Manufacturer: NVIDIA

GPU Enthusiasts Are Throwing a FET

NVIDIA is rumored to launch Pascal in early (~April-ish) 2016, although some are skeptical that it will even appear before the summer. The design was finalized months ago, and unconfirmed shipping information claims that chips are being stockpiled, which is typical when preparing to launch a product. It is expected to compete against AMD's rumored Arctic Islands architecture, which will, according to its also rumored numbers, be very similar to Pascal.

This architecture is a big one for several reasons.


Image Credit: WCCFTech

First, it will jump two full process nodes. Current desktop GPUs are manufactured at 28nm, which was first introduced with the GeForce GTX 680 all the way back in early 2012, but Pascal will be manufactured on TSMC's 16nm FinFET+ technology. Smaller features have several advantages, but a huge one for GPUs is the ability to fit more complex circuitry in the same die area. This means that you can include more copies of elements, such as shader cores, and do more in fixed-function hardware, like video encode and decode.

That said, we got a lot more life out of 28nm than we really should have. Chips like GM200 and Fiji are huge, relatively power-hungry, and complex, which is a terrible idea to produce when yields are low. I asked Josh Walrath, who is our go-to for analysis of fab processes, and he believes that FinFET+ is probably even more complicated today than 28nm was in the 2012 timeframe, which was when it launched for GPUs.

It's two full steps forward from where we started, but we've been tiptoeing since then.


Image Credit: WCCFTech

Second, Pascal will introduce HBM 2.0 to NVIDIA hardware. HBM 1.0 was introduced with AMD's Radeon Fury X, and it helped in numerous ways -- from smaller card size to a triple-digit percentage increase in memory bandwidth. The 980 Ti can talk to its memory at about 300GB/s, while Pascal is rumored to push that to 1TB/s. Capacity won't be sacrificed, either. The top-end card is expected to contain 16GB of global memory, which is twice what any console has. This means less streaming, higher resolution textures, and probably even left-over scratch space for the GPU to generate content in with compute shaders. Also, according to AMD, HBM is an easier architecture to communicate with than GDDR, which should mean a savings in die space that could be used for other things.

Third, the architecture includes native support for three levels of floating point precision. Maxwell, due to how limited 28nm was, saved on complexity by reducing 64-bit IEEE 754 decimal number performance to 1/32nd of 32-bit numbers, because FP64 values are rarely used in video games. This saved transistors, but was a huge, order-of-magnitude step back from the 1/3rd ratio found on the Kepler-based GK110. While it probably won't be back to the 1/2 ratio that was found in Fermi, Pascal should be much better suited for GPU compute.


Image Credit: WCCFTech

Mixed precision could help video games too, though. Remember how I said it supports three levels? The third one is 16-bit, which is half of the format that is commonly used in video games. Sometimes, that is sufficient. If so, Pascal is said to do these calculations at twice the rate of 32-bit. We'll need to see whether enough games (and other applications) are willing to drop down in precision to justify the die space that these dedicated circuits require, but it should double the performance of anything that does.

So basically, this generation should provide a massive jump in performance that enthusiasts have been waiting for. Increases in GPU memory bandwidth and the amount of features that can be printed into the die are two major bottlenecks for most modern games and GPU-accelerated software. We'll need to wait for benchmarks to see how the theoretical maps to practical, but it's a good sign.

Podcast #369 - Fable Legends DX12 Benchmark, Apple A9 SoC, Intel P3608 SSD, and more!

Subject: General Tech | October 1, 2015 - 02:17 PM |
Tagged: podcast, video, fable legends, dx12, apple, A9, TSMC, Samsung, 14nm, 16nm, Intel, P3608, NVMe, logitech, g410, TKL, nvidia, geforce now, qualcomm, snapdragon 820

PC Perspective Podcast #369 - 10/01/2015

Join us this week as we discuss the Fable Legends DX12 Benchmark, Apple A9 SoC, Intel P3608 SSD, 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: - 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, Josh Walrath, Jeremy Hellstrom, and Allyn Malventano

Program length: 1:42:35

  1. Week in Review:
  2. 0:54:10 This episode of PC Perspective is brought to you by…Zumper, the quick and easy way to find your next apartment or home rental. To get started and to find your new home go to
  3. News item of interest:
  4. Hardware/Software Picks of the Week:
  5. Closing/outro

Subscribe to the PC Perspective YouTube Channel for more videos, reviews and podcasts!!

TSMC Plans 10nm, 7nm, and "Very Steep" Ramping of 16nm.

Subject: Graphics Cards, Processors, Mobile | July 19, 2015 - 06:59 AM |
Tagged: Zen, TSMC, Skylake, pascal, nvidia, Intel, Cannonlake, amd, 7nm, 16nm, 10nm

Getting smaller features allows a chip designer to create products that are faster, cheaper, and consume less power. Years ago, most of them had their own production facilities but that is getting rare. IBM has just finished selling its manufacturing off to GlobalFoundries, which was spun out of AMD when it divested from fabrication in 2009. Texas Instruments, on the other hand, decided that they would continue manufacturing but get out of the chip design business. Intel and Samsung are arguably the last two players with a strong commitment to both sides of the “let's make a chip” coin.


So where do you these chip designers go? TSMC is the name that comes up most. Any given discrete GPU in the last several years has probably been produced there, along with several CPUs and SoCs from a variety of fabless semiconductor companies.

Several years ago, when the GeForce 600-series launched, TSMC's 28nm line led to shortages, which led to GPUs remaining out of stock for quite some time. Since then, 28nm has been the stable work horse for countless high-performance products. Recent chips have been huge, physically, thanks to how mature the process has become granting fewer defects. The designers are anxious to get on smaller processes, though.

In a conference call at 2 AM (EDT) on Thursday, which is 2 PM in Taiwan, Mark Liu of TSMC announced that “the ramping of our 16 nanometer will be very steep, even steeper than our 20nm”. By that, they mean this year. Hopefully this translates to production that could be used for GPUs and CPUs early, as AMD needs it to launch their Zen CPU architecture in 2016, as early in that year as possible. Graphics cards have also been on that technology for over three years. It's time.

Also interesting is how TSMC believes that they can hit 10nm by the end of 2016. If so, this might put them ahead of Intel. That said, Intel was also confident that they could reach 10nm by the end of 2016, right until they announced Kaby Lake a few days ago. We will need to see if it pans out. If it does, competitors could actually beat Intel to the market at that feature size -- although that could end up being mobile SoCs and other integrated circuits that are uninteresting for the PC market.

Following the announcement from IBM Research, 7nm was also mentioned in TSMC's call. Apparently they expect to start qualifying in Q1 2017. That does not provide an estimate for production but, if their 10nm schedule is both accurate and also representative of 7nm, that would production somewhere in 2018. Note that I just speculated on an if of an if of a speculation, so take that with a mine of salt. There is probably a very good reason that this date wasn't mentioned in the call.

Back to the 16nm discussion, what are you hoping for most? New GPUs from NVIDIA, new GPUs from AMD, a new generation of mobile SoCs, or the launch of AMD's new CPU architecture? This should make for a highly entertaining comments section on a Sunday morning, don't you agree?

Computex 2015: Micron Announces 16nm TLC For Consumer SSDs

Subject: Storage, Shows and Expos | June 2, 2015 - 11:47 PM |
Tagged: tlc, ssd, micron, flash, computex 2015, computex, 16nm

Chugging right along that TechInsights Flash Roadmap we saw last year, Micron has announced the TLC extension to their 16nm flash memory process node.

Micron Roadmap.png

While 16nm TLC was initially promised Q4 of 2014, I believe Micron distracted themselves a little with their dabbles into Dynamic Write Acceleration technology. No doubt wanting to offer ever more cost effective SSDs to their portfolio, the new TLC 16nm flash will take up less die space for the same capacity, meaning more dies per 300mm wafer, ultimately translating to lower cost/GB of consumer SSDs.


Micron's 16nm (MLC) flash

The Crucial MX200 and BX100 SSDs have already been undercutting the competition in cost/GB, so the possibility of even lower cost SSDs is a more than welcome idea - just so long as they can keep the reliability of these parts high enough. IMFT has a very solid track record in this regard, so I don't suspect any surprises in that regard.

Full press blast appears after the break.

You still haven't bought a Crucial MX100?

Subject: Storage | June 10, 2014 - 07:00 PM |
Tagged: ssd, 16nm, crucial, mx100

For a mere $100 you can pick up the 256GB model or for $200 you can double that to 512GB.  That certainly makes the drives attractive but the performance is there as well, often beating its predecessor the MX500 series.  If reliability is a concern the onboard RAIN feature guards against writes to bad flash, there are onboard capacitors to allow writes to finish in the case of power outages and a 3 year warranty.  Check out the full review at The Tech Report if you need a second opinion after Allyn's review.


"The Crucial MX100 is the first solid-state drive to use Micron's 16-nm MLC NAND. It's also one of the most affordable SSDs around, with the 256GB version priced at $109.99 and the 512GB at $224.99. We take a closer look at how the two stack up against a range of competitors, and the results might surprise you."

Here are some more Storage reviews from around the web:


Subject: Storage
Manufacturer: Crucial
Tagged: ssd, sata, mx100, crucial, 16nm

Introduction, Specifications and Packaging


Back in July of last year, Micron announced production of 16nm flash memory. These were the same 128gbit dies as the previous gen parts, but 16nm means the dies are smaller, meaning more dies from a single wafer, ultimately translating to lower end user cost.


It takes a bit of time for those new flash die shrinks to trickle into mainstream products. Early yields from a given shrink tend to not have competitive endurance on initial production. As production continues, the process gets tweaked, resulting in greater and longer enduring yields.

Continue reading for the full scoop!!

Podcast #301 - IN WIN 901 Chassis, MSI Z97 Gaming 7 Motherboard, R9 Price Drops and more!

Subject: General Tech | May 22, 2014 - 06:42 PM |
Tagged: Z97 Gaming 7, z97, xiaomi, video, tegra k1, tegra, SATA Express, podcast, msi, Intel, in win 901, Broadwell, asmedia, amd, 16nm

PC Perspective Podcast #301 - 05/22/2014

Join us this week as we discuss the IN WIN 901 Chassis, MSI Z97 Gaming 7 Motherboard, R9 Price Drops 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: - 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, Josh Walrath, Jeremy Hellstrom, and Allyn Maleventano

Program length: 1:16:22
  1. Week in Review:
  2. News items of interest:
  3. Hardware/Software Picks of the Week:
  4. Closing/outro

Be sure to subscribe to the PC Perspective YouTube channel!!


TSMC Begins 16nm FinFET-based 3D Chip Production

Subject: General Tech, Processors | December 14, 2013 - 03:08 AM |
Tagged: TSMC, process node, 16nm

Taiwan Semiconductor (TSMC) is one of the few chip fabrication companies in the world (especially when you omit the memory producers, etc.). Their customers include: AMD, NVIDIA, Qualcomm, Broadcom, and even a few Intel Atom processors have come out of their lines at one point. They will take money from just about anyone who wants a chip.


According to Bit-Tech, a few customers will even have access to 16nm before the end of the year.

The catch, which of course there is one, is that production runs will be very small. We would love to see a gigantic run of new AMD or NVIDIA GPUs based on 16nm but that will not be the case (and not just because Volcanic Islands and Maxwell are both 2Xnm products). The first customers, while otherwise anonymous, will be interested in mobile systems-on-a-chip (SoCs).

On the plus side, when future 1Xnm designs come out, TSMC's production could be reasonably caught up to make a smooth launch.

Intel, the current leader in the fabrication world, targeted a slightly smaller 14nm process and have already begun producing a few odds and ends at that level. Full production has not even really started yet.

Just so you can get an idea of the complexity we are dealing with: 16nm fabrication creates details that are just ~32 atoms in width.

Source: Bit-Tech

Micron Is Now Sampling 16nm NAND Flash, And Drives Using the Smaller Chips Are Expected in 2014

Subject: General Tech, Storage | July 18, 2013 - 02:29 AM |
Tagged: nand, micron, flash, 16nm

Micron recently announced that is has begun sampling 16nm NAND flash to select partners. Micron expects to begin full production of the NAND chips using the smaller flash manufacturing process in the fourth quarter of this year (Q4 2013). Drives based on its new 16nm MLC NAND flash are expected to arrive as early as next year. (PC Perspective's own storage expert is currently overseas, but I managed to reach out over email to get some clarification, and his thoughts, on the Micron annuoncement.)

The announcement relates to new NAND flash that is smaller, but not necessarily faster, than the existing 20nm and 25nm flash chips used in current solid state drives. In the end, Micron is still delivering 128Gb (Gigabit) per die, but using a 16nm process. The 16nm flash is a pure shrink of 20nm which is, in turn, a shrink of 25nm flash. In fact, Micron is able to get just under 6 Terabytes of storage out of a single 300mm wafer. These wafers are then broken down into dies in individual flash chips that are used in all manner of solid state storage devices from smartphone embedded storage to desktop SSDs. This 16nm flash still delivers 128Gb --which is 16GB-- per die allowing for a 128GB SSD using as few as eight chips.


A single 16nm NAND flash die with a SSD in the background

Micron expects the 16nm MLC (multi-level cell) flash to be used in consumer SSDs, USB thumb drives, mobile devices, and cloud storage.

The 16nm process will allow Micron to get more storage out of the same sized wafer (300mm) used for current processes, which in theory should mean flash memory that is not only smaller, but (in theory) cheaper.


A single wafer of 16nm NAND flash (just under 6TBs)

As Allyn further notes, the downside to the new 16nm NAND flash is a reduction in the number of supported PE cycles. Micron has not released specific information on this, but the new 16nm MLC flash is expected to have fewer than 1,000 P/E cycles. For comparison, 25nm and 20nm flash has P/E cycles of 3,000 and 1,000 respectively.

In simple terms, P/E (program-erase) cycles relate to the number of times that a specific portion of flash memory can be written to before wearing out. SSD manufacturers were able to work around this with the transition from 25nm to 20nm and still deliver acceptable endurance on consumer drives, and I expect that similar techniques will be used to do the same for 16nm flash. For example, manufactuers could enable compression that is used prior to writing out the data to the physical flash or over-provisioning the actual hardware versus the reported software capacity (ie a drive sold as a 100GB model that actually has 128GB of physical flash).

I don't think it will be a big enough jump that typical consumers wil have to worry too much about this, considering the vast majority of operations will be read operations and not writes. Despite the reduction in P/E cycles, SSDs with 16nm NAND MLC flash will still likely out-last a typical mechanical hard drive.

What do you think about the Micron announcement?

The full press release can be found below:

Source: Micron

16nm FinFET ARM processors from TSMC soon

Subject: General Tech | April 2, 2013 - 05:57 PM |
Tagged: arm, FinFET, 16nm, TSMC, Cortex-A57

While what DigiTimes is reporting on is only the first tape out, it is still very interesting to see TSMC hitting 16nm process testing and doing it with the 3D transistor technology we have come to know as FinFET.  It was a 64-bit ARM Cortex-A57 chip that was created using this process, unfortunately we did not get much information about what comprised the chip apart from the slide you can see below.


As it can be inferred by the mention that it can run alongside big.LITTLE chips it will not be of the same architecture, nor will it be confined to cellphones.  This does help reinforce TSMC's position in the market for keeping up with the latest fabrication trends and another solid ARM contract will also keep the beancounters occupied.  You can't expect to see these chips immediately but this is a solid step towards an new process being mastered by TSMC.


"The achievement is the first milestone in the collaboration between ARM and TSMC to jointly optimize the 64-bit ARMv8 processor series on TSMC FinFET process technologies, the companies said. The pair has teamed up to produce Cortex-A57 processors and libraries to support early customer implementations on 16nm FinFET for ARM-based SoCs."

Here is some more Tech News from around the web:

Tech Talk

Source: DigiTimes