There is no thread related ops. Besides, multi threads is faster than one
threads.
---
[Visit
Topic](https://discuss.tvm.ai/t/performance-of-same-op-and-workload-in-different-model-varies-differently/7766/3)
to respond.
You are receiving this because you enabled mailing list mode.
To un
> However, when setting `OMP_NUM_THREADS=1` the model inference time is same,
> seems it’s a problem with multiple threads.
Will it be possible that there's any thread realated limitation in your pytorch
script?
---
[Visit
Topic](https://discuss.tvm.ai/t/performance-of-same-op-and-work
Compared two similar Bert models running on CPU with TVM, one is PyTorch model,
the other is MXNet model. Due to the large performance difference, I did some
profiling. The result shows the run time of the same operation(matmul) with
same workload varies big.
ENV:
1. TVM: build with MKL.
2.
Hi,
I have tried to implement gotvm as a GPU-accelerating deep learning runtime
system on my edge computing architecture.
When I make gotvm without cuda, there is no error.
However, when I uncomment the cuda-related lines in tvm_runtime_pack.cc, the
following errors are occurred.
$ make
Hi, I'm trying to compile the following trivial function:
```
fn (%p0: Tensor[(3), bool], Primitive=1) -> Tensor[(3), int32] {
where(%p0, 1 /* ty=int32 */, -1 /* ty=int32 */) /* ty=Tensor[(3), int32] */
}
```
Note that the second and third arg to `where` is a scalar. Since this is not
suppor
