Sign in with
Sign up | Sign in

How We Tested Intel's SSD DC P3700

Intel SSD DC P3700 800GB and 1.6TB Review: The Future of Storage
By
Test Hardware
ProcessorIntel Core i7-3960X (Sandy Bridge-E), 32 nm, 3.3 GHz, LGA 2011, 15 MB Shared L3, Turbo Boost Enabled
Motherboard
Intel DX79SI, X79 Express
Memory
G.Skill Ripjaws Z-Series (4 x 4 GB) DDR3-1600 @ DDR3-1600, 1.5 V
System Drive
Intel SSD 320 160 GB SATA 3Gb/s
Tested Drives
Intel SSD DC P3700 800 GB and 1.6 TB
Graphics
AMD FirePro V4800 1 GB
Power Supply
OCZ ModXStream Pro 700 W
System Software and Drivers
Operating SystemWindows 7 x64 Ultimate/Windows Server 2012 R2
DirectXDirectX 11
DriverGraphics: AMD 8.883
Benchmark Suite
Iometer v1.1.0
Four Workers, 4 KB Random: LBA=Full, Span Varying Queue Depths 
ATTO
v2.4.7, 2 GB, QD=4
Custom
C++, 8 MB Sequential, QD=4
Enterprise Testing: Iometer Workloads
Read
Write
512 Bytes
1 KB
2 KB
4 KB
8 KB
16 KB
32 KB
64 KB
128 KB
512 KB
Database
67%
100%
n/a
n/a
n/a
n/a
100%
n/a
n/a
n/a
n/a
n/a
File Server
80%
100%
10%
5%
5%
60%
2%
4%
4%
10%
n/a
n/a
Web Server
100%
100%
22%
15%
8%
23%
15%
2%
6%
7%
1%
1%

The Storage Networking Industry Association (SNIA), a working group made up of SSD, flash, and controller vendors, has a testing procedure that attempts to control as many of the variables inherent to SSDs as possible. SNIA’s Solid State Storage Performance Test Specification (SSS PTS) is a great resource for enterprise SSD testing. The procedure does not define what tests should be run, but rather the way in which they are run. This workflow is broken down into four parts:

  1. Purge: Purging puts the drive at a known starting point. For SSDs, this normally means Secure Erase.
  2. Workload-Independent Preconditioning: A prescribed workloadthat is unrelated to the test workload.
  3. Workload-Based Preconditioning: The actual test workload (4 KB random, 128 KB sequential, and so on), which pushes the drive towards a steady state.
  4. Steady State: The point at which the drive’s performance is no longer changing for the variable being tracked.

These steps are critical when testing SSDs. It’s incredibly easy to not fully condition the drive and still observe out-of-box behavior, which may lead one to think that it’s steady-state. These steps are also important when going between random and sequential writes.

For all performance tests in this review, the SSS PTS was followed to ensure accurate and repeatable results.

All tests employ random data, when available. Intel's SSD DC P3700 does not perform any compression prior to writing, so there is no difference in performance-based data patterns. We also chose to focus our comparisons on the Micron P320h and P420m, which are quite similar in performance and architecture. Both employ a proprietary driver that, while not NVMe, yields a very close approximation.

Add a comment
Ask a Category Expert
React To This Article

Create a new thread in the Reviews comments forum about this subject

Example: Notebook, Android, SSD hard drive

Display all 27 comments.
  • 0 Hide
    blackmagnum , August 13, 2014 12:17 AM
    A large heat sink on an SSD? This thing is too hot to touch!
  • 0 Hide
    saturn85 , August 13, 2014 2:19 AM
    will this kind of ssd suffer from write wear out/reduce lifespan?
  • 1 Hide
    xback , August 13, 2014 2:44 AM
    In the 1st table on page 1, the "4k random write IOPS" are reversed :) 

    (3500 scores highest, while the 3700 scores lowest)
  • 0 Hide
    redgarl , August 13, 2014 3:55 AM
    OCZ already went there and even made their own connector for providing more bandwith to SSD... just a shame that now Intel try to remove the carpet from beneath the feet of OCZ. Well, old tech is new tech.

    By the way, OCZ revodrive was priced similarly, I don't see that big fuzz from Toms here.
  • 3 Hide
    Nuckles_56 , August 13, 2014 4:00 AM
    "Intel's 2 TB model purportedly needs 650 LFM across the drive"

    What the hell is LFM?
  • 0 Hide
    JeanLuc , August 13, 2014 5:04 AM
    The active power consumption numbers on first table are wrong (I hope!) 35,000 watts active?

    Edit:
    It's not actually wrong it might just be my out of date browser I'm using in the office but for me the numbers aren't lining up correctly.
  • 4 Hide
    pjmelect , August 13, 2014 5:29 AM
    Quote:
    "Intel's 2 TB model purportedly needs 650 LFM across the drive"

    What the hell is LFM?


    Linear Feet per Minute of airflow
  • -1 Hide
    pjmelect , August 13, 2014 5:33 AM
    Quote:
    "Intel's 2 TB model purportedly needs 650 LFM across the drive"

    What the hell is LFM?


    Linear Feet per Minute of airflow
  • 0 Hide
    Nuckles_56 , August 13, 2014 5:33 AM
    Quote:
    Quote:
    "Intel's 2 TB model purportedly needs 650 LFM across the drive"

    What the hell is LFM?


    Linear Feet per Minute of airflow


    Ah that makes sense now
  • 0 Hide
    xXXGamesmasheRXXx , August 13, 2014 5:39 AM
    These Expensive Numbers!
  • 0 Hide
    WyomingKnott , August 13, 2014 7:27 AM
    Did I misread the charts, or did this drive consistently come in second or third except in consistency?
  • 0 Hide
    chewrock , August 13, 2014 9:01 AM
    My OCZ Revo drive is a first generation PCIe model I got on sale from New Egg. No problems. What is iNTEL trying to claim? Nothing. Their new interface spec is just making it possible for low-tech users to install a product that OCZ has been selling for years.
  • 0 Hide
    drewriley , August 13, 2014 11:20 AM
    Quote:
    In the 1st table on page 1, the "4k random write IOPS" are reversed :) 

    (3500 scores highest, while the 3700 scores lowest)


    Fixed - Thanks!
  • 0 Hide
    drewriley , August 13, 2014 11:23 AM
    Quote:
    Did I misread the charts, or did this drive consistently come in second or third except in consistency?


    You are correct, there are PCIe SSDs that can beat the P3700, but Intel undercuts the price on those SSDs by a wide margin. SSDs that are in the same price ballpark as the P3700 don't come close in most tests.
  • 0 Hide
    drewriley , August 13, 2014 11:24 AM
    Quote:
    will this kind of ssd suffer from write wear out/reduce lifespan?


    Yes, these SSDs still have a write endurance specification that is listed on the first page. The P3700 can withstand 10 drive writes per day (DWPD) for a full 5 years.
  • -1 Hide
    drewriley , August 13, 2014 11:30 AM
    Quote:
    OCZ already went there and even made their own connector for providing more bandwith to SSD... just a shame that now Intel try to remove the carpet from beneath the feet of OCZ. Well, old tech is new tech.

    By the way, OCZ revodrive was priced similarly, I don't see that big fuzz from Toms here.


    The OCZ RevoDrive's that are similarly priced are more consumer drives and not enterprise like the P3XXX series from Intel. These drives will have more write endurance and greater sustained IOP performance, which is what enterprise customers pay for. Also, NVMe isn't an Intel unique thing. Expect to see all PCIe SSD companies, including OCZ, to follow.
  • 0 Hide
    drewriley , August 13, 2014 11:34 AM
    Quote:
    My OCZ Revo drive is a first generation PCIe model I got on sale from New Egg. No problems. What is iNTEL trying to claim? Nothing. Their new interface spec is just making it possible for low-tech users to install a product that OCZ has been selling for years.


    I wouldn't say Intel is trying to claim anything. They are following\leading an industry specification that most companies will move to eventually, including OCZ. Native booting is obviously one benefit, but low latency and fewer CPU cycles required are what enterprise customers are happy about.
  • 0 Hide
    bin1127 , August 13, 2014 7:51 PM
    Wanted to make a joke about the name but, nevermind.
  • 0 Hide
    f-14 , August 14, 2014 11:55 AM
    Quote:
    Wanted to make a joke about the name but, nevermind.

    AKA Megatron ?

    i don't see the point in this, it reminds me of the ISA memory storage cards. i can't see this lasting more than 5-10 years as some company already figured out how to do this with RAM (samsung wasn't it?) and is working on the need for storage drives altogether and just have RAM drives that don't lose their data sort of an mpci but in a 304-9 pin dimm slot form factor if i recall properly ?

    so these nvmhci might be on the market now but when that company brings their solution to market it's going to eliminate the need for pcie and sata except for optical disc reading and graphics cards. but i am sure those manufacturers will be looking for a way to incorporate gpus into DIMM slot factors to take real advantage of boards with 32+ PCIe lanes like socket 2011/X79/X99 solutions.

    it would eliminate the pathway needs for alot of peripherals and decrease the size of M/B tremendously to where you'd only need a PC the size of a 9"x 6"x 8" case which USB 3.1 and display port/thunderbolt/lightning eliminating the need for alot of built ins
  • 0 Hide
    saturn85 , August 15, 2014 9:02 AM
    Quote:
    Quote:
    will this kind of ssd suffer from write wear out/reduce lifespan?


    Yes, these SSDs still have a write endurance specification that is listed on the first page. The P3700 can withstand 10 drive writes per day (DWPD) for a full 5 years.


    oh, i see, i think i have miss that part. when NVMe first come to my mind, i thought their storage chips have move to non volatile memory base like PCM, ReRAM and ST-MRAM. but now only i notice their storage chips are still NAND base.
Display more comments
React To This Article