-
@cadam11 I think we should use the vectorization functionality now in the core MJ framework to offer people the ability to auto-vectorize a file or all files in a category. My thought is that:
* Fi…
AN-BC updated
1 month ago
-
- [ ] Implement a webhook to auto-load new models, but compare performance before deploying to prod server.
- [x] Connect MLflow with DagsHub.
- [x] Track experiments using MLflow.
- [x] Exp-1 Baselin…
-
Currently working on issue https://bugzilla.mozilla.org/show_bug.cgi?id=1887312 . I discovered inefficient/high-cost (from WebAssembly compilation point of view) shuffles. These shuffles generate more…
-
test: https://gcc.godbolt.org/z/f86hxd8cT
```
#define N 480
unsigned int
f (unsigned int res, signed char *restrict a,
unsigned char *restrict b)
{
for (__INTPTR_TYPE__ i = 0; i < N; ++i…
vfdff updated
1 month ago
-
Tracking any remaining algorithms to vectorize.
Optimized via C runtime library functions, like `memcpy`, counts as vectorized too, as these functions are optimized.
See also #7.
Algorithm …
-
Hello there, I met a strange issue when using LLVM/Clang to build c code with RISC-V Vector extension enabled, see test code here https://godbolt.org/z/GreE5bTWo
I am expecting when passing `-O2 -m…
-
Hi Sasha! Nice to see your take on the llama2.rs!
I did a port of Anrej’s llama.c [here](https://github.com/gaxler/llama2.rs)
Had a chance to go over the code and compare to my version, the only…
-
# Auto-Vectorization and Store-to-Load-Forwarding | Emanuel’s Blog
I have been working a lot on Hotspot JVM C2’s auto vectorization, and intend to continue with that. You can read more in my previous…
-
# Auto-Vectorization and Store-to-Load-Forwarding | Emanuel’s Blog
I have been working a lot on Hotspot JVM C2’s auto vectorization, and intend to continue with that. You can read more in my previous…
-
@Dandandan raised the idea of considering the `slipstream` crate for SIMD / auto-vectorization.
I agree that we should consider it - if anything, to offload that part of the code-base to `slipstre…