Finding The Perfect PC Components For Your Favorite Game Or Workload

[chrisb]

Depends on many factors, but I presume on many 5960X systems if the performance was poor for compile Linux kernel, the disks backing those systems weren't too fast.

Something is wrong... Clicking the 5960X link on the "Timed Linux Kernel Compilation v4.3" goes to http://openbenchmarking.org/s/Intel%20Core%20i7-5960X which has only 9 sets of results for 5960X. 7 of those results are for the Linux Kernel compile v3.1, none are for v4.3. For all those 7 of the v3.1 tests the compile took around 43 seconds. How was 68 seconds (SE=0.00) for the v4.3 test calculated? Is there missing data or is it including the wrong data?

[trifud]

what page are you referring to? They could be left out if there aren't enough results from a given graphics card to make it into the list. If you could show me a page and know for a fact there are more GPU results, I can look into it.

The search engine in http://openbenchmarking.org/ doesn't seems to be very good. Never mind, this comparison http://openbenchmarking.org/showdown/pts/gputest

lacks these results for example:

http://openbenchmarking.org/result/1...BE-GPUTESTRE02 You see that Titan X is a real monster.

[Michael]

On the Xonotic graph there are some odd/generic video card names to fix or filter - "AMD" "Intel HD" "Intel device ..." "Supported device ...." "Intel Xeon E3..."(??) "Intel ... IGP" "Intel Pitcairn" etc.

All these strings are generated client side when running the Phoronix Test Suite. So in these cases on OB side the only option is really to just detect them and then filter them out. I started doing that but still have some more strings to add.

[chrisb]

On the Xonotic graph there are some odd/generic video card names to fix or filter - "AMD" "Intel HD" "Intel device ..." "Supported device ...." "Intel Xeon E3..."(??) "Intel ... IGP" "Intel Pitcairn" etc.

[Michael]

Are all of the results being shown? On 3.1 kernel compile X5570 is 422s but checking X5570 results shows only 5 kernel compiles on that CPU with values of 62,62,62,170,174?

Is there a graph showing all the results of a test on a particular CPU? Like all X5570 results for kernel compile?

Hmmm, might be able to add something like that.

[Michael]

There are faster GPUs on OpenBenchmarking that for some reason haven't made it in this comparison.

what page are you referring to? They could be left out if there aren't enough results from a given graphics card to make it into the list. If you could show me a page and know for a fact there are more GPU results, I can look into it.

[chrisb]

Depends on many factors, but I presume on many 5960X systems if the performance was poor for compile Linux kernel, the disks backing those systems weren't too fast.

Yes slow disk vs SSD would account for maybe 15ish seconds according to this comparison but I would've thought people paying $1000+ for a CPU would invest in a decent SSD.

Does PTS drop the disk caches before running a test? It should be doing that for reproducibility otherwise subsequent test runs are barely going to hit the disk.

[chrisb]

Maybe also separate out whether or not the system is a VM or bare metal, it will make a big difference since there are people benchmarking shared VPS providers. e.g. this result I would guess is being counted as a E5-2680 which should be fast (it's 8 cores SNB CPU with 20MB cache) but it's obviously running under VMware with only 2 cores which invalidates the results (kernel compile is 357 seconds there). Whereas this is the same CPU but 2x with 32 cores and taking 78s. So it would make sense to consider showing separate results for factors like #cpus/#cores/bare metal/VM.

Misidentified CPU in kernel compile v4.3 - "Intel" at top (43 seconds)?

Are all of the results being shown? On 3.1 kernel compile X5570 is 422s but checking X5570 results shows only 5 kernel compiles on that CPU with values of 62,62,62,170,174?

Is there a graph showing all the results of a test on a particular CPU? Like all X5570 results for kernel compile?

[trifud]

There are faster GPUs on OpenBenchmarking that for some reason haven't made it in this comparison.

[Michael]

How come the 5960X result is so bad on the Linux kernel compile? It should be around 45 seconds.

Depends on many factors, but I presume on many 5960X systems if the performance was poor for compile Linux kernel, the disks backing those systems weren't too fast.