5w00p
|
|
August 06, 2014, 03:28:17 AM |
|
1600 H/s: 4x Opteron 6344 (48 physical cores @ 2.6ghz static) 64G ram (12x4GB ddr3- 14.04, built from wolf's git source inside KVM with cpu-passthrough (couldn't get it to run on 12.04 which is host's bare metal OS, could potentially be faster) sysctl -w vm.nr_hugepages=144 pool reporting > 2kh, miner at 1600-1650kh/s. Could probably get better performance by a) running it on baremetal, b) using numactl and a better task scheduler. I hit 1030 or so with 23 threads on AWS - you probably need to reduce your thread count. Wolf, why would he want to REDUCE his hashrate? He reports 1600 hash/sec and you report 1030. Because he has 48 physical cores, I had 16. OK. What AWS instance type has Opterons?
|
|
|
|
5w00p
|
|
August 06, 2014, 03:38:34 AM |
|
OK. What instance type did you get 1030 hash/sec on 16 cores?
|
|
|
|
tgt
Newbie
Offline
Activity: 19
Merit: 0
|
|
August 06, 2014, 06:40:40 PM Last edit: August 06, 2014, 06:53:19 PM by tgt |
|
It's fully utilizing the cores (minus one for some reason... maybe the scheduler thread is included in the thread limit?) so I can't see a huge gain other than running it on bare metal. The opteron cores are not as efficient per ghz as the haswells. The only advantage is that you have physical cores without any hyperthreading. I'll try and compile the miner on 12.04 to run it on bare metal and see what/if any advantages are seen vs running it kvm with cpu passthrough. The server is about $3300, so it's not exactly cost effective. Just fun to see. edit: just noticed the instructions to install it on 12.04, derp. https://i.imgur.com/iH7vs4r.png
|
|
|
|
primer-
Legendary
Offline
Activity: 1092
Merit: 1000
|
|
August 06, 2014, 07:13:44 PM |
|
It's fully utilizing the cores (minus one for some reason... maybe the scheduler thread is included in the thread limit?) so I can't see a huge gain other than running it on bare metal. The opteron cores are not as efficient per ghz as the haswells. The only advantage is that you have physical cores without any hyperthreading. I'll try and compile the miner on 12.04 to run it on bare metal and see what/if any advantages are seen vs running it kvm with cpu passthrough. The server is about $3300, so it's not exactly cost effective. Just fun to see. edit: just noticed the instructions to install it on 12.04, derp. What do you get when running on only 24 cores ?
|
|
|
|
PeaMine
|
|
August 07, 2014, 04:35:20 AM |
|
It's fully utilizing the cores (minus one for some reason... maybe the scheduler thread is included in the thread limit?) so I can't see a huge gain other than running it on bare metal. The opteron cores are not as efficient per ghz as the haswells. The only advantage is that you have physical cores without any hyperthreading. I'll try and compile the miner on 12.04 to run it on bare metal and see what/if any advantages are seen vs running it kvm with cpu passthrough. The server is about $3300, so it's not exactly cost effective. Just fun to see. edit: just noticed the instructions to install it on 12.04, derp. Is that the 16 core Intel system or the AMD 48 core?
|
Datacenter Technician and Electrician. If you have any questions feel free to ask me as I am generally bored looking at logs and happy to help during free time.
|
|
|
5w00p
|
|
August 07, 2014, 09:24:30 PM |
|
It's fully utilizing the cores (minus one for some reason... maybe the scheduler thread is included in the thread limit?) so I can't see a huge gain other than running it on bare metal. The opteron cores are not as efficient per ghz as the haswells. The only advantage is that you have physical cores without any hyperthreading. I'll try and compile the miner on 12.04 to run it on bare metal and see what/if any advantages are seen vs running it kvm with cpu passthrough. The server is about $3300, so it's not exactly cost effective. Just fun to see. edit: just noticed the instructions to install it on 12.04, derp. Is that the 16 core Intel system or the AMD 48 core? methinks its the Opteron machine. Wolf0, thanks for sharing. I should not be surprised that the coder of the miner is very effective at managing his rented rigs, and I am not really, but I gotta say that your ~64 h/s/core is quite impressive on the c3.8xlarge instances.
|
|
|
|
slb
|
|
August 08, 2014, 02:48:37 PM |
|
Hi, I am trying to compile on Mac, but I receive this error when I 'make' make[3]: Nothing to be done for `all-am'. gcc -DHAVE_CONFIG_H -I. -pthread -Qunused-arguments -falign-loops=16 -falign-functions=16 -falign-jumps=16 -falign-labels=16 -Ofast -flto -fuse-linker-plugin -funroll-loops -fvariable-expansion-in-unroller -ftree-loop-if-convert-stores -fmerge-all-constants -fbranch-target-load-optimize2 -fsched2-use-superblocks -maes -MT minerd-cpu-miner.o -MD -MP -MF .deps/minerd-cpu-miner.Tpo -c -o minerd-cpu-miner.o `test -f 'cpu-miner.c' || echo './'`cpu-miner.c clang: error: unknown argument: '-falign-loops=16' [-Wunused-command-line-argument-hard-error-in-future] clang: note: this will be a hard error (cannot be downgraded to a warning) in the future clang: error: unknown argument: '-falign-jumps=16' [-Wunused-command-line-argument-hard-error-in-future] clang: note: this will be a hard error (cannot be downgraded to a warning) in the future clang: error: unknown argument: '-falign-labels=16' [-Wunused-command-line-argument-hard-error-in-future] clang: note: this will be a hard error (cannot be downgraded to a warning) in the future clang: error: unknown argument: '-fuse-linker-plugin' [-Wunused-command-line-argument-hard-error-in-future] clang: note: this will be a hard error (cannot be downgraded to a warning) in the future clang: error: unknown argument: '-fvariable-expansion-in-unroller' [-Wunused-command-line-argument-hard-error-in-future] clang: note: this will be a hard error (cannot be downgraded to a warning) in the future clang: error: unknown argument: '-ftree-loop-if-convert-stores' [-Wunused-command-line-argument-hard-error-in-future] clang: note: this will be a hard error (cannot be downgraded to a warning) in the future clang: error: unknown argument: '-fbranch-target-load-optimize2' [-Wunused-command-line-argument-hard-error-in-future] clang: note: this will be a hard error (cannot be downgraded to a warning) in the future clang: error: unknown argument: '-fsched2-use-superblocks' [-Wunused-command-line-argument-hard-error-in-future] clang: note: this will be a hard error (cannot be downgraded to a warning) in the future make[2]: *** [minerd-cpu-miner.o] Error 1 make[1]: *** [all-recursive] Error 1 make: *** [all] Error 2
I have the dependencies installed. 'autogen.sh' and 'configure' run without errors.
|
|
|
|
tgt
Newbie
Offline
Activity: 19
Merit: 0
|
|
August 09, 2014, 01:31:28 AM |
|
It's fully utilizing the cores (minus one for some reason... maybe the scheduler thread is included in the thread limit?) so I can't see a huge gain other than running it on bare metal. The opteron cores are not as efficient per ghz as the haswells. The only advantage is that you have physical cores without any hyperthreading. I'll try and compile the miner on 12.04 to run it on bare metal and see what/if any advantages are seen vs running it kvm with cpu passthrough. The server is about $3300, so it's not exactly cost effective. Just fun to see. edit: just noticed the instructions to install it on 12.04, derp. https://i.imgur.com/iH7vs4r.pngIs that the 16 core Intel system or the AMD 48 core? methinks its the Opteron machine. Wolf0, thanks for sharing. I should not be surprised that the coder of the miner is very effective at managing his rented rigs, and I am not really, but I gotta say that your ~64 h/s/core is quite impressive on the c3.8xlarge instances. Actually, I can get 70H/s/core on c3.8xlarge, 64H/s/core is just with this miner... I get 64H/core on my opteron... the speed actually tops out at 26 cores (26*64=1664H/s same as in the screenshot). I guess that's L3 bandwidth limit - It's amusing to see how intel and amd are virtually identical per core due to this similar cache speed limitation. Pushing numactl to force workloads onto physical cores/cache pairs didn't make a difference.
|
|
|
|
nioc
Legendary
Offline
Activity: 1624
Merit: 1008
|
|
August 09, 2014, 01:45:15 AM |
|
i5-3450 windows 7
Downloaded both the 06-09-2014 Wolf miner and the LucasJones miner. Wolf is 5% faster according to the numbers the miners display.
|
|
|
|
PeaMine
|
|
August 09, 2014, 03:24:19 AM |
|
Anyone have any ideal performance/cost CPU desktop/server builds for XMR? Thinking about buy a new single/dual CPU setup for this + gaming rig and GPU mine also. AMD has some cheap setups, but don't want to waste money, but I also want to buy something on newegg with BTC....though the 10% discount expired I think =(
|
Datacenter Technician and Electrician. If you have any questions feel free to ask me as I am generally bored looking at logs and happy to help during free time.
|
|
|
Hotmetal
|
|
August 09, 2014, 05:10:48 PM |
|
Anyone have any ideal performance/cost CPU desktop/server builds for XMR? Thinking about buy a new single/dual CPU setup for this + gaming rig and GPU mine also. AMD has some cheap setups, but don't want to waste money, but I also want to buy something on newegg with BTC....though the 10% discount expired I think =(
I'm uncertain of the CPU side (cost vs performance). GPU wise, merged mining (XMR+FCN) on a GeForce GTX 750 Ti hits 220->250 h/s. (can probably get more if its just dedicated to that as I'm running it inside of Linux as a desktop) At the moment its the fastest GPU per watt of power used and its relatively cheap.
|
|
|
|
redsn0w
Legendary
Offline
Activity: 1778
Merit: 1043
#Free market
|
|
August 09, 2014, 06:06:08 PM |
|
Has anyone successfully compiled Wolfs cpuminer under centOS 6.4?
|
|
|
|
primer-
Legendary
Offline
Activity: 1092
Merit: 1000
|
|
August 09, 2014, 06:22:10 PM |
|
Has anyone successfully compiled Wolfs cpuminer under centOS 6.4?
Yes, remove MADV_HUGEPAGE from cpu-miner.c and it will compile
|
|
|
|
redsn0w
Legendary
Offline
Activity: 1778
Merit: 1043
#Free market
|
|
August 10, 2014, 07:40:31 AM |
|
Has anyone successfully compiled Wolfs cpuminer under centOS 6.4?
Yes, remove MADV_HUGEPAGE from cpu-miner.c and it will compile ok thanks for the reply ..
|
|
|
|
Frangomel
Legendary
Offline
Activity: 1022
Merit: 1000
FreshTheGame
|
|
August 11, 2014, 03:17:41 PM Last edit: August 11, 2014, 03:30:28 PM by Frangomel |
|
When I start CPU miner with i5-3350p have just only 75 h/s. I changed threads from 1 to 4, always same??? What is the problem???
edit: now have 120 h/s, hope it is ok now?
|
|
|
|
nioc
Legendary
Offline
Activity: 1624
Merit: 1008
|
|
August 12, 2014, 08:10:07 AM |
|
When I start CPU miner with i5-3350p have just only 75 h/s. I changed threads from 1 to 4, always same??? What is the problem???
edit: now have 120 h/s, hope it is ok now?
I didn't try 1 or 4 threads but did try 2 and 3 threads with an i5-3450 with 3 threads being slightly faster. Windows 7
|
|
|
|
Frangomel
Legendary
Offline
Activity: 1022
Merit: 1000
FreshTheGame
|
|
August 13, 2014, 12:20:40 PM |
|
have about 130 h/s with 3 threads, not so bad
|
|
|
|
tljenson
|
|
August 26, 2014, 08:16:21 AM |
|
I new to mining, I want to make sure this is working ok. Here is what I get when I start mining.
[2014-08-26 02:13:39] thread 1: 500 hashes, 49.30 H/s [2014-08-26 02:13:39] thread 0: 490 hashes, 48.25 H/s [2014-08-26 02:13:39] thread 2: 476 hashes, 46.93 H/s [2014-08-26 02:13:39] Stratum authentication failed [2014-08-26 02:13:39] ...retry after 10 seconds
Do I have to worry that authentication failed? If so what am I doing wrong. The reason I asked is I tried several pools and got the same failed message. So I assume that is part of the mining, or is it>
|
|
|
|
nioc
Legendary
Offline
Activity: 1624
Merit: 1008
|
|
August 26, 2014, 09:33:33 AM |
|
I new to mining, I want to make sure this is working ok. Here is what I get when I start mining.
[2014-08-26 02:13:39] thread 1: 500 hashes, 49.30 H/s [2014-08-26 02:13:39] thread 0: 490 hashes, 48.25 H/s [2014-08-26 02:13:39] thread 2: 476 hashes, 46.93 H/s [2014-08-26 02:13:39] Stratum authentication failed [2014-08-26 02:13:39] ...retry after 10 seconds
Do I have to worry that authentication failed? If so what am I doing wrong. The reason I asked is I tried several pools and got the same failed message. So I assume that is part of the mining, or is it>
Yes worry because it's not working. It's not the pool. Most likely there is a space in your wallet address when you copy and pasted it. I think it happens because the address wraps to 2 lines in the wallet and it is not always obvious when you copy it especially if it is on 2 lines in the bat file. Let me know what happens.
|
|
|
|
TimeHacker
|
|
August 26, 2014, 09:49:25 AM |
|
I new to mining, I want to make sure this is working ok. Here is what I get when I start mining.
[2014-08-26 02:13:39] thread 1: 500 hashes, 49.30 H/s [2014-08-26 02:13:39] thread 0: 490 hashes, 48.25 H/s [2014-08-26 02:13:39] thread 2: 476 hashes, 46.93 H/s [2014-08-26 02:13:39] Stratum authentication failed [2014-08-26 02:13:39] ...retry after 10 seconds
Do I have to worry that authentication failed? If so what am I doing wrong. The reason I asked is I tried several pools and got the same failed message. So I assume that is part of the mining, or is it>
Which pool do you use? Everything works OK for me on Minergate for exmple...
|
|
|
|
|