All | Editorial | General Tech | Graphics Cards | Networking | Motherboards | Cases and Cooling | Processors | Chipsets | Memory | Displays | Systems | Storage | Mobile | Shows and Expos
Subject: Processors | March 4, 2015 - 09:07 PM | Ryan Shrout
Tagged: GDC, gdc 15, Intel, Broadwell, iris pro, LGA1150, core i7
Consumer have been asking for it since the first time Intel announced it, but Iris Pro graphics is finally finding its way to the desktop, socketed market. Shown powering one of Dell's new 5K displays, this processor shipping in "mid-2015", is going to be configured with a 65 watt TDP and will be unlocked for overclockers to tweak. Intel first disclosed these plans way back in May of 2014 so we are going to be approaching the 12-month mark for availability.
It doesn't look special, but this system has the first desktop Iris Pro processor
In a new disclosure at GDC, Intel showed the first 5th Generation Core LGA-socketed CPU with Intel® Iris™ Pro graphics. This 65 watt unlocked desktop processor, available mid-2015, will bring new levels of performance and power efficiency to Mini PCs and desktop All-In-Ones. Since 2006 the 3D performance of Intel Graphics has increased nearly 100 fold (Intel 3DMark06 measurements) and powerful form factors from Acer, Medion and Intel’s own NUCs are becoming available with 5th Generation Intel Core processors with Intel Iris Graphics.
Under that little heatsink...
Details of this new CPU offering, including clock speed and graphics performance, are still unknown but Intel claims we will have this part in our hands in the near future. This isn't targeted to overtake consumers with mid-range discrete graphics systems but instead will bring users interested in a SFF or low power system with both home theater features and improved gaming capability. Our testing with Iris Pro graphics in notebooks has proven that the gaming performance gains can be substantial, but often the battery life demands have limited implementations from OEMs. With a desktop part, we might actually be able to see the full capability of an integrated GPU with embedded memory.
Subject: Graphics Cards, Processors | March 4, 2015 - 08:46 PM | Ryan Shrout
Tagged: GDC, gdc 15, API, dx12, DirectX 12, dx11, Mantle, 3dmark, Futuremark
It's probably not a surprise to most that Futuremark is working on a new version of 3DMark around the release of DirectX 12. What might be new for you is that this version will include an API overhead test, used to evaluate a hardware configuration's ability to affect performance in Mantle, DX11 and DX12 APIs.
While we don't have any results quite yet (those are pending and should be very soon), Intel was showing the feature test running at an event at GDC tonight. In what looks like a simple cityscape being rendered over and over, the goal is to see how many draw calls, or how fast the CPU can react to a game engine, the API and hardware can be.
The test was being showcased on an Intel-powered notebook using a 5th Generation Core processor, code named Broadwell. Obviously this points to the upcoming support for DX12 (though obviously not Mantle) that Intel's integrated GPUs will provide.
It should be very interesting to see how much of an advantage DX12 offers over DX11, even on Intel's wide ranges of consumer and enthusiast processors.
Subject: Processors | February 24, 2015 - 06:18 PM | Jeremy Hellstrom
Tagged: Puma+, Puma, Kaveri, ISSCC 2015, ISSCC, GCN, Excavator, Carrizo-L, carrizo, APU, amd
While it is utterly inconceivable that Josh might have missed something in his look at Carrizo, that hasn't stopped certain Canadians from talking about Gila County, Arizona. AMD's upcoming processor launch is a little more interesting than just another Phenom II launch, especially for those worried about power consumption. With Adaptive Voltage and Frequency Scaling the new Excavator based chips will run very well at the sub-15W per core pair range which is perfect for POS, airplane entertainment and even in casinos. The GPU portion speaks to those usage scenarios though you can't expect an R9 295 at that wattage. Check out Hardware Canucks' coverage right here.
"AMD has been working hard on their mobile Carrizo architecture and they're now releasing some details about these Excavator architecture-equipped next generation APUs."
Here are some more Processor articles from around the web:
- AMD's new Carrizo: The x86 notebook processor that thinks it's a GPU @ The Register
- AMD Carrizo APU Details Revealed @ TechARP
- AMD FX-8320E Performance On Linux @ Phoronix
- Intel Broadwell HD Graphics 5500: Windows 8.1 vs. Linux @ Phoronix
- Preliminary Tests Of Intel Sandy Bridge & Ivy Bridge vs. Broadwell @ Phoronix
Subject: General Tech, Processors, Systems | February 11, 2015 - 09:07 PM | Scott Michaud
Tagged: Intel, edison, meetup
This is just a quick note for a small subset of our audience. If any of our developer-minded readers are in the Phoenix, Arizona region on February 19th, Intel will be hosting a meetup at UAT (the University of Advancing Technology). The processor vendor will perform a technical presentation about the Edison Internet-of-Things (IoT) developer kit. Shortly after the presentation, the group will move to Aunt Chilada's for a social event.
The presentation will take place in the theatre (there is only one as far as I can tell) at 6:30pm. Admission is free and there will be 10 Intel Edison kits to be raffled. Food and beverages will be provided by Intel (at Aunt Chilada's restaurant).
Subject: General Tech, Processors | February 11, 2015 - 09:00 AM | Scott Michaud
Tagged: amd, amazon
So allegedly Amazon UK sold some AMD A8-7600 APUs, but they actually shipped Athlon 64 X2 5200+ CPUs. Despite what you would think, it was actually “dispatched and sold” by Amazon UK itself, rather than a dishonest seller who has some explaining to do. For those affected, Amazon is apparently handling customer service well, as expected, and promptly replacing the parts. It does not seem to affect other regions, and the problem started just a short time ago.
Unless you're Sebastian, these processors will not even fit in the motherboard socket. PC World has an interesting side-by-side comparison of the two pin configurations. They do not look alike at all. You should not have a hard time identifying the problem if you are careful enough to look before you insert, which is obviously something that you shouldn't have to do. Also, AMD refers customers to their authenticity support page for a few extra ways to be sure that the box that you got came from AMD.
What would be the most interesting part of this story is finding out what happened. Unfortunately, we probably will never know, unless it turns into a famous legal battle of some sort.
Subject: General Tech, Processors, Mobile | February 1, 2015 - 03:17 PM | Scott Michaud
Tagged: mt6753, mediatek
We do not talk about MediaTek's higher-end products too often. Part of that is because they use stock architectures, ARM's Cortex CPU, ARM's Mali GPU, and Imagination Technologies' PowerVR GPU, rather than designing their own CPU and/or GPU portion. Likewise, their design wins are also not covered too much on this site, such as the new Amazon Fire HD tablets, for their own reasons. They still make some interesting chips, though.
Image Credit: A Weibo user via GSM-Arena
The MediaTek MT6753 is a true eight-core, 64-bit ARM SoC. Its press release makes the rest of its details... confusing. The release claims that it is clocked at 1.5 GHz and contains an ARM Mali-T720 GPU that is capable of OpenGL ES 3.0 and OpenCL 1.2. The ARM Mali-T720 is actually capable of OpenGL ES 3.1 and OpenCL 1.1. This leads some sites to report that the MT6753 actually contains a Mali-T760, which is newer and can utilize OpenGL ES 3.1 and OpenCL 1.2 (it is also used in the MT6752 that was released several months ago). Other sites report what MediaTek claims.
GSM-Arena, one site that claims the (more-sensible) Mali-T760, also claims that the Cortex CPU cores can be clocked up to 1.7 GHz. This might not be inaccurate either, because it could be intended to run at ~1.3 to 1.5 GHz with a 1.7 GHz peak for vendors that want to take it to eleven. Alternatively, they could be wrong and it could peak at 1.5 GHz. We don't know, and MediaTek should be more clear about these important details.
Everyone seems to agree on the chip's networking capability, though. It will directly support LTE protocols for both China and western markets. This is expected to make them more competitive against Qualcomm, which might lead to more interesting designs.
Devices containing the MT6753 are expected to ship next quarter.
Subject: Processors | January 29, 2015 - 10:41 AM | Sebastian Peak
Tagged: rumor, processors, Kaveri, Godavari, cpu, Athlon X4, APU, amd
VR-Zone has published a report with a detailed slide showing upcoming AMD Godavari processors, and the updated lineup includes 12 new models.
The release schedule indicates a spring availability for most of the new APUs, with the Athlon X4 850 and 870K shipping in May. The APU line gets a new flagship desktop part with the A10-8850K, and this appears to be a higher-clocked version of the A10-7850K, with a 100MHz higher boost clock (4.1 GHz vs. 4.0 GHz) and a higher GPU clock of 856 MHz (vs. 720 MHz).
Of particular interest for the potential budget quad-core buyer is the Athlon X4 870K, a new 95W part which would presumably replace the X4 860K - a processor that has seen inconsistent availability (and is currently unavailable on Newegg). With more games being released that require a quad-core to run, these sub-$100 Athlon CPUs present a great value in constructing a low-cost gaming system these days.
The slide does not indicate a change in the 28nm process from Kaveri, and it should be safe to assume these will not represent a significant architectural change. The modest clock increases from Kaveri will result in some performance gains, and this is good for consumers assuming these will sell at the same price points as the outgoing models.
Subject: Processors | January 18, 2015 - 05:16 PM | Sebastian Peak
Tagged: SoC, rumor, processor, leak, iris pro, Intel, graphics, cpu, carrizo, APU, amd
A new report of leaked benchmarks paints a very interesting picture of the upcoming AMD Carrizo mobile APU.
Image credit: SiSoftware
Announced as strictly mobile parts, Carrizo is based on the next generation Excavator core and features what AMD is calling one of their biggest ever jumps in efficiency. Now alleged leaked benchmarks are showing significant performance gains as well, with numbers that should elevate the IGP dominance of AMD's APUs.
Image credit: WCCFtech
"The A10 7850K scores around 270 Mpix/s while Intel’s HD5200 Iris Pro scores a more modest 200 Mpix/s. Carriso scores here over 600 Mpix/s which suggests that Carrizo is more than twice as fast as Kaveri and three times faster than Iris Pro. To put this into perspective this is what an R7 265 graphics card scores, a card that offers the same graphics performance inside the Playstation 4."
While the idea of desktop APUs with greatly improved graphics and higher efficency is tantalizing, AMD has made it clear that these will be mobile-only parts at launch. When asked by Anandtech, AMD had this to say about the possibility of a desktop variant:
“With regards to your specific question, we expect Carrizo will be seen in BGA form factor desktops designs from our OEM partners. The Carrizo project was focused on thermally constrained form factors, which is where you'll see the big differences in performance and other experiences that consumers value.”
The new mobile APU will be manufactured with the same 28nm process as Kaveri, with power consumption up to 35W for the Carrizo down to a maximum of 15W for the ultra-mobile Carrizo-L parts.
Subject: Processors | January 15, 2015 - 03:41 PM | Jeremy Hellstrom
Tagged: Pentium G3258, overclock, Intel
You just don't see CPU overclocking guides much anymore, the process has become much easier over the years as Intel and AMD both now sell unlocked CPUs that they expect you to overclock and the motherboard tools and UEFI interfaces do a lot of the heavy lifting for you now. No longer are you doing calculations for frequency ratios or drawing on your CPU with conductive ink. Overclockers Club is revisiting those heydays with a guide on how to make your $70 3.2GHz Pentium G3258 into a more serious beast with a speed well over 4GHz. The steps for overclocking are not difficult but for those who do not have a background in overclocking CPUs, the verification testing steps they describe will be of great value. If you are already well versed in the ways of MemTest86 and Prime95 then perhaps it will be a nice reminder of the days of the Celeron and the huge increases in frequency that family rewarded the patient overclocker with.
"To reach 4.7GHz was a cinch once I adjusted all the smaller voltage settings. Like all overclockers, it was a journey with many failures along the way. One day it would boot and run Prime95, and the next time Windows would not load. It took a while to sort it out by backing down to 4.5GHz and raising each setting until I settled on the below settings."
Here are some more Processor articles from around the web:
- Pentium J2900 CPU Review @ Hardware Secrets
- Athlon 5150 CPU Review @ Hardware Secrets
- AMD FX-9590 @ Benchmark Reviews
- AMD FX-8320E @ Benchmark Reviews
Subject: General Tech, Processors, Mobile, Shows and Expos | January 7, 2015 - 08:04 PM | Scott Michaud
Tagged: smartwatch, mt2601, mediatek, ces 2015, CES
When you start getting into the wearables market, even mobile SoCs can be somewhat big and power-hungry. As such, we are seeing more innovation in processors that satisfy these lower classes (which could just be us paying more attention). The MediaTek MT2601 is one such device, which combines a pair of ARM Cortex-A7 cores (1.2 GHz) with an ARM Mali 400MP GPU (intended frequency unknown) on a
package PCB that is less than 480mm2. (Edit @ 9:48PM -- they seem to mean the SoC and other chips, like the Bluetooth module)
Of course, these chips are designed to be low cost, low power, and whatever performance can be squeezed out of those two requirements, so it might not be the most interesting SoC that we can talk about. Still, battery life has been a major hindrance to smart watches and other small, niche devices. It will be interesting to see new-generation devices that use these components.
Heck, if I had more time, I might even want to hack around with these directly.
Follow all of our coverage of the show at http://pcper.com/ces!
Subject: Processors | January 5, 2015 - 07:30 PM | Josh Walrath
Tagged: SoC, low power, Intel, Cherry Trail, cell phones, ces 2015, CES, Bay Trail, 14 nm trigate, tablets
It wouldn’t be CES if there wasn’t an Intel release. Today they are releasing their latest 14 nm Cherry Trail SOC. Very little information has been released about this part, but it is the follow-up to the fairly successful Bay Trail. That particular part was a second generation 22 nm part that exhibited very good power and performance characteristics for the price. While Bay Trail was not as popular as Intel had hoped for, it did have some impressive design wins in multiple market sectors.
The next generation process technology from Intel will improve power and performance for the Cherry Trail parts as compared to previous products. It will work in both Windows and Android environments. While Cherry Trail is x86, Intel has been working very closely with Google to get Android to work effectively and quickly with a non-ARM based ISA.
Intel is shipping these parts to their partners for integration into phones, tablets, and small form factor computers. We had previously seen Bay Trail parts integrated into low cost motherboards with the J1800 and J1900 SKUs from Intel. We can expect these products to be refreshed with the latest Cherry Trail products that are being released today.
There is very little information being provided by Intel about the nuts and bolts of the Cherry Trail products. Intel promises to release more information once their partners start announcing individual products. We know that these parts will have improved graphics performance and will exist in the same TDPs as previous Bay Trail products. Other than that, feeds and speeds are a big question for this latest generation part.
These products will be integrating Intel’s RealSense technology. Password-less security, gestures, and 3D camera recognition are all aspects of this technology. I am sure we will get more information on how this technology leverages the power of the CPU cores and GPU cores in the latest Cherry Trail SOCs.
Follow all of our coverage of the show at http://pcper.com/ces!
Subject: General Tech, Processors, Shows and Expos | January 5, 2015 - 10:00 AM | Scott Michaud
Tagged: iris graphics 6100, iris, Intel, hd graphics 6000, hd graphics 5500, ces 2015, CES, broadwell-u, Broadwell
When Intel launched Broadwell-Y in November, branded Core M by that point, they had a 4.5W processor that was just a little slower than a 15W Haswell Ultrabook CPU. This is quite a bit of power efficiency, although these numbers are maximum draw and might not be exactly proportional to average power under load.
At CES, Intel has launched Broadwell-U, which takes this efficiency and scales it up to 15W and 28W SKUs. The idea is that the extra thermal headroom will scale up for extra CPU and GPU performance. These are all BGA-attached components, which means that these processors need to be physically soldered to the motherboards -- they are destined for OEMs.
As an example of Broadwell-U's increased performance, the Core M 5Y70 has a base frequency of 1.1 GHz that can boost to 2.6 GHz; the top-end Broadwell-U has a base clock of 3.1 GHz and boosts to 3.4 GHz. From Core i3 up to Core i7, regardless of TDP, each of these processors are dual-core with HyperThreading (4 threads total). There is also a single Pentium and two Celeron SKUs, which are dual-core without HyperThreading (2 threads total).
Its GPU receives a large boost as well, particularly with the 28W SKUs receiving Iris Graphics 6100, although Iris Pro Graphics (6200 and 6300) do not yet make an appearance. If we had access to the number of execution units and we assumed the same instruction-per-clock count as Iris Graphics 5100, we would be able to calculate a theoretical FLOP figure, but that is information that we do not have. It would make sense if it were 48 execution units, twice Core M and consistent with the official die shot that Intel doesn't actually identify by product number. This would give it about 845 GFLOPs of performance, or about an OEM NVIDIA GeForce GTX 460 (the retail GTX 460 cards were about 4% faster than the OEM ones).
It is also within 2% of Haswell's Iris 5100 theoretical GFLOPs, albeit with a 15% drop in clock rate.
From a features standpoint, the GPU is a definite step-up. It has “Enhanced” hardware support for VP8, VP9, and h.265 (HEVC) video and 4K UltraHD output, wired or by Intel WiDi. Broadwell's iGPU was designed with DirectX 12 in mind and supports OpenCL 2.0 -- leaving NVIDIA behind in that regard, since AMD added that API in last month's Omega driver.
Intel is slightly behind in OpenGL support however, claiming 4.3 compatibility while AMD is at 4.4 and NVIDIA is at 4.5. This could mean that these GPUs do not (unless a future driver changes this) support “Efficient Multiple Object Binding”, “Sparse Texture Extension”, or “Direct State Access”. Then again, they could support these features as extensions or something, because it is OpenGL and extensions are its thing, but you know -- they're obviously missing some part of the spec, somewhere.
This leaves Broadwell-H and Broadwell-K, high performance BGA and socketed LGA respectively, to launch later in the year. These products will have significantly higher TDPs and stronger performance, at the expense of battery life (a non-issue for the desktop-bound -K parts) and heat.
Follow all of our coverage of the show at http://pcper.com/ces!
Subject: General Tech, Processors, Systems | December 23, 2014 - 04:07 AM | Scott Michaud
Tagged: x86, Nintendo, arm, amd
The tea leaves that WCCFTech have been reading are quite scattered, but they could be right. The weaker half is pulled from an interview between Shigeru Miyamoto and the Associated Press. At the very end, the creator of many Nintendo franchises states, “While we're busy working on software for the Wii U, we have production lines that are working on ideas for what the next system might be.”
Of course they do. That is not confirmation of a new console.
Original Mario Bros. Screenshot Credit: Giant Bomb (Modified)
A bit earlier, he also states, “I think that maybe when we release the next hardware system, you can look forward to seeing Mario take on a new role or in a new game.”
This, on the other hand, sounds a little bit like they are iterating on game design ideas that will shape the next console. From what I understand, this is how Nintendo tends to work – they apparently engineer hardware around concept use cases. It could also be a mistake.
The rumor's stronger half is a statement from Devinder Kumar, the CFO of AMD.
“I will say that one [design win] is x86 and [another] is ARM, and at least one will [be] beyond gaming, right,” said Devinder Kumar, chief financial officer of AMD, at the Raymond James Financial technology conference. “But that is about as much as you going to get out me today. From the standpoint [of being] fair to [customers], it is their product, and they launch it. They are going to announce it and then […] you will find out that it is AMD’s APU that is being used in those products.”
So AMD has secured design wins from two companies, one gaming and the other is something else. Also, one design will be x86 and the other will be ARM-based. This could be an awkward co-incidence but, at the same time, there are not too many gaming companies around.
Also, if it is Nintendo, which architecture would they choose? x86 is the common instruction set amongst the PC and other two consoles, and it is easy to squeeze performance out of. On the other hand, Nintendo has been vocal about Apple and the mobile market, which could have them looking at ARM, especially if the system design is particularly abnormal. Beyond that, AMD could have offered Nintendo an absolute steal of a deal in an effort to get a high-profile customer associated with their ARM initiative.
Or, again, this could all be coincidence.
Subject: General Tech, Processors | December 16, 2014 - 11:00 AM | Scott Michaud
Tagged: Intel, holiday, devil's canyon, 10 days of christmas
Are you still hunting for that perfect gift for the hardware and technology fan in your life? Or maybe you are looking for recommendations to give to your friends and family about what to buy for YOU? Or maybe you just want something new and cool to play with over the break? Welcome to PC Perspective's 10 Days of Christmas where we will suggest a new item each day for you to consider. Enjoy!
Today, we go from rusty gates (or rather cutting the bolts off of them with a Dremel) to tri-gates. Either way, you are probably looking for hardware that prides itself on variable speed. If you are looking to build or upgrade an upper-mainstream desktop PC, then the Intel Core i7-4790K is the last stop before Haswell-E.
The CPU, codenamed Devil's Canyon, was Intel's offering for mainstream gamers and non-Enthusiast (capital E) enthusiasts during their Haswell refresh. It is cooler than its 4770K predecessor due to an improved thermal interface under the processor lid. It is a deal this week because its price dropped down to $299.99, which is about $50 below Intel's list price.
If you are having trouble picking out a gift for a loved one, consider buying an Amazon.com gift card! Amazon has basically every product on the planet for your gift recipient to order and purchasing gift cards through these links directly sponsors and supports PC Perspective! And hey, if you were to buy gift cards for yourself to do your own Amazon-based Christmas shopping...that wouldn't exactly be a bad thing for us either! ;)
Did you miss any of our other PCPer 10 Days of Christmas posts?
Subject: Processors | November 21, 2014 - 04:08 PM | Sebastian Peak
Tagged: quad core, pentium, gaming, far cry 4, dual-core, dragon age inquisition, cpus, budget, athlon
A new report covering dual-core woes with Far Cry 4 paints a "bleak future" for budget gamers.
Image credit: Polygon
For a while now the dual-core Pentium processors have been a great option for budget gaming, with the Pentium G3220 and newer G3258 Anniversary Edition taking center stage in a number of budget gaming builds. Today, we may be nearing the end of the road for dual-core CPUs entirely as a couple of high-profile games now require a quad-core CPU.
Is the anniversary really...over?
Far Cry 4 won't even open with a dual-core CPU installed, and while the game will load when using dual-core CPU's with hyper-threading enabled (for 4 total "cores") the performance isn't very good. PC World's article points to users "reporting that Far Cry 4 flat-out refuses to work with 'straight' dual-core PCs - chips that don’t use hyperthreading to 'fake' having additional cores." The article references a "black-screen 'failure to launch' bug" being reported by users with these dual-core chips.
This should come as good news for AMD, who has embraced quad-core designs throughout their lineup, including very affordable offerings in the budget space.
Image credit: AMD
AMD offers very good gaming performance with a part like the Athlon X4 760K, which matched the Pentium G3220 in our budget gaming shootout and was neck and neck with the Pentium in our $550 1080p gaming PC article back in April. And the Athlon 760K is now selling for just under $77, close to the current best-selling $70 Pentium.
Ubisoft has made no secret of their new game's hefty system requirements, with an Intel Core i5-750 or AMD Phenom II X4 955 listed as the minimum CPUs supported. Another high-profile new release, Dragon Age: Inquisition, also requires a quad core CPU and cannot be played on dual-core machines.
Image credit: Origin
Looks like the budget gaming landscape is changing. AMD’s position looks very good unless Intel chooses to challenge the under $80 price segment with some true quad-core parts (and their current 4-core CPUs start at more than twice that amount).
Subject: Processors | November 20, 2014 - 01:31 PM | Josh Walrath
Tagged: amd, APU, carrizo, Carrizo-L, Kaveri, Excavator, Steamroller, SoC, Intel, mobile
AMD has certainly gone about doing things in a slightly different manner than we are used to. Today they announced their two latest APUs which will begin shipping in the first half of 2015. These APUs are running at AMD and are being validated as we speak. AMD did not release many details on these products, but what we do know is pretty interesting.
Carrizo is based on the latest iteration of AMD’s CPU technology. Excavator is the codename for these latest CPU cores, and they promise to be smaller and more efficient than the previous Steamroller core which powers the latest Kaveri based APUs. Carrizo-L is the lower power variant which will be based on the Puma+ core. The current Beema APU is based on the Puma architecture.
Roadmaps show that the Carrizo APUs will be 28 nm products, presumably fabricated by GLOBALFOUNDRIES. Many were hoping that AMD would make the jump to 20 nm with this generation of products, but that does not seem to be the case. This is not surprising due to the limitations of that particular process when dealing with large designs that require a lot of current. AMD will likely be pushing for 16 nm FinFET for the generation of products after Carrizo.
The big Carrizo supposedly has a next generation GCN unit. My guess here is that it will use the same design as we saw with the R9 285. That particular product is a next generation unit that has improved efficiency. AMD did not release how many GCN cores will be present in Carizzo, but it will be very similar to what we see now with Kaveri. Carrizo-L will use the same GCN units as the previous generation Beema based products.
I believe AMD has spent a lot more time hand tuning Excavator instead of relying on a lot of automated place and route. This should allow them to retain much of the performance of the part, all the while cutting down on transistor count dramatically. Some rumors that I have seen point to each Excavator module being 40% smaller than Steamroller. I am not entirely sure they have achieved that type of improvement, but more hand layout does typically mean greater efficiency and less waste. The downside to hand layout is that it is extremely time and manpower intensive. Intel can afford this type of design while AMD has to rely more on automated place and route.
Carrizo will be the first HSA 1.0 compliant SOC. It is in fact an SOC as it integrates the southbridge functions that previously had been handled by external chips like the A88X that supports the current Kaveri desktop APUs. Carrizo and Carrizo-L will also share the same infrastructure. This means that motherboards that these APUs will be soldered onto are interchangeable. One motherboard from the partner OEMs will be able to address multiple markets that will see products range from 4 watts TDP up to 35 watts.
Finally, both APUs feature the security processor that allows them access to the ARM TrustZone technology. This is a very small ARM processor that handles the secure boot partition and handles the security requests. This puts AMD on par with Intel and their secure computing solution (vPro).
These products will be aimed only at the mobile market. So far AMD has not announced Carrizo for the desktop market, but when they do I would imagine that they will hit a max TDP of around 65 watts. AMD claims that Carrizo is one of the biggest jumps for them in terms of power efficiency. A lot of different pieces of technology have all come together with this product to make them more competitive with Intel and their process advantage. Time will tell if this is the case, but for now AMD is staying relevant and pushing their product releases so that they are more consistently ontime.
Subject: General Tech, Processors, Mobile | November 19, 2014 - 07:36 PM | Scott Michaud
Tagged: x86, restructure, mobile, Intel
Last month, Josh wrote about Intel's Q3 earnings report. The company brought in $14.55 billion USD, of which they could keep $3.31 billion. Their PC group is responsible for $9 billion of that revenue and $4.12 billion of that profit, according to the Wall Street Journal. On the other hand, their mobile division is responsible for about $1 million – and it took over a billion to get that million. This has been the trend for quite some time now, as Intel pushes their square battering ram into the mobile and tablet round hole. Of course, these efforts could benefit the company as a whole, but they cannot show that in a quarterly, per-division report.
And so we hear rumors that Intel intends to combine their mobile and PC divisions, which Chuck Mulloy, an Intel spokesperson, later confirmed in the same article. The new division, allegedly called the “Client Computing” group in an internal email that was leaked to the Wall Street Journal, will handle the processors for mobile devices but, apparently, not the wireless modem chipsets; those will allegedly be moved to a “wireless platform research and development organization”.
At face value, this move should allow Intel to push for mobile even more aggressively, while simultaneously reducing the pressure from investors to give up and settle for x86 PCs. Despite some differences, this echos a recent reorganization by AMD, where they paired-up divisions that were doing well with divisions that were struggling to make a few average divisions that were each treading water, at least on paper.
The reorganization is expected to complete by the end of Q1 2015, but that might not be a firm deadline.
Subject: Processors | November 3, 2014 - 02:38 PM | Jeremy Hellstrom
Tagged: Sempron 2650, low cost, Intel, Celeron J1800, asus AM1M-A, ASRock D1800M, amd
For a mere $60 you can get the ASRock D1800M motherboard with a Celeron J1800 installed, or for about $8 more you can get a socketed Sempron 2650 and compatible motherboard. After that it is merely a matter of adding a PSU, RAM and storage and you have a working machine for very little cost. Those were the systems which Hardware Secrets tested out to see which low cost, low powered system made more sense to purchase for light browsing and media consumption. As you would expect the 1Ghz clock advantage that the Celeron enjoys pushed its performance above the Sempron in all tests but 3D Mark but what is interesting is that the performance gap was nowhere near as large a percentage difference as the clock speed. While it is clear that the Celeron runs cooler, quieter and faster the fact that the AMD solution is socketed might sway some buyers decision. Check out the full review if you are interested in working machines that cost less than $200 to assemble.
"Both AMD and Intel recently released new families of low cost, low TDP desktop CPUs. AMD launched the AM1 platform with Sempron and Athlon "Kabini" processors, while Intel released the "Bay Trail-D" Celeron and Pentium CPUs, recognizable by the use of the letter "J" on the model naming. Among the lowest-end models of each family are, respectively, the AMD Sempron 2650, and the Intel Celeron J1800. Let's compare the performance of those CPUs and discover which one is the best buy in the low-end market segment."
Here are some more Processor articles from around the web:
- AMD FX-9590 Processor Review: Brute Almighty @ Modders-Inc
- AMD FX-8370 and FX-8370e Review @HiTech Legion
- Intel Core i7 5820K Haswell-E @ Kitguru
- Intel Core i7-5960X Extreme Edition, Core i7-5930K and Core i7-5820K @ X-bit Labs
- Core i7-5960X 5930K 5820K Overclocking & Performance @ [H]ard|OCP
Subject: Processors | October 29, 2014 - 05:44 PM | Scott Michaud
Tagged: Intel, Haswell-E, Haswell-EX, Ivy Bridge-EX
Last February, Intel launched the Xeon E7 v2 line of CPUs. Based on the Ivy Bridge architecture, they replaced the original Xeon E7s, developed from Sandy Bridge, that were released in April 2011. Intel is now planning to release Haswell-EX in the second quarter of 2015. No specific SKUs are listed, this information describes the product family as a whole.
This is Ivy Bridge-EX. Haswell-EX will have 3 extra cores (and look a bit different).
To set the tone, these are not small chips. Using the previous generation as an example, Ivy Bridge-EX was over twice the size (surface area) of Ivy Bridge-E, and it contained over twice the number of transistors. While Ivy Bridge-EX was available with up to 15 physical cores per processor, double that with HyperThreading, Haswell-EX is increasing that to 18, or 36 simultaneous threads with HyperThreading. If that is not enough cores, then you can pick up an eight-socket motherboard and load it up with multiple of these.
Other than their gigantic size, these chips are fairly similar to the Xeon E5 processors that are based on Haswell-E. If you need eighteen cores per package, and can spare several thousand dollars per processor, you should be able to give someone your money in just a handful of months.
Subject: Processors, Mobile | October 29, 2014 - 04:30 AM | Scott Michaud
Tagged: arm, mali-T800, mali
While some mobile SoC manufacturers have created their own graphics architectures, others license from ARM (and some even have a mixture of each within their product stack). There does not seem to be a specific push with this generation, rather just increases in the areas that make the most sense. Some comments tout increased energy efficiency, others higher performance, and even API support got a boost to OpenGL ES 3.1, which brings compute shaders to mobile graphics applications (without invoking OpenCL, etc.).
Three models are in the Mali-T800 series: the T820, the T830, and the T860. As you climb in the list, the products go from entry level to high-performance mobile. GPUs are often designed in modularized segments, which ARM calls cores. You see this frequently in desktop, discrete graphics cards where an entire product stack contains a handful of actual designs, but products are made by disabling whole modules. The T820 and T830 can scale between one to four "core" modules, each core containing four actual "shader cores", while the T860 can scale between one to sixteen "core" modules, each core with 16 "shader cores". Again "core modules" are groups that contain actual shader processors (and L2 cache, etc.). Cores in cores.
This is probably why NVIDIA calls them "Streaming Multiprocessors" that contain "CUDA Cores".
ARM does not (yet) provide an actual GFLOP rating for these processors, and it is up to manufacturers to some extent. It is normally a matter of multiplying the clock frequency by the number of ops per cycle and by the number of shader units available. I tried, but I assume my assumption of instructions per clock was off because the number I was getting did not match with known values from previous generations, so I assumed that I made a mistake. Also, again, ARM considers their performance figures to be conservative. Manufacturers should have no problem exceeding these, effortlessly.
As for a release timeline? Because these architectures are designed for manufacturers to implement, you should start seeing them within devices hitting retail in late 2015, early 2016.