Show Posts

This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.


Messages - sandor111

Pages: [1]
1
MemoryCoin / Re: New YAM version release
« on: January 31, 2014, 09:46:08 pm »
Getting over 14hpm on E3-1230v2, I'm impressed!

2
MemoryCoin / Re: New YAM version release
« on: January 28, 2014, 12:10:02 pm »
Binding the process to each physical socket performs roughly the same as taskset

Did you measure exact HPM values? Does OS really support NUMA? What is output of

numactl --hardware

yvg1900

Yes it's enabled.

Code: [Select]
available: 2 nodes (0-1)
node 0 cpus: 0 1 2 3 4 5 12 13 14 15 16 17
node 0 size: 12278 MB
node 0 free: 123 MB
node 1 cpus: 6 7 8 9 10 11 18 19 20 21 22 23
node 1 size: 12288 MB
node 1 free: 990 MB
node distances:
node   0   1
  0:  10  20
  1:  20  10
Code: [Select]
MMC Agg. SPM: 12.304, HPM: 12.943; Rnds C/I: 9919/2596, Don. C/I: 109/22; Cfg/Wkr SPM: 12.304/0.5804, Cfg/Wkr HPM: 12.945/0.5884 10028 rnds AV=1, ART=101969
With numactl, roughly 6.45 hpm per socket, so 12.9 hpm total.
How do I measure the exact hpm, are the reported values accurate?

3
MemoryCoin / Re: New YAM version release
« on: January 27, 2014, 09:18:35 pm »
Binding the process to each physical socket performs roughly the same as taskset

4
MemoryCoin / Re: New YAM version release
« on: January 27, 2014, 06:15:21 pm »
Seems to perform worse than previous miner on dual L5639 :(
Code: [Select]
threads = 24
mining-params = mmc:av=0&aesni=on&m=22528&donation-interval=100

5
yvg1900, please optimize the miner for L5639 xeon CPU, currently it's mining performance seems to be maxed out at 12 threads.

6
Yeah I'm pretty bummed out, but 3 extra hpm is compared to previous miners is cool.

7
With a dual L5639 I get 13 hpm on 24 threads, not a huge improvement over the previous miners, definitely not 300% (btw I'm using Nehalem binary)

8
Here is the script I use to make it work with a dual L5639
Change <ADDRESS> to your MMC address.

wget http://ge.tt/api/1/files/5YYDYhC1/0/blob?download
tar -xvf blob?download
echo '#! /bin/bash' > run.sh
echo 'while true; do ./mc2miner --url http://mmcpool.1gh.com:8080 --threads 8 --noavx --idle <ADDRESS>; sleep 1; done' >> run.sh
chmod +x run.sh
screen -A -m -d -S mmc1 ./run.sh &
screen -A -m -d -S mmc2 ./run.sh &
screen -A -m -d -S mmc3 ./run.sh &

If this helped: MMuQj9wZQyepNL1SkKkDaCaHFmo4DqkYFb

9
It hangs after 5s on Ubuntu, CPU is dual L5639 so it should be supported..

Edit: 8 threads works fine, anything above that makes it hang.
Edit2: Solution is just start 3 instances, so they will use 24 threads total

10
MemoryCoin / Re: [ANN] MMC.1GH.COM - GPU mining
« on: December 30, 2013, 03:12:16 pm »
anyone running 280x, 290, 290x can you please post your stats?
i am getting 17h/m on 290x not sure if it's normal

Pages: [1]