-
### Describe the bug
I'm observing an annoying behavior with a .NET Core 3.1 web application. The memory used by the IIS process gradually increases over time. Before posting, I did some investigat…
-
### Summary
Currently we have been using an internal mock server `useMockServer` to simulate backend data fetching with the data source. It has a few caveats.
1. The proper network requests are …
-
# Key Takeaway:
- GPU cares about parallelism
- GPU cares about throughput (bandwidth) instead of latency for single thread (task(=)
- Memory hierarchy
-
## AX+Y demo
With memory ba…
-
**Section 1 - Create Virtual machine, Create Storage Account, Create File Share, and Create Storage Sync Service**
1.1. Search for "Virtual Machine" in the Azure portal and click "+ Add" to create a…
-
Don't take this as a negative criticism. There is a lot of content in this issue, which is not meant as an attack on code quality. I am merely attempting to point out how difficult it is to use `unsaf…
-
Apple figured out that precomputing a {Selector, IMP} static hash table significantly improves dispatch time and the memory footprint. This cache is stored inside the DYLD shared cache and includes th…
-
**Description**
Not technically a bug, but I have noticed that we have been doing a lazy parallelization (including from my side) in many loops.
For example see:
https://github.com/KratosMulti…
-
Dear @vincefn,
I have made significant changes to the register assignment logic of VkFFT, which should improve the generated kernel instructions usage, shared memory transfers, and occupancy, so I …
DTolm updated
1 month ago
-
I assume you probably only performance tested the A100, and saw that there is no issue there, but on my 2070s, its occupancy is reduced by 50%.
I read the source code and it seems to be hardcoded.
…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues.
### Which plugins are affected?
Storage
### Which platforms are affected?
iOS
### Description
The now closed …