Article on CPU usage

[john beardsworth]

I've not digested this yet, but take a look at Puget Systems' article on Adobe Lightroom CC/6 CPU Multi-threading Performance. There's also a Google spreadsheet to help Calculate which CPU is best for how you use Lightroom.

John

[hjulenissen]

Thank you for that link.

The Xeon E5 2687W v3 has some asymmetry in it. I wonder if that affects their test (where they are effectively flagging that some cores are off-limit for Lightroom):
http://anandtech.com/show/8584/intel-xeon-e5-2687w-v3-and-e5-2650-v3-review-haswell-ep-with-10-cores

Exporting raw images 80 ought to be a perfect candidate for multi-threading. Those 80 jobs should be AFAIK totally independent and each job is time-consuming. I am not sure that I am buying their conclusion that Lightroom scales well with #cpu cores but poorly with #cpus _because of_ interdependency.

Could it be that the PC they used for the test gets maxed out in memory bandwidth and adding one more cpu simply hits the same wall? How many passes and temporary buffers are needed in order to do that 1.8GB -> 700MB? (1800 [MB]+700 [MB])/100 [seconds] = 25MB/s of total read/write, not a very large number for cache systems or main memory (but within OOM for spinning harddrives?). Could it be that their method for reading/writing to disk somehow fails to take advantage of the bandwidth of their flash drive?

It seems to have 2.5MB of cache per core for a total of 10*2.5 = 25 MB per cpu for a total of 2*25 = 50MB for the system. Each raw file is 1800MB/80=22.5 MB, thus the working set of 20 threads (assuming that they are processed in one go) would be 450MB, far more than the total cache. Depending on how Adobe do things, this could mean significant extra traffic to main memory?

Another possibility would be that their threading is simply hardcoded limited to ~10 threads?

If one did a similar test with a dual 4-core system, one might be able to rule out some of the possibilities.

-h

[barryfitzgerald]

2 problems not every CPU is the same (I use an AMD myself) the other is that LR just isn't pulling the power from these processors (whatever they are) efficiently. I've a 6 core processor and it's spiking up and down with CPU usage during exporting (I can understand it not maxing each core out 100% so as not to kill the pc with other tasks but it's dropping down far too much) That isn't efficient CPU usable and there are newer instructions available that are not being used either.

Adobe need some fresh programmers those who understand multi threaded performance better

[Redcrown]

While we're talking about Adobe performance, pardon me for beating a dead horse from here:

http://forum.luminous-landscape.com/index.php?topic=97727.0

I'm still looking for someone willing and able to run tests to confirm (or deny) that ACR version 8.7 introduced a fault when implementing "AVX/AVX2" support.

Test is to run some ACR conversions (raw to anything, jpeg, tif) on a system with an AVX/AVX2 capable CPU. I think that's about any system made in the past 3 to 4 years. Run first under ACR 8.6 or older, then run same under ACR 8.7 or newer. Tests should include lots of raw adjustments (noise, lens correction, sharpening, etc.)

Easy to do with Photoshop/Bridge. Simply swap the Camera Raw.8bi files. Next to impossible to do with Lightroom since the ACR engine is embedded and Adobe has no way to keep multiple versions of LR on one system. But if I'm right, the performance problem is in Lightroom as well as Photoshop/ACR.

[jnewell]

I've not digested this yet, but take a look at Puget Systems' article on Adobe Lightroom CC/6 CPU Multi-threading Performance. There's also a Google spreadsheet to help Calculate which CPU is best for how you use Lightroom.

John

Thanks for the heads-up, that's really fascinating reading.  I will be keeping my 4770K for now, though.