AUR (en) - opencl-amd-dev

Search Criteria

Enter search criteria

Search by

Keywords

Out of Date

Sort by

Sort order

Per page

Package Details: opencl-amd-dev 1:6.4.0-1

Package Actions

Git Clone URL:	https://aur.archlinux.org/opencl-amd-dev.git (read-only, click to copy)
Package Base:	opencl-amd-dev
Description:	OpenCL SDK / HIP SDK / ROCM Compiler. This package needs at least 20GB of disk space.
Upstream URL:	http://www.amd.com
Licenses:	custom:AMD
Conflicts:	composablekernel-dev, hipblas, hipblas-common-dev, hipblas-dev, hipblaslt, hipblaslt-dev, hipcub, hipcub-dev, hipfft, hipfft-dev, hipfort, hipfort-dev, hipify-clang, hiprand, hiprand-dev, hipsolver, hipsolver-dev, hipsparse, hipsparse-dev, hipsparselt, hipsparselt-dev, hiptensor, hiptensor-dev, migraphx, migraphx-dev, miopen, miopen-hip, miopen-hip-dev, mivisionx, mivisionx-dev, openmp-extras-dev, rccl, rccl-dev, rocalution, rocalution-dev, rocblas, rocblas-dev, rocfft, rocfft-dev, rocm-developer-tools, rocm-hip-libraries, rocm-hip-runtime-dev, rocm-hip-sdk, rocm-llvm, rocm-ml-libraries, rocm-ml-sdk, rocm-opencl-sdk, rocprim, rocprim-dev, rocprofiler-compute, rocprofiler-sdk, rocprofiler-sdk-roctx, rocprofiler-systems, rocrand, rocrand-dev, rocsolver, rocsolver-dev, rocsparse, rocsparse-dev, rocthrust, rocthrust-dev, rocwmma-dev, rpp, rpp-dev
Provides:	composablekernel-dev, half, hipblas, hipblas-common-dev, hipblas-dev, hipblaslt, hipblaslt-dev, hipcub, hipcub-dev, hipfft, hipfft-dev, hipfort, hipfort-dev, hipify-clang, hiprand, hiprand-dev, hipsolver, hipsolver-dev, hipsparse, hipsparse-dev, hipsparselt, hipsparselt-dev, hiptensor, hiptensor-dev, migraphx, migraphx-dev, miopen, miopen-hip, miopen-hip-dev, mivisionx, mivisionx-dev, openmp-extras-dev, rccl, rccl-dev, rocalution, rocalution-dev, rocblas, rocblas-dev, rocfft, rocfft-dev, rocm-developer-tools, rocm-hip-libraries, rocm-hip-runtime-dev, rocm-hip-sdk, rocm-llvm, rocm-ml-libraries, rocm-ml-sdk, rocm-opencl-sdk, rocprim, rocprim-dev, rocprofiler-compute, rocprofiler-sdk, rocprofiler-sdk-roctx, rocprofiler-systems, rocrand, rocrand-dev, rocsolver, rocsolver-dev, rocsparse, rocsparse-dev, rocthrust, rocthrust-dev, rocwmma-dev, rpp, rpp-dev
Submitter:	luciddream
Maintainer:	luciddream
Last Packager:	luciddream
Votes:	9
Popularity:	0.26
First Submitted:	2021-12-26 15:01 (UTC)
Last Updated:	2025-04-11 22:54 (UTC)

Dependencies (5)

blas (blis-cblas-openmp^AUR, blis-cblas^AUR, aocl-blis-aocc^AUR, blas-git^AUR, atlas-lapack^AUR, blas-aocl-gcc^AUR, blas-aocl-aocc^AUR, blis-git^AUR, blis^AUR, blas-mkl^AUR, aocl-blis^AUR, openblas-lapack^AUR, blas-openblas)
lapack (aocl-libflame-aocc^AUR, lapack-git^AUR, atlas-lapack^AUR, blas-aocl-gcc^AUR, blas-aocl-aocc^AUR, blas-mkl^AUR, aocl-libflame^AUR, openblas-lapack^AUR, blas-openblas)
opencl-amd^AUR (amdapp-sdk^AUR)
suitesparse
wget (wget-git^AUR, wurl^AUR) (make)

Required by (153)

adaptivecpp (requires rocm-llvm) (make)
adaptivecpp-git (requires rocm-llvm) (make)
darknet-hankai-git (requires rocm-hip-sdk) (optional)
ggml-hipblas-git (requires rocm-hip-sdk) (make)
ggml-hipblas-git (requires hipblas)
ginkgo-hpc-cuda-git (requires hipfft) (make)
ginkgo-hpc-cuda-git (requires hiprand) (make)
ginkgo-hpc-cuda-git (requires hipblas) (make)
ginkgo-hpc-cuda-git (requires hipsparse) (make)
ginkgo-hpc-cuda-git (requires rocthrust) (make)
ginkgo-hpc-docs-git (requires hipfft) (make)
ginkgo-hpc-docs-git (requires hiprand) (make)
ginkgo-hpc-docs-git (requires hipblas) (make)
ginkgo-hpc-docs-git (requires hipsparse) (make)
ginkgo-hpc-docs-git (requires rocthrust) (make)
ginkgo-hpc-git (requires hipfft) (make)
ginkgo-hpc-git (requires hiprand) (make)
ginkgo-hpc-git (requires hipblas) (make)
ginkgo-hpc-git (requires hipsparse) (make)
ginkgo-hpc-git (requires rocthrust) (make)
ginkgo-hpc-hip-git (requires hipfft)
ginkgo-hpc-hip-git (requires hipfft) (make)
ginkgo-hpc-hip-git (requires hiprand)
ginkgo-hpc-hip-git (requires hiprand) (make)
ginkgo-hpc-hip-git (requires hipblas)
ginkgo-hpc-hip-git (requires hipblas) (make)
ginkgo-hpc-hip-git (requires hipsparse)
ginkgo-hpc-hip-git (requires hipsparse) (make)
ginkgo-hpc-hip-git (requires rocthrust) (make)
hipsycl-rocm (requires rocm-hip-sdk)
hipsycl-rocm-git (requires rocm-hip-sdk)
koboldcpp-hipblas (requires hipblas)
llama-cpp-rocm-git (requires rocm-llvm) (make)
llama-cpp-rocm-git (requires hipblas)
llama.cpp-hip (requires rocblas)
llama.cpp-hip (requires rocm-hip-sdk) (make)
llama.cpp-hip (requires hipblas)
llamafile (requires hipblas) (optional)
llamafile-bin (requires hipblas) (optional)
llamafile-git (requires hipblas) (optional)
local-ai-hipblas (requires rocm-hip-sdk) (make)
localai-git (requires miopen-hip) (make)
localai-git (requires rocm-hip-sdk) (make)
localai-git (requires rccl) (make)
localai-git-cuda (requires miopen-hip) (make)
localai-git-cuda (requires rocm-hip-sdk) (make)
localai-git-cuda (requires rccl) (make)
localai-git-cuda-python (requires miopen-hip) (make)
localai-git-cuda-python (requires rocm-hip-sdk) (make)
localai-git-cuda-python (requires rccl) (make)
localai-git-python (requires miopen-hip) (make)
localai-git-python (requires rocm-hip-sdk) (make)
localai-git-python (requires rccl) (make)
localai-git-rocm (requires miopen-hip) (make)
localai-git-rocm (requires rocm-hip-sdk) (make)
localai-git-rocm (requires hipblas)
localai-git-rocm (requires rccl) (make)
localai-git-rocm (requires rocblas)
localai-git-rocm-python (requires miopen-hip) (make)
localai-git-rocm-python (requires rocm-hip-sdk) (make)
localai-git-rocm-python (requires rccl) (make)
migraphx (requires half) (make)
migraphx (requires miopen)
miopen-opencl (requires rocm-llvm)
miopen-opencl (requires rocblas)
mivisionx (requires migraphx)
mivisionx (requires miopen-hip)
ollama-rocm-git (requires rocblas)
ollama-rocm-git (requires rocblas) (make)
ollama-rocm-git (requires rocm-hip-sdk) (make)
ollama-rocm-git (requires rocm-opencl-sdk) (make)
ollama-rocm-git (requires rocsolver)
ollama-rocm-git (requires rocsolver) (make)
ollama-rocm-git (requires rocsparse)
ollama-rocm-git (requires rocsparse) (make)
ollama-rocm-git (requires hipblas)
ollama-rocm-git (requires hipblas) (make)
opencl-amd (optional)
openmp-extras (requires rocm-llvm)
python-bitsandbytes-rocm-git (requires hipcub)
python-bitsandbytes-rocm-git (requires hiprand)
python-bitsandbytes-rocm-git (requires hipsparse)
python-bitsandbytes-rocm-git (requires rocthrust)
python-bitsandbytes-rocm-git (requires hipblaslt)
python-cupy-rocm (requires rocm-hip-sdk)
python-cupy-rocm (requires rocm-hip-sdk) (make)
python-jax-rocm (requires rocm-hip-sdk) (make)
python-jax-rocm (requires rccl)
python-jax-rocm (requires rccl) (make)
python-jax-rocm (requires miopen)
python-jax-rocm (requires miopen) (make)
python-pytorch-cxx11abi (requires hipblaslt) (make)
python-pytorch-cxx11abi (requires rocm-hip-sdk) (make)
python-pytorch-cxx11abi (requires miopen-hip) (make)
python-pytorch-cxx11abi-cuda (requires hipblaslt) (make)
python-pytorch-cxx11abi-cuda (requires rocm-hip-sdk) (make)
python-pytorch-cxx11abi-cuda (requires miopen-hip) (make)
python-pytorch-cxx11abi-opt (requires hipblaslt) (make)
python-pytorch-cxx11abi-opt (requires rocm-hip-sdk) (make)
python-pytorch-cxx11abi-opt (requires miopen-hip) (make)
python-pytorch-cxx11abi-opt-cuda (requires hipblaslt) (make)
python-pytorch-cxx11abi-opt-cuda (requires rocm-hip-sdk) (make)
python-pytorch-cxx11abi-opt-cuda (requires miopen-hip) (make)
python-pytorch-cxx11abi-opt-rocm (requires miopen-hip)
python-pytorch-cxx11abi-opt-rocm (requires miopen-hip) (make)
python-pytorch-cxx11abi-opt-rocm (requires hipblaslt)
python-pytorch-cxx11abi-opt-rocm (requires hipblaslt) (make)
python-pytorch-cxx11abi-opt-rocm (requires rocm-hip-sdk)
python-pytorch-cxx11abi-opt-rocm (requires rocm-hip-sdk) (make)
python-pytorch-cxx11abi-rocm (requires miopen-hip)
python-pytorch-cxx11abi-rocm (requires miopen-hip) (make)
python-pytorch-cxx11abi-rocm (requires hipblaslt) (make)
python-pytorch-cxx11abi-rocm (requires hipblaslt)
python-pytorch-cxx11abi-rocm (requires rocm-hip-sdk)
python-pytorch-cxx11abi-rocm (requires rocm-hip-sdk) (make)
python-tensorflow-opt-rocm (requires rocm-hip-sdk)
python-tensorflow-opt-rocm (requires rocm-hip-sdk) (make)
python-tensorflow-opt-rocm (requires rccl)
python-tensorflow-opt-rocm (requires rccl) (make)
python-tensorflow-opt-rocm (requires miopen)
python-tensorflow-opt-rocm (requires miopen) (make)
python-tensorflow-rocm (requires rccl)
python-tensorflow-rocm (requires rccl) (make)
python-tensorflow-rocm (requires miopen)
python-tensorflow-rocm (requires miopen) (make)
python-tensorflow-rocm (requires rocm-hip-sdk)
python-tensorflow-rocm (requires rocm-hip-sdk) (make)
python-torchvision-rocm (requires rocm-hip-sdk) (make)
python-torchvision-rocm (requires miopen-hip) (make)
rocblas-gfx1010-backend (requires rocblas)
rocm-validation-suite (requires rocblas)
rocsparse-gfx1010 (requires rocprim)
rocwmma (requires rocblas)
shadps4 (requires half) (make)
shadps4-git (requires half) (make)
stable-diffusion.cpp-hipblas-git (requires rocm-hip-sdk) (make)
stable-diffusion.cpp-hipblas-git (requires hipblas)
tensorflow-opt-rocm (requires rocm-hip-sdk) (make)
tensorflow-opt-rocm (requires rccl)
tensorflow-opt-rocm (requires rccl) (make)
tensorflow-opt-rocm (requires miopen)
tensorflow-opt-rocm (requires miopen) (make)
tensorflow-opt-rocm (requires rocm-hip-sdk)
tensorflow-rocm (requires rccl)
tensorflow-rocm (requires rccl) (make)
tensorflow-rocm (requires rocm-hip-sdk)
tensorflow-rocm (requires miopen)
tensorflow-rocm (requires rocm-hip-sdk) (make)
tensorflow-rocm (requires miopen) (make)
torchvision-rocm (requires rocm-hip-sdk) (make)
torchvision-rocm (requires miopen-hip) (make)
xkblas (requires hipify-clang) (make)
xkblas (requires hipblas)

Sources (56)

Pinned Comments

luciddream commented on 2022-01-12 16:47 (UTC) (edited on 2025-04-11 22:57 (UTC) by luciddream)

Latest release: 6.4.0. It uses 12.67GB of disk.

Latest Comments

« First ‹ Previous 1 .. 4 5 6 7 8 9

esistgut commented on 2022-01-11 16:15 (UTC)

This is my rocminfo:

ROCk module is loaded
=====================    
HSA System Attributes    
=====================    
Runtime Version:         1.1
System Timestamp Freq.:  1000.000000MHz
Sig. Max Wait Duration:  18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count)
Machine Model:           LARGE                              
System Endianness:       LITTLE                             

==========               
HSA Agents               
==========               
*******                  
Agent 1                  
*******                  
  Name:                    AMD Ryzen 7 3700X 8-Core Processor 
  Uuid:                    CPU-XX                             
  Marketing Name:          AMD Ryzen 7 3700X 8-Core Processor 
  Vendor Name:             CPU                                
  Feature:                 None specified                     
  Profile:                 FULL_PROFILE                       
  Float Round Mode:        NEAR                               
  Max Queue Number:        0(0x0)                             
  Queue Min Size:          0(0x0)                             
  Queue Max Size:          0(0x0)                             
  Queue Type:              MULTI                              
  Node:                    0                                  
  Device Type:             CPU                                
  Cache Info:              
    L1:                      32768(0x8000) KB                   
  Chip ID:                 0(0x0)                             
  Cacheline Size:          64(0x40)                           
  Max Clock Freq. (MHz):   3600                               
  BDFID:                   0                                  
  Internal Node ID:        0                                  
  Compute Unit:            16                                 
  SIMDs per CU:            0                                  
  Shader Engines:          0                                  
  Shader Arrs. per Eng.:   0                                  
  WatchPts on Addr. Ranges:1                                  
  Features:                None
  Pool Info:               
    Pool 1                   
      Segment:                 GLOBAL; FLAGS: FINE GRAINED        
      Size:                    32848796(0x1f53b9c) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
    Pool 2                   
      Segment:                 GLOBAL; FLAGS: KERNARG, FINE GRAINED
      Size:                    32848796(0x1f53b9c) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
    Pool 3                   
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED      
      Size:                    32848796(0x1f53b9c) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
  ISA Info:                
*******                  
Agent 2                  
*******                  
  Name:                    gfx1030                            
  Uuid:                    GPU-XX                             
  Marketing Name:          AMD Radeon RX 6900 XT              
  Vendor Name:             AMD                                
  Feature:                 KERNEL_DISPATCH                    
  Profile:                 BASE_PROFILE                       
  Float Round Mode:        NEAR                               
  Max Queue Number:        128(0x80)                          
  Queue Min Size:          4096(0x1000)                       
  Queue Max Size:          131072(0x20000)                    
  Queue Type:              MULTI                              
  Node:                    1                                  
  Device Type:             GPU                                
  Cache Info:              
    L1:                      16(0x10) KB                        
    L2:                      4096(0x1000) KB                    
    L3:                      131072(0x20000) KB                 
  Chip ID:                 29631(0x73bf)                      
  Cacheline Size:          64(0x40)                           
  Max Clock Freq. (MHz):   2660                               
  BDFID:                   2816                               
  Internal Node ID:        1                                  
  Compute Unit:            80                                 
  SIMDs per CU:            2                                  
  Shader Engines:          8                                  
  Shader Arrs. per Eng.:   2                                  
  WatchPts on Addr. Ranges:4                                  
  Features:                KERNEL_DISPATCH 
  Fast F16 Operation:      FALSE                              
  Wavefront Size:          32(0x20)                           
  Workgroup Max Size:      1024(0x400)                        
  Workgroup Max Size per Dimension:
    x                        1024(0x400)                        
    y                        1024(0x400)                        
    z                        1024(0x400)                        
  Max Waves Per CU:        32(0x20)                           
  Max Work-item Per CU:    1024(0x400)                        
  Grid Max Size:           4294967295(0xffffffff)             
  Grid Max Size per Dimension:
    x                        4294967295(0xffffffff)             
    y                        4294967295(0xffffffff)             
    z                        4294967295(0xffffffff)             
  Max fbarriers/Workgrp:   32                                 
  Pool Info:               
    Pool 1                   
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED      
      Size:                    16760832(0xffc000) KB              
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       FALSE                              
    Pool 2                   
      Segment:                 GROUP                              
      Size:                    64(0x40) KB                        
      Allocatable:             FALSE                              
      Alloc Granule:           0KB                                
      Alloc Alignment:         0KB                                
      Accessible by all:       FALSE                              
  ISA Info:                
    ISA 1                    
      Name:                    amdgcn-amd-amdhsa--gfx1030         
      Machine Models:          HSA_MACHINE_MODEL_LARGE            
      Profiles:                HSA_PROFILE_BASE                   
      Default Rounding Mode:   NEAR                               
      Default Rounding Mode:   NEAR                               
      Fast f16:                TRUE                               
      Workgroup Max Size:      1024(0x400)                        
      Workgroup Max Size per Dimension:
        x                        1024(0x400)                        
        y                        1024(0x400)                        
        z                        1024(0x400)                        
      Grid Max Size:           4294967295(0xffffffff)             
      Grid Max Size per Dimension:
        x                        4294967295(0xffffffff)             
        y                        4294967295(0xffffffff)             
        z                        4294967295(0xffffffff)             
      FBarrier Max Size:       32                                 
*** Done ***

esistgut commented on 2022-01-11 16:14 (UTC)

I installed python 3.9 from the AUR package and then installed pytorch with the same command you posted but it is not working:

(venv) esistgut@nibiru:~/coding/python/fastai$ python --version
Python 3.9.9
(venv) esistgut@nibiru:~/coding/python/fastai$ cat asd.py 
import torch

if torch.opencl.is_available():
    device = torch.device("opencl")
else:
    device = torch.device("cpu")

print(device)
(venv) esistgut@nibiru:~/coding/python/fastai$ python asd.py 
"hipErrorNoBinaryForGpu: Unable to find code object for all current devices!"
Aborted (core dumped)

luciddream commented on 2022-01-11 15:47 (UTC) (edited on 2022-01-11 15:52 (UTC) by luciddream)

Hi @esistgut, Yes, it should provide all files necessary. However I don't have a supported GPU to test if everything works, so feel free to report your experience :)

Personally I've installed Python 3.9 which is necessary, then Pytorch by running the command:

python39 pip install --pre torch torchvision -f https://download.pytorch.org/whl/nightly/rocm4.2/torch_nightly.html

esistgut commented on 2022-01-11 15:29 (UTC)

Hi, first off: thank you for your work. Can I ask if this provides support for the hip/rocm environment? I'm trying to use pytorch/rocm https://pytorch.org/get-started/locally/#linux-pip but installing it from the other Arch packages is too resource intensive so I'm looking for a way to install the prebuilt binary from AMD.