Exploring “Frame time” measurement – Part 2 – Is the SSD “smoother” than the HDD in Gaming?

Vantage

Vantage is Futuremark’s DX10 test. It is epecially useful for tracking changes in a single system – especially driver changes. There are two mini-game tests, Jane Nash and Calico and also two CPU tests, but we are still focusing on the graphics performance and on Jane Nash.

Let’s go right to the graphs and first check the overall Vantage results of the default benchmark GPU Test 1 with our overclocked i7-3770K and stock GTX 680 score using the SSD.

 Here is the benchmark’s first test, Jane Nash, run on the HDD with an average of 109.71 fps:

We now see nearly the same score for Jane Nash using the SSD – slightly faster at 110.57 but it varies from run to run by about 1 fps.  Remember that we are focusing in on two very specific and yet totally representative runs to give meaning to the charts.

Now lets look at the Fraps log of each of these runs for a frame rate comparison:

They are very close, within hundreths of a single fps from what Vantage reports.  Lets’s look at the frame time chart for the HDD.

It appears that the Jane Nash scene has been optimized for frame rates and not for smoothness.  Now check out the frame time chart for the SSD:

There is about as much variety between the charts as there are between individual runs of Jane Nash.  Because of the human variability in starting and stopping Fraps, there will not be perfect charts that line up exactly.

Next up is the HDD ranking.  We will show this chart in our future evaluations because they actually show the 99th percentile; including the amount of time that the frame rates spend beyond the norm and above 33.3ms.

Here is the SSD ranking which is nearly identical even though the fps dips a further 3fps to 36fps:

There is really no differences using a SSD or HDD in benching the synthetic Jane Nash scene.  The problem with using Fraps to measure frame times of the latest Futuremark benchmark, 3DMark11, is that the individual scenes are very short compared with Vantage.  Short benches will have greater variability and we generally choose benches that are at least a minute in length.  The 3DMark 11 overall scores are nearly identical whether run on SSD or HDD.

Of course, Vantage is a synthetic benchmark that uses a real scene for benching.  However, let’s move on to PC games and to mostly completely repeatable built-in benchnarks to see if there are measurable performance differences in gaming by using different drives.  Is there an advantage in “smoothness” by using a SSD over a HDD?