-
`v2.1` introduced a bug in detection of the number of threads. When disabling some cpus we do not detect the correct number of threads.
# Reproduce
On `conway` disable some cpus: `elab cpu enabl…
-
Hi folks,
I'm in the process of building a storage system and evaluating PhotonLib. Same architectural decisions on the system:
1. Thread per core, no context switching is desired
2. Share noth…
-
When the reconstruction volume is large, RAM needed becomes disproportional to the one CPU core:
```
Preparing 1 job with 1 CPU and 41 GB of memory per CPU.
```
Since HPC nodes don't usually h…
-
https://github.com/DataDog/glommio
I think we can use thread-per-core mode and io-uring to get higher performance
The kernel version required to run iouring is not a core issue.
-
### Describe the issue
I notice multiple threads when using ONNXRUNTIME (TRT EP). Is this a normal behavior?
…
-
The current system runs on thread per hyper-core. But this hasn't been benchmarked for a long time and the system has changed substantially since then. We should benchmark this when we have a reasonab…
-
**Describe the bug**
A race condition occurs in the ofi_get_core_info function in the libfabric library (v1.22.0). Specifically, the global variable log_prefix is modified at [line 317](https://githu…
-
### 📚 The doc issue
Hello.
I was taking a look at the document about CPU threading that torch internal uses, referring the link : https://pytorch.org/docs/stable/notes/cpu_threading_torchscript_in…
-
Hey,
Really neat project, reading through it felt like a breeze, it's some of the most beautiful Rust I've ever seen.
From my understanding of the thread per core architecture, one is supposed t…
-
This is the micro-benchmark written for the page fault scaling test. It maps a 256 MiB private anonymous area and assigns threads to trigger page faults on every pages.
Scaling micro-benchmark sour…