Kaveri Goes Mobile
The processor market is in an interesting place today. At the high end of the market Intel continues to stand pretty much unchallenged, ranging from the Ivy Bridge-E at $1000 to the $300 Haswell parts available for DIY users. The same could really be said for the mobile market - if you want a high performance part the default choice continues to rest with Intel. But AMD has some interesting options that Intel can't match when you start to enter the world of the mainstream notebook. The APU was slow to develop but it has placed AMD in a unique position, separated from the Intel processors with a more or less reversed compute focus. While Intel dominates in the performance on the x86 side of things, the GPU in AMD's latest APUs continue to lead in gaming and compute performance.
The biggest problem for AMD is that the computing software ecosystem still has not caught up with the performance that a GPU can provide. With the exception of games, the GPU in a notebook or desktop remains under utilized. Certain software vendors are making strides - see the changes in video transcoding and image manipulation - but there is still some ground AMD needs to accelerate down.
Today we are looking at the mobile version of Kaveri, AMD's latest entry into the world of APUs. This processor combines the latest AMD processor architecture with a GCN-based graphics design for a pretty advanced part. When the desktop version of this processor was released, we wrote quite a bit about the architecture and the technological advancements made into, including becoming the first processor that is fully HSA compliant. I won't be diving into the architecture details here since we covered them so completely back in January just after CES.
The mobile version of Kaveri is basically identical in architecture with some changes for better power efficiency. The flagship part will ship with 12 Compute Cores (4 Steamroller x86 cores and 8 GCN cores) and will support all the same features of GCN graphics designs including the new Mantle API.
Early in the spring we heard rumors that the AMD FX brand was going to make a comeback! Immediately enthusiasts were thinking up ways AMD could compete against the desktop Core i7 parts from Intel; could it be with 12 cores? DDR4 integration?? As it turns out...not so much.
Subject: Graphics Cards, Processors | June 3, 2014 - 02:10 PM | Ryan Shrout
Tagged: Intel, amd, richard huddy
Interesting news is crossing the ocean today as we learn that Richard Huddy, who has previously had stints at NVIDIA, ATI, AMD and most recently, Intel, is teaming up with AMD once again. Richard brings with him years of experience and innovation in the world of developer relations and graphics technology. Often called "the Godfather" of DirectX, AMD wants to prove to the community it is taking PC gaming seriously.
The official statement from AMD follows:
AMD is proud to announce the return of the well-respected authority in gaming, Richard Huddy. After three years away from AMD, Richard returns as AMD's Gaming Scientist in the Office of the CTO - he'll be serving as a senior advisor to key technology executives, like Mark Papermaster, Raja Koduri and Joe Macri. AMD is extremely excited to have such an industry visionary back. Having spent his professional career with companies like NVIDIA, Intel and ATI, and having led the worldwide ISV engineering team for over six years at AMD, Mr. Huddy has a truly unique perspective on the PC and Gaming industries.
Mr. Huddy rejoins AMD after a brief stint at Intel, where he had a major impact on their graphics roadmap. During his career Richard has made enormous contributions to the industry, including the development of DirectX and a wide range of visual effects technologies. Mr. Huddy’s contributions in gaming have been so significant that he was immortalized as ‘The Scientist’ in Max Payne (if you’re a gamer, you’ll see the resemblance immediately).
Kitguru has a video from Richard Huddy explaining his reasoning for the move back to AMD.
This move points AMD in a very interesting direction going forward. The creation of the Mantle API and the debate around AMD's developer relations programs are going to be hot topics as we move into the summer and I am curious how quickly Huddy thinks he can have an impact.
I have it on good authority we will find out very soon.
Subject: Processors | June 3, 2014 - 02:30 AM | Ryan Shrout
Tagged: Intel, i7-4790k, devil's canyon, computex 2014, computex, 4790k
Back in March, we learned from Intel that they were planning to release a new Haswell refresh processor targeted at the overclocking and gaming market, code named Devil's Canyon. As we noted then, this new version of the existing processors will include new CPU packaging and the oft-requested improved thermal interface material (TIM). What wasn't known were the final clock speeds and availability time lines.
The new Core i7-4790K processor will ship with a 4.0 GHz base clock with a maximum Turbo clock rate of 4.4 GHz! That is a 500 MHz increase in base clock speed over the Core i7-4770K and should result in a substantial (~10-15%) performance increase. The processor still supports HyperThreading for a total of 8 threads and is fully unlocked for even more clock speed improvements.
All of the other specifications remain the same - HD Graphics 4600, 8MB of L3 cache, 16 lanes of PCI Express, etc.
Intel spent some time on the Devil's Canyon Haswell processors to improve the packaging and thermals for overclockers and enthusiasts. The thermal interface material (TIM) that is between the top of the die and the heat spreader has been updated to a next-generation polymer TIM (NGPTIM). The change should improve cooling performance of all currently shipping cooling solutions (air or liquid) but it is still a question just HOW MUCH this change will actually matter.
You can also tell from the photo comparison above that Intel has added capacitors to the back of the processor to "smooth" power delivery. This, combined with the NGPTIM should enable a bit more headroom for clock speeds with the Core i7-4790K.
In fact, there are two Devil's Canyon processors being launched this month. The Core i7-4790K will sell for $339, the same price as the Core i7-4770K, while the Core i5-4690K will sell for $242. The lower end option is a 3.5 GHz base clock, 3.9 GHz Turbo clock quad-core CPU without HyperThreading. While a nice step over the Core i5-4670K, it's only 100 MHz faster. Clearly the Core i7-4790K is the part everyone is going to be scrambling to buy.
Not to be left out, Intel is offering an unlocked Pentium processor for users on a tighter budget. This dual core CPU runs at 3.2 GHz base frequency and includes not just HD Graphics but support for QuickSync video.
At just $72, the Pentium G3258 will likely be a great choice for gamers that lean towards builds like the one we made for the Titanfall release.
I was hoping to have a processor in hand to run benchmarks and overclocking testing on, but they haven't quite made it to the office yet. The 4.0 GHz clock speed is easily emulated by any 4770K and some BIOS tweaks but the additional overclocking headroom provided by the changed thermal interface is still in question. Honestly, based on conversations with motherboard vendors, Devil's Canyon headroom is only 100-200 MHz over the base Haswell parts, so don't expect to reach 6.0 GHz all of the sudden.
Later in the week we'll have the Core i7-4790K in hand and you can expect a full review shortly thereafter.
Subject: Processors | May 28, 2014 - 05:09 PM | Sebastian Peak
Tagged: tablet, SoC, Rockchip, mobile, Intel, atom, arm, Android
While details about upcoming Haswell-E processors were reportedly leaking out, an official announcement from Intel was made on Tuesday about another CPU product - and this one isn't a high-end desktop part. The chip giant is partnering with the fabless semiconductor manufacturer Rockchip to create a low-cost SoC for Android devices under the Intel name, reportedly fabricated at TSMC.
We saw almost exactly the opposite of this arrangement last October, when it was announced that Altera would be using Intel to fab ARMv8 chips. Try to digest this: Instead of Intel agreeing to manufacture another company's chip with ARM's architecture in their fabs, they are going through what is said to be China's #1 tablet SoC manufacturer to produce x86 chips...at TSMC? It's a small - no, a strange world we live in!
From Intel's press release: "Under the terms of the agreement, the two companies will deliver an Intel-branded mobile SoC platform. The quad-core platform will be based on an Intel® Atom™ processor core integrated with Intel's 3G modem technology."
As this upcoming x86 SoC is aimed at entry-level Android tablets this announcement might not seem to be exciting news at first glance, but it fills a short term need for Intel in their quest for market penetration in the ultramobile space dominated by ARM-based SoCs. The likes of Qualcomm, Apple, Samsung, TI, and others (including Rockchip's RK series) currently account for 90% of the market, all using ARM.
As previously noted, this partnership is very interesting from an industry standpoint, as Intel is sharing their Atom IP with Rockchip to make this happen. Though if you think back, the move is isn't unprecedented... I recall something about a little company called Advanced Micro Devices that produced x86 chips for Intel in the past, and everything seemed to work out OK there...
When might we expect these new products in the Intel chip lineup codenamed SoFIA? Intel states "the dual-core 3G version (is) expected to ship in the fourth quarter of this year, the quad-core 3G version...expected to ship in the first half of 2015, and the LTE version, also due in the first half of next year." And again, this SoC will only be available in low-cost Android tablets under this partnership (though we might speculate on, say, an x86 SoC powered Surface or Ultrabook in the future?).
Subject: Processors | May 27, 2014 - 06:58 PM | Sebastian Peak
Tagged: X99, rumors, octocore, lga2011, Intel, Haswell-E, cpu
As with any high-profile release there have been rumors circulating around Intel's upcoming high-end desktop processors for the X99 chipset, and a report today from Chinese site Coolaler claims to have the specs on these new Haswell-E CPU's.
Of particular interest are the core counts, which appear to have been increased compared to the current Ivy Bridge-E products. The lineup will reportedly include a 6-core i7-5820K, 6-core i7-5930K, and 8-core i7-5960X. Yep, not only are we looking at an octo-core desktop part but now even the "entry-level" Extreme part might have 6 cores.
Nothing wrong with more cores (and this will be especially attractive if we see the same MSRP's as Ivy Bridge-E) but there might be one caveat with the i7-5820K, as the reported specs show fewer PCIe lanes on this CPU with 28, compared to the 40 lanes found on the higher Haswell-E parts (and all current Ivy-Bridge-E parts).
Haswell-E would still provide more lanes than the current desktop i7 parts (an i7-4770K has only 16), but the disparity would create an interesting quandary for a potential adopter. Though x8 connections for multi-GPU setups is par for the course already on non-X79 desktop systems, the SATA Express and M.2 standards will put more of a premium on PCIe lane allocation for storage going forward.
Of course no official word from Intel on the matter yet, and only speculation on pricing. This is completely unsubstantiated, but is certainly of interest - particularly as hex-core i7's previously commanded the pricing of a more premium part in each prior iteration.
Subject: Processors | May 19, 2014 - 11:13 AM | Ryan Shrout
Tagged: Intel, Broadwell, z97, krzanich
Apparently attending Maker Faire gets you more than a look at the latest hacked gadgets produced by the community. Reuters got to talk with Intel CEO Brian Krzanich who confirmed that the company's upcoming Broadwell architecture processors using the new 14nm process technology would be on store shelves in time for the holidays.
"I can guarantee for holiday, and not at the last second of holiday," Krzanich said in an interview. "Back to school - that's a tight one. Back to school you have to really have it on-shelf in July, August. That's going to be tough."
Dissecting that comment we can assume that Broadwell will likely be made available in September or October of this year. This becomes the most precise word from the mouth of Intel about the release of these new parts but of course there wasn't much detail to be had. Though "computers" was mentioned he did not specify notebooks, all-in-ones or desktops. And more importantly for our readers, he did not specify anything about the socketed parts we have been promised would run on the newly released Intel Z97 chipset.
Subject: General Tech, Graphics Cards, Processors, Mobile | May 15, 2014 - 05:02 PM | Scott Michaud
Tagged: nvidia, xaiomi, mipad, tegra k1
Tegra K1 is NVIDIA's new mobile processor and this first to implement the Kepler graphics architecture. In other words, it has all of the same graphics functionality as a desktop GPU with 364 GigaFLOPs of performance (a little faster than a GeForce 9600 GT). This is quite fast for a mobile product. For instance, that amount of graphics performance could max out Unreal Tournament 3 to 2560x1600 and run Crysis at 720p. Being Kepler, it supports OpenGL 4.4, OpenGL ES 3.1, DirectX 11 and 12, and GPU compute languages.
Xiaomi is launching their MiPad in Beijing, today, with an 8-inch 2048x1536 screen and the Tegra K1. They will be available in June (for China) starting at $240 USD for the 16GB version and going up to $270 for the 64GB version. Each version has 2GB of RAM, an 8MP rear-facing camera, and a 5MP front camera.
Now, we wait and see if any Tegra K1 devices come to North America and Europe - especially at that price point.
Another Boring Presentation...?
In my old age I am turning into a bit of a skeptic. It is hard to really blame a guy; we are surrounded by marketing and hype, both from inside companies and from their fans. When I first started to listen in on AMD’s Core Innovation Update presentation, I was not expecting much. I figured it would be a rehash of the past year, more talk about Mullins/Beema, and some nice words about some of the upcoming Kaveri mobile products.
I was wrong.
AMD decided to give us a pretty interesting look at what they are hoping to accomplish in the next three years. It was not all that long ago that AMD was essentially considered road kill, and there was a lot of pessimism that Rory Read and Co. could turn AMD around. Now after a couple solid years of growth, a laser-like focus on product development based on the IP strengths of the company, and a pretty significant cut of the workforce, we are seeing an AMD that is vastly different from the one that Dirk Meyers was in charge of (or Hector Ruiz for that matter). Their view for the future takes a pretty significant turn from where AMD was even 8 years ago. x86 certainly has a future for AMD, but the full-scale adoption of the ARM architecture looks to be what finally differentiates this company from Intel.
Look, I’m Amphibious!
AMD is not amphibious. They are working on being ambidextrous. Their goal is not only to develop and sell x86 based processors, but also be a prime moving force in the ARM market. AMD has survived against a very large, well funded, and aggressive organization for the past 35 years. They believe their experience here can help them break into, and thrive within, the ARM marketplace. Their goals are not necessarily to be in every smartphone out there, but they are leveraging the ARM architecture to address high growth markets that have a lot of potential.
There are really two dominant architectures in the world with ARM and x86. They power the vast majority of computing devices around the world. Sure, we still have some Power and MIPS implementations, but they are dwarfed by the combined presence of x86 and ARM in modern devices. The flexibility of x86 allows it to scale from the extreme mobile up to the highest performing clusters. ARM also has the ability to scale in performance from handhelds up to the server world, but so far their introduction into servers and HPC solutions has been minimal to non-existent. This is an area that AMD hopes to change, but it will not happen overnight. A lot of infrastructure is needed to get ARM into that particular area. Ask Intel how long it took for x86 to gain a handhold in the lucrative server and workstation markets.
Subject: General Tech, Processors | May 11, 2014 - 11:41 PM | Tim Verry
Tagged: ulv, mobile apu, laptop, Kaveri, APU, amd
According to leaked information, AMD will allegedly be releasing mobile versions of its Kaveri APU later this year. There are reportedly seven new processors aimed at laptops and tablet that follow the same basic design as their desktop counterparts: steamroller CPU cores paired with a GCN-based graphics portion and an integrated memory controller.
According to information obtained by WCCF Tech, AMD will release four ULV and three standard voltage parts. All but one APU will have four Steamroller CPU cores paired with an Radeon R4, R5, R6, or R7 graphics processor with up to 512 GCN cores. The mobile APUs allegedly range in TDP from 17W to 35W and support various AMD technologies including TrueAudio, Mantle, and Eyefinity.
An AMD slide showing a die shot of the desktop "Kaveri" Accelerated Processing Unit (APU).
Of the seven rumored APUs, two of them are OEM-only parts that feature the “FX” moniker. The FX-7500 is the fastest ULV (ultra-low voltage) APU while the FX-7600P is AMD’s flagship mobile processor.
The FX-7600P is the chip that should most interest mobile gamers and enthusiasts looking for a powerful AMD-powered laptop or tablet. This processor allegedly features four CPU cores clocked at 2.7GHz base (that turbo to a maximum of 3.6GHz), a GPU with 512 GCN cores clocked at a base of 600MHz and a boost clock of 666MHz. The chip further uses 4MB of L2 cache and is a 35W TDP part. This should be a decent processor for laptops, offering acceptable general performance and some nice mobile gaming with the beefy integrated GPU!
The leaked AMD mobile Kaveri APU lineup via WCCF Tech.
Of course, for productivity machines where portability and battery life are bigger concerns, AMD will reportedly be offering up the dual core A6-7000. This 17W ULV processor combines two cores clocked at 2.2GHz (3.0GHz boost), a GPU based on the Radeon R4 with 192 GCN cores (494MHz base and 533MHz boost), and 2MB of L2 cache. Compared to the FX-7600P (and especially the desktop parts), the A6-7000 sips power. We will have to wait for reviews to see how it performs, but it will be facing stiff competition from Intel’s Core i3 Haswell CPUs and even the Bay Trail SoCs which come in at a lower TDP and offer higher thread counts. The GPU capabilities and GPGPU / HSA software advancements (such as LibreOffice adding GPGPU support) will make or break the A6-7000, in my opinion.
In all, the leaked mobile chips appear to be a decent upgrade over the previous generation. The new mobile APUs will bring incremental performance and power saving benefits to bear against competition from Intel. I’m looking forward to more official information and seeing what the OEMs are able to do with the new chips.
Subject: Processors | May 8, 2014 - 12:26 AM | Tim Verry
Tagged: TrustZone, server, seattle, PCI-E 3.0, opteron a1100, opteron, linux, Fedora, ddr4, ARMv8, arm, amd, 64-bit
AMD showed off its first ARM-based “Seattle” processor running on a reference platform motherboard at an event in San Francisco earlier this week. The new chip, which began sampling in March, is slated for general availability in Q4 2014. The “Seattle” processor will be officially labeled the AMD Opteron A1100.
During the press event, AMD demonstrated the Opteron A1100 running on a reference design motherboard (the Seattle Development Platform). The hardware was used to drive a LAMP software stack including an ARM optimized version of Linux based on RHEL, Apache 2.4.6, MySQL 5.5.35, and PHP 5.4.16. The server was then used to host a WordPress blog that included stream-able video.
Of course, the hardware itself is the new and interesting bit and thanks to the event we now have quite a few details to share.
The Opteron A1100 features eight ARM Cortex-A57 cores clocked at 2.0 GHz (or higher). AMD has further packed in an integrated memory controller, TrustZone encryption hardware, and floating point and NEON video acceleration hardware. Like a true SoC, the Opteron A1100 supports 8 lanes of PCI-E 3.0, eight SATA III 6Gbps ports, and two 10GbE network connections.
The Seattle processor has a total of 4MB of L2 cache (each pair of cores shares 1MB of L2) and 8MB L3 cache that all eight cores share. The integrated memory controller supports DDR3 and DDR4 memory in SO-DIMM, unbuffered DIMM, and registered ECC RDIMM forms (only one type per motherboard) enabling the ARM-based platform to be used in a wide range of server environments (enterprise, SMB, and home servers et al).
AMD has stated that the upcoming Opteron A1100 processor delivers between two and four times the performance of the existing Opteron X series (which uses four x86 Jaguar cores clocked at 1.9 GHz). The A1100 has a 25W TDP and is manufactured by Global Foundries. Despite the slight increase in TDP versus the Opteron X series (the Opteron X2150 is a 22W part), AMD claims the increased performance results in notable improvements in compute/watt performance.
AMD has engineered a reference motherboard though partners will also be able to provide customized solutions. The combination of reference motherboard and ARM-based Opteron A1100 is known at the Seattle Development Platform. This reference motherboard features four registered DDR3 DIMM slots for up to 128GB of memory, eight SATA 6Gbps ports, support for standard ATX power supplies, and multiple PCI-E connectors that can be configured to run as a single PCI-E 3.0 x8 slot or two PCI-E 3.0 x4 slots.
The Opteron A1100 is an interesting move from AMD that will target low power servers. the ARM-based server chip has an uphill battle in challenging x86-64 in this space, but the SoC does have several advantages in terms of compute performance per watt and overall cost. AMD has taken the SoC elements (integrated IO, memory, companion processor hardware) of the Opteron X series and its APUs in general, removed the graphics portion, and crammed in as many low power 64-bit ARM cores as possible. This configuration will have advantages over the Opteron X CPU+GPU APU when running applications that use multiple serial threads and can take advantage of large amounts of memory per node (up to 128GB). The A1100 should excel in serving up files and web pages or acting as a caching server where data can be held in memory for fast access.
I am looking forward to the launch as the 64-bit ARM architecture makes its first major inroads into the server market. The benchmarks, and ultimately software stack support, will determine how well it is received and if it ends up being a successful product for AMD, but at the very least it keeps Intel on its toes and offers up an alternative and competitive option.