Random Performance – Iometer (IOPS/latency), YAPT (random)
We are trying something different here. Folks tend to not like to click through pages and pages of benchmarks, so I'm going to weed out those that show little to no delta across different units (PCMark). I'm also going to group results performance trait tested. Here are the random access results:
Iometer is an I/O subsystem measurement and characterization tool for single and clustered systems. It was originally developed by the Intel Corporation and announced at the Intel Developers Forum (IDF) on February 17, 1998 – since then it got wide spread within the industry. Intel later discontinued work on Iometer and passed it onto the Open Source Development Lab (OSDL). In November 2001, code was dropped on SourceForge.net. Since the relaunch in February 2003, the project is driven by an international group of individuals who are continuesly improving, porting and extend the product.
Iometer – IOPS
Now we see where the Phoenix Blade truly surpasses the RevoDrive 350. There is a definite gain to be seen in the SBC technology at use here, as it can attain higher ultimate IOPS than OCZ's VCA 2.0 implementation.
Despite this gain over the competition, both solutions are fighting a losing battle in random IO performance when compared to just one modern SATA SSD at queue depths up to 8. Most desktop usage sits in this lower part of the chart, and the less latent SATA controllers are able to reach maximum speeds in this window, and before the Phoenix Blade and the RevoDrive even have a chance to really ramp up to full speed.
Some might believe the inclusion of a P3700 is a bit unfair here, but I disagree. The P3700 uses an 18 channel controller, but the G.Skill and OCZ solutions are using four 4-channel SandForce controllers (16 channels total). The reason the results are so different is mostly due to the significantly higher IO latency of SandForce, with the P3700 seeing added per-IO latency reductions thanks to its use of NVMe, which is significantly more efficient than SCSI or SATA.
Iometer – Average Transaction Time
For SSD reviews, HDD results are removed here as they throw the scale too far to tell any meaningful difference in the results. Queue depth has been reduced to 8 to further clarify the results (especially as typical consumer workloads rarely exceed QD=8). Some notes for interpreting results:
- Times measured at QD=1 can double as a value of seek time (in HDD terms, that is).
- A 'flatter' line means that drive will scale better and ramp up its IOPS when hit with multiple requests simultaneously, especially if that line falls lower than competing units.
The higher latency of the SandForce controller equipped units over other modern SATA SSDs is painfully clear here as well. The SATA units lose steam and become more latent after QD=8 mostly because they are saturating their respective busses by that point.
YAPT (yet another performance test) is a benchmark recommended by a pair of drive manufacturers and was incredibly difficult to locate as it hasn't been updated or used in quite some time. That doesn't make it irrelevant by any means though, as the benchmark is quite useful. It creates a test file of about 100 MB in size and runs both random and sequential read and write tests with it while changing the data I/O size in the process. The misaligned nature of this test exposes the read-modify-write performance of SSDs and Advanced Format HDDs.
The Phoenix Blade and RevoDrive 350 fare better as their controllers are not as sensitive to alignment. While this is labeled as a random test in YAPT, its block sizes are large enough to be considered borderline sequential for faster SSDs, which allows the top two units to blow past all of the SATA devices. The P3700 chokes hard on writes not aligned to 4k boundaries, and that definitely shows here.
That tramp stamp is a deal
That tramp stamp is a deal breaker
I resent that
I resent that
Dammit…I just spit my
Dammit…I just spit my coffee everywhere after reading that.
Agreed, this seems like it
Agreed, this seems like it would be good for a workstation build, but the cheesy graphic really makes it seem childish.
It’s inside your computer –
It’s inside your computer – who cares? It could be pink and have Hello Kitty all over it for all it matters.
The p3700’s wonky random
The p3700’s wonky random write YAPT test or similar tests are always amusing. That intel controller it uses is great, though it can be quite the special snowflake sometimes.
The wait for the p3500 continues…
according to amazon, it
according to amazon, it should be out in December.
I’ll be skipping it since I refuse to switch to Windows 8.
Why would you need
Why would you need to?
"Operating Systems: Windows 7 (64-bit)*, Windows 8, 64-bit*, Windows 8.1, 64-bit*, Windows Server 2008 R2*, Windows Server 2012 R2*, Windows Server 2012*"
I read here:
I read here:
that although you can use it with windows 7 once drivers are loaded, you cannot use it as a boot drive.
Was this incorrect?
IMO the price is still way
IMO the price is still way too high when I can RAID-0 4 SSDs and get similar performance. Even using 4x 128 GB 850 Pros is quite a bit cheaper ($40/512GB compared to $800/480GB), and those are premium drives with a 10-year warranty. I’d go with 256 GB drives which would give me a TB for the price of the 480 GB Phoenix Blade, or a lower priced alternatives for an even better savings.
Besides, my builds have more SATA ports than PCIe lanes to spare. 🙂
It is at least going in the right direction price-wise; they definitely deserve credit for producing a more reasonable costing and better performing option than the RevoDrive.
Can someone point me out a
Can someone point me out a use for PCIe drives if they can’t be used for OS/boot?
Most PCIe drives I’ve seen
Most PCIe drives I’ve seen the last year can be used to boot any modern OS. Even if the user wasn’t using it for the OS, it would be a good game storage drive, working space drive for photo or video editing, or even as swap space for compute or compile applications.
19nm eMLC User
19nm eMLC User Capacities** 200GB-400GB, Scalable across multiple memory slots
interface DDR3 <<<
Yeah, but that only works on
Yeah, but that only works on very particular server hardware with BIOS support for properly partitioning the memory space. You're not going to be putting that in any of your gaming PC's.
doesn’t the tattoo design
doesn’t the tattoo design look like the one used by Corsair Gaming?
After Corsair, another victim
After Corsair, another victim of the awful tramp stamp fashion. Were they running out of elves and naked amazons in the marketing division? Just awful.
Wait, I thought everyone
Wait, I thought everyone loved my fashion? now I feel sad 🙁
I can’t imagine having an
I can’t imagine having an internet connection so fast that a PCIe SSD drive limits Steam game downloads!!!