-
### 请提出你的问题 Please ask your question
mac环境
使用paddlepaddle-gpu预测模型,新装的虚拟环境,报错信息:Error: ../paddle/phi/kernels/gpu/embedding_kernel.cu:45 Assertion `id < N` failed. Id should smaller than 40000 but rec…
-
I'm facing a problem about nccl kernel overlaping with a cutlass gemm kernel.
I used a cutlass gemm kernel with a grid size of and my GPU has 142 SMs, so apparently there is a surplus of SMs. Then I…
-
**Describe the bug**
The current implementation of TDIGEST_MERGE when used in a group by context launches separate GPU operations (kernels/memory copies) on the order of the number of groups in the o…
-
* [ ] more selective ghost communication #4921
* [ ] Use AVX vectorization in all kernels (streaming, boundaries, reset force, ...). (It might be useful to automate the generatoin of kernel_traits.h…
-
In particular, I am interested to know:
- Is the aim to be a single-source compute language like CUDA?
- Can you run the same kernels both in the CPU and GPU?
- Is the aim to expose a set of common…
-
Hi dear team,
Is there any other way to accelerate this conv (ic=16, oc=16, height=208, width=32, stride=1, kernel=3) on a single core?
```bash
ONEDNN_VERBOSE=1 numactl -C 1 -m 0 ./benchdnn --m…
-
```chpl
on here.gpus[0] {
var myAtomic: atomic int;
@assertOnGpu
foreach i in 1..10 {
myAtomic.fetchAdd(i);
}
writeln(myAtomic);
}
```
fails because the loop is not GPU-e…
-
Hi,
I reported this issue twice on the fedora discussion board and had no answer.
Every video I click in Kodi flatpak (any version) results in an immediate crash with linux kernel 6.10.x:
```…
-
Hello,
I've been trying to compile spral for a while now to use it later with Ipopt. First , when compiling with autotools and running make check, the test corresponding to ssids_test fails with a …
-
**Describe the bug**
On the `2.x` branch, `omniperf profile` and the kernel filtering `-k` option is not limiting the kernels that are being profiled. After running `omniperf analyze` all kernels are…