We used an 8 GiB LBA range for each of our Iometer benchmarks, running each test for 90 seconds. We also aligned the read and write access patterns to a 4 KiB sector boundary.
This measurement is useful for looking at the read and write performance of common transfer sizes at queue depths ranging from one to 32. Queue depths in a typical client environment are generally quite low, so the results generated between one and four are of particular interest. Read operations are typically a lot more prevalent than writes operations, so read performance is also most relevant.










Plextor's M5 Pro dominates read performance across all transfers sizes and queue depths, while the Vertex 4 comes out on top in write performance, peaking high and early.
In order to compare our findings to what each manufacturer says its drive can do, we have to convert the MiB/s results to IOPS. Notably, the "up to" results that vendors like to use are typically based on a queue depth of 32, and it's possible to see significant variation in Iometer results depending on the span of the test file and prior write history.
As expected, there is some variation between our benchmark results and those specified by the manufacturers. This comes down to differences in how each company determines its performance specifications, the state of the drives, and the test system used. We're happy to see that Plextor's M5 Pro, though rated for the highest I/O performance, also finishes first in what we measure.
| Vendor-Rated "Up to" 4 KiB Read IOPS | Observed 4 KiB Read QD 32 IOPS | Vendor-Rated "Up to" 4 KiB Write IOPS | Observed 4 KiB Write QD 32 IOPS | |
|---|---|---|---|---|
| Samsung 830 | 80 000 | 76 309 | 30 000 | 39 657 |
| Crucial M4 | 50 000 | 46 824 | 50 000 | 59 175 |
| Vertex 4 | 90 000 | 85 159 | 85 000 | 82 335 |
| Plextor M5S | 73 000 | 73 888 | 70 000 | 69 346 |
| Plextor M5 Pro | 94 000 | 90 883 | 86 000 | 84 081 |
But those numbers are at a queue depth of 32. Let's instead have a look at 4 KiB read and write performance at a queue depth one, which is where you're going to see more activity. We again converted the MiB/s results to IOPS in our chart below.
Plextor's M5 Pro comes out on top again for read performance, but trails the Vertex 4 on write performance (though not by much).
| Iometer, 4 KiB Read QD 1 IOPS | Iometer, 4 KiB Write QD 1 IOPS | |
|---|---|---|
| Samsung 830 | 5 721 | 15 849 |
| Crucial m4 | 5 849 | 15 900 |
| Vertex 4 | 7 036 | 16995 |
| Plextor M5S | 7 076 | 15 823 |
| Plextor M5 Pro | 7 729 | 16 688 |
Here you go:
http://www.anandtech.com/bench/Product/665?vs=646
The old one was the 88SS9174-BKK2.
http://www.tomshardware.com/reviews/plextor-m3-crucial-m4-octane-performance-pro,3178.html
I believe we can all assume it will take around 10-15 minutes. My old SATA2 Vertex drive can have Windows installed with all the Windows updates I want in around 20 minutes, it would be less time but I have to install all my drivers first for my motherboard
Here you go:
http://www.anandtech.com/bench/Product/665?vs=646
Wow. The 840 Pro beat the M5 Pro in virtually everything according to that data. The 840 Pro does cost significantly more though.
TheSSDReview did something similar:
http://thessdreview.com/our-reviews/romex-fancycache-review-ssd-performance-at-13gbs-and-765000-iops-in-60-seconds-flat/
No point in even comparing RAM to SSDs, as even "slow" RAM is faster than even the best SSDs by about the same amount as the best SSDs are faster than floppy disks.
450 for 512gb
good luck beating that "stat", samsung
Report
-1+ .
JeanLuc :
I was on Youtube the other day on the Corsair channel and they were showing the advantages of 'Ram cache' which was lights years faster then SSD's in therms of throughput. Could Toms consider doing an article into Ram cache as I think it would be of interest to people who have 16-32Gb systems (since DDR3 is cheap at the moment) can spare the extra system ram to cache files and software.
TheSSDReview did something similar:
http://thessdreview.com/our-review [...] onds-flat/
No point in even comparing RAM to SSDs, as even "slow" RAM is faster than even the best SSDs by about the same amount as the best SSDs are faster than floppy disks.
I have read the article and have these thoughts on the subject.
1) Why have mobo manufactures not placed an extra four memory slots on their mobo to handle this concept ?
2) Why have RAM manufactures not teamed up with mobo manufactures to supply them with 256 GB memory sticks ?
3) Has the industry, video and others, (movies, ads, special effects, cartoons, simulations, etc.) moved to this type of strategy to increase their productivity ?
1) mobo manufacturers would have nothing to connect these RAM slots too. They need DDR3 controllers and they'd need more of them, so where are those going to come from? The only thing that I can think of is some sort of integrated PCIe device and it would make the motherboard quite expensive.
2) 256GB memory sticks would cost thousands of dollars. Even 16GB memory sticks and especially 32GB memory sticks can already be extremely expensive and difficult to make. We can't just make chips that have more memory capacity in a given size than current memory procces nodes can work with, so any such memory module with 256GB of RAM would be huge, to say the least.
3) It's too expensive.
Basically, cost is the main inhibitor for all three of your questions.
Some people might be tempted to throw their SSDs like tech ninjas.
"... reviewed previously uses 25 nm synchronous NAND from Micron and Marvell's 88SS9174-BLD2 controller, while the M5 Pro employs 19 nm Toggle-mode --DDR-- from Toshiba and a more modern Marvell 88SS9187-BLD2 processor."
Toggle-Mode Double Data Rate NAND Flash
1) Why have mobo manufactures not placed an extra four memory slots on their mobo to handle this concept ?
2) Why have RAM manufactures not teamed up with mobo manufactures to supply them with 256 GB memory sticks ?
3) Has the industry, video and others, (movies, ads, special effects, cartoons, simulations, etc.) moved to this type of strategy to increase their productivity ?
Luciferano has already commented, but I thought I'd make input on the first point. There are mobos with an extra four slots, enabling up to 64GB of RAM (such as the ASUS P9X79 PRO) but these are uncommon and expensive. Higher RAM capacities under today's technology will almost always require you to be using server hardware; the PC form factor just won't cut it.