0.3.10 has tcatm's 4-way SSE2 as an option switch.
Use the switch "-4way" to turn it on. Without the switch you get Crypto++ ASM SHA-256.
I could only get this working with Linux.
Download:
Get 0.3.10 from http://bitcointalk.org/index.php?topic=827.0
Please report back your CPU and results! I think it's pretty clear that Core 2 and lower are slower, i5 faster. I don't think we've heard any i7 results yet. We need to know about the different models of AMD or other less common CPUs.
Re: tcatm's 4-way SSE2 for Linux 32/64-bit 0.3.9 rc2
I hope someone can test an i5 or AMD to check that I built it right. I don't have either to test with.
I'm also curious if it performs much worse on 32-bit linux vs 64-bit.
I'm also curious if it performs much worse on 32-bit linux vs 64-bit.
Re: tcatm's 4-way SSE2 for Linux 32/64-bit 0.3.9 rc2
I just uploaded a quick build so testers can check if I built it right. (I don't have an i5 or AMD) If it checks out, I'll put together the full package and do all the release stuff.
Re: tcatm's 4-way SSE2 for Linux 32/64-bit 0.3.9 rc2
I propose to compile sha256.cpp with -O3 -march=amdfamk10 (will work on 32bit and 64bit) as only CPUs supporting this instruction set (AMD Phenom, Intel i5 and newer) benefit from -4way and it'll improve performance by ~9%.
GCC 4.3.3 doesn't support -march=amdfamk10. I get:sha256.cpp:1: error: bad value (amdfamk10) for -march= switch
With 4way, I get significantly better performance when I have all my virtual cores enabled. I think I get about the same amount of hashes when hyper threading is turned off with or without 4way.
Hey, you may be onto something!hyperthreading didn't help before because all the work was in the arithmetic and logic units, which the hyperthreads share.
tcatm's SSE2 code must be a mix of normal x86 instructions and SSE2 instructions, so while one is doing x86 code, the other can do SSE2.
How much of an improvement do you get with hyperthreading?
Some numbers? What CPU is that?
Re: tcatm's 4-way SSE2 for Linux 32/64-bit 0.3.9 rc2
try -march=amdfam10
That works.That's strange... are we sure that's the same thing? tcatm, try amdfam10 and make sure you get the same speed measurement.
Re: tcatm's 4-way SSE2 for Linux 32/64-bit is in 0.3.10
Code:
cpu family : 6
model : 26
model name : Genuine Intel(R) CPU 000 @ 3.20GHz
stepping : 4
model : 26
model name : Genuine Intel(R) CPU 000 @ 3.20GHz
stepping : 4
That's a 23% speedup with -4way, 63% total speedup with -4way + hyperthreading.
33% faster with hyperthreading than without it.
Re: tcatm's 4-way SSE2 for Linux 32/64-bit is in 0.3.10
I wrapped sha256.cpp in
#ifdef FOURWAYSSE2
#endif // FOURWAYSSE2
try it now.
#ifdef FOURWAYSSE2
#endif // FOURWAYSSE2
try it now.
Re: tcatm's 4-way SSE2 for Linux 32/64-bit is in 0.3.10
Any non-Mac i5 love?
Windows i5 64-bit got slower here.
That's the first I've heard anyone say i5 was slower. Everyone else has said 4way was faster on i5. Moreso with hyperthreading enabled.Windows i5 64-bit got slower here.
And i5, at least on my macbookpro
Good, so I take it that's a confirmation that it's working on Mac as well?Laszlo told me he did compile in the -4way stuff on Mac, so the -4way switch is also available to try on Mac. I don't think makefile.osx on SVN has it yet, just the built version.
Re: tcatm's 4-way SSE2 for Linux 32/64-bit is in 0.3.10
Thanks for clearing that up. I read the link someone posted about AMD making that change around 2007, but I didn't know what the story was for Intel.
There's no hope for Core/Core2 then. They only have half the SSE2 hardware.
Strange that Intel has 3 128bit units, but AMD with 2 128bit units is the faster one.
There's no hope for Core/Core2 then. They only have half the SSE2 hardware.
Strange that Intel has 3 128bit units, but AMD with 2 128bit units is the faster one.
Re: tcatm's 4-way SSE2 for Linux 32/64-bit is in 0.3.10
- AMD K10: 2 128bit units
- intel nehalem: 3 128bit units
Re: tcatm's 4-way SSE2 for Linux 32/64-bit is in 0.3.10
The simplification is intentional. There will only be more than one thash[7]=0 in one out of 134,217,728 cases. It only makes it 0.0000007% slower.