Specifications, Packaging, Internals, Testing Methodology and System Setup
Specifications:
Straight from Samsung:
Packaging:
Packaging is identical to that of the 840 series products from Samsung.
Internals:
Breaking open the shells:
Note that the two smaller capacities go as far as using smaller PCBs. There is simply not a need for as many flash packages, so Samsung chose to go with a different PCB design as opposed to just leaving empty space on a board. The change in design also places the controller on top for some, and on bottom for others. I thought this might impact cooling, but a closer look at the thermal pads:
The pads are there, but we're not sure why, as they do not come into contact with any components of any of the PCBs. No component imprints are left in the material, and the machined standoffs suspend the PCB too far above the pad to make any sort of contact. Also of note was that there was no pad present on our initial 512GB sample, yet it was present on samples we received at a later date. Another fun fact – look at the marking on the inner part of the shell. Apparently there was no need to update the 840 EVO design. If it ain't broke…
Here are the fronts and backs of the PCBs:
We covered this a bit on the previous article, but now that we've been able to lay out all capacities, we can present a clear picture on die count staggering among the entire line. Here are the flash memory packages we found installed:
- K9LPGY8S1M – DDP (2 dies)
- K9HQGY8S5M – QDP (4 dies)
- K9PRGY8S7M – ODP (8 dies)
- K9PRGY8S5M – ODP (8 dies)
- K9USGY8S7M – 16 die stack
While the VNAND die capacity (86Gbit) is lower than the typical 128Gbit of 2D NAND, Samsung appears to be more adept at stacking it within a package, as we don't typically see 2D NAND at more than four dies per package, meaning higher capacity models of competing SSDs are forced to mount 16 packages on their PCBs.
The 'odd' die capacity means that to deliver the typical 2^n capacities that people are used to, Samsung had to stagger the package types. As an example, the 512GB 850 Pro needs 48 86Gbit dies. It accomplishes this with 4 QDP (4 die) packages and 4 ODP (16 die) packages. Other capacities perform the same trick, just with different staggering of package types. If Samsung were to keep with the typical uniform die counts per package, they could theoretically make the 850 Pro in capacities of 96GB, 192GB, 384GB, 768GB, and 1.5TB. Yes, 1.5TB could be possible in the current form factor, simply by using all 16 die stack packages, yielding 128 dies.
Testing Methodology
Our tests are a mix of synthetic and real-world benchmarks. PCMark, IOMeter, HDTach, HDTune, Yapt and our custom File Copy test round out the selection to cover just about all bases. If you have any questions about our tests just drop into the Storage Forum and we'll help you out!
Test System Setup
We currently employ a pair of testbeds. A newer ASUS P8Z77-V Pro/Thunderbolt and an ASUS Z87-PRO. Variance between both boards has been deemed negligible.
PC Perspective would like to thank ASUS, Corsair, and Kingston for supplying some of the components of our test rigs.
| Hard Drive Test System Setup | |
| CPU | Intel Core i7-4770K |
| Motherboard | ASUS P8Z77-V Pro/TB / ASUS Z87-PRO |
| Memory | Kingston HyperX 4GB DDR3-2133 CL9 |
| Hard Drive | G.Skill 32GB SLC SSD |
| Sound Card | N/A |
| Video Card | Intel® HD Graphics 4600 |
| Video Drivers | Intel |
| Power Supply | Corsair CMPSU-650TX |
| DirectX Version | DX9.0c |
| Operating System | Windows 8.1 X64 |
- PCMark05
- Yapt
- IOMeter
- HDTach
- HDTune
- PCPer File Copy Test









These new charts are not the
These new charts are not the easiest to read.
Slightly larger text and solid colored bars would help a lot.
I second this. I find them
I second this. I find them very hard to read. The bar charts are okay because they are all in order, but when they wonder around like the line graphs, they’re practically illegible. Add in the mislabeled axies and I’m not sure what I’m supposed to be reading.
Agreed.
Agreed.
Not the easiest graphs to
Not the easiest graphs to read!
Background color hinder very much.
It looks like you mislabeled
It looks like you mislabeled the X axis on the PCPer File Copy Test charts. I’m guessing it’s supposed to be “seconds” rather than “MB/s”.
Agreed. Also, i’m pretty sure
Agreed. Also, i’m pretty sure that for the “IO Meter Average Transaction Time” lower – not higher – should be better.
Thanks for the catch, I’ve
Thanks for the catch, I've re-uploaded corrected versions, and expanded the QD out to 8 on these to more easily see where the drives are headed. Expanding it further would make the lower part of the scale harder to read.
Yeah, I almost went out and
Yeah, I almost went out and bought an ADATA SP610 in 128GB. 🙂 That thing beat everyone!
Got it. Fixed the axis label
Got it. Fixed the axis label on file creation and copy charts. Thanks for reporting this.
Look at how much extra room
Look at how much extra room is available in that 2.5in casing for the 512 and 1tb models! Going with full 16 layer packages and filling up the remaining space with them could yield a 2.5 inch SSD in excess of 3TB. O_O
This tech needs to hurry up and get fully commoditized so Samsung has an incentive to make drives that size and we can actually buy them at reasonable prices. Doing so would put a few more well earned nails in the HDD makers coffins.
hey Allyn when are you
hey Allyn when are you getting the intel 750 pci-e ssd? supposed to be out in Q4 and well… its Q4 now!
Possible error with the YAPT
Possible error with the YAPT chart. Shows queue depth on the bottom when it should be block size(or whatever the correct term would be). Regardless, interesting new benchmark along with a great article.
Fixed, and thanks!
Fixed, and thanks!
I’m wondering, can these
I’m wondering, can these drives perform any faster if connected to 12gb/s SAS ports?
The controller and connector
The controller and connector do not support SAS 12Gbit/sec. Even if connected to an appropriate HBA, the link would fall back to 6Gbit SATA.
As usual I’m late to posting
As usual I’m late to posting comments, but in case anyone notices my post: I have not found any source at Samsung or here where it addresses some sort of “hold-up” protection on the power line in case of a PSU failure. Anyone know?