[LOCKED] cpuminer-opt v3.12.3, open source optimized multi-algo CPU miner

[joblo]

Do you think is possible to make Lyra2RE to mine on AVX2? That will compete with the newest Nvidia cards.

Anything is possible but it would take a complete redesign of the miner engine and every algorithm to be able to process
multiple streams per thread to achieve parallelism. Each CPU thread would process multiple streams in parallel
instead of just one. Hodl was unique in that it lends itself to parallel processing within a single thread so it didn't
require a major design change.

The effort required would outweigh any benefits.

BTW, do you know which coin uses Lyra2RE?

[1714164828]

1714164828

[1714164828]

1714164828

[1714164828]

1714164828

[JarBinks]

Please direct me to somewhere else if this has already been answered.

I have a 32 core machine and I only want to use 16, easy enough -t 16.
But that loads up 1 processor and it runs hot, I would prefer to use half of the cores on each processor, every other would be perfect.

In comes the --cpu-affinity, which I cannot figure out.
I tried:
  --cpu-affinity 2863311530 and it seems to ignore it.
  --cpu-affinity and no -t but it just used all cores.
  --cpu-affinity AAAAAAAA and everything was moved to processor 2 (At least it did something)
 
I am probably just being a stupid human!

[ReiMomo]

Do you think is possible to make Lyra2RE to mine on AVX2? That will compete with the newest Nvidia cards.

Anything is possible but it would take a complete redesign of the miner engine and every algorithm to be able to process
multiple streams per thread to achieve parallelism. Each CPU thread would process multiple streams in parallel
instead of just one. Hodl was unique in that it lends itself to parallel processing within a single thread so it didn't
require a major design change.

The effort required would outweigh any benefits.

BTW, do you know which coin uses Lyra2RE?

There is Crypto [CTO], but Nice Hash seems to mine something else that have a different block number and higher difficulty. The other day their GUI was showing me 90 cents at .730 MH/s, today shows 41 cents.

[felixbrucker]

there always is VertCoin (VTC) using Lyra2re, might be that?

[joblo]

there always is VertCoin (VTC) using Lyra2re, might be that?

VTC and all the others converted to Lyra2REv2. CTO seems to still use Lyra2RE but appears to have been abandoned
by its devs. I wonder what all those orders at Nicehash are about.

[felixbrucker]

oh indeed

[clipto]

Its monacoin (well, thats what I think)

[sp_]

Maybe it's the new Vertcoin classic and the monacoin classic? (Old fork's brought back to life?)

[joblo]

Maybe it's the new Vertcoin classic and the monacoin classic? (Old fork's brought back to life?)

Interesting speculation but I find no evidence of it.

[johnsmithx]

Coincidentally Nicehash's Lyra2RE stopped working for me since the weekend, I am getting "stratum_recv_line failed" from all 4 (usa,eu,hk,jp) of their servers. Can anybody please check it because I am going crazy:

cpuminer -a lyra2re -o stratum+tcp://lyra2re.usa.nicehash.com:3342

[felixbrucker]

it works for me, but i had a similar problem when i pointed multiple miners to nicehash, asked support, they block your address if more then a dozen ip's connect to their service for this address
if thats the case, use multiple addresses for each location

[felixbrucker]

@joblo just ran the test for windows:

- i5-3330 from ~60-70 to ~210
- A6-6400K from ~40 to ~60


amd overall not that impressive

[pallas]

kinda botnet detector

[joblo]

@joblo just ran the test for windows:

- i5-3330 from ~60-70 to ~210
- A6-6400K from ~40 to ~60


amd overall not that impressive

Did you compile yourself? I haven't seen CMB post their bins yet.

The A6 is not a real CPU, kinda like Celerons. Since they are new you would think they have all the
technology but they don't. They have some new tech, but not all so it's difficult to find an optimum
pre-compiled build.

Some AMD users that have compiled their own have found better performance by specifying the -march
directly instead of -march=native.

On a tangent I'm curious about the mining performance of the A6's IGPU. The CPU alone is weak but CPU+IGPU
might make up for it.

[johnsmithx]

it works for me, but i had a similar problem when i pointed multiple miners to nicehash, asked support, they block your address if more then a dozen ip's connect to their service for this address
if thats the case, use multiple addresses for each location

Yes you are absolutely right, I figured that they probably block IPs. I think I will try to install a stratum proxy on a clear IP, then all my nodes will connect to the proxy and only the proxy will make one single connection to Nicehash.

Btw if anyone is interested, here I made a simple one-liner to test all Nicehash's ports on all their IPs (requires netcat => apt-get install netcat):

Code:

for port in $(seq 3333 3354); do echo "port $port"; for ip in 37.58.117.214 159.8.42.123 159.253.151.98 198.11.195.136 192.155.218.242 119.81.240.198 161.202.120.197; do echo -n " $ip: "; result=$(echo '{"id": 1, "method": "mining.subscribe", "params": ["cpuminer-multi/1.3-dev"]}' | nc -w 2 $ip $port); [ -n "$result" ] && echo $result || echo "no response"; done; echo; done

Nicehash is the only one I found where I can mine Lyra2RE, it seems to be way most profitable CPU algo. I mine ether on GPUs and Lyra2RE on CPUs. I guess everybody else is just leaving all their CPUs idle when they mine with GPUs   Mining Lyra2RE makes 20-25% additional profit on my machines.

[joblo]

it works for me, but i had a similar problem when i pointed multiple miners to nicehash, asked support, they block your address if more then a dozen ip's connect to their service for this address
if thats the case, use multiple addresses for each location

Seems a little harsh, they should only block multiple IPs using the same BTC addr simultaneously. If all miners have
the same IP it's a farm not a botnet.

[felixbrucker]

yes its "more than a dozen *different* ips", same ip but different miner should not get blocked

i used the precompiled bin for hodlminer posted in the hodl ann thread, but the optimizations should be the same for your miner, wil lswitch to yours once cmb compiled them, i like yours better (though github would be really great to get latest sources on linux easily)

i use the A6 machine for media purposes (thats why apu), mainly all my cpu miners are running on normal computers built for something else but while idle are mining for fun

[joblo]

I did some playing around with AVX, trying to use it to xor arrays 256 bits at a time.
My results were not encouraging. I got code working but with occasional segfaults,
likely due to alignmnet issues. That should be fixable. The discouraging part is there was
no performance improvement. I tried it looping and inline but it didn't seem to make a difference.
I'll poke around some more but it doesn't look good.

Edit: There are a coule of reasons why I may not have seen any performance increase. It is possible,
likely, the process was memory bound in which case optimizing CPU performance wouldn't help.
The other possibility is the compiler may be auto-vectorising which occurs with the -O3 flag.
The code I vectorised was almost identical to the example of auto-vectorising.

The coding is also quite strange with load and store functions like assembly language instructions.
I would expect the compiler to do that transparently.

Edit2:

Things are looking up. I solved the alignment problem and made progress with performance. I've added 3%
to Lyra2 so far and I have a few functions left to convert. So far I've only implemented AVX2, I still have to do
AVX implementations of al functions. The improvements are to the lyra2 core so they should also help lyra2v2.

[johnsmithx]

yes its "more than a dozen *different* ips", same ip but different miner should not get blocked

Yes, all my machines have (obviously) each a different IP and they all connect to Nicehash using the same BTC address of mine. So that's the problem? So it would be ok if all those connections went from the same IP address (if I for example NATed them all through one single IP) but it's not ok if they all use their own real IPs and my real single BTC? So I should give each machine a different BTC address?

But why Nicehash does that? They have no reason to do such a blockage, it doesn't prevent anyone from doing anything, and if I actually did give each of my machine a different BTC address then I would be having many incoming little transactions and I would be loosing money on transaction fees. The Nicehash fee is proportional to the amount so that wouldn't change but when they send BTC they also have to pay a transaction fee (which is not proportional to the amount but fixed) for each transaction and that, I suppose, they deduce from the amount being sent (i.e. I am paying it) so with many little transactions the sum of their fees may stack up.

Well I think the best solution will be the stratum proxy. If I won't get that to work then I will just tunnel all those machines through one single IP.

[johnsmithx]

Things are looking up. I solved the alignment problem and made progress with performance. I've added 3%
to Lyra2 so far and I have a few functions left to convert. So far I've only implemented AVX2, I still have to do
AVX implementations of al functions. The improvements are to the lyra2 core so they should also help lyra2v2.

You are talking about Lyra2RE, right? So it will get sped up? Because so far tpruvot-cpuminer-multi's Lyra2RE is faster than yours by some 3.8% on my servers. I guess it might be because of -flto that I use with his but can't use with yours (doesn't compile)