A1xLLcqAgt0qc2RyMz0y
Veteran
Maybe you should ask yourself the same question.
Nvidia Pascal Reviews [1080XP, 1080ti, 1080, 1070ti, 1070, 1060, 1050, and 1030]
- Thread starter Love_In_Rio
- Start date
Maybe you should ask yourself the same question.
Fermi definitely brought a lot of changes but poor execution killed a lot of the excitement. People are just happy to finally see some progress with the move to 16nm. For me the price totally kills it because it probably means no big Pascal anytime soon. We need more competition.
It's just a reflection of the stagnation of the main APIs in terms of elements of the graphics pipeline. When there aren't any major new features, there's no reason to ditch an already efficient architecture for something new. Fermi added tessellation. Kepler didn't really add anything. Maxwell added some minor DX12 features. All very incremental. All mostly focused on improving efficiency. Pascal is no different.
„Full Precision“ - that's why I asked Nvidia in the first place and they as well said „nope“. Of course, it can use FP16, but not faster than FP32 and with tailored tests it maybe even slower due to possible twice the register usage (which would make sense for real 2× FP16).
I'm not - already wrote it in my review, because... see above.
Ext3h
Regular
What I noticed, is that a couple of reviewers got confused by the term "Async Compute", using it both for the DX11 extension for explicit preemption by high priority context, and the asynchronous queues in DX12. And mixing these together badly, stating that Pascal would now fully support Async Compute in DX12 because it can do preemption now, or that Maxwell could perform the context switch (the reassignment of SMMs) in DX12 at draw call borders.
I would say NVs marketing for fuzzing this term was a complete success.
I would say NVs marketing for fuzzing this term was a complete success.
Yeah can't really blame the reviewers. nVidia's marketing also conflated the two.
My favorite (English) review so far is the writeup by Hexus.
http://hexus.net/tech/reviews/graphics/92846-nvidia-geforce-gtx-1080-founders-edition-16nm-pascal/
My favorite (English) review so far is the writeup by Hexus.
http://hexus.net/tech/reviews/graphics/92846-nvidia-geforce-gtx-1080-founders-edition-16nm-pascal/
Love_In_Rio
Veteran
Yeah, is the same as Maxwell, the changes, if really any, must be in the compiler. See AoTS with async activated at 4K, less performance than with it desactivated:What I noticed, is that a couple of reviewers got confused by the term "Async Compute", using it both for the DX11 extension for explicit preemption by high priority context, and the asynchronous queues in DX12. And mixing these together badly, stating that Pascal would now fully support Async Compute in DX12 because it can do preemption now, or that Maxwell could perform the context switch (the reassignment of SMMs) in DX12 at draw call borders.
I would say NVs marketing for fuzzing this term was a complete success.
http://www.computerbase.de/2016-05/...agramm-ashes-of-the-singularity-async-compute
Curiously that doesn´t happen at 1080p because there must be more SMs iddle that kick in the compute jobs.
Not async compute in sight.
Last edited:
That's incorrect. Unless you're claiming nVidia is outright lying about dynamic load balancing in Pascal. AOTS performance is really not proof of anything as we have no idea if Oxide's implementation is Pascal friendly. Other reviews actually showed gains with async enabled.
The way I see it Pascal's dynamic load balancing is functionally equivalent to GCN's async shaders. At least I haven't seen anything to indicate otherwise.
Pre-emption is something else entirely, i.e. an explicit interrupt for high priority tasks.
Love_In_Rio
Veteran
Yes, preemption and async are different. Sebbi explained greatly. Nvidia didn´t talk about async, only preemption and it improved its granularity in Pascal, compiler level doable.
Async in AoTS are compute tasks. The feature is called async-compute but you can run it like an "async-compute" architecture (ala GCN) capable of running at the same time both compute and graphics tasks at CU level or fully using entirely a SM for compute or graphics like Nvidia does.
Last edited:
Infinisearch
Veteran
preemption isn't controlled by the compiler... at best it's controlled by the driver.
Could you link it, please?
Simply matching Pascal would be a big deal for AMD. It would bring them back to a situation they haven't known since Kepler was launched.
Highly unlikely they matched em, if you take their best case as 2.0 (stated at the financial call last Q's) over their current midrange, which is Tonga, their best perf/watt chip. 95 watts will give ya Tonga performance. They might have closed the gap a little bit, but I'm thinking the gap pretty much stayed the same.
Some VR performance analysis here:
http://www.roadtovr.com/nvidia-gtx-...performance-head-to-head-against-the-980ti/3/
Not mind blowing but certainly interesting. I am assuming the multi projection doesn't apply in these games.
http://www.roadtovr.com/nvidia-gtx-...performance-head-to-head-against-the-980ti/3/
Not mind blowing but certainly interesting. I am assuming the multi projection doesn't apply in these games.
Love_In_Rio
Veteran
1920 shaders at 1,506 Ghz base clock and 1,683 Ghz bost clock.
So it is 1,60 times faster than a 970 more or less as the benches chart shows.
Not bad at all.
Last edited:
Similar threads
