Computer Chess Club
https://talkchess.com/
CUDA cores seem to perform well. Maybe for Leela case a 60-70% or so over RTX 2080 (non-super), but let's see the benches.mmt wrote: ↑Wed Sep 16, 2020 11:17 pm A lot of reviews of 3080 are out but they focus almost exclusively on games. The closest I've seen is this https://babeltechreviews.com/rtx-3080-a ... hmarked/4/ with a 27% increase of half-float performance over 2080Ti.
However maybe a bit less than 50% improvement with 3070 over my 2070 next month. This time 3080 seems the best deal. Last time it was 2070 or 2060. But aside money, 3080 seems way too large, and it consumes like an air conditioner, in real terms in excess of 350W.Laskos wrote: ↑Thu Sep 17, 2020 12:07 amCUDA cores seem to perform well. Maybe for Leela case a 60-70% or so over RTX 2080 (non-super), but let's see the benches.mmt wrote: ↑Wed Sep 16, 2020 11:17 pm A lot of reviews of 3080 are out but they focus almost exclusively on games. The closest I've seen is this https://babeltechreviews.com/rtx-3080-a ... hmarked/4/ with a 27% increase of half-float performance over 2080Ti.
After all, if only for Chess and Go, maybe the best is to spend just $250 and get a second hand 2060 Super on top of my 2070, close to 100% boost. Will anyway have to upgrade the case and the overall cooling.Laskos wrote: ↑Thu Sep 17, 2020 1:32 amHowever maybe a bit less than 50% improvement with 3070 over my 2070 next month. This time 3080 seems the best deal. Last time it was 2070 or 2060. But aside money, 3080 seems way too large, and it consumes like an air conditioner, in real terms in excess of 350W.Laskos wrote: ↑Thu Sep 17, 2020 12:07 amCUDA cores seem to perform well. Maybe for Leela case a 60-70% or so over RTX 2080 (non-super), but let's see the benches.mmt wrote: ↑Wed Sep 16, 2020 11:17 pm A lot of reviews of 3080 are out but they focus almost exclusively on games. The closest I've seen is this https://babeltechreviews.com/rtx-3080-a ... hmarked/4/ with a 27% increase of half-float performance over 2080Ti.
Or buy yourself 20 cores and abandon giant networks that insist on GPULaskos wrote: ↑Thu Sep 17, 2020 12:28 pmAfter all, if only for Chess and Go, maybe the best is to spend just $250 and get a second hand 2060 Super on top of my 2070, close to 100% boost. Will anyway have to upgrade the case and the overall cooling.Laskos wrote: ↑Thu Sep 17, 2020 1:32 amHowever maybe a bit less than 50% improvement with 3070 over my 2070 next month. This time 3080 seems the best deal. Last time it was 2070 or 2060. But aside money, 3080 seems way too large, and it consumes like an air conditioner, in real terms in excess of 350W.Laskos wrote: ↑Thu Sep 17, 2020 12:07 amCUDA cores seem to perform well. Maybe for Leela case a 60-70% or so over RTX 2080 (non-super), but let's see the benches.mmt wrote: ↑Wed Sep 16, 2020 11:17 pm A lot of reviews of 3080 are out but they focus almost exclusively on games. The closest I've seen is this https://babeltechreviews.com/rtx-3080-a ... hmarked/4/ with a 27% increase of half-float performance over 2080Ti.
Well, machine learning is important per se, and regarding board games, Go and some other turn based games not relying on AB search and massive pruning are best played by PCs using GPUs. Then, although I almost never play video games, to try one or two of the high end can be enjoyable.chrisw wrote: ↑Thu Sep 17, 2020 1:47 pmOr buy yourself 20 cores and abandon giant networks that insist on GPULaskos wrote: ↑Thu Sep 17, 2020 12:28 pmAfter all, if only for Chess and Go, maybe the best is to spend just $250 and get a second hand 2060 Super on top of my 2070, close to 100% boost. Will anyway have to upgrade the case and the overall cooling.Laskos wrote: ↑Thu Sep 17, 2020 1:32 amHowever maybe a bit less than 50% improvement with 3070 over my 2070 next month. This time 3080 seems the best deal. Last time it was 2070 or 2060. But aside money, 3080 seems way too large, and it consumes like an air conditioner, in real terms in excess of 350W.Laskos wrote: ↑Thu Sep 17, 2020 12:07 amCUDA cores seem to perform well. Maybe for Leela case a 60-70% or so over RTX 2080 (non-super), but let's see the benches.mmt wrote: ↑Wed Sep 16, 2020 11:17 pm A lot of reviews of 3080 are out but they focus almost exclusively on games. The closest I've seen is this https://babeltechreviews.com/rtx-3080-a ... hmarked/4/ with a 27% increase of half-float performance over 2080Ti.
Page 22 seems interesting:
What I gathered says "it's complicated", the cycles come from many parts of the computation, so is the cycle number reduction by different components like tensor cores. CUDA etc. The range 1.40 to 2.20 is still possible for the speed-up from RTX 2080 to 3080 with Lc0 as it is built now. Some links:smatovic wrote: ↑Fri Sep 18, 2020 12:54 pmPage 22 seems interesting:
https://www.nvidia.com/content/dam/en-z ... per-V1.pdf
But I am not able to forecast you how this 2xFP32 and 2xTensorOps of RTX 30xx will translate to current Lc0.
--
Srdja
Hmm, according to all those articles and papers, a slow down of RTX 3080 compared to RTX 2080 TI in some AI tasks is also possible.Laskos wrote: ↑Fri Sep 18, 2020 1:40 pmWhat I gathered says "it's complicated", the cycles come from many parts of the computation, so is the cycle number reduction by different components like tensor cores. CUDA etc. The range 1.40 to 2.20 is still possible for the speed-up from RTX 2080 to 3080 with Lc0 as it is built now. Some links:smatovic wrote: ↑Fri Sep 18, 2020 12:54 pmPage 22 seems interesting:
https://www.nvidia.com/content/dam/en-z ... per-V1.pdf
But I am not able to forecast you how this 2xFP32 and 2xTensorOps of RTX 30xx will translate to current Lc0.
--
Srdja
https://timdettmers.com/2020/09/07/whic ... nsor_Cores
https://www.pugetsystems.com/labs/hpc/R ... nary-1885/
I seem to manage to extrapolate from this chart:smatovic wrote: ↑Fri Sep 18, 2020 6:17 pmHmm, according to all those articles and papers, a slow down of RTX 3080 compared to RTX 2080 TI in some AI tasks is also possible.Laskos wrote: ↑Fri Sep 18, 2020 1:40 pmWhat I gathered says "it's complicated", the cycles come from many parts of the computation, so is the cycle number reduction by different components like tensor cores. CUDA etc. The range 1.40 to 2.20 is still possible for the speed-up from RTX 2080 to 3080 with Lc0 as it is built now. Some links:smatovic wrote: ↑Fri Sep 18, 2020 12:54 pmPage 22 seems interesting:
https://www.nvidia.com/content/dam/en-z ... per-V1.pdf
But I am not able to forecast you how this 2xFP32 and 2xTensorOps of RTX 30xx will translate to current Lc0.
--
Srdja
https://timdettmers.com/2020/09/07/whic ... nsor_Cores
https://www.pugetsystems.com/labs/hpc/R ... nary-1885/
You should compare 3080 with 2080 TI, they have similar SM core count.
--
Srdja
