As expected NVIDIA's next generation GPU release schedule was a bit optimistic

Subject: General Tech | July 8, 2011 - 12:37 PM |
Tagged: nvidia, amd, 28nm, kepler, maxwell

TSMC's 28nm wafer yields are having a negative effect on NVIDIA's scheduled release of their next generation of GPUs, no matter what the PR coming out of NVIDIA might suggest.  That news is coming from graphics card manufacturers who were hoping to release cards but have since seen NVIDIA's scheduled releases delayed by a year.  While it may be true that TSMC is partly to blame for the delay there is also talk about the chips performance being lower than was expected and is needed to challenge AMD.  The news for NVIDIA gets even worse as DigiTimes confirms that AMD is still on schedule with it's 28nm chips.  This may seem like a bit of deja vu, as we saw similar production problems from TSMC's initial 40nm chips; though that effected both major GPU makers more or less equally.

nvidia jensen.jpg

"Despite Nvidia CEO Huang Jen-hsun previously saying that the company is set to announce its new 28nm GPU architecture at the end of 2011 and 22/20nm in 2013, sources from graphics card makers have pointed out that Nvidia has already adjusted its roadmap and delayed 28nm Kepler and 22/20nm Maxwell to 2012 and 2014.

The sources believe that the delay is due to unsatisfactory yield rates of Taiwan Semiconductor Manufacturing Company's (TSMC) 28nm process as well as lower-than-expected performance of Kepler.

TSMC originally expected its 28nm capacity at Fab15 to be available in the fourth quarter of 2011 and was set to start pilot production for its 20nm process technology in the third quarter of 2012.

However, TSMC's other major client Qualcomm, currently, still has not yet adjusted its 28nm process schedule and is set to launch three new products, 8960. 8270 and 8260A using dual-core Krait architecture in the fourth quarter of 2011.

Meanwhile, AMD will follow its original schedule and enter the 28nm era in the first half of 2012. The company's next-generation graphics chips Southern Island as well as Krishna and Wichita processors, which will replace the existing Ontraio and Zacate processors, and will all adopt a 28nm process from TSMC."

Here is some more Tech News from around the web:

Tech Talk

Source: DigiTimes

Always someone to ruin the parade, NVIDIA's response to AMD's Southern Island news

Subject: General Tech | July 6, 2011 - 12:36 PM |
Tagged: southern islands, parade, nvidia, kepler, fermi, amd

As is common in the industry, when one company releases news their competitors have to do something to distract people.  Since in this case it was AMD's announcement of the Southern Islands release, it is NVIDIA who feels the need to hold a competing spectacle.  In this case it was news that their new Fermi based 28nm Kepler GPU has taped out ... maybe.  In this particular scenario we have an intentional leak from NVIDIA which was light on details and heavy on spin.  SemiAccurate takes a long look at some of NVIDIA's claims, from the doubling of transistors with no cost in TDP to the probable difference between Tesla branded Fermi and GeForce branded Fermi cards to NVIDIA's claims that switching from 40nm to 28nm is hard and that it is all TSMC's fault. 

CUDA_roadmap.jpg

"When SemiAccurate announced that AMD (NYSE:AMD) was aiming for September with Southern Islands (SI), you could almost set your watch to the Nvidia (NASDAQ:NVDA) response. If you are new to the PR game, you will probably scratch your head wondering what we mean by Nvidia response, officially there is silence, but there definitely was a response."

Here is some more Tech News from around the web:

Tech Talk

Source: SemiAccurate

Podcast #160 - Lenovo ThinkPad X1, OCZ RevoDrive 3 X2, Crysis 2 DX11 update, Llano preview and more!

Subject: General Tech | June 30, 2011 - 02:50 PM |
Tagged: podcast, X1, Thinkpad, revodrive, ocz, nvidia, llano, Lenovo, Intel, dx11, crysis 2, amd

PC Perspective Podcast #160 - 6/30/2011

This week we talk about the Lenovo ThinkPad X1, OCZ RevoDrive 3 X2, Crysis 2 DX11 update, Llano preview and more!

You can subscribe to us through iTunes and you can still access it directly through the RSS page HERE.

The URL for the podcast is: http://pcper.com/podcast - Share with your friends!

  • iTunes - Subscribe to the podcast directly through the iTunes Store
  • RSS - Subscribe through your regular RSS reader
  • MP3 - Direct download link to the MP3 file

Hosts: Ryan Shrout, Jeremy Hellstrom, Josh Walrath and Allyn Malventano

This Podcast is brought to you by MSI Computer, and their all new Sandy Bridge Motherboards!

Program length: 57:49

Program Schedule:

  1. 0:00:45 Introduction
  2. 1-888-38-PCPER or podcast@pcper.com
  3. http://pcper.com/podcast
  4. http://twitter.com/ryanshrout and http://twitter.com/pcper
  5. 0:02:16 Lenovo ThinkPad X1 Review: Thin is In
  6. 0:03:08 Samsung Nexus S 4G Review: Google Bliss.
  7. 0:05:04 Super Fast PCI Express Cable Capable of 32 Gbps Announced By The PCI SIG
  8. 0:08:37 OCZ RevoDrive 3 x2 480GB PCIe SSD Review - Seriously Fast Storage
  9. 0:24:23 This Podcast is brought to you by MSI Computer, and their all new Sandy Bridge Motherboards!
  10. 0:25:00 Crysis 2: DirectX 11 free update released
  11. 0:31:45 NVIDIA Releases GeForce GTX 580M and 570M, Brings Optimus to Hardcore Gaming Laptops
  12. 0:34:10 Badaboom, the once NVIDIA only transcoding accelerator, now works with Sandy Bridge
  13. 0:38:40 Llano's dance card is available, pick a date with your favourite new AMD APU tomorrow
  14. 0:41:05 Just Delivered: Cost effective AM3+ Boards.
  15. 0:42:30 Show and tell: Llano CPU and MB
  16. 0:44:26 Free games?
    1. http://www.pcper.com/news/General-Tech/Meet-Medic-Uber-Update-and-TF2-itself-are-freed
  17. 0:48:20 Quakecon Reminder - http://www.quakecon.org/
  18. 0:50:45 Hardware / Software Pick of the Week
    1. Ryan: Bitcoins?  Ken is testing a LOT of GPUs for this!
    2. Jeremy: I guess I'll shout out to Might & Magic entertaining me for 25 SMEGGING YEARS!
    3. Josh: Eyefinity!  It is a lot of fun.  Surprising capabilities from many modern applications.  Even a lot of older ones...
    4. Allyn: RevoDrive 3!
  19. http://pcper.com/podcast   
  20. http://twitter.com/ryanshrout and http://twitter.com/pcper
  21. 0:56:35 Closing

 

Source:

Badaboom, the once NVIDIA only transcoding accelerator, now works with Sandy Bridge

Subject: General Tech | June 28, 2011 - 11:34 AM |
Tagged: transcoding, quick sync video, nvidia, Intel, badaboom

When we first met Elemental Technologies Badaboom video transcoding accelerator it would only work with NVIDIA CPUs.  Ryan tested version 1.1 of the program, taking various movies and recorded TV and transcoding it into formats able to play on Blackberrys, iPhones, YouTube and a wide variety of other formats. 

slides01.jpg

The testing showed nice improvements when utilizing an NVIDA GPU and the ability to use multiple GPUs, each able to do their own transcoding simultaneously would help anyone who needed a couple of Blu-ray movies transferred to their mobile device in a hurry.  The quality of the transcoding was of high quality and Ryan did not see any of the issues that were present when using AMD's Avivo, as there is little point in quickly transcoding video if it ends up painful to watch.

We hadn't heard much else about Badaboom until today, when it was announce that version 2.0 will support Intel's new Quick Sync Video as well as NVIDIA's cards.  We don't have any benchmarks to show you how effective Sandy Bridge parts will be at accelerating transcoding but you can see the long list of pre-processing filters and learn a bit about Intel's media SDK on this page at Intel.

badaboom.gif

"Intel Quick Sync Video, built right into 2nd generation Intel Core processors, is breakthrough hardware acceleration that lets the user complete in minutes what used to take hours. Create DVDs or Blu-ray discs, cover video files for your media plater, and convert video for upload to your favorite social networking sites - all in a flash.

Badaboom uses Intel Quick Sync Video technology to transcode video files in just minutes. Why do videos need to be transcoded? In order for a video to play back on a device such as a smartphone or a tablet, it needs to be formatted to correct specifications. With so many different devices out there, odds are low a video from a camcorder will automatically play on all of them. That's where Badaboom comes in: it transcodes video files to play on hundreds of the most popular devices available today-and it does so quickly and easily."

Here is some more Tech News from around the web:

Tech Talk

 

Source: Intel

NVIDIA Releases GeForce GTX 580M and 570M, Brings Optimus to Hardcore Gaming Laptops

Subject: Mobile | June 28, 2011 - 08:47 AM |
Tagged: nvidia mobile, nvidia, mobile graphics, gtx 580m, gtx 560m

The green team today announced the GTX 580M and GTX 570M, the newest high-end GPUs for gaming laptops. These parts succeed the GTX 485M and GTX 470M, respectively. According to NVIDIA, the GTX 580M will be the quickest mobile graphics solution on the market, while the GTX 570M will be 20% faster than the 470M it replaces.

table.png

Gaming performance samples show a substantial improvement over the previous generation. According to the press material, a single GTX 580M is capable of outputting over 30 frames per second at 1920x1080 at high detail in various games including Crysis 2, DIRT3, and Civilization V. These high marks are only further improved when the two GPUs are placed into SLI. In Crysis 2, for example, this configuration achieves over 70 FPS with detail set to Extreme Quality.

physx.jpg

Both the GTX 580M and 570M will support all of the company’s typical hardware features including PhysX, Nvidia 3D Vision, 3DTV Play, SLI, CUDA and OpenCL. In addition to this, these new mobile solutions will offer support of Optimus.

This is the first time that Optimus support has been offered in high-end mobile GPUs, and it could provide the green team with a significant advantage. In past reviews of Optimus enabled laptops, such as the ASUS N53, we’ve found that the feature made it possible to offer battery life on par with laptops that don’t have a discrete GPU. Optimus in the 580M and 570M will likely replicate this, making it possible for gamers to enjoy extreme gaming performance while plugged in and reasonable battery life while on the go.

verde.jpg

NVIDIA also continues to push its NVIDIA Verde driver program. For those who missed the initial announcement, Verde can be summed up as a monthly driver release program. The goal is to consistently improve performance and stability, giving owners of Nvidia GPUs a better long-term experience. Driver updates have proven to increase performance in the past, sometimes significantly, so these monthly updates are welcome.

The initial wave of 580M mobile graphics will be found in three laptops: the Alienware M18x, the Clevo P170HM3, and the Clevo P270WM. It’s reasonable to expect that both Clevo models will be picked up by various companies, such as Origin and Maingear, and released with some modifications under those brands. MSI will be the only company launching a 570M equipped laptop, in this case the MSI GT780R. Pricing has yet to be announced.

lineup.jpg

With the release of these new parts, NVIDIA has converted nearly all of its current components to the 5xx series brand. Only the “mainstream” GeForce 315M and 410M remain outside the fold.

UPDATE: Need some more proof of the power of the GTX 580M?  Here it is seen running the brand-new DX11 variant of Crysis 2:

Source: Nvidia

PC Perspective Podcast #159 - AMD Llano Notebook Platform, AMD Fusion platform architecture, X79 Rumors, the deal about BAPCo and more!

Subject: General Tech | June 23, 2011 - 02:39 PM |
Tagged: x79, podcast, nvidia, llano, Intel, fusion, APU, amd

PC Perspective Podcast #159 - 6/23/2011

This week we talk about the AMD Llano Notebook Platform, AMD Fusion platform architecture, X79 Rumors, the deal about BAPCo and more!

You can subscribe to us through iTunes and you can still access it directly through the RSS page HERE.

The URL for the podcast is: http://pcper.com/podcast - Share with your friends!

  • iTunes - Subscribe to the podcast directly through the iTunes Store
  • RSS - Subscribe through your regular RSS reader
  • MP3 - Direct download link to the MP3 file

Hosts: Ryan Shrout, Jeremy Hellstrom, Josh Walrath and Allyn Malventano

This Podcast is brought to you by MSI Computer, and their all new Sandy Bridge Motherboards!

Program length: 1:27:10

Program Schedule:

 

  1. 0:00:30 Introduction
  2. 1-888-38-PCPER or podcast@pcper.com
  3. http://pcper.com/podcast
  4. http://twitter.com/ryanshrout and http://twitter.com/pcper
  5. 0:01:50 AMD A-Series Llano APU Sabine Notebook Platform Review
  6. 0:05:00 AMD Fusion System Architecture Overview - Southern Isle GPUs and Beyond
  7. 0:33:24 This Podcast is brought to you by MSI Computer, and their all new Sandy Bridge Motherboards!
  8. 0:34:00 AFDS11: AMD Demonstrates Trinity Powered Notebook
    1. AFDS11: Upcoming Trinity APU will use VLIW4 / Cayman Architecture
  9. 0:35:45 AFDS11: ARM Talks Dark Silicon and Computing Bias at Fusion Summit
  10. 0:41:30 AFDS11: Microsoft Announces C++ AMP, Competitor to OpenCL
  11. 0:45:45 New Rumor Indicates X79 Chipset Will Support Both 1366 and 2011 Sockets
  12. 0:49:49 Microsoft is probably laughing as AMD speculates the unlikelihood of Intel buying NVIDIA
  13. 0:54:45 Larrabee rides again, almost ... meet Knights Corner the new Many Integrated Core design
    1. Intel Hopes For Exaflop Capable Supercomputers Within 10 Years
  14. 0:58:35 What's the big deal with BAPCo? Why Benchmarking Matters
  15. 1:05:20 Crysis 2: Cry Harder (with DX11 and High Res textures)
  16. 1:06:00 *Allyn Show and Tell*
  17. 1:12:45 Quakecon Reminder - http://www.quakecon.org/
  18. 1:13:17 Hardware / Software Pick of the Week
    1. Ryan: https://www.findbigmail.com/
    2. Jeremy: How to Encrypt Your Dropbox Files, at Least until Dropbox Wakes the F* up
    3. Josh: nice combo!  http://www.newegg.com/Product/ComboDealDetails.aspx?ItemList=Combo.654093.24-176-144
    4. Allyn: Lytro
  19. http://pcper.com/podcast   
  20. http://twitter.com/ryanshrout and http://twitter.com/pcper
  21. 1:25:45 Closing

Source:

What's the big deal with BAPCo? Why Benchmarking Matters

Subject: Editorial, General Tech | June 21, 2011 - 02:36 PM |
Tagged: VIA, sysmark, nvidia, Intel, benchmark, bapco, amd

It seems that all the tech community is talking about today is BAPCo and its benchmarking suite called Sysmark.  A new version, 2012, was released just recently and yesterday we found out that AMD, NVIDIA and VIA have all dropped their support of the "Business Applications Performance Corporation".  Obviously those companies have a beef with the benchmark as it is, yet somehow one company stands behind the test: Intel.

Everyone you know of is posting about it.  My twitter feed "asplode" with comments like this:

AMD quits BAPCo, says SYSmark is nutso. Nvidia and VIA, they say, also.

AMD: Voting For Openness: In order to get a better understanding of AMD's press release earlier concerning BAPCO...

Ooh, BapCo drama.

Why Legit Reviews won't use the latest BAPCo benchmark:

Even PC Perspective posted on this drama yesterday afternoon saying: "The disputes centered mostly over the release of SYSmark 2012. For years various members have been complaining about various aspects of the product which they allege Intel strikes down and ignores while designing each version. One major complaint is the lack of reporting on the computer’s GPU performance which is quickly becoming beyond relevant to an actual system’s overall performance. With NVIDIA, AMD, and VIA gone from the consortium, Intel is pretty much left alone in the company: now officially."

aaaaa.png

Obviously while cutting the grass this morning this is the topic swirling through my head; so thanks for that everyone.  My question is this: does it really matter and how is this any different than it has been for YEARS?  The cynical side of me says that AMD, NVIDIA and VIA all dropped out because each company's particular products aren't stacking up as well as Intel's when it comes to the total resulting score.  Intel makes the world's fastest CPUs, I don't think anyone with a brain will dispute that, and as such on benchmarks that test the CPU, they are going to have the edge.  

We recently reviewed the AMD Llano-based Sabine platform and in CPU-centric tests like SiSoft Sandra, TrueCrypt and 7zip the AMD APU is noticeably slower.  But AMD isn't sending out press releases and posting blogs about how these benchmarks don't show the true performance of a system as the end user will see.  And Intel isn't pondering why we used games like Far Cry 2 and Just Cause 2 to show the AMD APU dominating there. Why?  Because these tests are part of a suite of benchmarks we use to show the overall performance of a system.  They are tools which competent reviewers wield in order to explain to readers why certain hardware acts in a certain way in certain circumstances.  

Continue reading for more on this topic...

Source: PCPer

BAPCo: BUPKIS? AMD, NVIDIA, and VIA exodus

Subject: General Tech, Processors | June 20, 2011 - 04:46 PM |
Tagged: VIA, sysmark, nvidia, bapco, amd

People like benchmarks. Benchmarks tell you which component to purchase while your mouse flutters between browser tabs of various Newegg or Amazon pages. Benchmarks let you see how awesome your PC is because often videogames will not for a couple of years. One benchmark you probably have not seen here in a very long time is Sysmark from the Business Applications Performance Corporation, known as BAPCo to its friends and well-wishers. There has been dispute over the political design of BAPCo and it eventually boiled over with AMD, NVIDIA, and VIA rolling off the sides of the pot.

BAPCO.png

Fixed that for you

The disputes centered mostly over the release of SYSmark 2012. For years various members have been complaining about various aspects of the product which they allege Intel strikes down and ignores while designing each version. One major complaint is the lack of reporting on the computer’s GPU performance which is quickly becoming beyond relevant to an actual system’s overall performance. With NVIDIA, AMD, and VIA gone from the consortium, Intel is pretty much left alone in the company: now officially.

Source: Semiaccurate

Microsoft is probably laughing as AMD speculates the unlikelihood of Intel buying NVIDIA

Subject: General Tech | June 16, 2011 - 12:57 PM |
Tagged: amd, Intel, nvidia

In some sort of bizarre voyeuristic hardware love/hate triangle AMD, Intel and NVIDIA are all semi-intertwined and being observed by Microsoft. Speaking with The Inquirer the VP of product and platform marketing at AMD, Leslie Sobon, stated that there was no chance that Intel would attempt to purchase NVIDIA as AMD did with ATI.  AMD's purchase was less about the rights to the Radeon series as it was taking possession of the intellectual property that ATI owned after a decade of creating GPUs and lead directly to the APUs that AMD has recently released which will likely become their main product.  Intel already has a working architecture that combines GPU and CPU and doesn't need to purchase another company's IP in order to develop that type of product. 

There is another reason for purchasing NVIDIA though, which has very little to do with their discreet graphics card IP and everything to do with Tegra and Fermi which are two specialized products which so far Intel doesn't have an answer for.  A vastly improved and shrunken Atom might be able to push Tegra off of mobile platforms and perhaps specialized SandyBridge CPUs could accelerate computation like the Fermi products do but so far there are no solid leads, only speculation.

If you learn more from your failures than your successes then Intel knows a lot about graphics.

microsoft.jpg

"CHIP DESIGNER AMD believes that it is on a divergent path from Intel thanks to its accelerated processor unit (APU) and that Intel buying Nvidia "would never happen"."

Here is some more Tech News from around the web:

Tech Talk

Source: The Inquirer

AFDS11: ARM Talks Dark Silicon and Computing Bias at Fusion Summit

Subject: Editorial, Processors, Shows and Expos | June 14, 2011 - 05:09 PM |
Tagged: nvidia, Intel, heterogeneous, fusion, arm, AFDS

Before the AMD Fusion Developer Summit started this week in Bellevue, WA the most controversial speaker on the agenda was Jem Davies, the VP of Technology at ARM.  Why would AMD and ARM get together on a stage with dozens of media and hundreds of developers in attendance?  There is no partnership between them in terms of hardware or software but would there be some kind of major announcement made about the two company's future together?

10.jpg

In that regard, the keynote was a bit of a letdown and if you thought there was going to be a merger between them or a new AMD APU being announced with an ARM processor in it, you left a bit disappointed.  Instead we got a bit of background on ARM how the race of processing architectures has slowly dwindled to just x86 and ARM as well as a few jibes at the competition NOT named AMD.

As is usually the case, Davies described the state of processor technology with an emphasis on power efficiency and the importance of designing with that future in mind.  One of the interesting points was shown in regard to the "bitter reality" of core-type performance and the projected DECREASE we will see from 2012 onward due to leakage concerns as we progress to 10nm and even 7nm technologies.

12.jpg

The idea of dark silicon "refers to the huge swaths of silicon transistors on future chips that will be underused because there is not enough power to utilize all the transistors at the same time" according to this article over at physorg.com.  As the process technology gets smaller then the areas of dark silicon increase until the area of the die that can be utilized at any one time might hit as low as 10% in 2020.  Because of this, the need to design chips with many task-specific heterogeneous portions is crucial and both AMD and ARM on that track.

13.jpg

Those companies not on that path today, NVIDIA specifically and Intel as well, were addressed on the below slide when discussing GPU computing.  Davies pointed out that if a company has a financial interest in the immediate success of only CPU or GPU then benchmarks will be built and shown in a way to make it appear that THAT portion is the most important.  We have seen this from both NVIDIA and Intel in the past couple of years while AMD has consistently stated they are going to be using the best processor for the job.  

16.jpg

Amdahl's Law is used in parallel computing to predict the theoretical maximum speed up using multiple processors.  Davies reiterated what we have been told for some time that if only 50% of your application can actually BE parallelized, then no matter how many processing cores you throw at it, it will only ever be 50% faster.  The heterogeneous computing products of today and the future can address both the parallel computing and serial computing tasks with improvements in performance and efficiency and should result in better computing in the long run.

So while we didn't get the major announcement from ARM and AMD that we might have been expecting, the fact that ARM would come up and share a stage with AMD reiterates the message of the Fusion Developer Summit quite clearly: a combined and balanced approach to processing might not be the sexiest but it is very much the correct one for consumers.

Source: PCPer