-
Here are my results from running the profiling methods included in https://github.com/johnmyleswhite/NullableArrays.jl/blob/master/perf/mapreduce.jl:
```
julia> profile_all()
Method: mapreduce(f, op,…
-
Performance profiling has indicated that a larger new gen with less frequent new gen collections could be beneficial for reducing startup time and/or reducing jank. However increasing new gen size by …
-
I am trying to use the NKI Allocation API to keep multiple PSUM banks active. In the documentation, I see, "rather than laying out
multiple 128x512 tensors in the same partition with offset `byte_add…
-
Hi,
This is not really an issue. I am wondering if the following is expected to allocate:
```julia
julia> F = zeros(31,61);
julia> PS = FastSphericalHarmonics.plan_sph_synthesis(copy(F))
Fa…
-
**Description:**
Several users have encountered issues with profiling GPU workloads using NVIDIA Nsight Compute (NCU) when the NVIDIA Multiprocess Service (MPS) is enabled. This includes difficulti…
-
### Describe the bug
NodesStats contains per-shard stats information from the node (NodeStats#indices). Admin API `/_cat/nodes` make broadcast calls to all nodes in cluster using TransportNodesSt…
-
And. Allocation timeline has v heavy instrumentation. Every single allocation triggers a callstack collection. So. Yah it will slow a busy app down to a crawl. Whereas allocation profile won't because…
-
We do have a use-case for low overhead heap profiling (production ready, continuously on) that is currently hard to archive in .NET. I would like to start a conversation about what would be needed in …
-
### Description
While tracking down memory leaks for my app, I noticed that Accelerometer and Gyroscope API produces a memory leak over time while listening `ReadingChanged `events.
My app is me…
-
Hi akka-http team,
in one of my applications I’m using the akka-http client and a few days ago I did some load testing and profiling to see, which components are doing most of the allocations and are…