Sieve Benchmark Thread

[amphoria]

Originally Posted by Flatlander

64-bit Windows 7, yes. I haven't tried 32-bit XP yet. (Under Lazarus. See my 'Clueless' post above, number 48.)

This was 32-bit Vista.

[amphoria]

Originally Posted by axn

I've noticed that sometimes FPC code generation for "for loops" goes a bit wonky. Maybe a for-less code would be better.

I tried turning off all optimizations with -O- and the for loop now works correctly. Given that the inner loop is written in asm this should not make any significant difference to the performance.

[Flatlander]

Originally Posted by Flatlander

...
I ran a 5T range on axnSieve (same PC) last night (90e6/90e5) and it took 14hrs 54m. A negligible slow down compared to 60e6/60e5.
NPG is now running the file using fast array, 384Mb.

A 7T range also fits in fast array, 384Mb.

[axn]

There is an unsafe code in the program in 32-bit compiler, that'll mess up sieve from primes p > 280m (2^32/15).

So ranges done with 32-bit siever with p > 280m should be redone.

Fix is to change line 200 from

t := (t*15) mod n

to

t := (QWord(t)*15) mod n

[amphoria]

Originally Posted by axn

There is an unsafe code in the program in 32-bit compiler, that'll mess up sieve from primes p > 280m (2^32/15).

So ranges done with 32-bit siever with p > 280m should be redone.

Fix is to change line 200 from

t := (t*15) mod n

to

t := (QWord(t)*15) mod n

This will affect all ranges done by me > 20T. I assume that you have now checked the code for other similar issues with 32-bit compilation.

Edit: BTW please read this as a statement of fact rather than any implied criticism. I well understand the risks of using experimental code. Fortunately you caught it pretty early on.

[axn]

Originally Posted by amphoria

I assume that you have now checked the code for other similar issues with 32-bit compilation.

I think so, but I haven't done a thorough enough check to be 100% sure. If you want, you can wait for my confirmation until proceeding further.

Originally Posted by amphoria

Edit: BTW please read this as a statement of fact rather than any implied criticism. I well understand the risks of using experimental code. Fortunately you caught it pretty early on.

Understood. In this case, however, any criticism would be well deserved.

[axn]

Originally Posted by axn

I think so, but I haven't done a thorough enough check to be 100% sure. If you want, you can wait for my confirmation until proceeding further.

The rest of the code checks out.

[amphoria]

Originally Posted by axn

The rest of the code checks out.

Thanks for confirming.

[amphoria]

For interest I compared the results of 23T-24T after applying the fix with the original results. There were about 39000 lines different.

[Flatlander]

Originally Posted by Flatlander

A 7T range also fits in fast array, 384Mb.

As does 10T. (90e6/90e5)

[Flatlander]

I'm having all sorts of problems trying to compile a Windows 32 bit axnSieve. Could someone please post an exe with as high as possible SmallPrimes and SieveSize that is already known to be good.

Thanks