Subject: General Tech | November 3, 2011 - 12:38 PM | Jeremy Hellstrom
Tagged: amd, vector computing, exascale, APU
Chuck Moore, CTO of AMD's Technology Group, gave a talk this week about AMD's plans for the future of their architecture. As you might conjecture the focus was on the further integration of the CPU and GPU, with an eye on power consumption. The hurdle he feels will be the tallest is the bandwidth for passing data back and forth between the two processors and he sees 3D stacks of memory sitting between the main system memory, the GPU and the CPU. Once developed he feels that the stacks of memory should be able to increase the amount of available communication bandwidth to the point where tasks can be handed smoothly back and forth between the two processors depending on which is more effective at certain tasks. Performance is not everything however, when The Register quotes Moore when he discusses the power requirements of a mid-range exascale class machine costing $200 million just to power and cool over a year, you begin to see the importance of bringing down power consumption and heat production.
"Because Advanced Micro Devices has not yet announced its 16-core "Interlagos" Opteron 6200 processors, it has to talk about something, and in situations like that, it is best to talk about the far-off future. And so AMD rounded up a bunch of its partners on Wednesday in San Francisco for a shindig to talk about the challenges of exascale computing."
Here is some more Tech News from around the web:
- JPR Reports Q3 Graphics Numbers @ SemiAccurate
- Western Digital and Samsung will not supply hard drives to Taiwan channels in November @ DigiTimes
- Facebook's "Open Compute" Server tested @ AnandTech
- HIS Desperate Upgrade GPU Competition @ XSReviews
- HiTechLegion Founder's Birthday Contest
Subject: General Tech, Processors | November 2, 2011 - 05:55 PM | Scott Michaud
Tagged: overclock, bulldozer, amd
Remember back in September when Ryan was all excited about seeing AMD exceed Intel with their Liquid Helium-cooled overclock? 8.429 GHz bulldozed past the 8.309 GHz record set upon Intel’s Celeron and all rejoiced at AMD’s 130 MHz triumph. Well out with the old and in with the new: there is a new overclocking king and it goes by the name of -- well it is also the AMD FX-8150. That is irrelevant, however, as the new record (if validated before someone beats it too) has become 8.461 GHz.
Someone’s the new king in town… the current king.
The new world record was set by Andre Yang, an overclocked from Taiwan, with an ASUS Crosshair V Formula motherboard. Benchmarks were not possible as when you get overclocking to this level: successfully running CPU-Z just to query the specifications of a CPU is generally considered sufficiently stable to be qualified as an overclock. Do not be surprised if SuperPi blows a hole through your chassis. It was not stated which method of cooling was used to allow the processor to reach those specifications.
The Alienware M17x Giveth
Mobile graphics cards are really a different beast than the desktop variants. Despite have similar names and model numbers, the specifications vary greatly as the GTX 580M isn't equivalent to the GTX 580 and the HD 6990M isn't even a dual-GPU product. Also, getting the capability to do a direct head-to-head is almost always a tougher task thanks to the notebook market's penchant for single-vendor SKUs.
Over the past week or two, I was lucky enough to get my hands on a pair of Alienware M17x notebooks, one sporting the new AMD Radeon HD 6990M discrete graphics solution and the other with the NVIDIA GeForce GTX 580M.
AMD Radeon HD 6990M on the left; NVIDIA GeForce GTX 580M on the right
Also unlike the desktop market - the time from announcement of a new mobile GPU product to when you can actually BUY a system including it tends to be pretty long. Take the two GPUs we are looking at today for example: the HD 6990M launched in July and we are only just now finally seeing machines ship in volume; the GTX 580M in June.
Well, problems be damned, we had the pair in our hands for a few short days and I decided to put them through the ringer in our GPU testing suite and added Battlefield 3 in for good measure as well. The goal was to determine which GPU was actually the "world's fastest" as both companies claimed to be.
Subject: Processors | November 1, 2011 - 02:48 PM | Jeremy Hellstrom
Tagged: bulldozer, a8-3850, thread scheduling, amd
Windows and to an extent other OSes are now familiar with Intel's HyperThreading and tend to be able to schedule threads in an optimized manner, but what about the eight 'cores' in the AMD A8-3850? The Tech Report found a way to test this and the results are conclusive; Windows 7 is not optimized properly for Bulldozer. The Bulldozer has two cores on each module, easy to see in the picture below. By playing with the core affinity via the command line you can run benchmarks using specific cores, to test the impact clustering together 4 threads in two modules versus spreading out the threads to one per module. As it turns out, there is a noticeable difference when you do set the processor to run with one thread in each cluster.
"Is an awareness of the shared nature of AMD's Bulldozer architecture the key to unlocking its performance? We investigate."
Here are some more Processor articles from around the web:
- AMD FX-8150 Bulldozer on Asus Crosshair V @ The Inquirer
- DIY Guides: How To Install/Remove AMD Socket FM1 CPU and Heatsink @ PCSTATS
- AMD FX-8150 Bulldozer Tested - Windows 8 vs. Windows 7 Performance @ Frostytech
- Mobile CPU Comparison Guide @ TechARP
- CPU Performance Comparison Guide @ TechARP
- Intel Core i7 2700k @ kitguru
- Intel Core i7 2700k Flagship Showdown Review @ eTeknix
Subject: Graphics Cards, Processors | October 31, 2011 - 02:22 PM | Matt Baynum
Tagged: video, sandy bridge, Intel, bf3, battlefield 3, APU, amd
Everyone is playing Battlefield 3 these days; we even had a virtual LAN party this weekend where forum members and PC Perspective team members played from about 10am until well after 1am ET. We have done more than our fair share of Battlefield 3 articles as well including hardware performance on high end graphics cards, multi-GPU scaling and more.
We had some requests and questions about what was the lowest priced hardware you could play the game on and while we had run some tests on the GeForce 9800 GT, I decided to take a stab at running BF3 at its lowest settings with integrated graphics on Intel's Sandy Bridge processor and AMD's A-series APU. Here were our test settings:
We ran at a fairly low resolution of 1366x768 (both indicative of mobile resolutions as well as low-end hardware restrictions) and the Low in-game preset. As it turns out this was the level at which the A8-3850 Llano APU was able to maintain an average around 30 FPS while the Intel Core i3-2105 (both priced around $140) was able to reach only a third of that.
With both systems coming in at the ~$450 mark, this could qualify as the lowest priced PC that is capable of getting you into the BF3 action!
You can see our full comparison right here in this short video!
Subject: Editorial | October 28, 2011 - 05:27 PM | Josh Walrath
Tagged: Q3 2011, ontario, llano, GLOBALFOUNDRIES, bulldozer, brazos, amd
Unlike Intel, AMD was unable to report record revenues. What they were able to report was a small profit. They also were able to show some growth above that expected by most analysts, and even those in AMD. Earlier this quarter AMD warned that revenues might not be as high as expected, but in the end AMD seemed to have done ok.
The company had a gross revenue of $1.69 billion, which is well above the expected $1.66 billion many analysts were predicting. Net profit for the quarter came in at a reasonable $97 million. This is a big improvement from Q3 2010, which had a net income of -$118 million. Being positive for a quarter is a big accomplishment for AMD. Controlling costs as a fabless semiconductor company is a lot easier as compared to running multiple Fabs and researching and implementing next generation process nodes. Margins increased to 45%, but are still a far cry from the 60% plus that Intel achieves. ASPs are also down due to the large amount of low priced, 45 nm parts that AMD still sells.
The primary movers for the positive results for AMD are their lineup of APUs. The “Bobcat” based APUs have been a success for quite a few months, and with their superior performance and features as compared to the competing Intel Atom series, AMD is making a tidy sum off of them. The big winner in the APU sector is of course Llano. The uptake on this processor in the mobile space has been tremendous. AMD has seen a 35% increase in mobile sales, and when combined with the already strong Brazos/Ontario platform, AMD is finally a factor in the mobile market. The only real issue in this market that AMD is facing is that of continued poor yields on Llano processors.
Subject: Graphics Cards | October 26, 2011 - 05:36 PM | Jeremy Hellstrom
Tagged: hd 6950, amd, gigabyte, msi, xfx, factory overclocked
Heading to The Tech Report will bring you to a round up of HD6950's including Gigabyte's GV-R695OC-1GD, the MSI R6950 Twin Frozr III 1G/OC and the XFX HD-695X-ZDDC. The GPU clocks range from 830MHz to 870MHz and RAM ranging from the stock 1250MHz to 1350MHz, with the MSI and XFX offering their own overclocking tools and Gigabyte relying on the Catalyst Control Center for further overclocking. MSI's offering came out looking very good, with the best performance and the best power efficiency and thanks to a mail in rebate it picks up the best ratings in the round up. It is a close race though with the cards performing very similarly, as you can see in the review.
"We've gathered three souped-up Radeon HD 6950 graphics cards from Gigabyte, MSI, and XFX. Which one delivers the most bang for your buck?"
Here are some more Graphics Card articles from around the web:
- Great Value from Sapphire: Radeon HD 6870 Dirt 3 Edition and Radeon HD 6850 Vapor-X @ X-bit Labs
- Inexpensive Hi-End: MSI R6950 Twin Frozr III 1 GD5 Power Edition/OC @ X-bit Labs
- Sapphire Radeon HD 6870 DiRT 3 Special Edition Review @ OCC
- AMD’s flagship HD6990: is silent air cooling possible? @ kitguru
- Desktop Graphics Card Comparison Guide @ TechARP
- Mobile GPU Comparison Guide @ X-bit Labs
- EVGA GeForce GTX 580 Classified 3 GB @ X-bit Labs
- Gigabyte GTX580 Super Overclock @ OC3D
- Palit GTX 560 Ti Twin Light Turbo 1GB @ Tweaktown
- ZOTAC GeForce GTX 550 Ti Video Card Drawing @ Legit Reviews
- NVIDIA GeForce GTX 550 Ti @ Phoronix
- Palit GTX 560 Ti Twin Light Turbo Graphics Card Review @ HardwareHeaven
Subject: General Tech | October 26, 2011 - 12:15 PM | Jeremy Hellstrom
Tagged: amd, bulldozer, FX 8150, linux
With the lacklustre performance we saw from AMD's new Bulldozer CPUs on Windows except in seriously multi-threaded applications; it is with a hopeful heart that Phoronix tests the performance of the FX-8150 under Ubuntu 11.04. There are a lot of benchmarks to go through, from general performance to specific AMD-centric tests to those focusing specifically on multi-threaded performance and even a look at the bundled watercooler. Read through the benchmarks they've run themselves as well as user submitted test and then realize that this is only the first of a series of articles they are working on ... so for now they hold judgment on AMD's newest product.
"Two weeks ago AMD introduced the Bulldozer FX-Series CPUs to much excitement, although many were letdown by the initial results, and it was months after showing the first Linux benchmarks of an AMD Dual-Interlagos pre-production system. In the days that followed I delivered some initial AMD FX-4100 Linux benchmarks when securing remote access to a low-end Bulldozer system running Ubuntu 11.04 (and there were also some Linux benchmarks from independent Phoronix readers), but then last week a Bulldozer kit arrived from AMD. The centerpiece of this kit is an eight-core AMD FX-8150 CPU, which is now being used to conduct a plethora of AMD Bulldozer benchmarks on Linux."
Here are some more Processor articles from around the web:
- AMD FX-4100 Bulldozer On Linux @ Phoronix
- Multi-Core Scaling Performance Of AMD's Bulldozer @ Phoronix
- Desktop CPU Comparison Guide @ TechARP
- Intel Core i7-2700K Sandy Bridge 3.5 GHz CPU Review @ Legit Reviews
- Intel Core i7 Processors for LGA1156, LGA1155 and LGA1366 @ iXBT Labs
Subject: General Tech | October 26, 2011 - 11:56 AM | Jeremy Hellstrom
Tagged: gpu, amd, nvidia, southern islands, kepler, TSMC, 28nm
While most enthusiasts are living up to the name as far as the build up to the coming GPU refreshes from both AMD and NVIDIA is concerned, the manufacturers are quite the opposite. There are several probable reasons for this attitude, not least of which are the number of HD 6570s and GTS 450s that are still in their stock. Remember those cards from back in the spring of this year, which were the high end of a huge range of GPUs from both companies spanning $20 to either side of $100? Think that with the current generation of Llano and SandyBridge that any knowledgeable person is going to purchase one, let alone when you consider how close the release of next generation of APUs is? The two major players in the discrete GPU market not only updated the top end of their cards quickly over the past several quarters there was a widening of the market which saw current generation cards available from ~$75 to ~$750 with some segments separated by as little as $10. That translates to huge inventories at the manufacturer level which they then have to convince resellers and retailers to purchase for stock to sell to the consumer and many of those cards are still sitting there collecting dust. No wonder these same companies are leery of purchasing more stock before finding a way to recover some profit from the stock they have now.
To make things even worse there exist doubts about the 28nm process from TSMC, which DigiTimes discusses here. While AMD is still claiming delivery of HD7000 family cards before the coming year, the troubles that NVIDIA seems to be having with the same process concerns those who need to be able to buy large volumes of chips in order to turn a profit selling graphics cards. Even worse is the realization that the first cards NVIDIA will be releasing are simply a die shrink, without architectural changes. When two companies go to the same source for the same thing and one reports getting apple cider and the other apple vinegar, you really have to start to wonder what is really going on.
"While Nvidia and AMD are poised to use Taiwan Semiconductor Manufacturing Company's (TSMC's) 28nm technology to produce the GPUs Kepler and Southern Islands respectively, most Taiwan-based graphics card makers hold a conservative attitude about the new GPUs with some makers cautiously watching the market status before making any further decisions, according to industry sources.
Compared to the makers' eagerness for the previous-generation GPUs, graphics card makers are rather conservative about the upcoming 28nm chips due to concerns such as TSMC's weak 40nm process yield rate issues may re-occur in its 28nm process and weakening demand for graphics cards and lower-than-expected gross margins."
Here is some more Tech News from around the web:
- Did Nvidia have to spin their 28nm GPU shrinks? @ SemiAccurate
- PARC, Thinfilm unveil first printed, flexible CMOS computer circuit @ ExtremeTech
- AIDA64 v2.00 is released !
- Linus Torvalds discusses ARM issues at Linuxcon Europe @ The Inquirer
- KDE 4: Leader of the Semantic Pack @ Linux
- IBM names Ginni Rometty prez and CEO @ The Register
- Samsung Announces PM830 Prices in NYC Gala Event With Batman @ SSD Review
Subject: General Tech | October 24, 2011 - 06:43 PM | Jeremy Hellstrom
Tagged: amd, ultrabook, Deccan, Kerala
Not to be deterred by the issues that Intel has run into trying to out Macbook Apple, AMD will also be jumping on a notebook similar to the Ultrabook. The successors to Brazos will be competing against Ivy Bridge and Haswell, so hopefully the statement that DigiTimes makes about vastly improved performance and power usage reduction are true. AMD is also lookign to refresh the chips they've designed for use in tablets which you should be able to get your hands on before the end of the year, if GLOBALFOUNDRIES can produce enough chips.
"AMD has made plans for ultrabook-like products for the next two years – in 2012, AMD will launch the Deccan platform to replace Brazos and will launch Kerala in 2013.
Since AMD's share in the global CPU market has been around 20% in recent years while the company has about 10% share in the global notebook CPU market, AMD is preparing plans for ultra-thin notebooks hoping to raise its share in the notebook CPU market.
In June 2012, AMD is set to launch Deccan, featuring Krishna and Wichita-based APUs and will upgrade to Kerala featuring Kabini-based APUs. With the upgrades, the overall performance and power consumption of AMD's platforms are expected to see an extraordinary improvement, allowing AMD to compete against Intel's Ivy Bridge platform in 2012 and Haswell platform in 2013.
For the traditional notebook market, AMD has already launched its Llano-based Sabine platform to replace Danube, but due to Globalfoundries' weak 32nm yield rates and production issues, supplies of Llano APUs has been limited, which should impact AMD's future plans for the notebook market. However, within AMD's latest plans, the company is set to launch the Comal platform, featuring Trinity-based APUs, for 2012 and will upgrade to the Indus platform in 2013 using Kaveri-based APUs.
As for the tablet PC market, AMD will push the Brazos platform with Windows operating system to target the enterprise market in 2011. In the second quarter of 2012, AMD will launch the Brazos T platform that features Hondo APUs and in 2013 will release the Samara platform, which features a similar architecture as its ultra-thin platform."
Here is some more Tech News from around the web:
- TSMC ramps volume production of 28nm process @ DigiTimes
- Desktop dreams: Ubuntu 11.10 reviewed @ Ars Technica
- World's stealthiest rootkit gets a makeover @ The Register
- Netgear Universal WiFi Range Extender WN3000RP Review @ MissingRemote
- Getting acquainted with Arduino @ The Tech Report
- Configure Android as Wi-Fi Internet Hotspot @ Benchmark Reviews
- OC3D & Be Quiet @ LITS 2011