Up until recently, AS SSD was the only benchmark created specifically for SSD testing and it uses incompressible data. AS SSD, for the most part, gives us the ‘worst case scenario’ in SSD transfer speeds because of its use of incompressible data and many enthusiasts like to AS SSD for their needs. Once again, we will display the standard system on the left with optimized on the right.
AS SSD BENCH
Both results have done very well, exceeding the hard to attain 1000 Score of AS SSD testing. The tell-tale sign that an SSD is an upper tier SSD in AS SSD benchmarks is always that of high sequential transfer results above 500MB/s.
AS SSD IOPS
In both cases, excellent IOPS were attained at the 4K-64thrd level, each being relatively close to listed specs. We also tested with AS SSD Copy bench but never observed any difference whatsoever between the two results. This result is from the standard configuration test:
Overall, we have seen better results in AS SSD Copy Bench. Specific to each result, the transfer time of 2.6sec with a high transfer speed of 410MB/s for the ISO is excellent.
ANVIL STORAGE UTILITIES PROFESSIONAL (BETA)
You may not see this for long (and its definitely not common) but you get a freebee simply for reading! Over the last little while, we have been assisting with beta testing new benchmark software called Anvil Storage Utilities which is an absolutely amazing SSD benchmarking utility. 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 utilize in our benchmark testing.
Up to this point, testing had not match or exceeded listed IOPS specifications so we pushed the SSD with Anvil IOPS testing just a bit:
Anvil 4K-QD128 read IOPS of 86502 and 4K-QD32 write IOPS of 87533 are the just below listed specs and the read high was definitely not expected at a queue depth of 128.
Any clue as to when will a new LSI Sandforce generation of consumer SSDs will reach the market – they seem long overdue…
The SF-2000 Rev B, which is a low power version of the original, has been announced in the last few days but no news on any new version controller.
Thanks.
Maybe they’ll take some more time, like Indilinx took from Vertex 1 to Vector products… but it is a pity as it would create more competition.