-
Hello! I've made recently an Occupancy Calculator for AMD GPUs similar to [CUDA Occupancy Calculator](https://docs.nvidia.com/cuda/cuda-occupancy-calculator/index.html#abstract)](https://docs.nvidia.c…
-
### Problem Description
Composable Kernel currently only contains code to support fused attention (FA2) on RDNA3(+) architectures in the forward direction. This greatly increases the VRAM requirement…
-
### Your current environment
Hi!
I have been trying to install vLLM on a cluster that has AMD MI250X GPUs using the documentation provided and running into the following issue:
`ninja: erro…
-
AFAIK, these opcodes are not supported on GFX940.
Examples of failed tests:
buffer_wbinvl1
buffer_wbinvl1_vol
buffer_store_lds_dword s[4:7], s2 offset:4095 lds
@rampitec, should t…
-
### Problem Description
https://github.com/ROCm/rpp/blob/develop/utilities/test_suite/README.md --
```
sudo apt-get install nasm
sudo apt-get install wget
git clone -b 2.0.6.1 https://github.c…
-
### Problem Description
CTest needs to verify all components are built and functional.
Missing
* VX_RPP
### Operating System
ALL
### CPU
ALL
### GPU
AMD Instinct MI300
### Other
_No respo…
-
### Suggestion Description
This GPU does not support image instructions, resulting in compilation errors when trying to use image-based operations.
The log more or less looks like this (i am usin…
-
### Problem Description
## CTest Failure 1
```
Observed error:
In file included from /opt/rocm-6.3.0-14771/share/rpp/test/HOST/../rpp_test_suite_misc.h:25:
1: /opt/rocm-6.3.0-14771/share/rpp/test…
-
**Describe the bug**
omniperf is unable to parse the input application's string arguments on MI300 (Not observed on MI200).
**Development Environment:**
- Linux Distribution: Ubuntu 22.04.4 LTS
…
-
### Problem Description
during Debug build, facing R_X86_64_REX_GOTPCRELX( R_X86_64_PC32) out of range errors as following:
```yml
# issue1
[ 83%] Built target test_convnd_bwd_data
ld.lld: …