Comments (4)
These are number of VGPR's per CU.
It is eventually from:
from hip.
Hi @yxsamliu. Thanks a lot for your help! That's indeed exactly what I was looking for.
In my code, I'm now retrieving the number of VGPRs and SGPRs from the comgr, by proceeding similarly as in the code in rocdevice.cpp
that you had referred me to.
I found that most of the functions used in rocdevice.cpp
are available from the api in amd_comgr/amd_comgr.h
. However, the function getValueFromIsaMeta
is in rocdevice.cpp
but it appears it's not in amd_comgr/amd_comgr.h
. So it might be a suggestion to try to include this function in amd_comgr/amd_comgr.h
. I'd be happy to post it as a suggestion on a GitHub repository, but it seems RadeonOpenCompute/llvm-project/tree/amd-stg-open/amd/comgr
doesn't accept issues.
from hip.
comgr was migrated from https://github.com/RadeonOpenCompute/ROCm-CompilerSupport
You may open an issue there
from hip.
Closing the issue, since this is not related to HIP.
Please open a ticket https://github.com/RadeonOpenCompute/ROCm-CompilerSupport here as @yxsamliu suggested.
from hip.
Related Issues (20)
- What are the supported APIs in HIP Graph Management? HOT 4
- [Issue]: Multiple definition error caused by using <hip/hip_bf16.h> HOT 1
- [Issue]: Unable to find header file cmath.h HOT 2
- [Issue]: lld: error: undefined hidden symbol: __ockl_get_group_id, __ockl_get_local_size, __ockl_get_local_id HOT 5
- [Issue]: hipModuleLoad returns error HOT 3
- [Issue]: `__syncthreads` not syncing global memory as per its definition. HOT 7
- [Documentation]: Add information that building on Windows is not supported HOT 1
- [Issue]: Stable diffusion, Pytorch conv2d breaks in rocm 6.0 HOT 2
- Is there any lossless compression available on AMD GPUs in ROCm or HIP? HOT 1
- [Issue]: Unable to install HIP extension for Visual Studio 2022 HOT 8
- [Feature]: Allow specifying maximum size for memory pool HOT 1
- [Issue]: templated __constant__ variables crashes in hipMemcpyToSymbol on ROCm 5.7.1
- support of __float2bfloat162_rn HOT 3
- [Feature]: Make the `options` parameter to `hiprtcCompileProgram` const char* const *` HOT 13
- [Documentation]: examples in "Reference" contain multiple syntax errors HOT 1
- [Issue]: `hipDeviceSetLimit(hipLimitMallocHeapSize, -)` does not behave as specified HOT 2
- [Documentation]: build guide does not handle dependency CppHeaderParser HOT 1
- [Issue]: Windows HIP SDK CMake HIP language support not working HOT 1
- [Issue]: COMGR failed to get code object ISA name HOT 6
- [Issue]: Cannot port with https://rocmdocs.amd.com/projects/HIP/en/latest/user_guide/hip_porting_guide.html
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from hip.