Gadgetory

welcome back to harbor unbox today we are looking at high speed storage performance by comparing the flagship aimed in Intel mainstream desktop chipsets with aiders latest and greatest XP GSX 8200 PCIe gen3 x 4m to 20 to 80 960 gigabyte solid state drive do I have to say that every time the SX 8200 is an nvme SSD packing an insane read and write throughput 3.2 gigabytes per second when reading and 1.7 gigabytes per second when writing as a super-fast nvme SSD it's perfect for comparing these storage performance of AMD's x4 70 and intel z3 17 chipsets before getting to the result so let's talk a little bit about this new SSD that a data has sent over for us to check out and they have generously sent along the big nine hundred and sixty gigabyte model and now it's just a few months ago now the SX 8200 Series packs the latest controller from silicon motion the SM 2262 supporting eight down channels and ARM Cortex r5 quad-core nvme 3.1 raid and more connected to the controller for 64 layer three detail scene and memory chips from micron as well as two nano ddr3 DRAM chips which act as a high speed buffer unlike most nvme SSDs the SX 8200 family uses the m2 2280 form factor and for maximum performance takes advantage of the pcie 3.0 x 4 interface for now this series offers 240 gigabyte 480 by and 960 gigabyte models and pricing is extremely competitive Intel were the first to adopt the silicon motion SM 2262 controller with their 760 p series and today the one terabyte model can be had for 370 dollars u.s. HP though has since undercut them with the ax 920 which cost just 300 dollars u.s. for the one terabyte model unfortunately a data hasn't been out of beat HP as the 960 gigabyte SX 8200 comes in at 350 dollars u.s. that said for those of you interested in the much cheaper 240 gigabyte and 256 gigabyte models hey Dad there is much more competitive here while there 240 gigabyte model is selling for just $90 u.s. HP are asking a hundred and ten dollars u.s. and Intel one hundred and fifteen dollars u.s. a data also offers a premium five-year warranty and 160 terabytes written for the base model 320 terabytes written for the 480 gigabyte version and a massive 640 terabytes written for the 960 gear baak model that we have on hand for testing ok so now for some information about today's test for testing on these EV 370 platform we're using the as rockers at 370 type sheet which features three m2 slots and like most said 370 motherboards they're all connected to the chipset in total the said 370 chipset supports a maximum of 30 high-speed input/output pathways and six of them are dedicated as USB 3.0 ports that leaves 24 to be divided up for PCI eSATA and USB 3.0 in total at I cheat has 34 lanes which doesn't quite work what they've done here is share lanes so if you happen to use all the m2 slots then half the SATA ports would be disabled for example the three pcie 3.0 x 16 slots found on the zed 370 types you're all connected directly to the CPU and therefore don't share bandwidth with any of the m2 slots for the zed 370 platform this isn't a big issue as this chipset connects to the cpu using the third-generation direct media interface or DMI 3.0 and this allows for a throughput of 3.9 three gigabytes per second this is quite a bit more than the lower-end h3 10 chipset for example which uses the older DMI 2.0 interface and therefore is limited to a bandwidth of just 2 gigabytes per second this is often a problem for high-speed nvme SSDs as it can significantly reduce their performance this is also why it's very important that those who own an nvme SSD need to be careful about where they stick it even on the latest and greatest AMD x4 70 motherboards this is because the x4 70 chipset only has a pcie 2.0 x 4 link so it suffers the same bandwidth limitations as that of the h3 10 chip set the asrock x4 70 Taichi used for testing features 2 m2 slots the slot which is referred to as m-21 is connected directly to the CPU and therefore enjoys a pcie 3.0 x 4 link the second slot however which is called m2 2 is connected to the chipset and therefore is limited to pcie 2.0 x 4 bandwidth in other words 2 gigabytes per second using a single nvme SSD like the ADATA SX 8200 how much impact does this have on performance well let's go find out shall we first up we have the sequential read and write performance in the a SSD benchmark this is a challenging benchmark for SSDs as it doesn't use any compressible data for these tests so it's often considered as a sort of worst case scenario this means while other benchmarks might show sequential read performance hitting 3 to 3 point 2 gigabytes per second here we are limited to 2 point 7 gigabytes per second which by all accounts is still blazing fast bright performance though is where you'd expect it to be given the SX 8200 is rated for 1.7 gigabytes per second now you can see here while these n3 17 X 470 platforms delivered very similar results when using the pcie 3.0 x fault connection we see when running the SSD through the chipset on the X 470 board the performance is severely limited the read throughput was reduced by 50% while the write bandwidth was reduced by almost 20% here we see that because performance is much slow and making a single 4k file read or write the limited bandwidth of the x4 17 chipset configuration isn't that impactful that said though we still do see a 13% decrease in write performance in this test 64 requests for 4k data are being made simultaneously though I have to say this is more of a server type workload general computing usually only makes a few simultaneous requests still this is a better test for maxing out SSDs random 4k read and write performance here we see when connected to the x4 70 chipset throughput is limited by almost 30% when looking at the write performance here's a quick look at the access times be aware that lower is better here the Rison platform has an advantage here when connected directly to the CPU and this has helped it to slightly reduce the read access time next up we have the so file test which is an undisguised system was a smidgen faster than the core i7 system when connected to the CPU however connecting the SSD to the chipset reduced performance by almost 25% limiting throughput to just 1.4 gigabytes per second the program copy test features a large number of small non compressed files and as a result the throughput is significantly reduced this time we only see a 10% reduction in throughput for the Rison platform and connecting via the chipset though this is still a decent reduction in throughput then we have the game copy test which features a mixture of small and large compressed and non compressed files and this time we see a 13% reduction of throughput for the arisin system when connecting via the chipset that said it should be noted that even the more optimal CPU connection for the Rison platform was still 8 percent slower than the Intel's at 370 system using an 8700 K the auto disk benchmark uses compressible data so we see the sequential read performance peak at around 3 gigabytes per second once we hit file sizes of 128 kilobytes the horizon and core i7 performance is much the same at least when connecting the SSD directly to the CPU on the Rison system the Rison rig was 20% slower working with files smaller than 128 kilobytes which is fairly significant and again we see that it was much slower at once connected via the chipset especially for the larger file size tests finally this time when measuring write performance the Zed 370 platform using the 87 hurricane was faster throughout the ad ODIs benchmark tests well there you have it using what is now a fairly typical nvme SSD it is possible to reduce read performance by as much as 50% on an AM 4 motherboard if you install it in a wrong m2 slot throughout our testing it seemed like though for the most part you will be looking at about a 10 to 20 percent reduction in throughput truth be told though this kind of reduction in throughput likely won't be noticed for day-to-day tasks including things like gaming loading games that is so for the most part it's not really a serious issue still if you've paid good money for a blazing fast SSD and you'll want to ensure the absolute fastest read and write performance you might as well make sure you whack it in the right slot making this job a little easier is the fact that the motherboard makers do space find the bandwidth for the m2 slots so be sure to consult the manual to make sure you're getting all the jeebies you should be as for Intel uses it's a little more simplified by the fact that the chipset has full bandwidth through the CPU so the slowdown via the chipset is very minimal as for a data's xpg SX 8200 it's a cracking good value nvme SSD particularly the 240 gigabyte and 480 gigabyte models I suppose the next step now would be to try and get my hands on a second drive for some raid testing that would no doubt deliver some interesting results on these platforms anyway that is going to do it for this one if you did enjoy the video be sure to hit the like button subscribe for more content and if you appreciate the work we do harbor on box then consider supporting us on patreon thanks for watching I'm your host Steve and I'll see you again next time