Microsoft DirectStorage API Available, but Without GPU-accelerated Decompression

[Valantar]

I'm confused. The end game of this direct storage is to let the video card do the decompression. However, if the video card is already struggling to keep FPS, rtx, etc, wouldn't adding decompression roles such as this Actually ADD to the video card burden, in turn reducing performance even further? I guess I'm asking in relation that most of the bottle necks seem video card related, how would this solve the bottleneck? Wouldn't we want to offload burdens on the video card? Or is this making use of some idle section of the card that is doing nothing while the rest is saturated? I would think having the cpu do more more would free up the card to do more. Couldn't apps/games just have more threading for the CPUs do that function?

It's a tradeoff between burdening the gpu with decompression vs. having it wait for data processed elsewhere. It likely means the burden of decompression is so low as to me meaningless. If it occupies a few % of the GPU you would never even notice - but you would notice less judder when loading new chunks or streaming assets, less pop-in, etc.

 

[Mussels]

I'm confused. The end game of this direct storage is to let the video card do the decompression. However, if the video card is already struggling to keep FPS, rtx, etc, wouldn't adding decompression roles such as this Actually ADD to the video card burden, in turn reducing performance even further? I guess I'm asking in relation that most of the bottle necks seem video card related, how would this solve the bottleneck? Wouldn't we want to offload burdens on the video card? Or is this making use of some idle section of the card that is doing nothing while the rest is saturated? I would think having the cpu do more more would free up the card to do more. Couldn't apps/games just have more threading for the CPUs do that function?

No, because it's doing this during loading screens - the total goal is to streamline the textures going from storage to GPU, without needing the CPU and system ram in the way
(Look at how bad windows is at moving small files, you'll see the appeal)

Do that, and even with no fancy alternate tech you get rid of a LOT of microstutter and hitching on lower VRAM cards. On higher end cards, they can use the spare VRAM and preload more.

When the compression/decompression tech gets sorted out, we save on disk space as well as VRAM needs. (which i think is rather crtitical, tbh)

 

[bug]

@Mussels Wrong as usual. This is not about load screens, it's about streaming textures during gameplay. Rage, anyone?

 

[Mussels]

@Mussels Wrong as usual. This is not about load screens, it's about streaming textures during gameplay. Rage, anyone?

We already stream textures, that's part of the rest of what i wrote - removing the CPU overhead