Subject: Processors | November 6, 2015 - 10:09 AM | Sebastian Peak
Tagged: tape out, processors, GLOBALFOUNDRIES, global foundries, APU, amd, 14 nm FinFET
GlobalFoundries has today officially announced their success with sample 14 nm FinFET production for upcoming AMD products.
(Image credit: KitGuru)
GlobalFoundries licensed 14 nm LPE and LPP technology from Samsung in 2014, and were producing wafers as early as April of this year. At the time a GF company spokesperson was quoted in this report at KitGuru, stating "the early version (14LPE) is qualified in our fab and our lead product is yielding in double digits. Since 2014, we have taped multiple products and testchips and are seeing rapid progress, in yield and maturity, for volume shipments in 2015." Now they have moved past LPE (Low Power Early) to LPP (Low Power Plus), with new products based on the technology slated for 2016:
"AMD has taped out multiple products using GLOBALFOUNDRIES’ 14nm Low Power Plus (14LPP) process technology and is currently conducting validation work on 14LPP production samples. Today’s announcement represents another significant milestone towards reaching full production readiness of GLOBALFOUNDRIES’ 14LPP process technology, which will reach high-volume production in 2016."
GlobalFoundries was originally the manufacturing arm of AMD, and has continued to produce the companies processors since the spin-off in 2012. AMD's current desktop FX-8350 CPU was manufactured on 32 nm SOI, and more recently APUs such as the A10-7850K have been produced at 28 nm - both at GlobalFoundries. Intel's latest offerings such as the flagship 6700K desktop CPU are produced with Intel's 14nm process, and the success of the 14LPP production at GlobalFoundries has the potential to bring AMD's new processors closer parity with Intel (at least from a lithography standpoint).
Full PR after the break.
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: General Tech | October 13, 2014 - 11:57 PM | Scott Michaud
Tagged: processors, microprocessor, FinFET, fab
Ah, Solid State Physics. Semiconductors are heavily based on this branch, because it explains the physical (mechanical, electrical, thermal, etc.) properties of solids based on how their atoms are organized. These properties lead into how transistors function, and why.
Put it back, Allyn.
Anandtech has published a seven-page article that digs into physics and builds upon itself. It starts with a brief explanation of conductivity and what makes up the difference between a conductor, an insulator, and a semiconductor. It uses that to build a simple transistor. From there it explains logic gates, wafers, and lithography. It works up to FinFETs and then keeps going into the future. It is definitely not an article for beginners, but it can be progressed from start to finish given enough effort on the part of the reader.
While this was not mentioned in the article, at least not that I found, you can derive the number of atoms per "feature" by dividing its size by the lattice-distance of the material. For silicon, that is about half of a nanometer at room temperature. For instance, 14nm means that we are manufacturing features that are defined by less than 30 atoms (up to rounding error). The article speculates a bit about what will happen after the era of silicon. This is quite interesting to me, particularly since I did my undergraduate thesis (just an undergrad thesis) on photonic crystals, which route optical light across manufactured defects in an otherwise opaque solid to make an optical integrated circuit. It has the benefit of, with a mixture of red, orange, and maybe green lasers, being able to "go plaid".
If you are interested, be sure to read the article. It is a bit daunting, but much more manageable than most sources. Congratulations to Joshua Ho and anyone else who might have been involved.
Subject: Processors | October 29, 2012 - 04:53 PM | Ryan Shrout
Tagged: processors, arm, amd, 64-bit
On a not very technically reliable webcast today, AMD has announced that it will produce 64-bit processors based on the ARM architecture and combine them with the "Freedom Fabric" they acquired with the purchase of SeaMicro.
In a move that is incredibly telling about the times we are in, but not really a surprise to those of us that follow the processor markets closely, AMD and ARM announced a partnership beyond previously discussed in public. AMD will start production of ARM-based processors in 2014 and will be among the first to include 64-bit technology.
The target for these processors will be the server market and AMD hopes to be at the forefront the often discussed ARM-in-the-server-world migration. While that server opportunity size is debatable, with partners on stage like Facebook and RedHat, there is little doubt that it will have an affect on enterprise computing in the next 24 months. AMD is hoping that its experience with the move to 64-bit technology in the x86 migration will aid them in development and migration in the ARM architecture world; one that is currently still limited to 32-bit.
UPDATE: As being reported by Anand Shimpi this is in fact NOT an architecture license but is instead a processor license. What does that mean? AMD is not going to develop its own core (as Apple and NVIDIA do) but instead will fully integrate an upcoming 64-bit ARM core in new AMD products.
SeaMicro's Freedom Fabric technology is another major angle that AMD has over other players in this field. The fabric technology is meant to facilitate communication between multiple processors on a specialized bus, removing bottlenecks on the platform and network. Dr. Lisa Su, SVP of Global Business at AMD, stated that simply connecting hundreds or thousands of ARM-based processors to each other isn't enough and moves the problem of computing management from the CPUs to the network itself. Using Freedom Fabric, the AMD-based ARM processors would be able to much more efficiently communicate and thus maintain the promised power benefits of ARM servers.
AMD did state that they will continue to develop x86 processors going forward but you have to wonder about its dedication to that goal. Working with ARM is a quick and easy way to get AMD into a growing market in the server world that Intel currently has no solutions for so it seems possible that this is simply a stop-gap until AMD can develop an x86-based solution. It is hard to say for sure but for an organization in AMD's financial position, having options in multiple segments is certainly a good idea.
What you won't see yet is AMD's graphics technology in the ARM-based processors announced today. This isn't an "ARM APU" but instead is a combination of SeaMicro and ARM for a very specific server workload.
We'll have more on this announcement if anything else interesting is divulged, but you can find the entire press release from AMD after the break!
Subject: Processors | January 19, 2012 - 02:08 PM | Tim Verry
Tagged: tuning plan, processors, overvolting, overclocking, cpu
Intel relatively recently started producing unlocked "K" series processors that enabled easy overclocking by way of increasing the multiplier. This is a feature that was traditionally reserved for the thousand dollar Extreme Edition products. AMD then followed suit with its own line of "K" series APUs (despite having FX and Black Edition branding already, but that's another story). Well, it is now Intel's turn to leap frog AMD who has traditionally been the overclocker friendly company. Yesterday Intel launched a new pilot program that overclockers and enthusiasts are sure to enjoy. The new Performance Tuning Protection Plan is a program aimed at users of "K" and "X" (unlocked and extreme edition) processors who are adventurous enough to overclock and overvolt their chips to wrangle the best possible performance from them. While the company has stressed that they still do not officially endorse overclocking or otherwise running their CPUs out of Intel specifications, the Performance Tuning Protection Plan is an additional service that can be added in addition to (though seperate from) the existing warranty wherein Intel will furnish a free replacement processor to any users that (unintentionally) damage their processors as a result of overclocking or increasing the voltage. Read on for more details.
The new Performance Tuning Protection Plan will be offered directly from Intel as well as various resellers and can be purchased for any of Intel's K series, X series, or Socket 2011 processors. Only one plan can be applied per processor, and once the CPU has been replaced with a replacement processor through the plan, the insurance does not "roll over" to the replacement part. This means that a second chance is all you get. If the replacement CPU fails as a result of overclocking or overvolting you're out of luck. The Protection Plan is further an additional expense that will applied in addition to the standard 3 year manufacturer's warranty. It only covers damage caused by running the processor out of spec. After purchasing the processor, users can buy the protection plan for a one time fee, and it will kick in within approximately 30 days of buying the plan. Intel says the delay is caused by the time needed for the various plan supporting databases to sync up and for payment to clear.
Prices vary depending on which processor you want to protect with the plan. The Performance Tuning Protection Plan pricing for currently supported processors is listed in the chart below.
|Processor||Price (USD) per CPU|
|Core i5 2500K||$20|
|Core i7 2600K||$25|
|Core i7 2700K||$25|
|Core i7 3930K||$35|
|Core i7 3960X||$35|
Intel is currently offering the new overclocking insurance for a limited time-- a six month trial run to be more specific. Starting January 18th, the company will begin selling the plan directly to customers on their website as well as through several resellers. Initially these resellers include CyberPower, Canada Computers and Electronics, Scan Computers, and Altech Computers. On February 13th, Intel will add additional resellers to the list. The pilot phase will last for six months; after which the company will "decide whether or not to proceed" with the plan. Obviously there is a slight risk for early adopters that after buying the plan, Intel will discontinue it at the six month mark; however, there is also a solid opportunity to overclock the heck out of the chips and have an official safety net for the next few months at the least. Are you running an unlocked processor, and if so will you be checking out the Tuning Protection Plan?
Phenom II End of Line
It was January, 2009 when AMD released their first 45 nm product to the desktop market. While the server market actually received the first 45 nm parts some months earlier, they were pretty rare until AMD finished ramping production and was able to release the next generation of Phenom parts into the wild. The Phenom II proved an able competitor to Intel’s seemingly unstoppable Core 2 architecture. While the Phenom II typically had to be clocked slightly higher than the competing products, they held up well in terms of price and performance.
AMD was finally able to overcome the stigma of the original Phenom launch, which was late, slow, and featured that wonderful revision B2 bug. The Phenom II showed none of those problems, per clock performance was enhanced, and the chips were able to run at speeds of 3.0 GHz. These chips were able to hit speeds of 4+ GHz on water cooling, and 5+ GHz using LNO2. AMD seemed finally back in the game. The Phenom II looked to propel AMD back into competitiveness with Intel, and the leaks pertaining to the 6 core versions of the architecture only made consumers all the more excited for what was to come.