Lazy SMP troubles

Discussion of chess software programming and technical issues.

Moderator: Ras

smatovic
Posts: 3225
Joined: Wed Mar 10, 2010 10:18 pm
Location: Hamburg, Germany
Full name: Srdja Matovic

Re: Lazy SMP troubles

Post by smatovic »

Yes.

--
Srdja
smatovic
Posts: 3225
Joined: Wed Mar 10, 2010 10:18 pm
Location: Hamburg, Germany
Full name: Srdja Matovic

Re: Lazy SMP troubles

Post by smatovic »

Robert Hyatt used these 24 positions to test his DTS up to 16 cores with time to depth, and Tom Kerrigan with ABDADA up to 32 cores:

Hyatt24:
https://github.com/smatovic/Zeta/blob/m ... rd.c#L1223

Speedup results on TK's website:
http://www.tckerrigan.com/Chess/Parallel_Search/

--
Srdja
adityachandra
Posts: 23
Joined: Sun Apr 23, 2023 9:26 am
Full name: Aditya Chandra

Re: Lazy SMP troubles

Post by adityachandra »

I suppose I'll look in to ABDADA, doesn't seem to hard to implement on the CPW wiki... Thanks @smatovic!