CRYSTAL DISK BENCHMARK VER. 4.0.3 X64
Crystal Disk Benchmark is used to measure read and write performance through sampling of random data which is, for the most part, incompressible. Performance is virtually identical, regardless of data sample so we have included only that using random data samples.
Crystal Disk Mark reveals some good numberswith 560MB/s read and over 500MB/s write. 4K reads and writes are decent as well, reaching 34MB/s read and just over 150MB/s write. The higher QD32 results show more impressive write performance than read, but both are close to their rated specification as well.
The toughest benchmark available for solid state drives is AS SSD as it relies solely on incompressible data samples when testing performance. For the most part, AS SSD tests can be considered the ‘worst case scenario’ in obtaining data transfer speeds and many enthusiasts like AS SSD for their needs. Transfer speeds are displayed on the left with IOPS results on the right.
In AS SSD, the Intel 540s attained an overall score of 1070 points. Sequential speeds are good once again at 505MB/s read and 489MB/s write. 4K reads reached a bit over 31MB/s and writes were 124MB/s, which is average for a drive of this type. Furthermore, it hit 75K IOPS read and nearly 81K IOPS write. During the copy test it did well too, with a best transfer speed of 425MB/s in the ISO copy.
ANVIL STORAGE UTILITIES PROFESSIONAL
Anvil’s Storage Utilities (ASU) are the most complete test bed available for the solid state drive today. The benchmark displays test results for, not only throughput but also, IOPS and Disk Access Times. Not only does it have a preset SSD benchmark, but also, it has included such things as endurance testing and threaded I/O read, write and mixed tests, all of which are very simple to understand and use in our benchmark testing.
Finally, similar to that of the other test results, we see average performance. Overall, the Intel 540s attained 4519 points. Sequential performance is over 500MB/s for reads and 485MB/s for writes and 4K performance hasn’t varied much from the other tests either. Again, good results here.
>ut why Intel would not be relying on their own fabs for memory is more than a bit curious.
Not really. Intel didn’t invest in 16nm NAND, so they have to source it somewhere else to be price competitive.
It is the bigger question with respect to memory in Intel’s future that we elude to…just adding an air of suspense. lol
Guess-Just a stop-gap until they can get their 3D out..
They couldn’t go to their partner Micron-their TLC is borderline LEMON.
For the average Joe that don’t regularly transfer large files-as long as it’s responsive enough it’ll be fine.
TLC has benefited us all-bringing down the cost of owning a SSD.
The sooner everyone goes 3D can’t come quick enough-we can then send planer TLC into history………………………………………….
I cant understatnd the overprovisioning. The drive is RAW 512GiB, usable space is 480GB, it means 447GiB. How do You calculate 7%. There is 7% overprovisioning and another 7% is gone. please use proper GiB and GB then everything will be clear.
Trying to explain the difference between GB and GiB to the typical person wanting this drive would make the report extremely confusing and would serve no purpose but to turn away the reader. GiB has no purpose in a consumer/client report and, IMO, really has no place whatsoever in current day reports, regardless of the target audience intended. Thanks for the input!
Easiest way to explain GB and GIB is that they are my initials 🙂
Keep smiling
Actually, internally NAND dies are even bigger than 128Gbit (so drive even has more than 512GiB flash) but thats just getting way too technical 🙂
Hm, no sequential write speed test all over the capacity?
It would make the drive look bad 🙂
Nothing is harder than the truth 😉
Our report is the same format that we have used for some time and is actually very telling of the drives ability.
Well, on my Laptop with USB2.0 the write speed of the SSD is not that important.
But for some other usecases the sequential write speed with large files is a criteria for me which says: Buy or buy not.
I mean files which are larger than the SLC-caches.
Because that’s a likely use case. /s
In most cases 30GB is enough to see the real write speed with SSDs that uses SLC-Cache-tricks.
It seems that all SSD-manufacturers choose the write cache size which is enough for standard-benchmark-tools.
And yeah, I use SSDs also for my movie-cutting-PC and copy more than 100GB in a row, so it´s a usecase for me
That’s fair, although surely as that’s highly sequential SATA III SSDs over a certain size are going to hit the interface ceiling regardless of the use of TLC?
I guess what I’m getting at is that I’d have thought that if the use case is mission critical and speed is /required/ then the investment in MLC PCIe drives would be justified.
Well, I use external USB3.0-drives to copy my DVB-S(2)-recordings for cutting to my PC. It depends on the external case how fast I can copy. Some TLC-drives like the 850 Evo or Sandisk Ultra 2 offer speed >200MB/s with 500GB/480GB-versions, thats still OK as far I don´t start more than one copy at one time
But TLC-drives like Crucial BX200 which going down to ~75MB/s (960GB-version) are shitty for that usecase
Oh wow. Yeah, that’s a pretty substantial difference and knowing that comparison between drives would obviously be useful. Fair enough!
Incidentally the Crucial MX300 looks like it would be more your style. PC Perspective have a review including full drive writes and latency measurements.
What are the SSD’s better than this for the same price? I don’t have much knowlegde about it and in my country (Brazil) I don’t have too much options…
Sandisk x400 512MB — better performance, lower price.
Samsung 850 EVO 500MB — best performance in class, about the same price.
Nice test: inducted me to buy the 120GB for a Linux-powered netbook given 1. Its idle consumption, 2. Price and 3. Perfs vs HDD.
Before proper set-up (e.g. pcie_ASPM and so on) the little box total consumption was the *same* than with a 5400 Momentus. After set-up, I got a very slightly lower consumption when systems idle. And to my surprise, a 10-15% lower battery consumption when surfing, (or even with just the wireless chipset On and connected) reapeatedly on two OS.