Gadgetory


All Cool Mind-blowing Gadgets You Love in One Place

Benchmarking Windows 10 Meltdown Flaw Emergency Patch, What Can Desktop Users Expect?

2018-01-04
welcome back to harbor unboxed today's video is a follow-up of yesterday's video where we talked about the Intel processor exploit now in that video we covered much of what we knew at the time and that was that major operating systems were getting patched or had just been patched to solve a potential security issue with Intel CPUs we've now let this issue also extend to a few select ARM processor architectures but AMD still appear to be mostly in the clear there are three variants of the exploit an AMD was vulnerable to one of them the bounds check bypass method but this can be solved via an OS update shouldn't come at a significant performance cost the other two variants though they don't appear to impact AMD processors due to the differences in architectural design now in yesterday's video we looked at some testing done by fir onyx so that was the main reason I went ahead with d'Ovidio at the time as we had some real numbers to talk about at the time only the Linux operating system had to receive the update addressing the exploit and for onyx benchmark performance before and after they found some pretty crippling performance for the server related tests using the core i7 87 are okay with a samsung 950 pro nvme storage device they then followed up with a Linux gaming test and looked at half a dozen tiles and mostly found the difference was within the margin of error so gamers and desktop users looked as though they would be unaffected and I assume this would be the case at the time but I promised I'd also test to the impact for Windows users as soon as I could after a late night working on that video I was up bright and early today for some reason I don't know why but it was a good thing that I was because Microsoft had already pushed out an emergency fix for Windows users Windows 10 users should be able to get that update automatically through the Windows Update feature now Windows 7 & 8 users well they can get the patch directly from the Microsoft web site today or they can wait till patch Tuesday to receive it automatically via the Windows Update the patch titled kb 4 0 5 6 8 9 2 does have one fairly severe known issue Microsoft notes that your update installation may stop at 99% and this may show elevated CPU or disk utilization if the device was reset using the reset this PC functionality after installing the KB 4:05 I've four zero double to update anyway the good news is we can finally retest to see what impact this update has on performance for desktop users if any at all now a few things to note here I've only had time to test the 87 okay so no older generation Intel CPUs have been tested yet I've also not checked to see if this patch has any impact on AMD CPUs the benchmarks you're about to see for the 87 ok were all conducted today they are all fresh and testing was conducted on the same test system under the same conditions I first updated all my pre patched data and then applied the patch and retested as usual a gaming performance figures are all based on an average of three runs now for the storage tests I dude things are a little differently since those numbers tend to fluctuate a bit more normally I again do take the average from three runs but for this test I've taken the best result for each individual test and shown that instead in total I gave each configuration for temps to post the best result it could and between each run the system was powered completely down and then build it back up ok so that's enough about that let's get to the benchmarks starting with the storage tests we have the a s SSD benchmark and for those tests I'm using the Samsung SSD 950 Pro with the 87 or okay here we see very similar sequential read and write results the figures after the update are actually slightly better though we're talking just a one to two percent difference here where we see a significant difference as we're looking at the 4k read result here we see a very large 23 percent reduction in performance going from a throughput of 44 megabytes per second to just 34 megabytes per second the random 4k write performance though well that goes unchanged so it's just the random 4k reads that are significantly down interestingly though the 4k 64 thread read and write performance is improved with the patch the write performance here has been boosted by 17% so that's certainly not bad news though I'd argue that the 4k read result is more serious read access times were also 14% lower before the update but the right access time is much the same moving on we find that crystal D smart confirms what we've seen when testing with a SSS D benchmark here the 4k Reaper formance has been reduced by 23% after the patch the rest of the margins are within 5% so nothing really worth noting the last storage focus test I ran was a toe disk benchmark and here we find something very interesting these are all sequential read and write tests so the 4k results here won't necessarily reflect what we saw previously and while they clearly don't however as the file size grows to 16 kilobytes we start to see a noticeable drop in performance with the update the drop-off isn't as significant as the 4k read results seen previously but we are still seeing up to a 9% reduction in throughput the Cinebench r15 score is based on an average of 3 runs and here we see a slight variation in performance but nothing to be alarmed about the multi-threaded score is reduced by 2% while this single thread score was increased by a percent so margin of error stuff then we see much the same in blender the update came in a fraction ahead but again within the margin of error another render test this time over the corona benchmark and again nothing really to report here so it seems like your rendering workloads won't be impacted likewise your spreadsheets will remain as snappy as ever we see no improvement or decline in performance here at all the 7-zip compression and decompression performance looks much the same again this is within the margin of error for this test veracrypt also saw no difference for the one gigabyte and 50 megabyte AES encryption and decryption testing okay so time to get serious with a few game benchmarks first that we have the always dependable ash of the singularity here we see a small uplift in performance after the patch has been applied granted the 1% low result was only improved by 1.7 percent but still it's certainly not slower we're also CPU bound for this test using the high quality preset so not GPU bound boosting the quality preset to crazy does result in a GPU limited scenario and again we find similar results before and after the patch has been installed Assassin's Creed origins was a game I was really keen to check out due to the type of protection that game uses to stop piracy that said though as you can see nothing worth talking about here apart from the fact that patch has no negative impact on frame rates and switching to the ultra high quality preset doesn't either then finally we have the battlefield 1 results and using the medium quality settings at 1080p with the gtx 1080i we see similar performance before and after the patch in fact once again after the patch has been applied we do see a very minor improvement this is again seen with the ultra quality settings so things look pretty good with the core i7 87 ok well there you have it as suspected based on the Linux results that we featured in yesterday's video and desktop users really have nothing to worry about particularly gamers that said I am yet to test older CPUs but given the type of workloads we're seeing impacted by the patch I don't think there's really gonna be any issue there with your typical desktop workloads but if there is I'll certainly report back with that information the reduction in 4k performance though for the high-speed nvme drives that is a bit of a concern and while this shouldn't impact things like games any applications that are sensitive to this might show a reduction in performance of course the brief list of applications I tested were all fine and there was no issues there as we also saw in yesterday's benchmark which looked at some server benchmarks that's really where the problem is so it's a bit of a non-issue for desktop users but it could be quite a serious concern for data centers and the like that's not really our area of expertise or interest though so we'll leave that testing for those better equipped to tackle it if you have any questions or something you'd like to add to the topic then please feel free to drop that down in the comment section below I'm your host Steve see you next time
We are a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for us to earn fees by linking to Amazon.com and affiliated sites.