TalkChess.com

While we are comparing IBM's deep blue hardware to today's hardware and deep blue chess performance to today's computer chess performance. It's also interesting to compare IBM 1997 to IBM 2017. In 1997, IBM earned 78.5 billion. In 2017, IBM earned 79.1 billion. In 20 years an increase of 0.8%. Not ...

h1a8 wrote: ↑

Wed Nov 14, 2018 8:00 pm

I have a question.
I can buy a dual 2080 OC with 8gb GDDR6 each
for a similar price as
A single 2080 ti OC with 11GB GDDR6

Which would give the stronger Leela performance and by how much?

Dual 2080 hands down.

AFAIK Deep Blue source code had evaluation function in a generalized form. This function was "trained" and this training data is not part of source code, but rather dynamic data, which can be enhanced with more games thrown on it and also manually intervented by team stuff. I doubt DB can be reprod...

While we are comparing IBM's deep blue hardware to today's hardware and deep blue chess performance to today's computer chess performance. It's also interesting to compare IBM 1997 to IBM 2017. In 1997, IBM earned 78.5 billion. In 2017, IBM earned 79.1 billion. In 20 years an increase of 0.8%. Not ...

Unless you have infinite money like IBM or Google, it doesn't make sense to do an ASIC. However, we're seeing more and more integration between FPGA and CPU (you can even rent some on Amazon Web Service), but i didn't think there is an FPGA powered chess engine that beat an X86_64 CPU... yet ? That...

But from user experience perspective, Windows is still better for many tasks, including image processing (Gimp/Krita/Pinta is much worse than Photoshop), sound recording (Protools/Cubase/etc is much worse than whatever Linux has, although there's finally version of Reaper for Linux), and playing/an...

I will watch your Test Results with the RTX 2070 with interest, Mr Laskos. The day Lc0 starts beating the mickey out of Stockfish ( as AlphaZero did so memorably) using the 2070, I'll go out and grab myself a 2070 Ti, price be damned ! Yes this is my position also. At the moment I'm sticking to my ...

Just curious if anyone happens to know.. Before the scandalous ones it was rybka. Nothing could approoach the versions. Before that were fruit derivatives, before that was shredder, before that, hiarcs had a long rule. Chessmaster 6 had a short reign, but genius 3 had a very long reign. It was the ...

Just curious if anyone happens to know.. Rybka comes to mind. After Rybka comes to mind ippolit that there are claims that they were illegal and I did not use them. looking at wikipedia for ippolit I find IPPOLIT, released on May 2, 2009 RobboLito released in September 2009 Igorrit released in Janu...

Tensor cores as is are just matmul ASICs. Matrix multiplication makes up a large part of convolutions, but it is totally possible to get even more application specific, should you want another large jump up. Currently, matmul ASICS are limited by data movement, which puts an upper bound on latency,...