[Dev] NeoScrypt Hardware Comparison Site
-
The 280x may be hashing faster than the 290x simply because of memory manufacturer, the hynix memory seems to allow miners to hash a lot lot faster than with elpida memory, perhaps this is due to differences in memory timings (seems most likely) but if you wish to get the highest hashrate out of a gpu, try to get hynix memory
I’ve been testing a couple of older AMD cards, and in general it seems the newer and faster the card, the better, i have a HD 5670 (picked up for £10 as fault off ebay, just needed a clean as the fan/heatsink were locked solid with some disgusting looking brown/yellow dusty stuff), with sha256 it is comparable to my 660Ti (about 100Mh/s) but in neoscrypt it really does kinda suck… only hitting 7kh/s after tweaking it for several hours, where my 660Ti gets 24kh/s at stock and up to 34kh/s after tweaks
funnily enough the HD 5670 i have is from XFX :P still holding strong with its 7kh/s so far (hits 74c, but the fan doesnt go up on its own, it stays at 25% unless i set it to something with sgminer startup config
soon im gonna be out on hols for 2 weeks, maybe more, do you recon i should perhaps downclock my cards slightly to reduce the chance of any crashes? hopefully i can get it to last 2 weeks solid without a crash
-
############### Update ###############
Been testing a new style for the site, you may check it out here;
http://hw.neoscrypt.tk/index2.php
currently i cannot get the in-page links to go below the header block (which is rather annoying tbh) so if anyone knows how i could fix that, would be awesome!
please comment on what you think of this style and any changes that could/should be made to it (there are probably quite a few)
note: the tables wont look like that with white/thick-ish borders, they will be made more clean
############### Thanks ###############
Sydney
-
Nice , SpartanC001 . If you need help,please PM to me . I can give some hardware comparison to you. soon
-
Yes, the 280x also has hynix, and that is part of why it beats the XFX. But XFX made a choice to put that cheaper memory in their card, yet charge the same price for it as other cards that have better memory. So I am making the choice to never buy another XFX card. :P
Yes, clock back your cards to where they will be rock solid stable if you are going to leave them unattended for 2 weeks.
And the new style is much easier to read than the old style!!
-
Nice , SpartanC001 . If you need help,please PM to me . I can give some hardware comparison to you. soon
If you know how to fix the in-page links (they currently make the content go up under the header) please let me know :D
Yes, the 280x also has hynix, and that is part of why it beats the XFX. But XFX made a choice to put that cheaper memory in their card, yet charge the same price for it as other cards that have better memory. So I am making the choice to never buy another XFX card. :P
Yes, clock back your cards to where they will be rock solid stable if you are going to leave them unattended for 2 weeks.
And the new style is much easier to read than the old style!!
I generally stick with ASUS or Gigabyte cards, ive never had an issue with gigabyte, and their windforce coolers are great, 660Ti tops out at 70c if i turn the fan to min, and 57c if i put fan at max, and is silent compared to my i7’s stock cooler lol
Asus i find have better performing cards, ive not had an issue with an asus gpu, although i had a motherboard have its built in audio crap out, i didnt request a replacement as i already had a sound card for it anyway, but they gave me a refund which was nice
As for the style, im trying to keep it non blocky, and ill be changing it about a bit more tonight with rounded borders for tables and stuff
-
############### Update ###############
Been testing a new style for the site, you may check it out here;
http://hw.neoscrypt.tk/index.php
currently i cannot get the in-page links to go below the header block (which is rather annoying tbh) so if anyone knows how i could fix that, would be awesome!
please comment on what you think of this style and any changes that could/should be made to it (there are probably quite a few)
note: the tables wont look like that with white/thick-ish borders, they will be made more clean
############### Thanks ###############
Sydney
############### Update ###############
Just updated the style some more, looking a bit better i think!
http://hw.neoscrypt.tk/index.php
Please comment how you think this looks!
############### Thanks ###############
Sydney
-
I like it, but there is to much grey dots blinking (white lines crossings)
-
I like it, but there is to much grey dots blinking (white lines crossings)
hmmm, now i look at it more i see what you mean, i will try to fix ^^ (running out of shades of grey :P)
thanks
############### Update ###############
Style fixed! (tables are no longer garishly bright and make your eyes go funny)
http://hw.neoscrypt.tk/index.php
############### Thanks ###############
Sydney
-
I attempted to add some R9 270x settings, but once I finished submitting the form the settings do not seem to appear in the main table. I don’t know if i did something wrong or if the submissions are moderated and need to be approved.
-
I attempted to add some R9 270x settings, but once I finished submitting the form the settings do not seem to appear in the main table. I don’t know if i did something wrong or if the submissions are moderated and need to be approved.
I have to approve the submissions first (stops people spamming silly entries)
Edit: also, where did you get your power value from? Is this measured at the wall or via gpu-z? As 80w consumption from a 180w R9 270x is a little odd :P i’ll assume you meant 180 and it was a typo unless you can prove otherwise :)
Edit 2: I’m not sure on many of the specs, cores, power, datarate dont match to what an R9 270x has, can you use GPU-z (get it here: http://www.techpowerup.com/downloads/2418/techpowerup-gpu-z-v0-8-0/) to get your information and re-enter it?
Thanks
-
I have to approve the submissions first (stops people spamming silly entries)
Edit: also, where did you get your power value from? Is this measured at the wall or via gpu-z? As 80w consumption from a 180w R9 270x is a little odd :P i’ll assume you meant 180 and it was a typo unless you can prove otherwise :)
Edit 2: I’m not sure on many of the specs, cores, power, datarate dont match to what an R9 270x has, can you use GPU-z (get it here: http://www.techpowerup.com/downloads/2418/techpowerup-gpu-z-v0-8-0/) to get your information and re-enter it?
Thanks
Yeah, the bus width and stuff I had placeholder info, I was going to look it up and update later. I misunderstood how the submission worked, thought it would be real time and not big a big deal to update it right away.
The power values are correct using under-volted cards. I measured a 4x 270x rig drawing 370 watts total from the wall, subtract the 50 watts idle for the system and divide by 4 to get the per card wattage.
Edit: Resubmitted with correct values from GPUz.
Also, I tried adding (Elpida) on the memory entry, so “GDDR5 (Elpida)” but there were not enough allowed characters in the field, perhaps you could extend the field length to allow a few more extra?
-
Actually looking at the other entries on the chart all the power values seem to be on the high side. I know some of those were applicable when using scrypt settings and overclocking, but for instance the 280x cards are showing 250 watts each. I have some 4x 280x rigs as well and they are only drawing about 150 watts each, also undervolted, and mildly overclocked.
The rig I am using for reference (4X 280x) draws 660 watts total from the wall, I first check the idle usage, which draws about 60 watts, then check after it has been mining for about 5 minutes, which is the 660 watt figure. Again subtracting the 60 system watts and dividing the remaining 600 watts by 4 gives me an average of 150 watts per card. These are giving me ~315 kHash each with a mild 1100 core and 1500 memory overclock. Since they are undervolted they are not stable much higher, but I only get maybe 10-20 more khash each for quite a large increase in power draw, so not worth it in my opinion.
Edit: Actually on further investigation, if I ran a 280x giving only 315 kHash at a 250 watt power draw (let’s assume this includes the pro-rated share of the system draw as well; i.e. 230 watt GPU 20 watts system on a multi-GPU rig), this would work out to just breaking even if you pay $0.08 per kw/hour. You would not be in profit unless you were paying $0.07 or less per kw/hour, which unfortunately in my case is closer to $0.10.
-
Those power entries for the 280X etc, are for the rated TDP (where the actual power could not be measured, e.g no meter)
Seems pretty good that you undervolted and it only hit 80w ^^, and for the nvidia card that is actual power draw, as you can see they arent very power efficient at scrypt lol
As for GDDR5 (Elpida), please can you add that in the more info box, alomg with the info of what voltages and miner parameters, thats what that box is for :)
Also adding a submission is a 1 time thing, however if youve submitted one, but would like it updating, in the notes you would send the link to the individual card page (use the more info link in the main tables), and say that it needs updating.
-
############### Update ###############
Styles are now updated for all base pages, ACP still under construction.
Had a massive panic attack when i deleted new submission form page by accident, luckily i had a backup, so panic over, and its all alive :D
ACP Pages are a pita, since i have to do checks to make sure user is logged in and in a legit session (-_-) also designing them all to interface together is a bigger pita (-_-)
The new style should be a bit cleaner to use, and a bit easier on the eyes.
As always, any suggestions are welcome!
############### Thanks ###############
Sydney
-
Type: GPU
Hashrate: 21.60 Kh/s
Vendor: AMD HD 6870
Est. Power: 151w
Miner: cgminer 3.7.8
Proof: -I 13 -w 128
Type: GPU
Hashrate: 57.34 Kh/s
Vendor: AMD HD 7870
Est. Power: 185w
Miner: cgminer 3.7.8
Proof: -I 14 -w 32
-
Type: GPU
Hashrate: 20.38 Kh/s
Vendor: AMD HD 6850
Est. Power: 127w
Miner: cgminer 3.7.8
Proof: -I 12 -w 32
Type: GPU
Hashrate: 97.22 Kh/s
Vendor: AMD HD 7950
Est. Power: 200w
Miner: cgminer 3.7.8
Proof: -I 14 -w 128
-
Type: GPU
Hashrate: 10.34 Kh/s
Vendor: AMD HD 6770
Est. Power: 108w
Miner: cgminer 3.7.8
Proof: -I 12 -w 64
Type: GPU
Hashrate: 56.68 Kh/s
Vendor: AMD HD 7850
Est. Power: 130w
Miner: cgminer 3.7.8
Proof: -I 13 -w 32
-
Thanks for those Lizhi, ill add those once i’m back on the pc, and i’ve replied to your message about the html/css page link thing,
Thanks,
Sydney
-
Type: GPU
Hashrate: 20.38 Kh/s
Vendor: AMD HD 6850
Est. Power: 127w
Miner: cgminer 3.7.8
Proof: -I 12 -w 32I’m looking to help someone setup a 6850 GPU, and ran across this.
The info shows -I12, but the image shows -I14.
Also, isn’t 98c a little high temp?
-
I agree, lizhi, check out that card and re-fit the cooler! you’re gonna burn that poor thing lol
98c is too high in my opinion, even for an AMD card (i remember those first batches of 512mb 4870/4890’s idling at 80c+ in load 120c+ lol)
speaking of 4870’s, i have one lying round somewhere, was a good one aswell, overclocked to 800/1000, undervolted a lot and nice and stable, idled at 37c, load 55c
doubt it would push out many hashes, as the general trend with neoscrypt seems to be the newer/faster the hardware the better, and seems less dependant on compute performance, 660Ti vs HD 5670 are equal in SHA256 (both about 100mh/s), but in neoscrypt, the newer bigger 660Ti leaves it in the dust (34kh/s vs 7kh/s).
Either way lizhi check that card before it sets fire to something!
