AMD Introduces Two New Low Power Opteron 6300 Series Processors

Subject: Processors | January 22, 2014 - 08:12 PM |
Tagged: server, piledriver, opteron 6300, amd, 32nm

AMD has updated its Opteron 6300 series lineup with two new processors with lower TDPs. Previously code-named "Warsaw," the Opteron 6370P and Opteron 6338P boast 99W TDPs and 12 and 16 Piledriver cores respectively.

The chips are similar to the existing Opteron 6300-series chips including the 32nm manufacturing process, dual die design, and the use of AMD's older Piledriver CPU cores instead of the latest Steamroller cores found in AMD's new Kaveri APUs. According to Supermicro, the lower 99W TDP parts offer up to 27% higher performance/watt compared to the existing "Abu-Dhabi" 6300 CPUs.

The Opteron 6338P is a twelve core processor clocked at 2.3 GHz base and 2.8 GHz turbo. The Opteron 6370P is a sixteen core part clocked at 2.0 GHz base and 2.5 GHz turbo. As such, the chips are two six and two eight-core silicon dies in one package respectively. The chips have 16MB of L3 cache and support the same instruction sets as the existing 6300 lineup including FMA3, BMI, and F16c. The new chips use AMD's Socket G34 which supports up to 4 sockets (dual die processors) per motherboard.

The new 99W 12-core 6338P and 16-core 6370P are available now for $377 and $598 respectively. The chips will be used in servers from Supermicro and Sugon, and purchasable directly from system integrators including Avnet and Penguin. AMD is aiming these chips at large data centers and cloud computing tasks. While the drop to 99W from the top-end series' 140W TDP does not seem like much, it makes a dramatic difference in the data center world where the electricity costs for racks of servers adds up rapidly.

Source: Ars Technica

The Atom ain't dead yet! New ultra low power Avoton chips for servers

Subject: General Tech | December 11, 2012 - 04:48 PM |
Tagged: 32nm, 22nm, tri-gate, Intel, atom, Avoton

Intel's Atom S1200 line of chips are obviously designed to compete with ARM's upcoming 64bit chips in the server room.  The family of processors will all be under 10W TDP, with the top chip, the Atom S1260, which is a dual core 2GHz part that produces 8.5W.  The three chips they have released are on the older 32nm process but according to EETimes you can expect new models using the 22nm tri-gate processors in the near future.  From what The Register could find out Intel has not yet ruled out LGA models as well as the embedded chips you will be seeing first.  They did pin down some more stats, with the new Atoms supporting DDR3 1333MHz and support  eight lanes of PCI Express 2.0, what they will not be able to support on chip is network connectivity, these chips will still be at least partially dependent on other chips for some of their features so they are not truly an SoC, yet.

EET_intel2.jpg

"CHIPMAKER Intel has released its Atom S1200 series aimed at low power single socket servers.

Intel's race to meet ARM in the low power server market has seen the firm push its Atom branded chips into sub-10W territory while supporting 64-bit memory addressing and ECC memory. Now the firm has released three dual-core chips that make up its Atom S1200 series, all sporting sub-10W TDP."

Here is some more Tech News from around the web:

Tech Talk

Source: The Register

Intel Releases New Cedar Trail Atom Processors

Subject: Processors | December 28, 2011 - 04:15 PM |
Tagged: pine trail, netbook, Intel, cedar trail, atom, 32nm

Intel has been pumping out quite a few new processors lately, with new Sandy Bridge-E CPUs, a new Sandy Bridge i7 2700K processor coming out, and now a new line of Atom CPUs sneaking in the news right before the new year!  Not to mention, they are also working on Ivy Bridge.

The new Atom CPUs are of the Cedar Trail variety and succeed the older Pine Trail-M Atom processors.  Currently, there are three Cedar Trail chips that will be available as soon as January in OEM systems including the N2600, N2800, and D2700 CPUs.  Further, the new chips are 32nm and have a 22x22mm package size.  These little chips are destined to power netbooks, tablets, embedded devices (think medical devices, ruggedized tablets, machinery).  Yes, Intel still believes in netbooks, and feels as though emerging markets will keep the market alive and growing as people want for cheap computers that are able to get them on the web.  While the netbook is losing popularity in the US, Intel expects the South American, Eastern European, and African markets to see great interest in the netbook platform.  Their netbook plans involve three price tiers with accompanying use cases including netbooks at $200 with minimal features and a price to match that enables people to access the web all the way to $400+ netbooks with lots of features that would fill out the market up to where the Ultrabook territory begins at around $900.

Intel_Netbook_Outlook.png

The new Cedar Trail processors improve upon the previous gen Atom chips by quite a bit, according to Intel.  The graphics aspect in particular has been improved such that 1080p HD Youtube and HD Netflix streams are playable at at least 24 FPS.  Something that early netbooks using Intel's integrated graphics will never be able to do.  Intel further estimates a 50% lower TDP and a 28% processor performance increase over the Pine Trail chips.  Further, the new Cedar Trail chips have more cache at 2 x 512 L2 cache(s), higher clockspeeds, lower TDP, higher C-State (C6 vs C4E)/lower power usage in sleep mode, a 200MHz higher clocked graphics card (400MHz vs 200 MHz), and increased memory speeds (DDR3 800 and 1066 vs DDR3-667).  The fastest Nxx chip, the N2800 manages a .2GHz clock speed increase while also knocking off 2 watts from the TDP versus the previous top N570.

Needless to say, Cedar Trail is looking very good, on paper at least.  The individual chip specifications are listed below.

  CPU Clock Speed Graphics Clock Speed TDP
N2600 1.60 GHz 400 MHz 3.5 W
N2800 1.86 GHz 640 MHz 6.5 W
D2700 2.10 GHz 640 MHz 10 W

What are your thoughts on the new Cedar Trail chips, do you think they will provide enough "oomph" to make new netbooks desirable again?  Some more information can be found here and straight from Intel here.

Intel_PineTrail_vs_CedarTrail.png

Mighty Mite; the ARM Cortex A15 and Samsung

Subject: General Tech | December 2, 2011 - 10:37 AM |
Tagged: Exynos 5250, Samsung, cortex a15, arm, 32nm

Samsung is the first to put ARM's new chip into a product, the Cortex A15.  While only 500MHz faster on paper, enhancements to the architecture have wonks predicting double the performance of the Cortex A9.  This little chip will be capable of outputting 2560 x 1600 video over DisplayPort as well as supporting SATA, UART, and USB 3.0.  This is a rather impressive list for a chip from a manufacturer that many have ignored.  You can bet that the power consumption on this chip will be minuscule, but the capabilities are not.  Check out SemiAccurate for the full story.

arm-cortex-a15.jpg

"Samsung (SEO:005930) has started sampling a processor based on the latest microarchitecture, the A15, from ARM. The processor is fabbed using 32nm high-k metal gate low-power process technology. The processor clocks in at 2GHz, but thanks to advances in the microarchitecture, it is roughly twice as powerful as an A9-based processor running at 1.5GHz.

Samsung has named its new chip the Exynos 5250."

Here is some more Tech News from around the web:

Tech Talk

 

Source: SemiAccurate

Two families of lower power Intel chips arriving soon

Subject: General Tech | November 30, 2011 - 09:24 AM |
Tagged: cedar trail m, atom, 32nm, sandybridge DT, Pentium 350, socket 1155

There are two very different families of low power chips from Intel; one of which is available now and the other will be shipping in December after a 2 month delay.  First off are the new Atom chips which DigiTimes mentions, both dual core 32nm Cedar Trail-M parts.  Neither chip represent any major changes to the Atom lineup apart from a die shrink which allows higher frequencies at lower power.  The original delay was reported to be because of issues with 64-bit support as well as DX10 support but there has been no definitive news either way about if those problems will exist on release.   The graphics core does jump from 400MHz to 640MHz which may help Atom compete with Llano but it is still not going to be a fair competition.

The Register reports on a completely different low power chip which may find its way into some server applications.  Don't let the name fool you, the Pentium 350 is a Sandy Bridge-DT chip based on the same core you find in the Xeon E3 chips that are already on the market.  They support Turbo Boost, Trusted Execution Technology, Hyperthreading and virtualization optimization as well as all the other improvements in the Sandy Bridge lineup.  The 32nm chip has two cores running at 1.2GHz, sports a TDP of 20W and is expected to sell for around $150.  At that price and TDP it is unlikely to be a good answer to the smaller chips that ARM is now trying to sneak into the server room but at least Intel now has a low power chip for the server room.

elreg_intel_low_power_server_chip_roadmap.jpg

"Intel will launch its Cedar Trail-M platform for netbooks including 32nm-based Atom N2800 and N2600 processors in December, according to industry sources.

Because of shrinking demand for Atom processors and chipsets due to competition from tablet PCs, Intel's third-quarter 2011 revenues of US$269 million from related products dropped 32% on year, the sources indicated. Due to weak demand, Intel has delayed Cedar Trail-M from September to December, the sources noted."

Here is some more Tech News from around the web:

Tech Talk

 

Source: DigiTimes

You can see the layout of the Bulldozer but you can't see it in the flesh yet

Subject: General Tech | October 11, 2011 - 09:16 AM |
Tagged: bulldozer, 32nm

At SemiAccurate is a brief look at the architecture of Bulldozer, the long awaited successor to the Phenom II chip.  We are still languishing under several NDA's which cover the actual performance of the chip, so you can only see the floor plans ... for now.  Even that is enough to raise some questions about what AMD has done and what a CPU core is now.  At each corner of the chip you can see a Bulldozer Core which adds to four, only half of what we were lead to expect on Bulldozer.  That is because each Bulldozer Core is comprised of two CPU cores, so thoroughly fused that they are essentially one core and this will lead to great confusion as to what a CPU core actually is now.  Thankfully this is not an APU so we do not have to include integrated graphics in the count of cores on the die.  Read the full article to learn more about what has been done to the fetch and predict branches as well as the FP scheduler.

SA_Bulldoser_floor_plan.jpg

"During the always excellent Hot Chips conference this year, AMD’s Sean White gave a talk about the architecture, and only the architecture, of the new CPU. To say it is different is understating things, it is really a bold step into places where few have gone, and no one has tried on a consumer product. The closest thing to AMD’s new Bulldozer architecture out there is Sun’s Niagara, and no one would accuse those designers of following the pack."

Here is some more Tech News from around the web:

Tech Talk

 

Source: SemiAccurate

Oh Llano, wherefore art thou?

Subject: General Tech | October 3, 2011 - 09:14 AM |
Tagged: llano, APU, GLOBALFOUNDRIES, 28nm, 32nm, trinity, amd

Woe is AMD, as it becomes ever more obvious that Llano is not giving good yields at GLOBALFOUNDRIES.  Back in July the market noticed that while the new Llano chips were great at providing good enough graphics for a great price, they were very hard to find.  As a consumer you might be able to find a notebook to purchase for yourself but as a reseller who needs to buy processors in the thousands before considering that chip as a part of the new product line up you have been out of luck.  According to DigiTimes this will change in 2012 with the arrival of Trinity which will still use GLOBALFOUNDRIES 32nm process, turning to TSMC for the 28nm graphical portion.  The previous hope that the supply problems would be solved in September were obviously a little too optimistic.

empty.jpg

"Supply of AMD's Llano APUs, affected by Globalfoundries's lower-than-expected 32nm yield rates, has been significantly limited and is unlikely to recover until the company's upcoming Trinity arrives in 2012, according to sources from motherboard players. When asked about the company's upcoming Trinity schedule, AMD Taiwan declined to comment on unannounced products.

AMD started suffering from Llano APU supply shortages in July due to the yield issues and the company originally expected the supply status to return to normal in September. However, judging from the current situation, the sources believe the company's supply volume is unlikely to meet client demand through the end of 2011.

The sources estimated that the yield rate issue should be resolved in 2012, when Trinity launches."

Here is some more Tech News from around the web:

Tech Talk

Source: DigiTimes

More on GLOBALFOUNDRIES 32nm process and the supply problems we've seen

Subject: General Tech | September 7, 2011 - 11:07 AM |
Tagged: GLOBALFOUNDRIES, 32nm, llano

We have mentioned in the Podcast and on the front page that GLOBALFOUNDRIES 32nm process has been having some problems.  Poor yields have prevented AMD from hitting the targets that they wanted to see from Llano thought they still produce enough to sell.  The supply is enough to keep up with the demands of the individual DIY system builders but AMD really wants major laptop and system vendors to pick up Llano as a base for new models.  Since they want to order very large numbers of APUs at the same time, until Llano can reliably be available for bulk purchases AMD's new APU is not terribly attractive to those vendors.  Why is the Llano having such troubles? Check out Charlie's theory over at SemiAccurate.

gflogo_lo-res.jpg

"Global Foundries is having the proverbial ‘issues’ with their high end 32nm-SHP process. The knee-jerk reaction is to kick GloFo for the problems, but that doesn’t take in to account the good partss of the process.

To say this story is complex and nuanced is putting things mildly. The 32nm-SHP process is the first foundry process to ship High-K Metal Gate (HKMG) chips, and it is the first foundry to ship customer products on a sub-40nm process. They are also the only foundry shipping HKMG products with strain, aka a SiGe cap. That is the hard part, compared to strain, the rest of the HKMG process is easy. The fact that AMD has shipped almost 10 million Llano CPUs by now says that something is going right. GloFo is currently making things that no one else can, and with a 6+ month lead on the competition."

Here is some more Tech News from around the web:

Tech Talk

 

Source: SemiAccurate

Intel Unveils 16 New 32nm Processors

Subject: Processors | September 5, 2011 - 06:52 PM |
Tagged: sandy bridge, pentium, Intel, cpu, Core, celeron, 32nm

Intel today released a price list which included 16 new 32nm processors. The new additions fill in gaps in the Celeron, Pentium, and Core product lines. The new additions are then further broken down into the desktop and mobile camps. On the desktop front, there are four Celeron models ranging from $47 to $52, three Pentium models ranging from $70 to $86, and four new Core i series processors ranging from $127 to $177. Within that range, there are three hyper-threaded dual core Core i3 part and one quad core Core i5 processor.

Intel.png

The mobile additions include one low end and four high end models. On the low end is the dual core Celeron B840 at 1.9GHz with 2 MB L3 cache and 35W TDP. On the high end are four Core i7 chips. The Core i7 2640M is a $346 part and is a hyper-threaded dual core chip at 2.8 GHz, 4 MB L3 cache, and 35W TDP. The Core i7 2760QM is a hyper-threaded quad core part at 2.4 GHz, 6 MB L3 cache, and a 45W TDP. As another 45W TDP part, the Core i7 2860 QM is also a hyper-threaded quad core at 2.5 GHz with 8 MB L3 cache. The highest end mobile chip addition is the Core i7 2960XM, which is a hyper-threaded quad core at 2.7 GHz, a 55W TDP, and 8 MB of L3 cache.

As you can see, there are quite a few new additions filling out the product lineup at various price points and performance segments. See the chart below for the full list and specs.

  Processor Clockspeed Cores/Threads L3 Cache TDP Price
Desktop            
  Core i5-2320 3.0 GHz 4/4 6MB 95W $177
  Core i3-2130 3.4 GHz 2/4 3MB 65W $138
  Core i3-2125 3.3 GHz 2/4 3MB 65W $134
  Core i3-2120T 2.6 GHz 2/4 3MB 35W $127
             
  Pentium G860 3.0 GHz 2/2 3MB 65W $86
  Pentium G630 2.7 GHz 2/2 3MB 65W $75
  Pentium G630T 2.3 GHz 2/2 3MB 35W $70
             
  Celeron G540 2.5 GHz 2/2 2MB 65W $52
  Celeron G530T 2.0 GHz 2/2 2MB 35W $47
  Celeron G530 2.4 GHz 2/2 2MB 65W $42
  Celeron G440 1.6 GHz 1/1 1MB 35W $37
Mobile            
   Core i7-2960XM  2.7 GHz  4/8  8MB  55W  $1,096
   Core i7-2860QM  2.5 GHz  4/8  8MB  45W  $568
   Core i7-2760QM  2.4 GHz  4/8  6MB  45W  $378
   Core i7-2640M  2.8 GHz  2/4  4MB  35W  $346
             
   Celeron B840  1.9 GHz  2/2  2MB  35W  $86

 

Source: Tech Connect

TSMC gets AMD's 28nm APU business

Subject: General Tech | June 17, 2011 - 11:24 AM |
Tagged: TSMC, southern islands, northern islands, llano, global foundries, arm, amd, 40nm, 32nm, 28nm

Back in April there was a kerfuffle in the news about a deal penned between AMD, Global Foundries and TSMC.  It is not worth repeating completely as you can follow the story by using the previous link, suffice to say that it did not indicate problems with the relationship between AMD and Global Foundries. 

The previous post was specifically about 40nm and 32nm process chips, however today we hear from DigiTimes that TSMC has scored a deal with AMD for the 28nm Southern Islands APUs of which we have seen much recently.  The 40nm Northern Islands GPUs will also be produced by TSMC.  That leaves a lot of production capabilities free at Global Foundries to work on ARM processors.  

DT_AMD_APU.jpg

"AMD reportedly has completed the tape-out of its next-generation GPU, codenamed Southern Islands, on Taiwan Semiconductor Manufacturing Company's (TSMC) 28nm process with High-k Metal Gate (HKMG) technology, according to a Chinese-language Commercial Times report. The chip is set to expected to enter mass produciton at the end of 2011.

TSMC will also be AMD's major foundry partner for the 28nm Krishna and Wichita accelerated processing units (APUs), with volume production set to begin in the first half of 2012, the report said.

TSMC reportedly contract manufactures the Ontario, Zacate and Desna APUs for AMD as well as the Northern Island family of GPUs. All of these use the foundry's 40nm process technology.

TSMC was quoted as saying in previous reports that it had begun equipment move-in for the phase one facility of a new 12-inch fab (Fab 15) with volume production of 28nm technology products slated for the fourth quarter of 2011. The foundry previously said it would begin moving equipment into the facility in June, with volume production expected to kick off in the first quarter of 2012."

Here is some more Tech News from around the web:

Tech Talk

Source: DigiTimes