Poor RAMdisk speeds

I've got 16GB now so decided to try making a 10GB RAMdisk and loading a game (DCS World) from that to see if the stuttering problems I experience are indeed caused by the HDD not being able to stream the data fast enough.

However, as you can see from the images below, when I benchmarked the RAMdisk the Seq and 512K speeds were much lower than were achieved by Raymond here 12 RAM Disk Software Benchmarked for Fastest Read and Write Speed

Note, he only had 2GB but running at 1600Mhz (I'm currently running at 1333Mhz as my Motherboard loses 4GB (it's detected in the BIOS but W7 says it's unusable) at 1600Mhz) and tested with a 512MB NTFS RAMdisk but I don't see why any of that should make a significant difference. I've previously benched my RAM (when I had 8GB) at 1333Mhz and 1600Mhz and have added the results at the end of this post so that you can see the difference isn't anywhere near enough to account for his better results.

I tried a couple of different programs and RAMdisk sizes just to check it wasn't just one particular config that was causing the slow speeds.

This is my 10GB NTFS RAMDisk Enterprise disk in ATTO:


and this is my 512MB FAT32 DataRAM RAMdisk:


This is the 10GB NTFS RAMdisk Enterprise disk in CDM:


and this is the 512MB FAT32 DataRAM RAMdisk:


and lastly I made a 512MB FAT disk with Bond Disc (which did very well in Raymond's tests):


As you can see, the Seq and 512k results are about half what Raymond got and only on the 4K and 4K QD32 figures do I match, or in some cases exceed his results. In fact, on the 4K QD32 Write I exceeded his best result (324MB/s) quite considerably but that's not much consolation when I want to use a RAMdisk for loading games (i.e. only reading) and I'm getting such poor Seq and 512k results.

I also tried the SoftPerfect RAMdisk and was able to create a 10GB NTFS RAMdisk but whilst copying the DCSW files to it, it said it was unable to continue as the files were corrupt. Checking the RAMdisk showed that that the DCSW folder was now inaccessible and non delete-able and so I had to unmount the RAMdisk and re-mount it (now empty) to clear that problem. Trying again gave the same result so I gave up on that software.

I've tested the RAM with MaxxMem Preview and that seems fine.

DDR3-666 (1333) Mhz (9-9-9-24-1T), NB 2000Mhz:
Copy 10466 MB/s
Read 8107 MB/s
Write 6831 MB/s
Score 7.47GB/s
Latency 66.9 ns

DDR3-800 (1600) Mhz (9-9-9-24-1T), NB 2000Mhz:
Copy 10560 MB/s
Read 8667 MB/s
Write 6734 MB/s
Score 7.70 GB/s
Latency 65.0 ns

So does anyone know what's up and what needs adjusting/fixing to get the RAMdisk speeds up to normal?

OK, thanks guys. I'll just have to console myself with the fact that I beat his 4K QD32 scores

I have previously overclocked the NB to 2600 with 8GB and benchmarked it, so I'll post the results for comparison but it wasn't stable at that speed even with the overvolt so I had to drop down to 2400. There's not a massive difference in read speed anyway (write speed increases more) so like Blameless says, I'm not going to see much difference in the RAMdisk speed.

DDR3-800 (1600) Mhz (9-9-9-24-1T), NB 2600, CPU-NB 1.32v, NB 1.3v
Copy 11867 MB/s
Read 9822 MB/s
Write 8457 MB/s
Score 9.14 GB/s
Latency 60.4 ns

Well I did also previously test at 2800, which obviously wasn't any more stable than 2600 but I've got the results.

DDR3-800 (1600) Mhz (9-9-9-24-1T), NB 2800, CPU-NB 1.4v, NB 1.3v
Copy 12049 MB/s
Read 10094 MB/s
Write 9021 MB/s
Score 9.56 GB/s
Latency 58.9 ns

DDR3-800 (1600) Mhz (9-9-9-24-1T), NB 2800, CPU-NB 1.3v, NB 1.394v
Copy 12464 MB/s
Read 10082 MB/s
Write 9216 MB/s
Score 9.65 GB/s
Latency 56.7 ns

As you can see, the results from the two runs differ a fair bit even though the only thing different was the CPU-NB and NB voltages being swapped round.

Even if I got it stable at 2800 though, I'd still only have a read speed of 10,000MB/s compared to 8,100MB/s now, about a 23% increase which would only boost my Seq Read speed of 3115MB/s to 3831MB/s and it hardly seems worth spending hours (days?) tweaking and rebooting to achieve that.

No. I was asking why Raymond's RAMdisk speeds are about 200% faster than mine.. I've been told it's probably because I'm using AMD, which has a crappy memory controller and he's using Intel, which gives much faster RAM speeds and thus much faster RAMdisk speeds, which is fair enough.

By the way, wanted to mention that the author of SoftPerfect tells me he's identified the problem and is looking at fixing it, so hopefully that should be an option in the near future. I'm using IMDisk at the moment as it makes it very easy to load/save images and unmount the RAMdisk to release the memory, unlike RAMdisk Enterprise. The only downsides are it seems to take longer to load images than the other programs I've tried, doesn't provide a progress bar so you can see how long it's going to take and gives much lower 4k and 4k QD32 results than the other RAMdisks. I'm not sure if those or the Seq and 512k speeds are most relevant as far as my games are concerned though.