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

[stevascha]

Hi Joblo! 3.7.8 avx-sha is better than ever!

Im mining m7m algo, but I mine with both GPUs and Ryzen. The 16thread mining are slowing down the GPUs mining.

How could I set CPU affinity for all threads but CPU0 (or threads 0 and 1)?

I searched for an option to do it, but I havent found nothing  


EDIT:'

I found it:
https://phempshall.github.io/cpuminer-affinity-setter/

works

i wanna ask, for ryzen 7
do you use  --cpu-affinity 255 --cpu-priority 4? or --cpu-affinity 255 --cpu-priority 2
what's different?

[1714016303]

1714016303

[1714016303]

1714016303

[1714016303]

1714016303

[joblo]

Hi Joblo! 3.7.8 avx-sha is better than ever!

Im mining m7m algo, but I mine with both GPUs and Ryzen. The 16thread mining are slowing down the GPUs mining.

How could I set CPU affinity for all threads but CPU0 (or threads 0 and 1)?

I searched for an option to do it, but I havent found nothing  


EDIT:'

I found it:
https://phempshall.github.io/cpuminer-affinity-setter/

works

i wanna ask, for ryzen 7
do you use  --cpu-affinity 255 --cpu-priority 4? or --cpu-affinity 255 --cpu-priority 2
what's different?

First use hex because it's easier to map the bits to cores. 255 = 0x00ff = 0b0000000011111111
Only 8 bits/cores for 16 threads?
My previous post showed how to run 14 miner threads leaving one core (2 threads) free.
Some users when mining 8 threads have reported better performance with affinity 0x5555.

Second, priority isn't very useful unless you're also running background tasks and want to
prioritize between them and mining.

[guytechie]

Now that m7m is back (hashrefinery), some m7m numbers for cpuminer-opt v3.7.8v2 (maybe should call it 3.7.8.1, lol).

Ryzen Threadripper 1950X @ 3.7 GHz

sse2
545 kH/s

avx-sha
565 kH/s

4way-sha
545 kH/s

aes-avx
550 kH/s

aes-avx2
535 kH/s

aes-sse42
516 kH/s

sse42
580 kH/s

[joblo]

Now that m7m is back (hashrefinery), some m7m numbers for cpuminer-opt v3.7.8v2 (maybe should call it 3.7.8.1, lol).

Ryzen Threadripper 1950X @ 3.7 GHz

sse2
545 kH/s

avx-sha
565 kH/s

4way-sha
545 kH/s

aes-avx
550 kH/s

aes-avx2
535 kH/s

aes-sse42
516 kH/s

sse42
580 kH/s

Those results are very suspicious, Particularly the fastest is sse42 and the slowest is aes-sse42.There is no aes
in m7m so they should be identical. Also the sha builds are not significantly faster than the equivalent non-sha,
but are significantly slower than sse42.

I don't know why but I don't think it's due to mislabeled files.

[guytechie]

Now that m7m is back (hashrefinery), some m7m numbers for cpuminer-opt v3.7.8v2 (maybe should call it 3.7.8.1, lol).

Ryzen Threadripper 1950X @ 3.7 GHz

sse2
545 kH/s

avx-sha
565 kH/s

4way-sha
545 kH/s

aes-avx
550 kH/s

aes-avx2
535 kH/s

aes-sse42
516 kH/s

sse42
580 kH/s

Those results are very suspicious, Particularly the fastest is sse42 and the slowest is aes-sse42.There is no aes
in m7m so they should be identical. Also the sha builds are not significantly faster than the equivalent non-sha,
but are significantly slower than sse42.

I don't know why but I don't think it's due to mislabeled files.

Probably due to background processes?  This *is* Windows we're talking about.

The first time I ran aes-sha I got 607 kH/s, but I could never reproduce it.  Ran for a few minutes for each executable.

[alucard20724]

I'm trying to run lyraZ2 on an i7-7820X with 4way, avxSha, and 4waysha.  using version 3.7.8 and win10

i get constant rejects from the pool "reject reason: low difficulty share of 0.000005" or smaller
from miningpoolhub

cpu is hashing at 1.3MH/s

i tried to manually lower the difficulty to d=0.01 but didn't seem to take it.

any suggestions?

[ss10miner]

Perfect!  CPUMINER now is more and more stronger.  I will test it with YTN mining.

[jbmustaq]

Hi Dev,

Can you please let me know the steps to install cpuminer in centos 6 as I am getting error.

algo/m7m.c:369: warning: implicit declaration of function ‘mpz_clears’
make[2]: *** [algo/cpuminer-m7m.o] Error 1
make[2]: *** Waiting for unfinished jobs....
mv -f algo/.deps/cpuminer-lbry.Tpo algo/.deps/cpuminer-lbry.Po
mv -f .deps/cpuminer-util.Tpo .deps/cpuminer-util.Po
mv -f .deps/cpuminer-cpu-miner.Tpo .deps/cpuminer-cpu-miner.Po
make[2]: Leaving directory `/root/cpuminer-opt'
make[1]: *** [all-recursive] Error 1
make[1]: Leaving directory `/root/cpuminer-opt'
make: *** [all] Error 2
strip: 'cpuminer': No such file
[root@host cpuminer-opt]#

[joblo]

any suggestions?

Yes. Read a few posts back, it's been discussed.

[joblo]

Hi Dev,

Can you please let me know the steps to install cpuminer in centos 6 as I am getting error.

algo/m7m.c:369: warning: implicit declaration of function ‘mpz_clears’
make[2]: *** [algo/cpuminer-m7m.o] Error 1
make[2]: *** Waiting for unfinished jobs....
mv -f algo/.deps/cpuminer-lbry.Tpo algo/.deps/cpuminer-lbry.Po
mv -f .deps/cpuminer-util.Tpo .deps/cpuminer-util.Po
mv -f .deps/cpuminer-cpu-miner.Tpo .deps/cpuminer-cpu-miner.Po
make[2]: Leaving directory `/root/cpuminer-opt'
make[1]: *** [all-recursive] Error 1
make[1]: Leaving directory `/root/cpuminer-opt'
make: *** [all] Error 2
strip: 'cpuminer': No such file
[root@host cpuminer-opt]#

You didn't actually show the error but Centos6 is too old.

[nizzuu]

-t 14 --cpu-affinity 0xfffd should mine on logical cores 2 through 15 leaving cores 0 & 1 free.
But I'm not sure threads 0 & 1 are mapped to the same physical core. You might have to
play with the affinity mask to isolate 2 threads on the same physical core.
Other possibilities include 0xfefe (threads 0 & and 0xffee (threads 0 & 4). I can't think of
any other way they could be mapped. Please let us know which one works.

For all: as well as using https://phempshall.github.io/cpuminer-affinity-setter/ you may use this affinity calculator: http://www.gatwick-fsg.org.uk/affinitymask.aspx

If you want to isolate virtual cores on physical cores, you may use (I do) this old tool: https://developer.amd.com/resources/articles-whitepapers/processor-and-core-enumeration-using-cpuid/

So, download coreenumcodesample.zip out there, unzip, create bat file to launch:

enum.exe -more
pause

You will get the info - which cores are physical, and which ones are virtual. This info is very useful for HT cpus.

Note: I have never tested it on AMD cpus, but works ok for skylake/kaby lake/haswell/ivy bridge/skylake-x/broadwell-ep.

joblo may attach these tools to the 1st post (in a smaller size i guess) so everybody could know.

[stevascha]

Hi Joblo! 3.7.8 avx-sha is better than ever!

Im mining m7m algo, but I mine with both GPUs and Ryzen. The 16thread mining are slowing down the GPUs mining.

How could I set CPU affinity for all threads but CPU0 (or threads 0 and 1)?

I searched for an option to do it, but I havent found nothing  


EDIT:'

I found it:
https://phempshall.github.io/cpuminer-affinity-setter/

works

i wanna ask, for ryzen 7
do you use  --cpu-affinity 255 --cpu-priority 4? or --cpu-affinity 255 --cpu-priority 2
what's different?

First use hex because it's easier to map the bits to cores. 255 = 0x00ff = 0b0000000011111111
Only 8 bits/cores for 16 threads?
My previous post showed how to run 14 miner threads leaving one core (2 threads) free.
Some users when mining 8 threads have reported better performance with affinity 0x5555.

Second, priority isn't very useful unless you're also running background tasks and want to
prioritize between them and mining.

i didn't see what a different using hexa or dec
im try 255, its running well

1700x yescryptr16
avx-sha around 1300khs (many reject)
4way-sha around 1200khs (many reject)
avx2 around 1100khs (many reject)
the reject appears after difficulty pool has changed

im not tested long day because have ram problem stability (3200mhz)

[joblo]

First use hex because it's easier to map the bits to cores. 255 = 0x00ff = 0b0000000011111111
Only 8 bits/cores for 16 threads?
My previous post showed how to run 14 miner threads leaving one core (2 threads) free.
Some users when mining 8 threads have reported better performance with affinity 0x5555.

Second, priority isn't very useful unless you're also running background tasks and want to
prioritize between them and mining.

i didn't see what a different using hexa or dec
im try 255, its running well

1700x yescryptr16
avx-sha around 1300khs (many reject)
4way-sha around 1200khs (many reject)
avx2 around 1100khs (many reject)
the reject appears after difficulty pool has changed

im not tested long day because have ram problem stability (3200mhz)

I didn't say there was a difference with hex, I said it's easier to understand. As an example
which cores are used with affinity= 43690?

If you think it's running well with 16 threads and affinity 255 then you don't understand,
That's only 8 cores for 16 threads meaning you have 8 cores idle and 8 cores with 2 threads each.

The rejects and the share flood are pool issues.

[moreAndMoreAndMore]

Hi.

I tried multiple times to use the API feature but I think I didn't get how it works.

I tried to open in Chrome http://127.0.0.1:4048 but I received "ERR_EMPTY_RESPONSE", same if I try http://127.0.0.1:4048/api
I also tried with telnet 127.0.0.1 4048 but I don't receive any response there as well.

I am using the release version for Windows x64 3.7.8

[joblo]

Hi.

I tried multiple times to use the API feature but I think I didn't get how it works.

I tried to open in Chrome http://127.0.0.1:4048 but I received "ERR_EMPTY_RESPONSE", same if I try http://127.0.0.1:4048/api
I also tried with telnet 127.0.0.1 4048 but I don't receive any response there as well.

I am using the release version for Windows x64 3.7.8

You need to enter a command in telnet to get anything, start with help.

[joblo]

cpuminer-opt-3.7.9

Partial 4way optimizations for veltor, skunk, polytimos, lyra2z.
Additional 4way optimizations for X algos.
New algo yescryptr8 for BitZeny, not to be confused with original
yescrypt Globalboost-Y.

https://github.com/JayDDee/cpuminer-opt/releases/tag/v3.7.9

This release marks a milestone for cpuminer-opt. All 11 functions of x11 are
now optimized. 5 have 4-way AVX2, 2 have serial AVX2, 3 have AES & SSE2
and 1 has only SSE2.

[alucard20724]

cpuminer-opt-3.7.9

Partial 4way optimizations for veltor, skunk, polytimos, lyra2z.
Additional 4way optimizations for X algos.
New algo yescryptr8 for BitZeny, not to be confused with original
yescrypt Globalboost-Y.

https://github.com/JayDDee/cpuminer-opt/releases/tag/v3.7.9

This release marks a milestone for cpuminer-opt. All 11 functions of x11 are
now optimized. 5 have 4-way AVX2, 2 have serial AVX2, 3 have AES & SSE2
and 1 has only SSE2.

nice... running 4way now with lyra2z on i7-7820X... shares are being accepted on miningpoolhub.

thanks

[joblo]

cpuminer-opt-3.7.9

Partial 4way optimizations for veltor, skunk, polytimos, lyra2z.
Additional 4way optimizations for X algos.
New algo yescryptr8 for BitZeny, not to be confused with original
yescrypt Globalboost-Y.

https://github.com/JayDDee/cpuminer-opt/releases/tag/v3.7.9

This release marks a milestone for cpuminer-opt. All 11 functions of x11 are
now optimized. 5 have 4-way AVX2, 2 have serial AVX2, 3 have AES & SSE2
and 1 has only SSE2.

nice... running 4way now with lyra2z on i7-7820X... shares are being accepted on miningpoolhub.

thanks

How does the hash rate compare? I saw less than 1% improvement on i7-6700K.

[car1999]

So many exe files, which one is best for ryzen 1700?

[alucard20724]

cpuminer-opt-3.7.9

Partial 4way optimizations for veltor, skunk, polytimos, lyra2z.
Additional 4way optimizations for X algos.
New algo yescryptr8 for BitZeny, not to be confused with original
yescrypt Globalboost-Y.

https://github.com/JayDDee/cpuminer-opt/releases/tag/v3.7.9

This release marks a milestone for cpuminer-opt. All 11 functions of x11 are
now optimized. 5 have 4-way AVX2, 2 have serial AVX2, 3 have AES & SSE2
and 1 has only SSE2.

nice... running 4way now with lyra2z on i7-7820X... shares are being accepted on miningpoolhub.

thanks

How does the hash rate compare? I saw less than 1% improvement on i7-6700K.

I'm getting 1.36MH/s for 4waysha as apposed to only 1.28MH/s for avx2 and 800KH/s for avx for my i7-7820X.   I just got this cpu this weekend.  I'm currently running the test on my i7-5930K (AVX2@800KH/s with ver 3.7.8 ), and i7-7700K (AVX2@680KH/s with ver 3.7.8 )... these are all at stock speeds with no overclocks added.