That was with 2 1070s.

Interesting. It seems you're right but only because the compiler was upgraded, otherwise the AVX2 code would have been skipped:


I agree the way forward would be to upgrade all of gcc's dependencies: rpm -q --requires gcc

It's not so trivial anymore.

It might be worthwhile to focus the problem a little more. I suggest trying to compile with a lesser arch
like core2 to see if you can, then try to other arches until you identify the one that fails.

The problem seems to be with the compile environment but it could also be your CPU. If it's an AMD it
adds another dimension because their implementation of some features is incompatible with Intel.
The RELEASE_NOTES have some tips.

You can try moving the pragma directives outside the function to see if that works.
If it's trivial to support gcc4.4 I'll make the change in the next release.

OK I'm a smartass. My cards don't throttle when I raise the clock so I get a directly proportional increase
in hashrate with all other settings, except fan, stock. As the first reply suggested, you need to find out why you're
cards are throttling.

But it seems you're mind is already made up, it just doesn't work. So why should anyone bother discussing it
intellegently with a closed mind?

ARM is not supported.

I don't understand the error, that code did not change. How did you compile?

cpuminer-opt-3.6.6 is released.

git: https://github.com/JayDDee/cpuminer-opt

tarball: https://drive.google.com/file/d/0B0lVSGQYLJIZV2NBRjF5bVJUeHc/view?usp=sharing

Windows binaries: https://drive.google.com/file/d/0B0lVSGQYLJIZNHhCeE5iUHluUUE/view?usp=sharing

New in v3.6.6

added tribus algo for Denarius (DNR).

configure removed from .gitignore. This should allow source cloned from git to compile
on Windows/mingw when aclocal is not available.

Fixed CPU temperature monitoring on some CPUs (Linux only).

Fixed a compile error on FreeBSD. FreeBSD is not officially supported, ymmv.

I hope you reported it to Ebay.

I found the announcement, it would have been nice if you had posted the link.

https://www.amd.com/en/ryzen-pro

It's all marketing speak so I have no idea what it means technically. AES_NI is already a 128 bit encryption
and decryption engine so I have no idea what improvements are implied, maybe a faster implementation.

Another implied improvement is the mention of low-latency cache. Intel cache performance is currently better
than AMD so maybe the're catching up. That combined with the larger-than-Intel cache size could further give
an edge to AMD in the CPU market.

With Ryzen they have pulled ahead of Intel with threads, price, cache size, HW SHA. Between Threadripper
(4 channel DDR4, more threads, even bigger cache) and whatever improvements come in the Ryzen Pro there's
not much left where Intel has an edge.

It's nice to see some real competition in the CPU market. It will be interesting to see how Intel will respond.

On a bit of a tangent...

I am still curious about AVX2 performance on Ryzen. I have read that their implementation isn't native but I haven't
seen any performance comparisons. If anyone has a Ryzen I would be interested in a performance comparison of
AVX vs AVX2 on algos that have AVX2 optimizations.

What did you do to get it to work? Does build.sh work or did you change some options?

Missing gmp dev package.

The stratum difficulty is too high for CPU mining. If the pool uses vardiff it should adjust over time. Some pools
offer a low-diff port and others (like yiimp) allow the diff to be specified in the command line password.

Try reading and following the instructions in RELEASE_NOTES. When you have problems it helps if you provide a proper
description including what you did and what happened when you did it.

./cpuminer -h

It's still likely a power issue even if not a PSU issue. Make sure you haven't overloaded any power cables
(avoid using splitters) then try removing one GPU. If that doesn't solve it start looking at your house supply.
Do lights dim when you start the miner?

Nothing in software (drivers) should cause a sudden power down.

A customized array of low power CPUs would beat a desktop on power efficiency. But that's not
a smartphone and Android wouldn't be the OS of choice.

A smartphone carries too much baggage (HW & SW) not related to mining and you need
many of them to match the performance of a basic desktop CPU. As I said it's only of intrerest to botnets.

I've never heard of Perk and can't find any info about it. What algo did it use?

Just what is a smartphone coin, exactly? Do you mean a coin that can be mined on a smartphone?
There is no coin property that makes it attractive to mine on a smartphone.

Android and mining don't go together. Android is an OS designed for low power mobile devices.
It is not designed for continuous high power usage and neither are the devices than run it.

Mining on an Android device is like using a mini car to carry heavy loads, it's stupid.

Only botnets are interested in Android mining.

AES-NI is one of the few advantages a CPU has over a GPU for mining. Most algos that don't use AES are even less competitive
compared to GPU mining. Just mine the most profitable algo on your CPU regardless of whether it uses AES.

Pretty impressive CPU for mining. In addition to everything in the R7 it also has 4 channel memory.
I also like that the L3 cache scales with the number of cores. The 16 core Threadripper should perform
about double the 8 core R7 at the same clock speed. It'll be interesting to see how the price compares.