Bitcoin Forum
March 28, 2024, 11:47:47 PM *
News: Latest Bitcoin Core release: 26.0 [Torrent]
 
   Home   Help Search Login Register More  
Pages: [1] 2 »  All
  Print  
Author Topic: 50-core Intel Xeon Phi of no use to us?  (Read 14255 times)
Quantus (OP)
Legendary
*
Offline Offline

Activity: 883
Merit: 1005



View Profile
June 27, 2012, 12:03:19 AM
 #1

50-core Intel Xeon Phi
http://www.extremetech.com/computing/131699-larrabee-lives-50-core-intel-xeon-phi-unveiled-lures-supercomputers-away-from-nvidia-tesla
Will this be of any use to us? We need "float point calculations" right? I think I read it won't have many.
I have never herd of a co-processor before.


(I am a 1MB block supporter who thinks all users should be using Full-Node clients)
Avoid the XT shills, they only want to destroy bitcoin, their hubris and greed will destroy us.
Know your adversary https://www.youtube.com/watch?v=BKorP55Aqvg
1711669667
Hero Member
*
Offline Offline

Posts: 1711669667

View Profile Personal Message (Offline)

Ignore
1711669667
Reply with quote  #2

1711669667
Report to moderator
1711669667
Hero Member
*
Offline Offline

Posts: 1711669667

View Profile Personal Message (Offline)

Ignore
1711669667
Reply with quote  #2

1711669667
Report to moderator
TalkImg was created especially for hosting images on bitcointalk.org: try it next time you want to post an image
Advertised sites are not endorsed by the Bitcoin Forum. They may be unsafe, untrustworthy, or illegal in your jurisdiction.
rjk
Sr. Member
****
Offline Offline

Activity: 448
Merit: 250


1ngldh


View Profile
June 27, 2012, 12:13:28 AM
 #2

Floating point is the thing we don't need for mining. Search the forum; there are about 2 other threads on this device. Estimates for hash rate are around 280mh/s, and it should be pretty good with litecoin.

Mining Rig Extraordinaire - the Trenton BPX6806 18-slot PCIe backplane [PICS] Dead project is dead, all hail the coming of the mighty ASIC!
crazyates
Legendary
*
Offline Offline

Activity: 952
Merit: 1000



View Profile
June 27, 2012, 12:40:09 AM
 #3

https://bitcointalk.org/index.php?topic=88407.0

Tips? 1crazy8pMqgwJ7tX7ZPZmyPwFbc6xZKM9
Previous Trade History - Sale Thread
A_CardeN
Newbie
*
Offline Offline

Activity: 42
Merit: 0


View Profile
June 27, 2012, 04:54:47 AM
 #4

I actually know a person who works for Intel who is developing this.  You would all shit your pants if you knew who he was in this community and you probably wouldn't believe me.

He says this is going to get about 2.4 Ghash range (they are still testing it) and it was supposed to cost about 1000 dollars but maybe they want to compete with asic and offer cheaper prices?  But again, this card isn't really for Bitcoin, so who knows.
naz86
Member
**
Offline Offline

Activity: 111
Merit: 10


View Profile
June 27, 2012, 10:15:12 AM
 #5

ok i want to shit my pants! who is it ?  Tongue
crazyates
Legendary
*
Offline Offline

Activity: 952
Merit: 1000



View Profile
June 27, 2012, 12:15:33 PM
 #6

I actually know a person who works for Intel who is developing this.  You would all shit your pants if you knew who he was in this community and you probably wouldn't believe me.

He says this is going to get about 2.4 Ghash range (they are still testing it) and it was supposed to cost about 1000 dollars but maybe they want to compete with asic and offer cheaper prices?  But again, this card isn't really for Bitcoin, so who knows.

By the time this becomes available, it better be 2.4 GH/s for $100 to compete with a 3.5GH/s ASIC for $150.

Tips? 1crazy8pMqgwJ7tX7ZPZmyPwFbc6xZKM9
Previous Trade History - Sale Thread
mrb
Legendary
*
Offline Offline

Activity: 1512
Merit: 1027


View Profile WWW
June 27, 2012, 12:35:14 PM
 #7

I actually know a person who works for Intel who is developing this.  You would all shit your pants if you knew who he was in this community and you probably wouldn't believe me.

I don't think you are telling the truth.

He says this is going to get about 2.4 Ghash range (they are still testing it) and it was supposed to cost about 1000 dollars but maybe they want to compete with asic and offer cheaper prices?  But again, this card isn't really for Bitcoin, so who knows.

Xeon Phi should get about 280 Mhash/s (1200 billion 32-bit operations per sec / 4300 operations):
https://bitcointalk.org/index.php?topic=88407.msg974306#msg974306
Lethos
Sr. Member
****
Offline Offline

Activity: 476
Merit: 250


Keep it Simple. Every Bit Matters.


View Profile WWW
June 27, 2012, 01:20:39 PM
 #8

I actually know a person who works for Intel who is developing this.  You would all shit your pants if you knew who he was in this community and you probably wouldn't believe me.

He says this is going to get about 2.4 Ghash range (they are still testing it) and it was supposed to cost about 1000 dollars but maybe they want to compete with asic and offer cheaper prices?  But again, this card isn't really for Bitcoin, so who knows.

I think you "friend" who works for Intel is off by a factor of 10. 240 Mhash/s might be possible, but not 2400 Mhash/s.
Some have predicted a bit more than 240Mhash/s of course, but not off by much. Numbers just don't add up to do as you suggest.
Mrb post details the core of those numbers of how 2400 Mhash/s isn't going to be possible.

It's all mute now with FPGA coming out at lower prices and better results without using tons of electricity.
ASIC is of course on the horizon, should prove to be an improvement that most FPGA out right now.
I don't expect what BFL suggests, but ASIC will eventually be the next step forward, after FPGA.

malevolent
can into space
Legendary
*
Offline Offline

Activity: 3472
Merit: 1721



View Profile
June 27, 2012, 02:19:57 PM
 #9

I actually know a person who works for Intel who is developing this.  You would all shit your pants if you knew who he was in this community and you probably wouldn't believe me.

He says this is going to get about 2.4 Ghash range (they are still testing it) and it was supposed to cost about 1000 dollars but maybe they want to compete with asic and offer cheaper prices?  But again, this card isn't really for Bitcoin, so who knows.

2.4GHash/s but what hashes? bitcoin double sha2-256 or maybe 2.4 md5 GHash/s? This is important.

Signature space available for rent.
A_CardeN
Newbie
*
Offline Offline

Activity: 42
Merit: 0


View Profile
June 28, 2012, 04:51:33 AM
 #10

I actually know a person who works for Intel who is developing this.  You would all shit your pants if you knew who he was in this community and you probably wouldn't believe me.

He says this is going to get about 2.4 Ghash range (they are still testing it) and it was supposed to cost about 1000 dollars but maybe they want to compete with asic and offer cheaper prices?  But again, this card isn't really for Bitcoin, so who knows.

2.4GHash/s but what hashes? bitcoin double sha2-256 or maybe 2.4 md5 GHash/s? This is important.

That I do not know. 
A_CardeN
Newbie
*
Offline Offline

Activity: 42
Merit: 0


View Profile
June 28, 2012, 04:53:14 AM
 #11

I actually know a person who works for Intel who is developing this.  You would all shit your pants if you knew who he was in this community and you probably wouldn't believe me.

I don't think you are telling the truth.

Everyone is entitled to their own opinion.  I know so much about the bitcoin community ... you guys have no clue.  I have no reason lie.  I don't need the approval of anyone from this forum.
naz86
Member
**
Offline Offline

Activity: 111
Merit: 10


View Profile
June 28, 2012, 08:30:01 AM
 #12

I actually know a person who works for Intel who is developing this.  You would all shit your pants if you knew who he was in this community and you probably wouldn't believe me.

I don't think you are telling the truth.

Everyone is entitled to their own opinion.  I know so much about the bitcoin community ... you guys have no clue.  I have no reason lie.  I don't need the approval of anyone from this forum.

thats right you don't need approval, and because we guys have no clue, we don't care Tongue

i dont't know what knowledge about the community has to do with knowloedge about gpu/cpu architecture ?

please explain....
bulanula
Hero Member
*****
Offline Offline

Activity: 518
Merit: 500



View Profile
June 28, 2012, 04:40:27 PM
 #13

I actually know a person who works for Intel who is developing this.  You would all shit your pants if you knew who he was in this community and you probably wouldn't believe me.

He says this is going to get about 2.4 Ghash range (they are still testing it) and it was supposed to cost about 1000 dollars but maybe they want to compete with asic and offer cheaper prices?  But again, this card isn't really for Bitcoin, so who knows.

Stop the mystery. It is me Wink

What is the price for this monster anyway ? No doubt like $2000 or something because this is not for users like us but big business.
Gabi
Legendary
*
Offline Offline

Activity: 1148
Merit: 1008


If you want to walk on water, get out of the boat


View Profile
June 28, 2012, 07:10:08 PM
 #14

Quote
Will this be of any use to us?
No

Quote
We need "float point calculations" right? I think I read it won't have many.
We need exactly 0 float point calculations. And the Xeon Phi will have a lot of float calculation power, it will have 1TFLOPs in Double Precision, all with x86 code (easier to use than opencl or cuda)

Quote
I have never herd of a co-processor before.
Never heard of a GPU too? Because a GPU is a co-processor  Cheesy

Koooooj
Member
**
Offline Offline

Activity: 75
Merit: 10



View Profile
June 28, 2012, 07:53:00 PM
Last edit: July 01, 2012, 05:54:09 PM by Koooooj
 #15

(EDIT) PAY NO ATTENTION TO ME. I AM APPARENTLY A COMPLETE IDIOT.  THANKS FOR SETTING ME STRAIGHT.

Rather than suggesting numbers that I think sound good, I'll attempt to recreate a lot of the math found in https://bitcointalk.org/index.php?topic=58511.msg996572#msg996572

In that thread, it was stated that the Bitcoin Hash Function takes about 3375 operations.  If we can assume that each of the 50 cores can perform one operation per clock, and we assume an aggressive clock of, say, 1,500 MHz (1.5 GHz), then the following math ensues:

Code:
50 (cores) * 1,500 (Million operations/s) / 3375 (ops/hash) = about 22 MHash/s

Now, I'm not saying that that is what the actual performance will be, but it is a number that is supported by real math.  If you want, you can play around with those numbers to get different results, but I doubt that it'll wind up getting all the way up to 2,400 MHash/s.  Note that you aren't allowed to change the 50 (there will definitely be 50 cores), and you aren't allowed to change the 3375--that's just the amount of math it takes to do a hash.  All you can do is speculate on the clock speed and the number of operations that can be done by a processor in a given clock cycle.

To give a comparison to show the validity of the math, I have an Intel Core i7 3930K @ 4.4GHz.  That's:

Code:
6 (cores) * 4,400 (Million operations/s) / 3375 (ops/hash) = 7.82 MHash/s
Compare this to the 8.7 that I actually see.  The discrepancy is caused by the hyperthreading that allows more than one operation to be done in a given clock cycle, since there are two concurrent threads executing.  Still, though, even with a hyperthreaded processor the math is pretty close.

In all, it's not too surprising that it's not that high, as it's x86, not straight OpenCL.  It's good for more things, but not as good at the few things that an ATI/AMD graphics card (or FPGA/ASIC) is good at.
Koooooj
Member
**
Offline Offline

Activity: 75
Merit: 10



View Profile
June 28, 2012, 10:12:43 PM
 #16

Just saw the reference to https://bitcointalk.org/index.php?topic=88407.msg974306#msg974306.

Probably more accurate than my math.
antares
Hero Member
*****
Offline Offline

Activity: 518
Merit: 500


View Profile
June 28, 2012, 11:32:40 PM
 #17

Rather than suggesting numbers that I think sound good, I'll attempt to recreate a lot of the math found in https://bitcointalk.org/index.php?topic=58511.msg996572#msg996572

In that thread, it was stated that the Bitcoin Hash Function takes about 3375 operations.  If we can assume that each of the 50 cores can perform one operation per clock, and we assume an aggressive clock of, say, 1,500 MHz (1.5 GHz), then the following math ensues:

Code:
50 (cores) * 1,500 (Million operations/s) / 3375 (ops/hash) = about 22 MHash/s

Now, I'm not saying that that is what the actual performance will be, but it is a number that is supported by real math.  If you want, you can play around with those numbers to get different results, but I doubt that it'll wind up getting all the way up to 2,400 MHash/s.  Note that you aren't allowed to change the 50 (there will definitely be 50 cores), and you aren't allowed to change the 3375--that's just the amount of math it takes to do a hash.  All you can do is speculate on the clock speed and the number of operations that can be done by a processor in a given clock cycle.

To give a comparison to show the validity of the math, I have an Intel Core i7 3930K @ 4.4GHz.  That's:

Code:
6 (cores) * 4,400 (Million operations/s) / 3375 (ops/hash) = 7.82 MHash/s
Compare this to the 8.7 that I actually see.  The discrepancy is caused by the hyperthreading that allows more than one operation to be done in a given clock cycle, since there are two concurrent threads executing.  Still, though, even with a hyperthreaded processor the math is pretty close.

In all, it's not too surprising that it's not that high, as it's x86, not straight OpenCL.  It's good for more things, but not as good at the few things that an ATI/AMD graphics card (or FPGA/ASIC) is good at.

should point out that your math is crap, since your core i7 has SIMD and MIMD extensions that do far more than one operation per second, as the name suggests(Single input, multiple data). Besides that, Hyperthreading doesnt make your cpu run more instructions per second, it just allows for better parallelization. You can also bet that the Phi will have SIMD and MIMD instructions. Then it should be added that a cpu will not reach its nominal ops/second speed in most scenarios(bitcoin mining might be close to the theoretical values because the functions are rather compact and can be held within the 1:1 L1 cache of the cpu most of the time) du to the limited L1 and L2 cache, and other tasks/kernel messing with the instruction pipeline. finally, not every instruction can be done in one clock. then again some instructions can be done in less than one effective clock(strict prefetching).
AzN1337c0d3r
Full Member
***
Offline Offline

Activity: 238
Merit: 100

★YoBit.Net★ 350+ Coins Exchange & Dice


View Profile
June 29, 2012, 12:05:42 AM
 #18

The discrepancy is caused by the hyperthreading that allows more than one operation to be done in a given clock cycle, since there are two concurrent threads executing.  Still, though, even with a hyperthreaded processor the math is pretty close.

I think the technology you are looking for here is superscalar. Modern day CPUs have IPC well over 1 which is only possible due to the architecture being superscalar. Superscalar means that the processor can issue and retire more than 1 instruction per cycle.

Hyperthreading (aka simultaneous multithreading) is simply a technology that simply tries to keep the processor as busy as possible by simultaneously assigning instructions from different threads to fill up the functional units as efficiently as possible.

Koooooj
Member
**
Offline Offline

Activity: 75
Merit: 10



View Profile
June 29, 2012, 08:02:41 PM
 #19

I was afraid my math was flawed.  I will maintain that if both the Phi and my 3930K both use SIMD and MIMD, or at least vaguely similar architecture (I have read that the Phi will use a pentium like architecture, just built on 22nm and tied together for better parallel processing), then the (MHash/s) per (core count * clock speed) comparison should at least be ballpark, and the validation that the MHash/s that I see running with a CPU miner is at least ball park lends at least a little bit of weight.  Not so much weight that it should be taken as truth without thought, but enough that it should perhaps be considered.

Ignoring that implication, though, there is the simple fact that this is going to be a VERY expensive card.  With well-proven GPUs easily available that will probably compete on the MHash/s, FPGAs readily buyable from a few manufacturers, and the ASICs in development, buying a card that will probably be priced a little above the nVIDIA Tesla cards (since they have x86 support) will simply not be economical for bitcoin miners.  For people building massive super-computing clusters for general computation, it is a different story.
Soros Shorts
Donator
Legendary
*
Offline Offline

Activity: 1616
Merit: 1003



View Profile
June 30, 2012, 07:23:57 PM
 #20

To give a comparison to show the validity of the math, I have an Intel Core i7 3930K @ 4.4GHz.  That's:

Code:
6 (cores) * 4,400 (Million operations/s) / 3375 (ops/hash) = 7.82 MHash/s
Compare this to the 8.7 that I actually see. 
What miner are you using? With the Ufasoft miner I remember seeing something like of 25 mhash/s on a 6-core Xeon clocked less than your i7.
Pages: [1] 2 »  All
  Print  
 
Jump to:  

Powered by MySQL Powered by PHP Powered by SMF 1.1.19 | SMF © 2006-2009, Simple Machines Valid XHTML 1.0! Valid CSS!