-
How do you plan to optimize serial processing on SIMD?
Another thing, how your project bypassed [this](https://en.wikipedia.org/wiki/Amdahl%27s_law) law?
-
In combination with issue #1, extend the tuning executable to read and parse the log file that is generated. The log file contains all the clBLAS functions and their parameters that a particular app n…
kknox updated
7 years ago
-
**🐛 Bug**
### GatherV2
There is at least one wrong Antares IR in the following candidates.
```
[INFO] 2021-02-01T03:02:52z src/nnfusion/engine/pass/graph/kernel_tuning.cpp 249 GatherV2,…
-
### Code Version:
[v0.9.dev0 ]
### Exec tune_relay_vta.py through VTA interface using SIM device
Host: start a tracker
python3 -m tvm.exec.rpc_tracker --host=0.0.0.…
-
Hi I am getting this error when I set use_gpu=True.
(scheduler +6s) Tip: use `ray status` to view detailed cluster status. To disable these messages, set RAY_SCHEDULER_EVENTS=0.
(scheduler +6s) Er…
-
This issue exists to document what I think are the highest priorities in the short-medium term.
**Models and training:**
- [x] Document how to repeat the model training process (https://github.c…
-
Attached is a reproducer from Chromium:
[formatutilsgl.ii.gz](https://github.com/llvm/llvm-project/files/14448933/formatutilsgl.ii.gz)
Without runtime runtime counter relocation it compiles in 14 …
-
-
We should experiment more with alternative allocators, such as `jemalloc`, to see if we can optimize our allocation behavior and fragmentation in a cheap (essentially free) way.
-
## Motivation
WebAssembly runtimes, such as the open-source WasmEdge runtime, are very well suited for running lightweight serverless functions. A particularly useful use case is Wasm functions tha…