Exclusive: A-DATA S501 128GB Marvell Controlled 400MB/s Preview

Introduction

With the solid state market moving faster than Han Solo trying to escape a fleet of Star Destroyers, we have some instant breaking news for you. It appears that Marvell has reworked their SATA 6G SSD controller and paired it with 128MB of DDR3 cache memory. At the time of writing it looks like the new controller will be able to run in 64, 128, 256 and a massive 512GB capacity configuration.

A-DATA allowed us to shut down a portion of their Computex Booth today for a few hours so we could run some of our standard benchmarks on the new A-DATA S501 pre-production drive. We have to give them a big "Thank You" for allowing this test to take place. Hundreds of people were flowing through the booth and we want to say sorry to those that wanted to see the new drive, but were not able to since we were taking up the space.

We know this is going to be an interesting story and don't want to keep you from the benchmarks, so we will just get right down to the good stuff.

Specifications, Pricing and Availability

Restricted Access, User Level Set to 'Need to Know Only'.

It isn't that secret, but we don't have the full product specifications breakdown at this time. Here is what we do know. When it comes to capacity the new Marvell controller should be able to run in everything from 64GB to 512GB. ONFI 2.1 is supposed to be used with this controller and TRIM was confirmed working today on the show floor. We will get into those details in a few. Toggle Mode is also used; we will be getting into Toggle Mode in the next State of Solid State article in a week or so.

The controller itself is a bit of a mystery to us; we don't even know the model number at this time. One source is stating that this was once a product being considered for the enterprise market, while another states that it is just a new revision of the same Marvell controller used in the Crucial RealSSD C300. At this time we are pretty confident that it is has 8-channels and our own tests ran on a drive that has been beat to hell from R&D testing is able to read at close to 400MB/s and write around 200MB/s on a 128GB drive. Your first reaction is going to be the massive 400MB/s read speed and that is fine, but it is only half of the story. Still, that half of the story is pretty bad ass!

The drive we tested on today is the 128GB drive. It uses a Marvell controller. The Crucial RealSSD C300 uses a Marvell controller, but the 128GB version is only able to hit 140MB/s write speeds in ATTO. The 256GB model is able to hit just above 200MB/s, but not the 128 model. This fact is pretty much the main reason behind why we do not recommend the Crucial RealSSD C300 in the 100 / 120 / 128GB capacity range. There are other things as well, but it really all just leads back to the lower write speeds of the 128GB C300. The 256GB C300 is much more competitive to the SF-1200 drives in our real world tests and we see real benefits in writing data at 200MB/s when compared to 140MB/s in these tests.

At this time you can forget about pricing and availability specs. We will have that info around August, maybe sooner, but then again it might drag into September. It's really just unknown at this time and with the market always changing, what I say now will not mean a thing in August anyhow.

Test System Setup and ATTO Baseline Performance

Test System Setup

You can read more about TweakTown's Storage Product Testing Workstation and the procedures followed to test products in this article.

The first thing to consider in our test of the pre-production A-DATA S501 is in the disclaimer itself. This is a very early sample. Performance could go up or a bug could be found, then fixed and the performance could go down. Either way, these numbers are most likely not what we will see when our retail sample arrives.

On top of that, the drive was tested on a system provided by A-DATA. The motherboard was the same as what I test with at my own office, a GIGABYTE X58A-UD7, but the drive was attached to a Marvell controller that I had never seen before. The controller appeared to be a PCIe 8x lane card without cache. It was a RAID controller with two drives attached, but I disabled RAID functionality before starting testing.

As I stated previously, we know TRIM is working with this drive right now. A-DATA had been running benchmarks on the drive at their booth with a RAID 0 arrayed pair of drives. These things have been hammered over and over again prior to us starting testing. We had a few reboots from the benchmark installation and the results below in ATTO were the first thing we ran.

Today we are testing an early pre-production A-DATA S501 solid state drive with 128GB capacity. Our charts are filled with SandForce SF-1200 products that arrived with firmware ranging from RC to MP1 and even a couple of "High IOPS" drives; the two Vertex 2's and Corsair Force. The Crucial C300 128GB drive is also listed in both SATA 3G and SATA 6G.

We were not able to finish testing yesterday. This was not due to A-DATA, they have been great to work with and did everything possible to make this preview possible. The show floor closed at 5PM and by 5:30 the lights go out and everyone has to be out of the hall, no exception...not even for a TweakTown Editor with a smile? - So, no Crystal Disk Mark tests or Passmark Advanced (server) tests. I will be getting those numbers in less than 24 hours.

I will stop pounding the keys and we can get down to what you came here for.


ATTO Baseline Performance

Version and / or Patch Used: 2.34

ATTO is used by many disk manufacturers to determine the read and write speeds that will be presented to customers.



In ATTO we see the read speeds actually breaking the 400MB/s mark in a couple of places. As if I really need to say anything else about that. WTFBBQLEETJUICE! Even now, after seeing it with my own eyes it is hard to believe, but look! There it is. Now, go back to the disclaimer above and settle down a little. Still, WTFBBQLEETJUICE!

When it comes to write speeds, we see the 128GB A-DATA S501 doesn't have a 140MB/s limit like the RealSSD C300 128GB does. Things are about to get interesting really fast.

Benchmarks - HD Tune Pro

HD Tune Pro

Version and / or Patch Used: 4.00
Developer Homepage: http://www.efdsoftware.com
Product Homepage: http://www.hdtune.com


HD Tune is a Hard Disk utility which has the following functions:

- Benchmark: measures the performance
- Info: shows detailed information
- Health: checks the health status by using SMART
- Error Scan: scans the surface for errors
- Temperature display

HD Tune Pro gives us accurate read, write and access time results and for the last couple of years has been gaining popularity amongst reviewers. It is now considered a must have application for storage device testing.





It is one thing to talk about high sequential numbers and it is something else to see them compared to a group of the fastest solid state drives on the market. When I finally looked at the chart I called Cameron over to see it. At the same time, we both smiled and then started laughing to the point where it was uncontrollable. So yeah, pretty much the same thing you are doing right now.



As I stated before, the drive being tested today has been hit pretty hard prior to testing with just about every kind of benchmark you can think of. The minimum write speed was at the beginning of the test and the results were typical for a drive that has been ran hard during testing (one of the reasons why you don't want to pound your drive with benchmarks, just read about them here).

So, with in a fraction of a second of around 165MB/s, the A-DATA S501 quickly reached the average speed of around 207MB/s and peaked at 211. These are not quite SandForce SF-1200 MP1 speeds, but they are getting pretty close.

The other Marvell controlled drive on the chart is also the only other SATA 6G interface drive. Here we see the Crucial RealSSD C300 128GB drive running into its wall at just under 140MB/s. It looks like A-DATA and Marvell have found a way to get around that little issue with this controller.

Benchmarks - Everest Random Access Time

Everest Random Access Time

Version and / or Patch Used: 4.60
Developer Homepage: http://www.lavalys.com
Product Homepage: http://www.lavalys.com



Everest Ultimate and Corporate Edition offer several different benchmarks for testing and optimizing your system or network. The Random Access test is one of very few if not only that will measure hard drives random access times in hundredths of milliseconds as oppose to tens of milliseconds.

Drives with only one or two tests displayed in write the write test mean that they have failed the test and their Maximum and possibly their Average Scores were very high after the cached fills. This usually happens only with controllers manufactured by JMicron.



The A-DATA S501 is running with a little more read latency than the C300 128GB, but the S501 is still hanging in there with the SandForce SF-1200 drives.



The Marvell controller in the Crucial RealSSD C300 had some of the highest write latency speeds we have tested outside of the JMicron stuff. It looks like that is no longer an issue with the new Marvell controller.

That's it for the synthetics. We will head to the hall to get the CDM 4K numbers in the morning.

Benchmarks - PCMark Vantage Hard Disk Tests

PCMark Vantage - Hard Disk Tests

Version and / or Patch Used: 1.0.0
Developer Homepage: http://www.futuremark.com
Product Homepage: http://www.futuremark.com/benchmarks/pcmark-vantage/
Buy It Here



PCMark Vantage is the first objective hardware performance benchmark for PCs running 32 and 64 bit versions of Microsoft Windows Vista. PCMark Vantage is perfectly suited for benchmarking any type of Microsoft Windows Vista PC from multimedia home entertainment systems and laptops to dedicated workstations and high-end gaming rigs. Regardless of whether the benchmarker is an artist or an IT Professional, PCMark Vantage shows the user where their system soars or falls flat, and how to get the most performance possible out of their hardware. PCMark Vantage is easy enough for even the most casual enthusiast to use yet supports in-depth, professional industry grade testing.

FutureMark has developed a good set of hard disk tests for their PCMark Vantage Suite. Windows users can count on Vantage to show them how a drive will perform in normal day to day usage scenarios. For most users these are the tests that matter since many of the old hat ways to measure performance have become ineffective to measure true Windows performance.



HDD1 - Windows Defender
HDD2 - Gaming
HDD3 - Windows Photo Gallery
HDD4 - Vista Startup
HDD5 - Windows Movie Maker
HDD6 - Windows Media Center
HDD7 - Windows Media Player
HDD8 - Application Loading

SSDs don't follow the traditional route that has been carved by HDDs where high sequential numbers always mean high real world numbers. The new Marvell controller has only 8 channels while the SandForce SF-1500 has double that amount. Here we see the pre-production A-DATA S501 in some tests running with the SandForce SF-1200 drives, but losing in many.

If you remember back to our tests of the RunCore Pro V at CES, a SandForce drive we tested at around the same stage we are testing the A-DATA S501 at right now, the drive improved quite a bit between the early sample test and the final production units we are testing now. At this point you are fairly certain that the A-DATA S501 will be able to pick up quite a bit of speed in the real world tests, but these are the numbers that are popping out now.

Benchmarks - AS SSD

AS SSD Benchmark

Version and / or Patch Used: 1.2.3577.40358
Developer Homepage: Alex Intelligent Software
Product Homepage: Alex Intelligent Software
Download here: http://www.alex-is.de/PHP/fusion/downloads.php?cat_id=4&download_id=9

AS determines the performance of Solid State Drives (SSD). The tool contains four synthetic as well as three practice tests. The synthetic tests are to determine the sequential and random read and write performance of the SSD. These tests are carried out without the use of the operating system caches.

In all synthetic tests the test file size is 1GB. AS can also determine the access time of the SSD, the access of which the drive is determined to read through the entire capacity of the SSD (Full Stroke). The write access test is only to be met with a 1 GB big test file. At the end of the tests three values for the read and write as well as the overall performance will be issued. In addition to the calculated values which are shown in MB/s, they are also represented in IO per seconds (IOPS).

- Copy Benchmark



If you transfer a lot of files to and from a drive then the AS SSD transfer test results are looking pretty impressive for you. Still, two of the tests are right at or just under what we already achieved with the Crucial RealSSD C300 drives.

Final Thoughts

Over the next few days I will try to gather as much information as I can on the new Marvell SATA 6G controller used in the A-DATA S501. It is still too early to start talking about awards, pricing or even availability.

When it comes to the performance of the A-DATA S501, we can already see that the drive is capable of some very impressive results in the synthetic tests, but the real world results are still a bit on the low side. When we tested the RunCore Pro V at CES this past January we were told the drive was ready to go; just wrap it in a retail package and the two would match up. We later learned that this was not the case.

A-DATA hasn't said just how far they are out on the S501, but we are guessing the final stages will be completed very soon. Given the amount of performance increased with the RunCore Pro V from early to final production, I think the S501 deserves a chance to get finished before we really jump to conclusions on the final real world performance.

So there you have it, early synthetic and real world numbers on a pre-production A-DATA S501 128GB SSD. We are very excited to see results that we achieved today even though the performance will change a bit between now and the retail product. It would be pretty difficult to imagine A-DATA going the wrong direction with final product performance.

I am glad to see the 140MB/s write speed limit erased on a Marvell controlled SATA 6G 128GB drive and really, what all do I need to say other than just giving you the read speed results. At right around 400MB/s sequential read, this is highest performance we have ever seen in this test from a single drive.