-
Idea:
* Implemented `FrameBuffer` and `CaptureDevice` handles device specific allocation in inside it.
* V4L2 can almost support (`mmap` allocator)
* DirectShow maybe support (`IMediaSample` inte…
kekyo updated
2 years ago
-
# Proposal
## Problem statement
It would be useful to have a version of `io::copy` that can use:
- splice or sendfile, some of the existing optimizations have to be rolled back in [rust#10828…
-
I am willing to use the concurrent queue for a low latency network application. Overall, I need to enqueue network packets on one thread, and decode them in another thread - in practice that would be …
-
Hello,
With XPMEM, MPICH supports zero-copy intra-node sends for non-contiguous datatypes.
But AFAICT there are some restrictions:
- Can't use with `hindexed` or `struct` datatypes.
- The size o…
-
Zero-copy decoding consists of decompressing scanlines directly to the output buffer, this would be limited to non-interlaced images with the following PNG format -> output format combinations:
- […
-
There is a bug in the current AD implementation for eigsolve when the eigenvalues are degenerate.
A simple example
```julia
using KrylovKit
using Zygote
@testset "degenerated eigsolve ad" …
-
Hello,
I browsed the source code of chDB today (having read DuckDBs papers first) and had two questions:
As of today, chDB takes over the final query result (which is presumably refcounted) for …
-
In unix-like systems, it's possible to send files using "sendfile" (or other syscalls) to gain a little bit of performance boost but it would mean we can't use things like "gzip" and in-memory caching…
-
### Search before asking
- [X] I searched in the [issues](https://github.com/apache/pulsar/issues) and found nothing similar.
### Motivation
Here's an example of CompressionCodeZLib which has seve…
-
Most of text just exists on source code. We don't need to copy them until the source exist.
This is not trivial but worth to try if we really need to do.