Info DirectStorage 1.1 benchmark

psolord

Golden Member
Sep 16, 2009
1,920
1,194
136
Guys, if I am not mistaken, copying the folder elsewhere and running the .exe, runs the bench from THAT drive, right?

If so, here are my two runs, on my 8600k+GTX 1070, on the Gammix S11 1TB (placed on a pcie card) and my old SSD EVO 850 512MB.





I was running msi afterburner osd while running the bench and I noticed the gpu usage really did jump to 100% for a second or so. I wonder if it will run on my GTX 970 and Radeon 7950.

Quoting myself, to add some more results (including the quote's).











12400f+3060ti+Gigabyte Aorus 7000s 1TB (nvme pcie 4.0) = 13.30GB/sec
12400f+3060ti+Crucial MX500 1TB (sata)= 2.05GB/sec
8600k+1070+Gammix S11 pro 1TB(nvme pci 3.0)=1.96GB/sec
8600k+1070+Samsung EVO 850 512GB(sata)=1.91GB/sec
2500k+Radeon 7950+Patriot P210 256GB(sata)=1.34GB/sec

Regarding the 8600k+GTX 1070, son, I'm disappoint. Dunno why, I was expecting better. Maybe because in general these two systems provide me with equal gaming experience, but at different resolutions (different houses). It seems the 1070 is the culprit, but I am having some tiny reservations, because that nvme is on a pcie 3.0 card, which is controlled by the chipset and not the cpu. It benchmarks OK with convensional storage benchmarks though, so I guess it's the gpu.

The MX500 and EVO results, both being sata and so close, I think means that a sata drive is good enough up to a GTX 1070. Also, the MX500 is limited by itself on the 3060ti, while the Gammix is limited by the 1070 I think. I'll see on the next primary gpu upgrade, which will upgrade all systems by one tier up (3060ti goes in the 8600k system etc).

Very surprised with the 2500k+7950 system. I didn't expect it to even run. But it did and it was not too shabby for a 12yo cpu and a 11yo gpu. Also for whatever reason, the avocado scrolling was the smoothest of all systems. Have no idea why.

I tried to run it on the work's i5-8400 system (only igp), but it doesn't even run. GPUz says Direct X 12_1 compatibility while the 7950 is DX12_0, so it can't be it.

Next and final step, will be a GTX 970 testing.
 
Last edited:
  • Like
Reactions: DAPUNISHER

psolord

Golden Member
Sep 16, 2009
1,920
1,194
136
Yeah, well so much for GTX 970 testing. It doesn't run at all. Beats me why. Thought maybe it was MSI Afterburner because it is setup differently on that system. Closed it, still nothing.

I know it's not the Sandy, or the old GTX 970 or windows version, since all these apply for the 7950 system and it run there. So let's see if any new version comes out later on.
 

Ranulf

Platinum Member
Jul 18, 2001
2,355
1,175
136
More info:


Github download:

Video by the guys who I think did the google drive link:

 

Makaveli

Diamond Member
Feb 8, 2002
4,722
1,058
136
More info:


Github download:

Video by the guys who I think did the google drive link:


you are correct that youtube video is where I got the google drive link.
 
  • Like
Reactions: Ranulf

AdamK47

Lifer
Oct 9, 1999
15,231
2,851
126
Ran it from my System/OS drive which is a Rocket 4. Got 0.52 second load.

Moved it to my 24TB RAID-0 array of three 8TB Rocket Q drives and got this:

1673927881900.png

Edit: Specs
Ryzen 7950X
RTX 4090
1TB Rocket 4
24TB RAID-0 of three 8TB Rocket Q
Win11 latest
 
Last edited:

SteveGrabowski

Diamond Member
Oct 20, 2014
6,896
5,833
136
Win 10 22H2
i5-12400F
RX 6700 XT PCI e 4.0
Adrenalin 22.11.1
AData XPG1 Gammix S70 Blade 1TB (PCIE-4.0x4)

Bulk-Load-Demo.png




Win 10 22H2
i5-12400F
RX 6700 XT PCI e 4.0
Adrenalin 22.11.1
Samsung 850 EVO 256GB SATA

Bulk-Load-Demo-SATA.png
 
Last edited:

KompuKare

Golden Member
Jul 28, 2009
1,016
934
136
it will massively improves loading times
If loading data is the only bottleneck while loading.

On one of the TES benchmarks threads in CPU (I think the Oblivion one), a post speculated that there's a lot more going on that storage speed and having lots of memory - as CPUs made a huge difference there.

I know, an ancient game using an engine which was barely fit for purpose even when it came out (and Bethesda repeated that part with Skyrim and FO4 so will be interesting what the engine in Starfield will be like), but the point might still be valid: there's a lot more to loading a game than storage performance even if getting rid of that bottleneck will be nice.
 
  • Like
Reactions: Leeea

Tup3x

Senior member
Dec 31, 2016
965
951
136
If loading data is the only bottleneck while loading.

On one of the TES benchmarks threads in CPU (I think the Oblivion one), a post speculated that there's a lot more going on that storage speed and having lots of memory - as CPUs made a huge difference there.

I know, an ancient game using an engine which was barely fit for purpose even when it came out (and Bethesda repeated that part with Skyrim and FO4 so will be interesting what the engine in Starfield will be like), but the point might still be valid: there's a lot more to loading a game than storage performance even if getting rid of that bottleneck will be nice.
The bottleneck is almost always decompressing speed related and how the data is structured etc. This aims to solve the compression bottleneck and ensures that you can make use of that bandwidth (actually even improves speed because decompression is so fast).
 
  • Like
Reactions: Leeea and Makaveli

pj-

Senior member
May 5, 2015
481
249
116
I wonder if this tech will enable a PC equivalent of consoles' game quick suspend/resume features. I wouldn't mind setting aside 100gb of SSD space if i could suspend a game in a second or two and pick it up just as quickly hours later. That would be one of those small friction reducers that I think would result in people playing games more.

If loading data is the only bottleneck while loading.

On one of the TES benchmarks threads in CPU (I think the Oblivion one), a post speculated that there's a lot more going on that storage speed and having lots of memory - as CPUs made a huge difference there.

I know, an ancient game using an engine which was barely fit for purpose even when it came out (and Bethesda repeated that part with Skyrim and FO4 so will be interesting what the engine in Starfield will be like), but the point might still be valid: there's a lot more to loading a game than storage performance even if getting rid of that bottleneck will be nice.

The fact that other stuff happens during load times doesn't mean storage isn't a significant or primary bottleneck, it could just mean developers were smart enough to use that time to also do other stuff.

And it's not just load times, games should require fewer compromises if the developers don't have to worry about fetching data seconds/minutes in advance of its use. Story cutscenes could easily jump between very different locations without special planning. Gimmicks like gates/doors with long opening animations could go away, tight squeezes between areas could go away, pointless elevator rides could go away.

A lot of the impacts will probably be subtle, but I bet games will feel increasingly "slick" as this matures.
 
  • Like
Reactions: cherullo and Leeea

psolord

Golden Member
Sep 16, 2009
1,920
1,194
136
Guys, if I am not mistaken, copying the folder elsewhere and running the .exe, runs the bench from THAT drive, right?

If so, here are my two runs, on my 8600k+GTX 1070, on the Gammix S11 1TB (placed on a pcie card) and my old SSD EVO 850 512MB.





I was running msi afterburner osd while running the bench and I noticed the gpu usage really did jump to 100% for a second or so. I wonder if it will run on my GTX 970 and Radeon 7950.
 
  • Like
Reactions: Leeea and Makaveli

BFG10K

Lifer
Aug 14, 2000
22,709
2,971
126
what games leverage this? benchmarking DS on its own is pretty meaningless. how does it improve game performance or loading times?
Exactly right. Until we see real games tested with and without, showing reduction in load times, it's absolutely useless.

I remember when NVMe drives came out and people were showing game IOPS to be thousands of times higher than regular SSDs, but it actually didn't make any difference with loading.

Even today, unless you copy files all day or have some kind of niche I/O workload, in almost every situation there isn't a lick of difference between the fastest NVMe and an Intel X18.
 
Last edited: