I stumbled upon this article on the new Nvidia RTX GPUs

[Laskos]

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.

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.

[Laskos]

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.

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.

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]

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.

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.

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.

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.

[chrisw]

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.

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.

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.

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.

Or buy yourself 20 cores and abandon giant networks that insist on GPU

[Laskos]

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.

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.

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.

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.

Or buy yourself 20 cores and abandon giant networks that insist on GPU

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.

[Laskos]

Someone who understands better can see and explain something here?

[smatovic]

Someone who understands better can see and explain something here?

Page 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

[Laskos]

Someone who understands better can see and explain something here?

Page 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

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:

https://timdettmers.com/2020/09/07/whic ... nsor_Cores
https://www.pugetsystems.com/labs/hpc/R ... nary-1885/

[smatovic]

Someone who understands better can see and explain something here?

Page 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

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:

https://timdettmers.com/2020/09/07/whic ... nsor_Cores
https://www.pugetsystems.com/labs/hpc/R ... nary-1885/

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.

You should compare 3080 with 2080 TI, they have similar SM core count.

--
Srdja

[Laskos]

Someone who understands better can see and explain something here?

Page 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

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:

https://timdettmers.com/2020/09/07/whic ... nsor_Cores
https://www.pugetsystems.com/labs/hpc/R ... nary-1885/

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.

You should compare 3080 with 2080 TI, they have similar SM core count.

--
Srdja

I seem to manage to extrapolate from this chart:
https://www.pugetsystems.com/labs/hpc/R ... nary-1885/



Here we cannot compare directly old RTX 2080 Ti numbers with the RTX 3080 test. RTX 3080 test (1023 images/sec) uses significantly newer drivers, TensorFlow version, testing setup. But we have RTX Titan tested now which got 1082 images/sec on FP16 with the old result which was 653, compared with RTX 2080 Ti of 532 (old result). By extrapolation, with the "old setup" 3080 would get 617 images/sec, and now we can compare to 2080 Ti (532) and 2080 (382). The speed-up RTX 2080 --> 3080 is about 60%, which is good but not great.