Bitcoin Forum
December 07, 2016, 02:46:31 PM *
News: To be able to use the next phase of the beta forum software, please ensure that your email address is correct/functional.
 
   Home   Help Search Donate Login Register  
Pages: [1] 2 »  All
  Print  
Author Topic: Bitcoin x86 for Windows  (Read 3402 times)
Olipro
Member
**
Offline Offline

Activity: 70


View Profile
July 26, 2010, 08:17:20 AM
 #1

Figured I'd make a new topic since anyone on x86 Windows probably won't even bother to read the x64 thread, however, since you're here, I suggest you read page 5 of that thread after reading this.

OK, so essentially I've compiled 2 builds of Bitcoin with the new SHA caching optimisation, one build has full optimisation for the SSE instruction sets and will require a modern CPU, and the other is compiled without any SSE optimisation at all and should therefore run on pretty much any CPU capable of running XP or higher. The SSE version is a bit faster than the non-SSE version and both are inferior to the x64 builds, if you have a 64-bit OS, don't bother with these.

Beware however that the libeay32.dll that I included may have SSE and therefore, if you can't get either to run on your machine, replace that DLL with the one bundled with the stock Bitcoin

You can grab the builds here
1481121991
Hero Member
*
Offline Offline

Posts: 1481121991

View Profile Personal Message (Offline)

Ignore
1481121991
Reply with quote  #2

1481121991
Report to moderator
Advertised sites are not endorsed by the Bitcoin Forum. They may be unsafe, untrustworthy, or illegal in your jurisdiction. Advertise here.
FreeMoney
Legendary
*
Offline Offline

Activity: 1246


Strength in numbers


View Profile WWW
July 26, 2010, 11:48:14 AM
 #2

Amazing. ~1250 up to ~2200.

Is this for real? Other machine from ~600 to ~1350

Play Bitcoin Poker at sealswithclubs.eu. We're active and open to everyone.
BlackEye
Newbie
*
Offline Offline

Activity: 17


View Profile
July 26, 2010, 12:12:41 PM
 #3

I don't see the source code included with any of your builds.  It would be great to be able to independently verify and compile the sources.

1CLJbMgYsaRUbcN2LwQDx2WkG3NJJ2KyJr
Olipro
Member
**
Offline Offline

Activity: 70


View Profile
July 26, 2010, 12:13:45 PM
 #4

I don't see the source code included with any of your builds.  It would be great to be able to independently verify and compile the sources.

If you don't trust my builds, don't use them, if you want to set up your own build environment, do the work yourself, all the source code in the app is publically available.
BlackEye
Newbie
*
Offline Offline

Activity: 17


View Profile
July 26, 2010, 12:38:27 PM
 #5

No need to be hostile.  I do have a build environment set up, but I am completely unable to compile your changes without your source code.  This just sends up a big red flag for me as you've obviously modified the source for some of your builds and are unwilling to provide those changes for peer review.  I think this goes against the spirit of open source.  Modified binary only releases don't help progress the software and create an unnecessary dependency on an individual to provide those binaries.

1CLJbMgYsaRUbcN2LwQDx2WkG3NJJ2KyJr
Olipro
Member
**
Offline Offline

Activity: 70


View Profile
July 26, 2010, 01:04:41 PM
 #6

No need to be hostile.  I do have a build environment set up, but I am completely unable to compile your changes without your source code.  This just sends up a big red flag for me as you've obviously modified the source for some of your builds and are unwilling to provide those changes for peer review.  I think this goes against the spirit of open source.  Modified binary only releases don't help progress the software and create an unnecessary dependency on an individual to provide those binaries.

Crypto++ 5.6.0: http://www.cryptopp.com/
Cached SHA256: http://pastebin.com/rJAYZJ32 (although I'm pretty sure this is publically submitted elsewhere, I was linked to it on IRC)
knightmb
Sr. Member
****
Offline Offline

Activity: 308


Timekoin - Save Electricity, Don't Waste It!


View Profile WWW
July 26, 2010, 02:15:21 PM
 #7

Thanks for thinking about those still on the 32bit chips  Grin

sgtstein
Member
**
Offline Offline

Activity: 61


View Profile
July 26, 2010, 02:28:25 PM
 #8

Or those with servers stuck on 32-bit OSes. :-D
Quad core Xeon@1.6GHz
Stock: 1100kh/s
Full Opt: 2600kh/s

THANKS!
BitCoinPurse
Jr. Member
*
Offline Offline

Activity: 34



View Profile
July 26, 2010, 02:53:27 PM
 #9

More than doubled my khash/sec from 800 to 1900.

AMD Phenon II X2 550

My Coin Purse is sagging!  13WXS46x634zook2MHSJbc7gwdrXK1JLq4
Olipro
Member
**
Offline Offline

Activity: 70


View Profile
July 26, 2010, 03:42:01 PM
 #10

Or those with servers stuck on 32-bit OSes. :-D
Quad core Xeon@1.6GHz
Stock: 1100kh/s
Full Opt: 2600kh/s

THANKS!

BitCoins are always appreciated, address in my sig
satoshi
Founder
Sr. Member
*
qt
Offline Offline

Activity: 364


View Profile
July 27, 2010, 01:29:42 AM
 #11

Crypto++ 5.6.0: http://www.cryptopp.com/
Cached SHA256: http://pastebin.com/rJAYZJ32 (although I'm pretty sure this is publically submitted elsewhere, I was linked to it on IRC)
I added the cached SHA256 state idea to the SVN, rev 113.  The speedup is about 70%.  I credited it to tcatm based on your post in the x64 thread.

I can compile the Crypto++ 5.6.0 ASM SHA code with MinGW but as soon as it runs it crashes.  It says its for MASM (Microsoft's assembler) and the sample command line they give looks like Visual C++.  Does it only work with the MSVC and Intel compilers?
knightmb
Sr. Member
****
Offline Offline

Activity: 308


Timekoin - Save Electricity, Don't Waste It!


View Profile WWW
July 27, 2010, 02:01:11 AM
 #12

Or those with servers stuck on 32-bit OSes. :-D
Quad core Xeon@1.6GHz
Stock: 1100kh/s
Full Opt: 2600kh/s

THANKS!

BitCoins are always appreciated, address in my sig
I just sent you a wad of coin  Wink

dkaparis
Jr. Member
*
Offline Offline

Activity: 53


View Profile
July 27, 2010, 09:59:06 AM
 #13

I can compile the Crypto++ 5.6.0 ASM SHA code with MinGW but as soon as it runs it crashes.  It says its for MASM (Microsoft's assembler) and the sample command line they give looks like Visual C++.  Does it only work with the MSVC and Intel compilers?

I recently also made an attempt to use Crypto++ 5.6.0 (as an external library) instead of the old integrated code, with the same result - it crashed on the first invocation of CryptoPP::SHA256::Transform. Only I built everything with VC++ 2008. I haven't investigated in depth, but someone mentioned Crypto++'s routine required aligned input - maybe that's the reason, or we may have other bug we don't figure.
BlackEye
Newbie
*
Offline Offline

Activity: 17


View Profile
July 27, 2010, 12:43:35 PM
 #14

You need to change the assembly instructions that require aligned input to unaligned - http://bitcointalk.org/index.php?topic=453.msg5774#msg5774, or make the blocks that are being hashed aligned.  I haven't tried yet, but this assembly code combined with the state caching modification should make this blazing fast.

1CLJbMgYsaRUbcN2LwQDx2WkG3NJJ2KyJr
satoshi
Founder
Sr. Member
*
qt
Offline Offline

Activity: 364


View Profile
July 27, 2010, 06:27:30 PM
 #15

I was able to integrate the SHA256 functionality from Crypto++ 5.6.0 into Bitcoin.  This is the fastest SHA256 yet using the SSE2 assembly code.  Since Bitcoin was sending unaligned data to the block hash function, I had to change the MOVDQA instruction to MOVDQU.

I think using the SHA256 functionality from Crypto++ 5.6.0 is the way forward right now.
I added a subset of the Crypto++ 5.6.0 library to the SVN.  I stripped it down to just SHA and 11 general dependency files.  There shouldn't be any other crypto in there other than SHA.

I aligned the data fields and it worked.  The ASM SHA-256 is about 48% faster.  The combined speedup is about 2.5x faster than version 0.3.3.

I guess it's using SSE2.  It automatically sets its build configuration at compile time based on the compiler environment.

It looks like it has some SSE2 detection at runtime, but it's hard to tell if it actually uses it to fall back if it's not available.  I want the release builds to have SSE2.  SSE2 has been around since the first Pentium 4.  A Pentium 3 or older would be so slow, you'd be wasting your electricity trying to generate on it anyway.

This is SVN rev 114.
knightmb
Sr. Member
****
Offline Offline

Activity: 308


Timekoin - Save Electricity, Don't Waste It!


View Profile WWW
July 27, 2010, 06:36:03 PM
 #16

...
I guess it's using SSE2.  It automatically sets its build configuration at compile time based on the compiler environment.

It looks like it has some SSE2 detection at runtime, but it's hard to tell if it actually uses it to fall back if it's not available.  I do want the release builds to have SSE2.  SSE2 has been around since the first Pentium 4.  A Pentium 3 or older would be so slow, you'd be wasting your electricity trying to generate on it anyway.
I've got some older machines (for the windows client and linux clients) to test with that don't support SSE2. Mainly if you try to run them, the program just crashes when I tried some of the experimental builds here, but I'll be glad to test some future official builds to see if the "detect SSE2" part works or the program goes belly up.

satoshi
Founder
Sr. Member
*
qt
Offline Offline

Activity: 364


View Profile
July 27, 2010, 07:47:42 PM
 #17

OK, thanks.  I'd also like to know if it runs fine as long as you don't turn on Generate.  You'd think as long as it doesn't actually execute any SSE2 instructions, it would still load.  At least Pentium 3's could run it without generating.
knightmb
Sr. Member
****
Offline Offline

Activity: 308


Timekoin - Save Electricity, Don't Waste It!


View Profile WWW
July 27, 2010, 08:09:54 PM
 #18

OK, thanks.  I'd also like to know if it runs fine as long as you don't turn on Generate.  You'd think as long as it doesn't actually execute any SSE2 instructions, it would still load.  At least Pentium 3's could run it without generating.
I thought the SSE2 mode would just be for those those with processors that support it, so far the release client runs just fine on older PI, PII, PIII machines, just very slow on the khash/s part. For example, a PIII 933MHz Linux machine can muster about 125 khash/s, some old 1.1GHz Celerons I have can reach 172 khash/s

I wouldn't want to exclude those that have older processors from at least trying to generate coin, hehe.

BlackEye
Newbie
*
Offline Offline

Activity: 17


View Profile
July 27, 2010, 08:47:10 PM
 #19

I added a subset of the Crypto++ 5.6.0 library to the SVN.  I stripped it down to just SHA and 11 general dependency files.  There shouldn't be any other crypto in there other than SHA.

I think you should be able to pare it down to at most 5 files from Crypto++, config.h, cpu.h, cpu.cpp, sha.h, and sha.cpp.  Take a look at the zip file I posted on the other thread.  It's just excluding some headers that aren't needed and I think I had to move 1 or 2 functions as well, ByteSwap being one if I remember.

1CLJbMgYsaRUbcN2LwQDx2WkG3NJJ2KyJr
Olipro
Member
**
Offline Offline

Activity: 70


View Profile
July 29, 2010, 04:28:25 PM
 #20

Or those with servers stuck on 32-bit OSes. :-D
Quad core Xeon@1.6GHz
Stock: 1100kh/s
Full Opt: 2600kh/s

THANKS!

BitCoins are always appreciated, address in my sig
I just sent you a wad of coin  Wink

so you weren't the guy who sent me 0.02 I take it?  Grin
Pages: [1] 2 »  All
  Print  
 
Jump to:  

Sponsored by , a Bitcoin-accepting VPN.
Powered by MySQL Powered by PHP Powered by SMF 1.1.19 | SMF © 2006-2009, Simple Machines Valid XHTML 1.0! Valid CSS!