Full-scale file system acceleration on GPU [pdf]
1–10 of 50 posts
Re: Full-scale file system acceleration on GPU [pdf]
#2According to this paper, GPU4FS is a file system that can run on the GPU and be accessed by applications. Since GPUs cannot make system calls, GPU4FS uses shared video memory (VRAM) and a parallel queue implementation. Applications running on the GPU can utilize GPU4FS after modifying their code, eliminating the need for a CPU-side file system when accessing the file system. The experiments are done on Optane memory.
It would be interesting to know if this approach could optimize the performance of training and inference for large models.
Re: Full-scale file system acceleration on GPU [pdf]
#3Given that PCIe allows data to be piped directly from one device to another without going through the host CPU[1][2], I guess it might make sense to just have the GPU read blocks straight from the NVMe (or even NVMe-of[3]) rather than having the CPU do a lot of work.
edit: blind as a bat, says so right in the paper of course:
PMem is mapped directly to the GPU, and NVMe memory is accessed via Peer to Peer-DMA (P2PDMA)
[1]: https://nvmexpress.org/wp-content/uploads/Enabling-the-NVMe-...
[2]: https://lwn.net/Articles/767281/
[3]: https://www.nvmexpress.org/wp-content/uploads/NVMe_Over_Fabr...
Re: Full-scale file system acceleration on GPU [pdf]
#4According to this paper, GPU4FS is a file system that can run on the GPU and be accessed by applications. Since GPUs cannot make system calls, GPU4FS uses shared video memory (VRAM) and a parallel queue implementation. Applications running on the GPU can utilize GPU4FS after modifying their code, eliminating the need for a CPU-side file system when accessing the file system. The experiments are done on Optane memory.…
[flagged]
Re: Full-scale file system acceleration on GPU [pdf]
#5According to this paper, GPU4FS is a file system that can run on the GPU and be accessed by applications. Since GPUs cannot make system calls, GPU4FS uses shared video memory (VRAM) and a parallel queue implementation. Applications running on the GPU can utilize GPU4FS after modifying their code, eliminating the need for a CPU-side file system when accessing the file system. The experiments are done on Optane memory.…
[flagged]
Then this isn't for them
Re: Full-scale file system acceleration on GPU [pdf]
#6According to this paper, GPU4FS is a file system that can run on the GPU and be accessed by applications. Since GPUs cannot make system calls, GPU4FS uses shared video memory (VRAM) and a parallel queue implementation. Applications running on the GPU can utilize GPU4FS after modifying their code, eliminating the need for a CPU-side file system when accessing the file system. The experiments are done on Optane memory.…
[flagged]
Highly unlikely any non-technical folks ever learn about this, much less try to decipher what it does.
Or perhaps I'm misunderstanding your comment? What do you mean exactly?
Re: Full-scale file system acceleration on GPU [pdf]
#7Interesting they would discuss system call overhead of opening a file, reading from it and closing it. Seems like in almost all cases the open and close calls would be overwhelmed by the other operations.
Re: Full-scale file system acceleration on GPU [pdf]
#8Like Microsoft DirectStorage?
Re: Full-scale file system acceleration on GPU [pdf]
#9According to this paper, GPU4FS is a file system that can run on the GPU and be accessed by applications. Since GPUs cannot make system calls, GPU4FS uses shared video memory (VRAM) and a parallel queue implementation. Applications running on the GPU can utilize GPU4FS after modifying their code, eliminating the need for a CPU-side file system when accessing the file system. The experiments are done on Optane memory.…
[flagged]
This sounds like projection.
Re: Full-scale file system acceleration on GPU [pdf]
#10Interesting they would discuss system call overhead of opening a file, reading from it and closing it. Seems like in almost all cases the open and close calls would be overwhelmed by the other operations.
For lots of small files, that might not be the case.
(I worked on a FUSE filesystem that had these issues.)