N2DCRYPT
Jr. Member
Offline
Activity: 148
Merit: 5
|
 |
March 26, 2019, 11:43:03 PM |
|
Even if I can appreciate a generic answer like yours, my post was a direct request to the author to add Polaris cards in the KnownGpus of this tool
Open source, you can easily add whatever you want ;-) Cheers! For me "easily" mean I caused a kernel panic and/or a pci-error on every attempt to modify your code...  Anyway running an unmodified version of your tool I get this output: ./amdmemtweak -i 0 --current # NOTHING :-) I think the problem is I'm using an OSS Driver from debian and not the amd one.... ( https://wiki.debian.org/it/AtiHowTo) My card (WX-5100) is peculiar and I could not achive a decent install on debian 9 of the amd driver.. Anyway, still reading your code, a brilliant work! (even if I can understand just a 10% of it) Bye I also tried running a Radeon Polaris Pro Duo (dual WX-7100) and got nothing when running the tool... I'm obviously doing something wrong or this uncommon gpu just isn't supported, which wouldn't be too surprising. Thought it might be worth a try, simply because like your gpu bios mods aren't particularly practical with this guy and are fairly non-existent on the web.
|
|
|
|
|
|
|
|
Bitcoin addresses contain a checksum, so it is very unlikely that mistyping an address will cause you to lose money.
|
|
|
Advertised sites are not endorsed by the Bitcoin Forum. They may be unsafe, untrustworthy, or illegal in your jurisdiction.
|
|
|
Eliovp (OP)
Legendary
Offline
Activity: 1050
Merit: 1293
Huh?
|
 |
March 27, 2019, 12:01:56 AM |
|
For me "easily" mean I caused a kernel panic and/or a pci-error on every attempt to modify your code...  Anyway running an unmodified version of your tool I get this output: ./amdmemtweak -i 0 --current # NOTHING :-) I think the problem is I'm using an OSS Driver from debian and not the amd one.... ( https://wiki.debian.org/it/AtiHowTo) My card (WX-5100) is peculiar and I could not achive a decent install on debian 9 of the amd driver.. Anyway, still reading your code, a brilliant work! (even if I can understand just a 10% of it) Bye I added support for your GPU  You can check last commits how it's done, it's fairly easy. So next time, when you encounter this "issue" you know what to do  I also pushed a new release with a bunch of new HBM2 timings and a bunch of fixes  Enjoy!
|
|
|
|
cl4r0s
Newbie
Offline
Activity: 5
Merit: 0
|
 |
March 27, 2019, 12:09:52 AM |
|
I also tried running a Radeon Polaris Pro Duo (dual WX-7100) and got nothing when running the tool... I'm obviously doing something wrong or this uncommon gpu just isn't supported, which wouldn't be too surprising. Thought it might be worth a try, simply because like your gpu bios mods aren't particularly practical with this guy and are fairly non-existent on the web. [/quote] I've done some debug of the code for my card.... The card is recognized as an ATI and amdgpu_regs is read 555 snprintf(buffer, sizeof(buffer)-1, "/sys/kernel/debug/dri/%d/amdgpu_regs", instance); but when the program try to identify the memory type, all the defined value in the buffer are wrong: 574 lseek(gpu->mmio, MC_SEQ_RAS_TIMING, SEEK_SET); (gdb) p lseek(gpu->mmio, MC_SEQ_RAS_TIMING, SEEK_SET) No symbol "MC_SEQ_RAS_TIMING" in current context. No symbol "MC_SEQ_CAS_TIMING" in current context. No symbol "MC_SEQ_MISC_TIMING" in current context. etc. etc.. Simply the values in the amdgpu_regs are not as expected. Every time I try to analize those values and correct them, my server crash an reset  I was thinking the problem where in the driver, but if you got the same result with a wx-7100 the problem could be in the bios itself... Surely I'm too tired tonight to try again, I will let you know if I can go further... Bye
|
|
|
|
N2DCRYPT
Jr. Member
Offline
Activity: 148
Merit: 5
|
 |
March 27, 2019, 12:53:09 AM |
|
For me "easily" mean I caused a kernel panic and/or a pci-error on every attempt to modify your code...  Anyway running an unmodified version of your tool I get this output: ./amdmemtweak -i 0 --current # NOTHING :-) I think the problem is I'm using an OSS Driver from debian and not the amd one.... ( https://wiki.debian.org/it/AtiHowTo) My card (WX-5100) is peculiar and I could not achive a decent install on debian 9 of the amd driver.. Anyway, still reading your code, a brilliant work! (even if I can understand just a 10% of it) Bye I added support for your GPU  You can check last commits how it's done, it's fairly easy. So next time, when you encounter this "issue" you know what to do  I also pushed a new release with a bunch of new HBM2 timings and a bunch of fixes  Enjoy! nice @Eliovp! Definitely recognized now. Time to play around, thanks for your work on this tool! 
|
|
|
|
cl4r0s
Newbie
Offline
Activity: 5
Merit: 0
|
 |
March 27, 2019, 01:13:49 AM |
|
For me "easily" mean I caused a kernel panic and/or a pci-error on every attempt to modify your code...  Anyway running an unmodified version of your tool I get this output: ./amdmemtweak -i 0 --current # NOTHING :-) I think the problem is I'm using an OSS Driver from debian and not the amd one.... ( https://wiki.debian.org/it/AtiHowTo) My card (WX-5100) is peculiar and I could not achive a decent install on debian 9 of the amd driver.. Anyway, still reading your code, a brilliant work! (even if I can understand just a 10% of it) Bye I added support for your GPU  You can check last commits how it's done, it's fairly easy. So next time, when you encounter this "issue" you know what to do  I also pushed a new release with a bunch of new HBM2 timings and a bunch of fixes  Enjoy! nice @Eliovp! Definitely recognized now. Time to play around, thanks for your work on this tool!  YOU ARE A MASTER! root@clarosrv:~/build/amdmemorytweak# ./amdmemtweak --current GPU 0: Device 67c7 pci:0000:42:00.0 CAS CL: 22 W2R: 16 CCDS: 5 CCLD: 3 R2W: 30 NOPR: 0 NOPW: 0 RAS RC: 74 RRD: 8 RCDRA: 25 RCDR: 25 RCDWA: 16 RCDW: 16 MISC RFC: 164 TRP: 23 RP_RDA: 26 RP_WRA: 54 MISC2 WDATATR: 0 T32AW: 9 CRCWL: 25 CRCRL: 3 FAW: 14 PA2WDATA: 0 PA2RDATA: 0 DRAM1 RASMACTWR: 35 RASMACTRD: 30 ACTWR: 10 ACTRD: 15 DRAM2 RAS2RAS: 15 RP: 10 WRPLUSRP: 30 BUS_TURN: 35 You really deserve your donation man! TXID 0x4563bf67d18a7bd552b3d78ada5ca59f57b76726f26f3263f8f48818ef30a1d8 Thank You! 
|
|
|
|
NefariousFool
Jr. Member
Offline
Activity: 36
Merit: 7
|
 |
March 27, 2019, 08:21:14 AM |
|
I am trying to port this over to Windows for everybody. Is there any tips you might have besides making use of the PCUtil's app? I've not programmed in a long while so this is a bit out of my wheelhouse but somebody should step up.. well i'm that sucker.
Thank you! Any help is greatly appreciated. The fact you got this working on Linux and how fast the many mining OS's are implementing this, is great. I only wish i could do this conversion to Windows faster.
Thank you for this beautiful code.
Nefarious Fool "To run a thousand miles is in awesome feat... too bad you can just take a flight and do the same thing in 2hrs... It sure does make it a lot less monumental"
|
|
|
|
Remember remember the 5th of November
Legendary
Offline
Activity: 1862
Merit: 1007
Reverse engineer from time to time
|
 |
March 27, 2019, 09:18:23 AM |
|
I am trying to port this over to Windows for everybody. Is there any tips you might have besides making use of the PCUtil's app? I've not programmed in a long while so this is a bit out of my wheelhouse but somebody should step up.. well i'm that sucker.
Thank you! Any help is greatly appreciated. The fact you got this working on Linux and how fast the many mining OS's are implementing this, is great. I only wish i could do this conversion to Windows faster.
Thank you for this beautiful code.
Nefarious Fool "To run a thousand miles is in awesome feat... too bad you can just take a flight and do the same thing in 2hrs... It sure does make it a lot less monumental"
Yes. Linux provides the mechanisms to work with MMIO, physical memory etc, but windows exposes no such API or method. So you need a kernel mode driver to work with physical memory. On top of that you need to self-sign it, or disable Driver Signature Enforcement for said driver to work. Or pay $100 or so to sign it legitimately.
|
BTC:1AiCRMxgf1ptVQwx6hDuKMu4f7F27QmJC2
|
|
|
Zorg33
Jr. Member
Offline
Activity: 144
Merit: 2
|
 |
March 27, 2019, 09:14:59 PM |
|
cwl has no effect
it has indeed...
|
|
|
|
neuromancer4867
Member

Offline
Activity: 86
Merit: 16
|
 |
March 28, 2019, 08:58:02 AM |
|
ElioVP, since you are sort of the local AMD God.. You have any solid ideas on how to get R9 Furys jiving with TeamRedMiner?
|
|
|
|
Bbrodka
Newbie
Offline
Activity: 21
Merit: 0
|
 |
March 28, 2019, 03:32:59 PM |
|
|
|
|
|
Beave162
|
 |
March 28, 2019, 04:31:41 PM |
|
The readme states "./amdmemtool --RFC 43 --ras2ras 176" in the example for GDDR5.
Is that the optimal settings for a 580?
Also, "amdmemtweak" works for me not "amdmemtool." Am I missing something?
|
YaCoin: YL5kf54wPPXKsXd5T18xCaNkyUsS1DgY7z BitCoin: 14PFbLyUdTyxZg3V8hnvj5VXkx3dhthmDj
|
|
|
Bbrodka
Newbie
Offline
Activity: 21
Merit: 0
|
 |
March 28, 2019, 04:40:23 PM |
|
Since you are advertising *paid* solution at least have the decency to *donate* to the developers! I've made 20 posts here since July 23, 2015, does it look like I'm a spamer? I'm just trying to share with others. Thanks for encouraging conversation! I'm just a happy minerstat customer, no finacial involvement.
|
|
|
|
coinscrow
|
 |
March 28, 2019, 04:42:36 PM |
|
Since you are advertising *paid* solution at least have the decency to *donate* to the developers! I've made 20 posts here since July 23, 2015, does it look like I'm a spamer? I'm just trying to share with others. Thanks for encouraging conversation! I'm just a happy minerstat customer, no finacial involvement. He is not advertising. bbrodka is our paying customer and is having no benefit of posting this. However, we have talked in private and he genuinely missed J's previous posts. AMD Memory Tweak is open and free to use for everyone and can be used also from a dashboard and not just from the console. Also, need to thank Eliovp as he's been very supportive during the implementation period. Once we are ready with our Timing Database, we'll give back and contribute further to the community.
|
|
|
|
dierickxalexandre@gmail.c
Newbie
Offline
Activity: 4
Merit: 0
|
 |
March 28, 2019, 06:43:12 PM |
|
hello Eliovp, thank u for your job! can u please tel me if u have good seting for the rx 470 and 570?
|
|
|
|
Beave162
|
 |
March 28, 2019, 10:02:17 PM |
|
hello Eliovp, thank u for your job! can u please tel me if u have good seting for the rx 470 and 570?
+1
|
YaCoin: YL5kf54wPPXKsXd5T18xCaNkyUsS1DgY7z BitCoin: 14PFbLyUdTyxZg3V8hnvj5VXkx3dhthmDj
|
|
|
fluxy12
Jr. Member
Offline
Activity: 145
Merit: 1
|
 |
March 29, 2019, 06:40:18 AM |
|
hello Eliovp, thank u for your job! can u please tel me if u have good seting for the rx 470 and 570?
+1 Seems it's not so relevant for RX series compared to vega's.
|
|
|
|
pbfarmer
Member

Offline
Activity: 340
Merit: 29
|
 |
March 29, 2019, 09:59:12 AM |
|
hello Eliovp, thank u for your job! can u please tel me if u have good seting for the rx 470 and 570?
+1 Seems it's not so relevant for RX series compared to vega's. It's relevant, it's just that we already had a way to update timings for polaris, via bios flash. But 'live' timing updates are still quite valuable.
|
|
|
|
Zorg33
Jr. Member
Offline
Activity: 144
Merit: 2
|
 |
March 29, 2019, 02:55:34 PM Last edit: March 29, 2019, 04:01:22 PM by Zorg33 |
|
my results with Vega56 (samsung) on CN-R so far 
|
|
|
|
swongsR1thing
Newbie
Offline
Activity: 23
Merit: 0
|
 |
March 29, 2019, 03:07:42 PM |
|
Holy shit, that's nice man. Is it stable? Is this ubuntu or you use hiveos/minerstat/similar?
|
|
|
|
Zorg33
Jr. Member
Offline
Activity: 144
Merit: 2
|
 |
March 29, 2019, 03:23:18 PM |
|
Holy shit, that's nice man. Is it stable? Is this ubuntu or you use hiveos/minerstat/similar?
Ubuntu 18.04.2 LTS and AMD-gpu-pro 18.50 Still struggling with 4.15 kernel not able to set clocks properly. Anything above 1700MHz in P7 state puts the GPU in crimp mode. So I have to use 1700/1030mV in P7 to get the highest possible coreclk. Ideal would be something like 1800/975mV in P7, that would make ~1650 effective clock in P7 at much lower wattage I learned I will have to upgrade kernel, but don't know which version, there are also complains everywhere about 4.17-4.20 all over the forums. I'm currently testing stability. Wondering what would be the eth hashrate with these timings. Implying on CN algos it gives +15%, 45mh*1.15=51.75mh Gonna test it later.
|
|
|
|
|