CCminer(SP-MOD) Modded GPU kernels.

[djm34]

Winners don`t use drugs. My crypto kernals are profitable. Yours are not. Finish the plegde please...

lol, they are profitable to me  mostly done, just had to add the name of the donators

[djm34]

so basically you expect other dev to work on the opensource so to make your private miner faster
pallas says thank you to you 

I will study your new optimized Neoscrypt code and learn.
You should study my code as well. We use different ways to reach our goal. I do small compiler/assembly optimalizations while you are reinventing the algorithm. You should buy my private miner and analyze it. I will give you a discount of 0.05 BTC. 

I'm aware of a couple of  assembly code optimizing techniques I've used before but require an initimate knowledge
of the CPU (GPU in this case) architecture including memory interface, cache organization and execution environment.

I intend to give this a try with cpuminer-opt once I get up to speed on Intel architecture. Would you be interested in
doing it for cuda? I could explain the details.

yeah because it is well known that we just do random stuff 

LOL. Trial and error also works sometimes, the key is to figure out exactly why it works.

In my teaser ity's about code scheduling to maximize throughput by avoiding processor stalls
and maximizing superscalar operation.. It's not something that compilers can do easilly
because it requires so much anlysis and detailed understanding of the operation of
a CPU.

You may think I'm joking or boasting but I'm willing to discuss it openly and be subject to humiliation.

You may also wonder why I would do this. If the techniques work I would ask the developpers to
open some of their private code. Also I want to leverage the cuda expertise available to improve
the product for everyone.

I'll post one technique in a while that requires CPU support, but I have to dig out my old processor manuals
for a refresher. This one is something compilers should do since it is documented.

Edit: I've reviewed my manuals and checked out haswell optimization maual online and didn't see
anything at first glance that indicates they have the support to do the following:

allocate load

A special form of the load instruction will cause a line of cache to be allocated without accessing memory to fill it.
This is usefull when allocating mem and you don't care what data is in it. Memory isn't accessed unless the cache line
gets flushed for oother reasons. An if the bufer is used for a short time it may never need to access memory.

Example:

uint32_t* p = allocate_load( size )
crunch some data
free_and invalidate_cache ( &p )

What do you think?

may-be it would be better to discuss that on irc channel #ccminer

[joblo]

Im selling popcorn for 0.1 BTC with 500% faster pop.

But how are the temps and TDP?

[s7icky]

Im selling popcorn for 0.1 BTC with 500% faster pop.

But how are the temps and TDP?

My 980ti's run at 66 and i added extra butter

my popcorn brings all the miners to the yard cause my kernals are better then yalls.

i need another beer



why is no one working on x15 or x13..... 980ti speeds are not wut they should be meeee thinks.

[scryptr]

Im selling popcorn for 0.1 BTC with 500% faster pop.

But how are the temps and TDP?

My 980ti's run at 66 and i added extra butter

my popcorn brings all the miners to the yard cause my kernals are better then yalls.

i need another beer



why is no one working on x15 or x13..... 980ti speeds are not wut they should be meeee thinks.

HASHPOWER JUST DROPPED X13 and X15 ALGOS--

I am suspecting the coins associated with these algos are in the toilet further than others.       --scryptr

[s7icky]

Im selling popcorn for 0.1 BTC with 500% faster pop.

But how are the temps and TDP?

My 980ti's run at 66 and i added extra butter

my popcorn brings all the miners to the yard cause my kernals are better then yalls.

i need another beer



why is no one working on x15 or x13..... 980ti speeds are not wut they should be meeee thinks.

HASHPOWER JUST DROPPED X13 and X15 ALGOS--

I am suspecting the coins associated with these algos are in the toilet further than others.       --scryptr

zpool

0.3553*    x15

   EverGreen  coin i guess

[joblo]

Im selling popcorn for 0.1 BTC with 500% faster pop.

But how are the temps and TDP?

My 980ti's run at 66 and i added extra butter

my popcorn brings all the miners to the yard cause my kernals are better then yalls.

i need another beer



why is no one working on x15 or x13..... 980ti speeds are not wut they should be meeee thinks.

HASHPOWER JUST DROPPED X13 and X15 ALGOS--

I am suspecting the coins associated with these algos are in the toilet further than others.       --scryptr

X15 had a flare for a few days, I think the coin was evergreen. But yesterday it went wonky on zpool
it was the higherst paying algo and I was hashing away and submitting shares but nothing was
registering at the pool.

Edit: The problem is when an algo gets hot it's too late to shift the optimization focus to it. By the time
something is delievered the heat is off

[s7icky]

Im selling popcorn for 0.1 BTC with 500% faster pop.

But how are the temps and TDP?

My 980ti's run at 66 and i added extra butter

my popcorn brings all the miners to the yard cause my kernals are better then yalls.

i need another beer



why is no one working on x15 or x13..... 980ti speeds are not wut they should be meeee thinks.

HASHPOWER JUST DROPPED X13 and X15 ALGOS--

I am suspecting the coins associated with these algos are in the toilet further than others.       --scryptr

X15 had a flare for a few days, I think the coin was evergreen. But yesterday it went wonky on zpool
it was the higherst paying algo and I was hashing away and submitting shares but nothing was
registering at the pool.

Edit: The problem is when an algo gets hot it's too late to shift the optimization focus to it. By the time
something is delievered the heat is off

i think something wonky is going on with zpool reguardless... i dumped a bunch of x11  on it when it was high and i renteed real low.... payout wasent even close to what it was supoosed to be. I gonna dump 50mhs x15 on zpool for 24 hours and see if there is any fuckery going on.

[chrysophylax]

Winners don`t use drugs. My crypto kernals are profitable. Yours are not. Finish the plegde please...

lol, they are profitable to me  mostly done, just had to add the name of the donators

add names of donors? ... nice touch ...

#crysx

[s7icky]

Winners don`t use drugs. My crypto kernals are profitable. Yours are not. Finish the plegde please...

lol, they are profitable to me  mostly done, just had to add the name of the donators

add names of donors? ... nice touch ...

#crysx

I want my name added as king peanus

[flipclip]

djm very nice with the 30% increase.

[sp_]

[2016-01-24 10:24:24] GPU #3 Found nounce c0031ac7
[2016-01-24 10:24:25] GPU #0 Found nounce 000bbb86
[2016-01-24 10:24:30] GPU #2 Found nounce 8025d939
[2016-01-24 10:24:40] GPU #1 Found nounce 4029bd92
[2016-01-24 10:24:42] GPU #0 Found nounce 00aab9f6
[2016-01-24 10:24:42] GPU #0: GeForce GTX 970, 623
[2016-01-24 10:24:43] GPU #0 Found nounce 00bb9b78
[2016-01-24 10:24:43] GPU #0: GeForce GTX 970, 599
[2016-01-24 10:24:55] GPU #1 Found nounce 40522fa2
[2016-01-24 10:24:55] GPU #1: GeForce GTX 750 Ti, 169
[2016-01-24 10:25:00] GPU #0 Found nounce 015574ec
[2016-01-24 10:25:00] GPU #0: result for nonce $015574EC does not validate on CP
U!
[2016-01-24 10:25:02] GPU #2 Found nounce 80d8d5c1
[2016-01-24 10:25:02] GPU #2: GeForce GTX 960, 366
[2016-01-24 10:25:11] GPU #0 Found nounce 01c362db
[2016-01-24 10:25:11] GPU #0: result for nonce $01C362DB does not validate on CP
U!
[2016-01-24 10:25:29] GPU #0 Found nounce 02667a39
[2016-01-24 10:25:29] GPU #0: GeForce GTX 970, 619

[sp_]

DJM34's neoscrypt.

My testrig is showing +15.5 % (gtx 970, 2x 960, 1 750ti)
With a few validation errors
But I have compiled with cuda 7.5

[sp_]

cuda 6.5 is bether:

the rig is up (+20%)

[2016-01-24 10:40:56] Binding thread 3 to cpu 3 (mask
[2016-01-24 10:40:59] GPU #3 Found nounce c0031ac7
[2016-01-24 10:41:00] GPU #0 Found nounce 000bbb86
[2016-01-24 10:41:05] GPU #2 Found nounce 8025d939
[2016-01-24 10:41:13] GPU #0 Found nounce 008deedf
[2016-01-24 10:41:13] GPU #0: result for nonce $008DEEDF does not validate on CP
U!
[2016-01-24 10:41:14] GPU #1 Found nounce 4029bd92
[2016-01-24 10:41:14] GPU #0 Found nounce 009955c5
[2016-01-24 10:41:14] GPU #0: GeForce GTX 970, 663
[2016-01-24 10:41:16] GPU #0 Found nounce 00aab9f6
[2016-01-24 10:41:16] GPU #0: GeForce GTX 970, 658
[2016-01-24 10:41:16] GPU #0 Found nounce 00abd7c9
[2016-01-24 10:41:16] GPU #0: result for nonce $00ABD7C9 does not validate on CP
U!
[2016-01-24 10:41:18] GPU #0 Found nounce 00bb9b78
[2016-01-24 10:41:18] GPU #0: GeForce GTX 970, 636
[2016-01-24 10:41:28] GPU #0 Found nounce 01237c6c
[2016-01-24 10:41:28] GPU #0: result for nonce $01237C6C does not validate on CP
U!
[2016-01-24 10:41:30] GPU #1 Found nounce 40522fa2
[2016-01-24 10:41:30] GPU #1: GeForce GTX 750 Ti, 172
[2016-01-24 10:41:34] GPU #2 Found nounce 80d8d5c1
[2016-01-24 10:41:34] GPU #2: GeForce GTX 960, 396
[2016-01-24 10:41:49] GPU #0 Found nounce 01f599c2
[2016-01-24 10:41:49] GPU #0: result for nonce $01F599C2 does not validate on CP
U!

[djm34]

DJM34's neoscrypt.

My testrig is showing +15.5 % (gtx 970, 2x 960, 1 750ti)
With a few validation errors
But I have compiled with cuda 7.5

your release 78 is so crappy that I lose even 50kh/s...  most of that is on you (as usual)
but I was asked to use it so...

[sp_]

My 980ti is doing 835khash when compiled with cuda 6.5.

Good job.

[bensam1231]

so basically you expect other dev to work on the opensource so to make your private miner faster
pallas says thank you to you 

I will study your new optimized Neoscrypt code and learn.
You should study my code as well. We use different ways to reach our goal. I do small compiler/assembly optimalizations while you are reinventing the algorithm. You should buy my private miner and analyze it. I will give you a discount of 0.05 BTC. 

that's your problem, you need to study my code to get something out, while if you knew what you were doing it is the original code would have to read to make it easier for the gpu.
Basically you don't get any real upgrade because you don't look at what the code does, you are just trying random stuff expecting it will work based on what and other devs wrote... well good luck with that

That is basically how science works in a nutshell. You build off other peoples research. If they get past hurdles you couldn't it gives you ideas and different ways of looking at things to help surpass their work. Remaking the wheel is stupid and it's actually pretty asinine that developers assume everyone should learn from the ground up without assistance besides wizard style 'hints'. This is also the fun that's entailed with 'nix when I was using it. People would hint at what I needed to do instead of tell me what I needed to do and why to make it seem like their knowledge has more meaning.

I guess it makes sense though. As soon as you help someone learn they can build off your stuff and make it better, which pretty much obsoletes your work, but that's the way of the world and that's why you're listed in credits.

Ethereum to the moon. that's what i'm seeing!

Damn i'm so happy that i own AMD cards 

Except you owned them for a year and a half in which Nvidia was more profitable (sometimes AMD wasn't profitable at all). Ethereum is one coin, it is definitely profitable right now, betting the farm on it isn't a wise choice.

[djm34]

so basically you expect other dev to work on the opensource so to make your private miner faster
pallas says thank you to you  

I will study your new optimized Neoscrypt code and learn.
You should study my code as well. We use different ways to reach our goal. I do small compiler/assembly optimalizations while you are reinventing the algorithm. You should buy my private miner and analyze it. I will give you a discount of 0.05 BTC.  

that's your problem, you need to study my code to get something out, while if you knew what you were doing it is the original code would have to read to make it easier for the gpu.
Basically you don't get any real upgrade because you don't look at what the code does, you are just trying random stuff expecting it will work based on what and other devs wrote... well good luck with that

That is basically how science works in a nutshell. You build off other peoples research. If they get past hurdles you couldn't it gives you ideas and different ways of looking at things to help surpass their work. Remaking the wheel is stupid and it's actually pretty asinine that developers assume everyone should learn from the ground up without assistance besides wizard style 'hints'. This is also the fun that's entailed with 'nix when I was using it. People would hint at what I needed to do instead of tell me what I needed to do and why to make it seem like their knowledge has more meaning.

no it isn't how science works.
Yes you build on other people works, but you do it with an understanding of what has been done before and the inner concept behind... and
once you have reached a dead end (optimization wise...) you get back to the basis.

And in the case of neoscrypt if you don't see that fastkdf is just a massive rotation, there isn't much you can do on top of what has been done...

[Eliovp]

Ethereum to the moon. that's what i'm seeing!

Damn i'm so happy that i own AMD cards  

Except you owned them for a year and a half in which Nvidia was more profitable (sometimes AMD wasn't profitable at all). Ethereum is one coin, it is definitely profitable right now, betting the farm on it isn't a wise choice.

I have never had a moment where nvidia was more profitable. Though, i have to say, i have had almost always access to private kernels. So that did help.

True it is "VERY" profitable right now. And there's another one coming. "Decred", look it up, check the community behind it. Read about it.

Altcoin mining will and stay profitable for at least a year (in my opinion).


Btw. Add some cards          --- >           check my sig                l
                                                                                             l
                                                                                             l
                                                                                             V

[go6ooo1212]

Guys , is there any optimization on ETH for Maxwell GPUs? Last releases are much slower than the AMD cards...