Topic: Flops to hashes question (Read 1871 times)
Worse yet, ASICs have high hps but zero flops.
Thanks.
I often see the power of a computer listed in flops, and I just wanted to get an approximate conversion measure to know how useful they would be for btc.
It's a little bit like expecting to be able to predict a vehicle's MPG by what its top speed is. So much variability. I often see the power of a computer listed in flops, and I just wanted to get an approximate conversion measure to know how useful they would be for btc.
Thanks.
I often see the power of a computer listed in flops, and I just wanted to get an approximate conversion measure to know how useful they would be for btc.
I often see the power of a computer listed in flops, and I just wanted to get an approximate conversion measure to know how useful they would be for btc.
One can only approximate because:
- Different hardware performs differently on integer operations vs floating point operations. Floating point uses different CPU instructions that use different transistor circuits that are optimized differently (or don't exist in hardware at all, see 386SX).
- a FLOPS test has to be optimized to a GPU platform, without taking advantage of hardware specific features it may not get full performance possible,
- Hashing requires optimized programming too, you ask for FLOPS to hashes, but GPU miners have also nearly doubled in efficiency since the first releases from optimized coding.
Core 2 Q6600 = 11.0 Mhash/s & 5 GFLOPS
doesn't compare at all with
5870: 400Mhash/s:
- Different hardware performs differently on integer operations vs floating point operations. Floating point uses different CPU instructions that use different transistor circuits that are optimized differently (or don't exist in hardware at all, see 386SX).
- a FLOPS test has to be optimized to a GPU platform, without taking advantage of hardware specific features it may not get full performance possible,
- Hashing requires optimized programming too, you ask for FLOPS to hashes, but GPU miners have also nearly doubled in efficiency since the first releases from optimized coding.
Core 2 Q6600 = 11.0 Mhash/s & 5 GFLOPS
doesn't compare at all with
5870: 400Mhash/s:
FLOPS = 12.7 * HASH.
Generally speaking, and not entirely accurate.
Bitcoin is 17 times more powerful than the world's most powerful supercomputer.
Generally speaking, and not entirely accurate.
Bitcoin is 17 times more powerful than the world's most powerful supercomputer.
Basically my question is is there some sort of method to get an approximate number of hashes from the number of flops?
FLOPS = floating point instructions per second
SHA256 = integer math
SHA256 = integer math
Is there any way to convert flops to hashes or is there no relation between the two?
Jump to: