast label, Intel may push things further this time around and opt for a quad -core chip. Expect to pay for this level of performance though as NUC’s are not cheap, least of all an enthusiast one.

Apple Considering Custom AMD Zen SoCs for iMac

Having moved from PowerPC to Intel’s x86 a little under a decade ago, it looks like Apple may be considering a CPU switch again. This time around, the rumours point o a much less dramatic change, with Intel being dropped in favour of AMD. This is due to AMD’s new Zen architecture which is expected to launch next year, with the new chips expected to improve their IPC by 40% and bring them much closer to Intel’s offerings. A move by Apple to use Zen would serve as a high-profile endorsement and an indicator of Zen’s performance.

One of the biggest reasons Apple may consider a change to AMD is due to the latter’s semi-custom designs. AMD allows their customers to make and choose their own style of APU SoC, allowing creative blends like the chips found in the PS4 and XBox One. While Intel’s move towards better iGPUs can be traced partially to pressure from Apple, AMD would allow more flexibility than Intel currently allows. It would allow Apple, for instance, to order a custom APU paired with HBM in a unique configuration available only to Apple.

Another reason is that Apple stands to save a good chunk of cash as AMD chips ar generally cheaper and the 2nd place chip manufacturer is in a worse bargaining position. While Apple could design their own chips, the need for x86 support still requires either Intel or AMD. Supporting AMD also allows Apple to gain a better bargain from Intel if Apple continues to source chips from the latter.

Apple has started a shift to include more AMD chips recently. Despite using Nvidia for a long period, Apple has moved to include AMD’s Radeon 7970, R9 285 and M370X in their systems. A move to using AMD CPUs and APUs makes sense as long as the performance and efficiency are there. As long as Apple can maintain their computing experience for users with ADM chips, it is unlikely many of Apple’s customers will care.

Thank you WCCFTech for providing us with this information 

Intel Skylake Gen9 iGPU Graphics Examined

While much of the focus for Skylake has been on the CPU side, Intel has also invested heavily in improving the iGPU side of things as well. As part of IDF 2015, Intel shared some details about what makes their iGPUs tick. Intel has long been improving their iGPUs and eroding the budget space for AMD and Nvidia.

With their Gen9/Skylake graphics, Intel largely makes iterative improvements. API support is one noticeable area of improvement with support improved to DX12/11.3, OpenCL and OpenGL 4.4. The architecture largely remains the same with the 3 domains of unslice, slice and subslice. For the unslice which is pretty much the GPU control unit, Intel introduced a number of improvements, most notably improved bandwidth to memory and better performance.

The biggest changes can be found in the slice, where all the Execution Units (EU) can be found. Each Alice is made up of 24 EUs which is the smallest iGPU Intel will ship in most cases. Here, Intel improved on MSAA performance for 2x, 4x and 8x while also adding 16x. While most iGPU gamers probably want higher fps rather than fewer jaggies, for the top end GT4 unit with eDRAM, 16x may be an option for say 720p.

 

Another major feature is the inclusion of lossless colour compression which is critical for the bandwidth starved iGPU. By compressing at up to a 2:1 ratio, 3-11% gains can be found in games as it increases the practical memory bandwidth for loading textures. Since the iGPUs have relatively low bandwidth and fast cache memory, moving textures from system ram quickly is critical. Both AMD and Nvidia have implemented lossless colour compression for their GPUs and it’s what allows the R9 380 and GTX 960 to have narrow 256 and 128-bit memory bus respectively. The lossless colour compression ties in with the improved ring, L3 and IMC bandwidth and latency. Other changes are an increase to the top GT4 SKU to have 72 EUs (3 slices), increased L3 cache available to the iGPU and improved pixel fill rate. This ties into the subslice which can now output up to 12 texels/CLK.

On the video front, Intel has improved their Codec support for encoding and decoding. HEVC (High-Efficiency Video Coding) 8bit, also known as H.265, encode and decode is supported and both VP8 and MJPEG decode added. HEVC 10bit is supported for decode but will require the use of the GPU and not dedicated hardware units. These additions should make streaming/recording HEVC 8bit on the iGPU much more palatable as you’re going to be losing a lot fewer frames compared to a software solution.

With Intel making such huge strides in the iGPU space, both AMD and Nvidia must be worried as Intel already dominates iGPU marketshare. AMD should probably update their APUs soon as well as they don’t yet support any form of large cache like HBM and Intel has caught up with important features like colour compression, API support and accelerated encoding/decoding. 2016 will be very interesting as AMD may finally catch up on the CPU front with Zen, HBM may be used as a cache and the GPU side continues to grow.

Intel Ultra Low Power Skylake-U Lineup Revealed

While much of the attention have been focused on the i7 6700K and the i5 6600K, Intel’s latest 14nm process should shine best in the power limited mobile environment. Intel intends to be mum about their other Skylake chips, but someone has leaked slides detailing the Skylake-U ultra low power lineup.

Starting off, all of the chips are dual-core only given the limited power envelope, with the i3, i5 and i7 having hyperthreading to expose 4 logical cores. We have 2 i7s with 4MB L3 cache that breach the 3Ghz barrier at max turbo while the i5 lineup loses 1MB of cache and tops off at 3Ghz. The i3 is limited to a much more pedestrian 2.3Ghz while the Pentium and Celerons are even slower and lose another MB of cache and hyperthreading. TDP remains low at 15W max with a configurable TDP that drops as low as 7.5W.

On the GPU side, we have the HD 530 for the i3 and above at 300/1000Mhz with the i7 variant boosting an additional 50Mhz. The Pentium and Celeron are paired with the slower HD 510 that clocks slower at 300/900Mhz, with the Pentium iGPU boosting 50Mhz higher. The Intel 520 should have 24EUs (Execution Unit) while nothing about the 510 has leaked yet. It will be interesting to see if the 34% promised gain over Broadwell iGPU will manifest in the 520 or will there be other higher end iGPUs launching later.

While the desktop side of things has shown lower levels of progress, the mobile side continues to show good improvement. It wasn’t long ago that mobile CPUs hit 35W TDPs with anemic iGPUs and poor battery life. Now, we will soon have chips that are leaps and bounds ahead of their predecessors with higher IPC, clock rates and better iGPU performance, all in a smaller, cooler, and more power efficient package.

Thank you FanlessTech for providing us with this information

Leaked Skylake Slides Suggest Focus on iGPU

More Skylake details have leaked out ahead of its August launch and this time around, we’re being treated to what appears to be official Intel slides. Once again, it seems like Intel is emphasizing the iGPU side of things though we do see that Intel expects some decent IPC gains for the CPU.

According to Intel, Skylake will bring IPC improvements of 10% to single threaded operations and 20% to multithreaded tasks. The single-threaded performance increase does seem to fall in the range we’ve seen from some leaked benchmarks which have put IPC improvements at about 8-11%. 10% is probably closer to a best case scenario all things being equal. The 20% on the multithreaded side of things also matches up with what we known, with leaked benchmarks showing strong improvements in multi-threaded efficiency and Hyper-Threading.

Real benefits from 14nm also show for the mobile side of things, with the increased power efficiency allowing much better CPU and iGPU performance for the low power Y SKUs. Intel is claiming about 30% improvement in battery life, which given that the CPU and iGPU only contribute a portion, is pretty amazing. A lot of value added features like better touch, audio, video and camera features are also being included. Overall, it looks like Intel is selling Skylake as an incremental improvement for desktops users but brings much more to mobile users.

Thank you FanlessTech for providing us with this information

Intel to Improve iGPU Performance With Skylake

Something that Intel always struggled with in the past was the internal graphics processing units (iGPU), mainly the performance (or lack of) compared to the AMD counterpart. Although, Intel did make an improvement thanks to the Iris and Iris Pro graphics cores.

With the upcoming launch of Intel Skylake processors, we can expect to see the new graphics cores utilised to the fullest potentials. The CPU’s will come in 4 key variants, Skylake-S (Desktop), Skylake-H (High-Performance Mobile), Skylake-Y (Low TDP) and Skylake-U (Ultra Low Power); all of which will be poised at all possible consumer markets in terms of price and performance.

Earlier today, WFFCTech compiled a list of the comparable differences between the Skylake and Broadwell variants of the iGPU. Thanks to Compubench, information was sourced regarding 3 new CPU’s, the Core m3-6Y30 which is the successor to the Core M5Y31, the Core i5-6200U which is the successor to the Core i5-5200U and finally an unknown CPU with Iris Graphics 540; which was compared against the Core i5-5257U with Iris Graphics 6100.

“The Core i5-6200U which is powered by the HD Graphics 520 iGPU is the successor of the Core i5-5200U that features the HD Graphics 5500 iGPU. Being a GT2 level Broadwell graphics chip, the HD Graphics 5200 features 24 execution units, 1300 million transistors and a clock speed ranging from 300 MHz (Base) up to 950 MHz (Boost) clock. The HD Graphics 520 iGPU could also be a GT2 level core with 24 execution units while the more performance heavy GT3e variants featured on faster Core i7 variants will be integrated with 48 execution units and 64 MB eDRAM LLC (Last Level Cache).”

“The Core M-6Y30 will be powered by the HD Graphics 515 iGPU that is the successor to the Core M-5Y31 which is part of the Broadwell-Y lineup that launched last year. The HD 5300 featured on the Core M-5Y31 is powered by 24 execution units and a clock speed of 300 MHz (Base) and 900 MHz (Boost) clock speeds. All Broadwell-Y Core M processors are based on the HD Graphics 5300 core which is the entry level iGPU chip but that will kind of change with Skylake-Y which will be getting GT1 and GT1.5 chips with 12 and 18 Execution units each that deliver better performance per core unit and faster clocks.”

“Finally we have the Iris Graphics 540 which is the successor to the Iris Graphics 6100. Note that these are not the Iris Pro variants being compared which feature higher execution units and clock speeds. The current Iris Graphics 6100 core features 48 Execution units, 1900 Million transistors and clock speeds of 300 MHz (base) and 1100 MHz (Boost). The Iris Graphics 540 will feature similar amount of execution units with faster clocks and a eDRAM cache of 64 MB. A faster GT4e graphics core is also confirmed which will be part of the Iris Pro Graphics 550 with 72 Execution units and 128 MB cache but we don’t have any specific results for the chip. The performance of these chips can be seen in the pictures below but do note that they aren’t represnetative of final performance nor do they showcase actual gaming performance you might expect from the processor it self. There are notable improvements from these chips which shows Intel did make some graphics architecture updates on Skylake platform.”

As you can see, there are noticeable improvements, but there is no information on the high-end i7-6700k or i5-6600k; which I’m sure is what everyone wants to see. Will you be buying a different variant of the Skylake line up other than the ‘K’ series? Let us know in the comments.

Intel Launches Broadwell Desktop At Last

Delayed so long that rumors were spreading that there would never be a desktop launch, Intel has at last launched Broadwell for the desktop. The meant to follow the Haswell Tock, Broadwell was aimed at improving efficiency, quite minor tweaks and a move to the 14nm process. The complexity of 14nm production caused Broadwell to be severely delayed, with only Core-M, a mobile variant, being released last year. Desktop users had to make do with Haswell-Refresh but no more.

While there are mobile Broadwell chips launching today, the focus is on the 5 desktop CPUs. There are the i5-5575R, i5-5675R, i5-5675C, i7-5775R, and i7-5775C. All 5 processors are compatible with Z97 and H97 motherboards. However, with the exception of the C processors, they are all BGA chips, meaning they come soldered directly onto the motherboard. This means the R chips, like the 4770R before, will likely only be sold by OEMs or as part of a motherboard bundle. The C chips being unlocked (C is the new K), are LGA and the standard BIOS update for your motherboard should suffice.

The biggest change is for the frist time, Intel’s Iris Pro graphics, in this case, HD6200, are being sold with an LGA and overclockable SKU. While most users getting an unlocked chip tend to use dGPU, the addition of a strong iGPU is good for cases where you need to do an RMA or the dGPU croaks. More importantly, Iris Pro graphics means the chip comes with Crystal well, a 128MB eDRAM that acts like L4 cache. This fast low latency memory can provide a boost to single threaded performance that many might be interested in.

Broadwell on desktop, despite being unlocked and with an eDRAM cache, may face a cold reception. Skylake, Intel’s next Tock with a new architecture, is set to release later this year. With its replacement on its way o soon, Broadwell may have a tough time convincing consumers it’s a viable choice. Maybe Intel may ver well surprise us by holding Skylake desktop back, or maybe it’ll refrain from offering eDRAM on the i7 6700K? The issue becomes dicier as Broadwell desktop is only set for public availability near the end of the month.

AMD Releases Mobile Carrizo APUs and Cuts Desktop Kaveri Pricing

AMD is busy releasing the OEM models and mobile solutions in order to get that part out of the way early as well as prevent anything from stealing news space from their highly anticipated next generation of CPUs, APUs and not to forget GPUs such as the R9 390x liquid cooled micro card.

This time around they’re ready with five new Carrizo mobile APUs that already have begun shipping and being available in Greater China. Worldwide availability will follow shortly as the chips make their way across the globe to manufacturers and resellers. The information is relative sparse at the moment, but we do know that none of them have a TDP higher than 25W and go all the way down to 2W, have two to four CPU cores and a clock speed up to 2.5GHz backed by up to 2MB cache. The only exception to the quad-core and 2MB cache scheme is the small AMD E1-7010 APU that only has half of both.

The Carrizo platform will be extended to the desktop market later and it will also enter the FX processor line-up. But until that time arrives, AMD cut the prices on the current Kaveri desktop APUs. Cheaper products is a thing that we always like to see and AMD cuts up to a third of their original pricing.

Thank you TomsHardware for providing us with this information

AMD A8-7650k Kaveri APU Review

Introduction


In January 2014 AMD unveiled its latest generation of accelerated processing units dubbed “Kaveri”. The range was formed of the A10-7850K flagship, the A10-7700K mid-range part and the entry-level & low power A8-7600; of which a previous comparison can be found here. These new range of APU’s brought forward a new leap in internal graphic processing units (iGPU); making them more powerful and energy-efficient than ever before. Today we have the newest addition to the lineup, the A8-7650k. This chip is based on the A8-7600, but has been given the famous AMD ‘Black Edition’ treatment, allowing the user to overclock the core somewhat freely. Pricing in today’s market is paramount, and producing a fully unlocked processor for the same price as its predecessor is mind-boggling.

AMD seem to know how to pile the goodies into their products, offering a multitude of graphical advantages at such a low price throughout its entire range of APU’s.

Are we expecting anything different with this newest addition? I’d say not, with the same architecture as its little brother, the A8-7600, but just an unlocked multiplier and configurable TDP, we may seem some small gains once overclocked.

Latest Intel Graphics Drivers Enhanced for 4th and 5th gen Core Processors

Timed for the release of the 5th generation of Intel Core processors, Intel released a new version of their graphics drivers that also brings along a long row of benefits for the current 4th generation.

Benefits of updating to this driver include addition of video playback of VP9 video format, for Chrome video playback and Google Hangouts for example, through partial hardware acceleration. Accelerated decoding of the HEVC video format for 4K Ultra HD video playback with both 8-bit and 10-bit support was added as well as and expanded Open CL and Open GL extension support.

Intel also fixed a long row of issues ranging from log off screens being displayed when changing display mode to ordinary bluescreen situations and issues with a long row of games such as Call of Duty, Quake 4, Sleeping Dogs, AC:Unity and more.

You can view a list of changes in the Release Notes and download the new drivers from Intel’s official website for 32bit and 64bit systems.

Thanks to Intel for providing us with this information

Leaked AMD A10-7850K Kaveri APU Cinebench Benchmark Revealed

AMD Kaveri APUs are expected to launch early next year housing SteamrollerB CPU cores and GCN 2.0 graphics. 3DMark scores have also been leaked of the flagship AMD A10-7850K APU, making it 40% faster than Haswell Core i5-4570K. The latest leak comes form a Japanese website leaked Cinebench R15 CPU benchmarks of A10-7850K as well.

It is said that AMD A10-7850K Kaveri APU will feature four SteamrollerB CPUs cores and GCN 2.0 Radeon graphics with DirectX 11.1 and AMD Mantle support. The CPU is expected to be 20% faster compared to Richland while the GPU will have a 30% performance gain over Richland. Kaveri APUs have a major advantage over Intel CPUs in terms of graphics since they come with discrete Radeon graphics iGPUs.

We can see that AMD A10-7850K will be compatible with Socket FM2+ (906) and will come with 4 MB L2 cache. It will also house GCN 2.0 Radeon R7 graphics with 512 Stream processors and the new Turbo Core 3.0 technology. AMD A10-7850K is manufactured using the 28 nm process, other than that not much is revealed. However, the screenshot tells us that the software failed to recognize the AMD A10-7850K’s iGPU, therefore any accurate information cannot be provided. The A10-7850K is reported to be 40% faster than Intel Core i5-4570K in 3DMark and 8% in PCMark 8. The disappoint comes in terms of CPU performance which is measured through Cinebnech R15.

AMD A10-7850K managed to score only 88 points in Cinebench R15 which is even slower than Intle Core i5-3317U (Low Voltage) SoC. Intel’s Core i7 4770K scores nearly double compared to A10-7850K. As long as the SteamrollerB cores do not bottleneck the GPU and compromise the performance in games, I think its good to go. Lets just wait for real world performance numbers.

Thank you Chip Loco for providing us with this information
Images courtesy of Chip Loco