-
I looked at the generated assembler code for auto vectorisation across work-items, and for manual vectorisation using 4 and 8 width vector types.
file kernel_auto.cl
```
__kernel void benchmark_op(
…
-
[Implements #13334 ]
As per https://discourse.llvm.org/t/rfc-scalable-vectorisation-in-linalg/, we need to add any missing support for scalable vectors in the Vector --> LLVM lowering path.
-
1. Garder des fichiers SVG de petite taille (inkscape à tendance à rajouter plein de balises dans le SVG)
2. Doit-on utiliser des SVG non compressés pour Git ?
3. Expliquer `potrace` (vectorisation de…
-
| | |
|--------------------|----|
| Bugzilla Link | [PR43161](https://bugs.llvm.org/show_bug.cgi?id=43161) |
| Status | NEW |
| Importance | P normal |
|…
-
- [x] Add configuration for multithreading (e.g. clang multithreading fails unittests, cf. #1026) - handled in #1028
- [x] Build and test in Debug and Release mode (handled in #1028)
- [x] Add confi…
-
Hi really cool repo 🚀
I am 100% sure that this this code can be *significantly* sped up by using numpy vectorisation.
I was able to write a pure numpy-python implementation which could downsa…
-
When JIT compiling and running of the VM is it possible to ensure, perhaps through additional tests, that the bytecode gets compiled and VM implementation, is the best possible set of instruction. Thi…
-
Hello,
so i've somehow managed to write a filter that crackles when compiled with -vec -vc 16, but runs fine without the -vc 16 or without vectorisation at all. Could this be a bug on my part? Anyone…
-
The level of support and performance for SVE and scalable vectors in IREE are quite encouraging. It's good time to start looking into Data Tiling.
- [ ] Add tests for `linalg.mmt4d` in MLIR core (r…
-
The mathematics input should support the following features
- [x] Assignment
- [x] Solve Arrow
- [ ] Multiple lines (`3+4\xrightarrow{\begin{equation}cat \\ neko \\ lol\end{equation}}7`)
- Matrix
…