Subject: General Tech, Processors | May 6, 2014 - 12:19 AM | Scott Michaud
Tagged: Skylake, Intel, Broadwell
VR-Zone is returning to their "leak everything Intel has" gig with a few light details about Skylake, the architecture after Broadwell, and its accompanying 100-Series chipset. The main detail is that Skylake, despite Broadwell and its delays, is still expected for 2015. This sort of makes sense, because this architecture runs on the same 14nm fabrication process as Broadwell, but it is surprising nonetheless. Intel could have slowed down its entire release cycle to compensate for how difficult it is to make smaller transistors and keep a steady "Tick-Tock".
Or maybe they hope that the process shrink after Skylake, Cannonlake at 10nm, will be on schedule?
Image Credit: VR-Zone
The second major detail is the available sockets. A couple of years ago, there was a fear that Intel would drop LGA sockets, starting with Broadwell, and switch entirely to the non-replaceable BGA soldered-to-the-motherboard format. Intel has later decided to support LGA with Broadwell and that will continue with Skylake.
This leads us to the third major detail - product categories. There will be four of them in the consumer range: H (BGA) for regular notebooks, Y (BGA) for desktops and all-in-ones, U (BGA) for ultrabooks, and S (LGA) for standard desktop computers. The slide lists a few more details which I believe signify core count and GPU version. If so, the lineup of Skylake processors would be the following:
- (BGA) Quad Core Skylake-H with GT2 Graphics
- (BGA) Quad Core Skylake-H with GT4e Graphics, the successor to Iris Pro.
- (BGA) Dual Core Skylake-Y with GT2 Graphics
- (BGA) Dual Core Skylake-U with GT2 Graphics
- (BGA) Dual Core Skylake-U with GT3e Iris Pro Graphics
- (LGA) Quad Core Skylake-S with GT2 Graphics
- (LGA) Dual Core Skylake-S with GT2 Graphics
- (LGA) Quad Core Skylake-S with GT4e Graphics, the successor to Iris Pro.
The inclusion of an enthusiast, LGA SKU with GT4e graphics is promising, especially for us. We, of course, continue to want products that we can, you know, buy and put into our desktops at will. It will certainly be interesting to see how these GPUs perform and it could lead to some healthy SteamOS builds.
There's a lot of information here. Expect us to chew on this over the next little while.
Subject: Processors, Mobile | April 30, 2014 - 04:06 PM | Ryan Shrout
Tagged: Intel, clover trail, Bay Trail, arm, Android
While we are still waiting for those mysterious Intel Bay Trail based Android tablets to find their way into our hands, we met with ARM today to discuss quite few varying topics. One of them centered around the cost of binary translation - the requirement to convert application code compiled for one architecture and running it after conversion on a different architecture. In this case, running native ARMv7 Android applications on an x86 platform like Bay Trail from Intel.
Based on results presented by ARM, so take everything here in that light, more than 50% of the top 250 applications in the Android Play Store require binary translation to run. 23-30% have been compiled to x86 natively, 20-21% run through Dalvik and the rest have more severe compatibility concerns. That paints a picture of the current state of Android apps and the environment in which Intel is working while attempting to release Android tablets this spring.
Performance of these binary translated applications will be lower than they would be natively, as you would expect, but to what degree? These results, again gathered by ARM, show a 20-40% performance drop in games like Riptide GP2 and Minecraft while also increasing "jank" - a measure of smoothness and stutter found with variances in frame rates. These are applications that exist in a native mode but were tricked into running through binary conversion as well. The insinuation is that we can now forecast what the performance penalty is for applications that don't have a natively compiled version and are forced to run in translation mode.
The result of this is lower battery life as it requires the CPU to draw more power to keep the experience close to nominal. While gaming on battery, which most people do with items like the Galaxy Tab 3 used for testing, a 20-35% decrease in game time will hurt Intel's ability to stand up to the best ARM designs on the market.
Other downsides to this binary translation include longer load times for applications, lower frame rates and longer execution time. Of course, the Galaxy Tab 3 10.1 is based on Intel's Atom Z2560 SoC, a somewhat older Clover Trail+ design. That is the most modern currently available Android platform from Intel as we are still awaiting Bay Trail units. This also explains why ARM did not do any direct performance comparisons to any devices from its partners. All of these results were comparing Intel in its two execution modes: native and translated.
Without a platform based on Bay Trail to look at and test, we of course have to use the results that ARM presented as a placeholder at best. It is possible that Intel's performance is high enough with Silvermont that it makes up for these binary translation headaches for as long as necessary to see x86 more ubiquitous. And in fairness, we have seen many demonstrations from Intel directly that show the advantage of performance and power efficiency going in the other direction - in Intel's favor. This kind of debate requires some more in-person analysis with hardware in our hands soon and with a larger collection of popular applications.
More from our visit with ARM soon!
AMD Makes some Lemonade...
I guess we could say that AMD has been rather busy lately. It seems that a significant amount of the content on PC Perspective this month revolved around the AMD AM1 platform. Before that we had the Kaveri products and the R7 265. AMD also reported some fairly solid growth over the past year with their graphics and APU lines. Things are not as grim and dire as they once were for the company. This is good news for consumers as they will continue to be offered competing solutions that will vie for that hard earned dollar.
AMD is continuing their releases for 2014 with the announcement of their latest low-power and mainstream mobile APUs. These are codenamed “Beema” and “Mullins”, but they are based on the year old Kabini chip. This may cause a few people to roll their eyes as AMD has had some fairly unimpressive refreshes in the past. We saw the rather meager increases in clockspeed and power consumption with Brazos 2.0 a couple of years back, and it looked like this would be the case again for Beema and Mullins.
I was again expecting said meager improvements in power consumption and clockspeeds that we had received all those years ago with Brazos 2.0. Turns out I was wrong. This is a fairly major refresh which does a few things that I did not think were entirely possible, and I’m a rather optimistic person. So why is this release surprising? Let us take a good look under the hood.
Subject: General Tech, Processors, Mobile | April 16, 2014 - 05:40 PM | Scott Michaud
Tagged: Intel, silvermont, arm, quarterly earnings, quarterly results
Sean Hollister at The Verge reported on Intel's recent quarterly report. Their chosen headline focuses on the significant losses incurred from the Mobile and Communications Group, the division responsible for tablet SoCs and 3G/4G modems. Its revenue dropped 52%, since last quarter, and its losses increased about 6%. Intel is still making plenty of money, with $12.291 billion USD in profits for 2013, but that is in spite of Mobile and Communications losing $3.148 billion over the same time.
Intel did have some wins, however. The Internet of Things Group is quite profitable, with $123 million USD of income from $482 million of revenue. They also had a better March quarter than the prior year, up a few hundred million in both revenue and profits. Also, Mobile and Communications should have a positive impact on the rest of the company. The Silvermont architecture, for instance, will eventually form the basis for 2015's Xeon Phi processors and co-processors.
It is concerning that Internet of Things has over twice the sales of Mobile but I hesitate to make any judgments. From my position, it is very difficult to see whether or not this trend follows Intel's projections. We simply do not know whether the division, time and time again, fails to meet expectations or whether Intel is just intentionally being very aggressive to position itself better in the future. I would shrug off the latter but, obviously, the former would be a serious concern.
The best thing for us to do is to keep an eye on their upcoming roadmaps and compare them to early projections.
Subject: Processors | April 14, 2014 - 09:09 PM | Tim Verry
Tagged: z97, Intel, i7-4790, haswell refresh, haswell, h97
Intel is releasing a refreshed lineup of processors based on its latest generation “Haswell” micro-architecture. The new lineup is comprised of 27 new desktop processors and 17 new mobile CPUs (44 in total). The new chips will displace the existing Haswell processors at their existing price points with small clockspeed increases.
On the desktop side of things, the Haswell Refresh lineup includes four new Core i7, ten Core i5, five Core i3, five Pentium, and three Celeron processors. The new chips come in both standard and (multiple) lower-TDP variants. At the top end, Intel is introducing a new non-K part called the Intel Core i7 4790 which is a quad core (eight thread) processor clocked at 3.6 GHz with 8MB of L3 cache. The new CPU also comes in 65W i7-4790S (3.2 GHz) and 45W i7-4790T (2.7 GHz). The new desktop parts range in tray price from $45 to $303.
Additionally, Intel is updating its mobile lineup by introducing 17 new chips. The refreshed lineup includes six Core i7s, four Core i5s, five Core i3s, one Pentium, and one Celeron CPU. The mobile parts range in tray price from $75 to $434. Like the desktop range, the mobile chips come in multiple low power TDP SKUs. Five of the new chips are quad cores while the rest are dual cores.
Intel’s new refreshed Haswell processors are reportedly coming early next month as part of the "Haswell Refresh Platform." The chips will fully support motherboards based on Intel’s upcoming LGA 1150 9-series chipsets, and the various motherboard manufactures appear to be hard at work getting their lineups ready. As a result, enthusiasts can expect to see the new chips and motherboards (using the H97 and Z97 chipsets) on store shelves soon.
If you have not already bought into Haswell, the refreshed lineup is worth waiting for. if you are already running a Haswell-based system, upgrading to a refreshed Haswell CPU and H97 or Z97 motherboard makes much less sense. Instead, you should ride it out until Sky Lake or at least Broadwell (upgrade itch permitting, of course).
Subject: Processors | April 14, 2014 - 12:22 PM | Jeremy Hellstrom
Tagged: Kabini, linux, Athlon 5350, Athlon 5150, Sempron 3850, Semprov 2650, amd, athlon, sempron
An easy way to trim the cost of a lower end system is to skip Windows and install Linux, along with picking a less expensive AMD chip to power your system. AMD has recently gifted us with new Kabini based Sempron and Athlon chips, the most expensive of which is available for less that $70. For testing Phoronix used Ubuntu 14.04, the 3.14 kernel and Mesa 10.2 along with the Radeon 7.3.99 driver. You will be glad to know that there were no compatibility problems with Linux whatsoever, all CPUs performed more or less as expected as you can see for yourself in the full review.
"It's been a busy past few days since AMD launched their "AM1" Socketed Kabini APUs. After the initial Athlon 5350 Linux review on launch-day, I did some tests involving a faster kernel and newer Mesa code along with some reference DDR3 memory scaling benchmarks for these APUs with Jaguar processor cores. Since then the Athlon 5150 and Sempron 3850/2650 APUs arrived."
Here are some more Processor articles from around the web:
- AMD Athlon 5350 APU On Linux @ Phoronix
- AMD Athlon 5350 APU and AM1 Platform Review @ Legit Reviews
- AMD Athlon 5350 @ Kitguru
- AMD “Kabini” AM1 Athlon 5350 @ eTeknix
- AMD Athlon 5350 Kabini AM1 APU Review @ Modders-Inc
- The Workstation & Server CPU Comparison Guide @ Tech ARP
Subject: Processors | April 10, 2014 - 01:38 PM | Tim Verry
Tagged: sempron, Kabini, Athlon 5350, athlon, amd, AM1
AMD has officially announced its socketed Kabini chips and the AM1 platform. Information on the chips and motherboards have been slowly trickling out since CES, but now they are finally official and available for purchase at retail.
Specifically, AMD has launched four desktop Kabini processors under the Athlon and Sempron brands. In addition ASRock, ASUS, Biostar, ECS, Gigabyte, and MSI all have AM1 platform motherboards ready to accept the new AMD chips. The motherboards come in mini ITX and micro ATX form factors.
The AMD Athlon 5350 SoC Installed in the ASUS AM1I-A motherboard which was used in our full Kabini review.
All four of the AMD chips have 25W TDPs and integrated GPUs with 128 stream processors. The Kabini chips support four PCI-E 2.0 lanes, two SATA III 6 Gbps ports, two USB 3.0 ports, and eight USB 2.0 ports. Motherboard permitting, the Kabini GPU supports up to three display outputs (HDMI, DisplayPort, and VGA). The chips differ by CPU and GPU clockspeeds, core count, and DDR3 memory frequency support. On the low end, the $34 (MSRP) Sempron 2650 is a dual core part clocked at 1.45 GHz with a GPU clocked that 400 MHz that supports a maximum memory clockspeed of 1333 MHz. The top-end Athlon 5350 is a quad core processor clocked at 2.05 GHz with a GPU clocked at 600 MHz and supports DDR3 1600 MHz. This chips has a $59 MSRP. The desktop chips are similar to their mobile counterparts, with slight differences in clockspeed and (of course) price and the socketed implementation.
|Processor||TDP||CPU||L2 Cache||GPU||Maximum Memory Speed||Price|
|Athlon 5350||25W||4 cores @ 2.05 GHz||2MB||128 SPs @ 600 MHz||1600 MHz||$59|
|Athlon 5150||25W||4 cores @ 1.6 GHz||2MB||128 SPs @ 600 MHz||1600 MHz||$49|
|Sempron 3850||25W||4 cores @ 1.3 GHz||2MB||128 SPs @ 450 MHz||1600 MHz||$39|
|Sempron 2650||25W||2 cores @ 1.45 GHz||1MB||128 SPs @ 400 MHz||1333 MHz||$34|
The motherboards for the new Kabini processors will come in mini ITX and micro ATX. We previously covered AM1 platform boards from ASRock, Biostar, and MSI. In general, the boards offer up most of the standard IO and other functionality that enthusiasts are used to from existing AMD motherboards including multiple display outputs, networking, audio, and a plethora of USB ports on the rear IO panel and SATA ports, PCI Express slot(s), and two DDR3 DIMM slots internally. Interestingly, the boards are fairly bare and free from chipsets because the IO is included in the processor itself. This enables motherboards that are notably cheaper than, say, FM2+ and AM3 boards.
When AMD first launched the AM1 platform, the company stated that a combination of a Kabini chip and FS1b-socketed motherboard would add up to about $60. Now that the platform is official, retail prices are starting to pop up. With the Kabini processors and motherboards each ranging from around $30 to $60, AMD has technically hit that mark. Adding a hard drive, RAM, and enclosure will get you a baisc and complete system for less than $150.
AMD's Kabini chips are set to compete against Intel's Bay Trail-D processor which comes pre-soldered onto motherboards. The AM1 platform does look to be the slightly cheaper option that also gives users the choice of motherboard and the possibility of upgrading to soecketed Beema (Kabini's successor) SoCs.
If you are interested in desktop Kabini, be sure to check out our full review of the AMD Athlon 5350 at PC Perspective!
AMD Brings Kabini to the Desktop
Perhaps we are performing a study of opposites? Yesterday Ryan posted his R9 295X2 review, which covers the 500 watt, dual GPU monster that will be retailing for $1499. A card that is meant for only the extreme enthusiast who has plenty of room in their case, plenty of knowledge about their power supply, and plenty of electricity and air conditioning to keep this monster at bay. The product that I am reviewing could not be any more different. Inexpensive, cool running, power efficient, and can be fit pretty much anywhere. These products can almost be viewed as polar opposites.
The interesting thing of course is that it shows how flexible AMD’s GCN architecture is. GCN can efficiently and effectively power the highest performing product in AMD’s graphics portfolio, as well as their lowest power offerings in the APU market. The performance scales very linearly when it comes to adding in more GCN compute cores.
The product that I am of course referring to are the latest Athlon and Sempron APUs that are based on the Kabini architecture which fuses Jaguar x86 cores with GCN compute cores. These APUs were announced last month, but we did not have the chance at the time to test them. Since then these products have popped up in a couple of places around the world, but this is the first time that reviewers have officially received product from AMD and their partners.
Subject: General Tech, Graphics Cards, Processors, Shows and Expos | April 8, 2014 - 12:43 PM | Scott Michaud
Tagged: Intel, NAB, NAB 14, iris pro, Adobe, premiere pro, Adobe CC
When Adobe started to GPU-accelerate their applications beyond OpenGL, it started with NVIDIA and its CUDA platform. After some period of time, they started to integrate OpenCL support and bring AMD into the fold. At first, it was limited to a couple of Apple laptops but has since expanded to include several GPUs on both OSX and Windows. Since then, Adobe switched to a subscription-based release system and has published updates on a more rapid schedule. The next update of Adobe Premiere Pro CC will bring OpenCL to Intel Iris Pro iGPUs.
Of course, they specifically mentioned Adobe Premiere Pro CC which suggests that Photoshop CC users might be coming later. The press release does suggest that the update will affect both Mac and Windows versions of Adobe Premiere Pro CC, however, so at least platforms will not be divided. Well, that is, if you find a Windows machine with Iris Pro graphics. They do exist...
A release date has not been announced for this software upgrade.
Subject: Editorial, General Tech, Graphics Cards, Processors, Shows and Expos | March 29, 2014 - 10:45 PM | Scott Michaud
Tagged: gdc 14, GDC, GCN, amd
While Mantle and DirectX 12 are designed to reduce overhead and keep GPUs loaded, the conversation shifts when you are limited by shader throughput. Modern graphics processors are dominated by sometimes thousands of compute cores. Video drivers are complex packages of software. One of their many tasks is converting your scripts, known as shaders, into machine code for its hardware. If this machine code is efficient, it could mean drastically higher frame rates, especially at extreme resolutions and intense quality settings.
Emil Persson of Avalanche Studios, probably known best for the Just Cause franchise, published his slides and speech on optimizing shaders. His talk focuses on AMD's GCN architecture, due to its existence in both console and PC, while bringing up older GPUs for examples. Yes, he has many snippets of GPU assembly code.
AMD's GCN architecture is actually quite interesting, especially dissected as it was in the presentation. It is simpler than its ancestors and much more CPU-like, with resources mapped to memory (and caches of said memory) rather than "slots" (although drivers and APIs often pretend those relics still exist) and with how vectors are mostly treated as collections of scalars, and so forth. Tricks which attempt to combine instructions together into vectors, such as using dot products, can just put irrelevant restrictions on the compiler and optimizer... as it breaks down those vector operations into those very same component-by-component ops that you thought you were avoiding.
Basically, and it makes sense coming from GDC, this talk rarely glosses over points. It goes over execution speed of one individual op compared to another, at various precisions, and which to avoid (protip: integer divide). Also, fused multiply-add is awesome.
I know I learned.
As a final note, this returns to the discussions we had prior to the launch of the next generation consoles. Developers are learning how to make their shader code much more efficient on GCN and that could easily translate to leading PC titles. Especially with DirectX 12 and Mantle, which lightens the CPU-based bottlenecks, learning how to do more work per FLOP addresses the other side. Everyone was looking at Mantle as AMD's play for success through harnessing console mindshare (and in terms of Intel vs AMD, it might help). But honestly, I believe that it will be trends like this presentation which prove more significant... even if behind-the-scenes. Of course developers were always having these discussions, but now console developers will probably be talking about only one architecture - that is a lot of people talking about very few things.
This is not really reducing overhead; this is teaching people how to do more work with less, especially in situations (high resolutions with complex shaders) where the GPU is most relevant.
Get notified when we go live!