Vous n'êtes pas identifié(e).
L'icône rouge permet de télécharger chaque page du wiki visitée au format PDF et la grise au format ODT →
Ci-dessous, les différences entre deux révisions de la page.
Les deux révisions précédentes Révision précédente Prochaine révision | Révision précédente Prochaine révision Les deux révisions suivantes | ||
atelier:chantier:opencl-avec-amd [12/12/2021 13:40] Debian Alain [Script git] |
atelier:chantier:opencl-avec-amd [13/12/2021 21:33] Debian Alain [Commande AMD (RX 6000)] |
||
---|---|---|---|
Ligne 22: | Ligne 22: | ||
* carte AMD RX 6800 16GB | * carte AMD RX 6800 16GB | ||
le tout , fait sur linux [[doc:systeme:apt:sources.list:testing|debian testing bullseye]] / debian bookworm sid et avec | le tout , fait sur linux [[doc:systeme:apt:sources.list:testing|debian testing bullseye]] / debian bookworm sid et avec | ||
- | * X.org GNOME 3.34.2 , 3.36.2 , 40.4 et 41 | + | * X.org GNOME 3.34.2 , 3.36.2 , 40.4 et 41.1 |
- | * Blender 2.82a et 2.93.4 | + | * Blender 2.82a , 2.93.4 et 2.93.5 |
* Darktable 3.6.1-1 | * Darktable 3.6.1-1 | ||
* processeur AMD RYZEN 7 1700 X et AMD RYZEN 9 3900 X | * processeur AMD RYZEN 7 1700 X et AMD RYZEN 9 3900 X | ||
Ligne 200: | Ligne 200: | ||
prise en charge du noyau 5.11 (en théorie). | prise en charge du noyau 5.11 (en théorie). | ||
- | maintenant fonctionnel sur debian sid . (noyau 5.15.6 (kernel.org)) | + | maintenant fonctionnel sur debian sid . (noyau 5.15.6 kernel.org) |
[[https://github.com/kytulendu| -- site github de kytulendu -- ]] | [[https://github.com/kytulendu| -- site github de kytulendu -- ]] | ||
Ligne 213: | Ligne 213: | ||
<note tip> merci à kytulendu </note> | <note tip> merci à kytulendu </note> | ||
- | ===== Commande AMD (RX 6000)===== | + | ===== Commande AMD ===== |
Télécharger l'archive 21.30 | Télécharger l'archive 21.30 | ||
Ligne 243: | Ligne 243: | ||
vérifier l'installation : | vérifier l'installation : | ||
<code user>clinfo </code> | <code user>clinfo </code> | ||
- | |||
- | <note important>Malheureusement , à ce jour , OpenCL pour RX6000 ne fonctionne pas encore (noyau 5.15.0-2-amd64 bookworm/sid) </note> | ||
pour désinstaller : | pour désinstaller : | ||
<code user>sudo amdgpu-uninstall </code> | <code user>sudo amdgpu-uninstall </code> | ||
- | ==== archive au format .DEB ==== | + | ==== Sources AMD(fichier .DEB) ==== |
AMD vient de créer une archive au format DEB . | AMD vient de créer une archive au format DEB . | ||
Ligne 256: | Ligne 254: | ||
archive 21.40.1 , en théorie pour AMD RX 6000 . a vérifier . | archive 21.40.1 , en théorie pour AMD RX 6000 . a vérifier . | ||
- | aux dernières nouvelles , sur ma config , s'installe mais n'est pas fonctionnelle . | + | aux dernières nouvelles , sur ma config , installe le dépôt AMD (ubuntu). |
[[https://amdgpu-install.readthedocs.io/en/21.40/install-script.html|La Documentation officielle A.M.D. (AMDGPU) ]] | [[https://amdgpu-install.readthedocs.io/en/21.40/install-script.html|La Documentation officielle A.M.D. (AMDGPU) ]] | ||
Ligne 699: | Ligne 697: | ||
</code> | </code> | ||
- | ==== pilote 20.10 CL Info ==== | + | ==== AMD RX 6800 16GB GDDR6 ==== |
- | <code user>clinfo</code> | + | lspci -nnkd::0300 |
- | <code>Number of platforms 1 | + | <code user>0a:00.0 VGA compatible controller [0300]: Advanced Micro Devices, Inc. [AMD/ATI] Navi 21 [Radeon RX 6800/6800 XT / 6900 XT] [1002:73bf] (rev c3) |
+ | Subsystem: Sapphire Technology Limited Navi 21 [Radeon RX 6800/6800 XT / 6900 XT] [1da2:e437] | ||
+ | Kernel driver in use: amdgpu | ||
+ | Kernel modules: amdgpu | ||
+ | </code> | ||
+ | |||
+ | glxinfo -B | ||
+ | <code user>name of display: :0 | ||
+ | display: :0 screen: 0 | ||
+ | direct rendering: Yes | ||
+ | Extended renderer info (GLX_MESA_query_renderer): | ||
+ | Vendor: AMD (0x1002) | ||
+ | Device: AMD Radeon RX 6800 (SIENNA_CICHLID, DRM 3.42.0, 5.14.0-3-amd64, LLVM 12.0.1) (0x73bf) | ||
+ | Version: 21.2.4 | ||
+ | Accelerated: yes | ||
+ | Video memory: 16384MB | ||
+ | Unified memory: no | ||
+ | Preferred profile: core (0x1) | ||
+ | Max core profile version: 4.6 | ||
+ | Max compat profile version: 4.6 | ||
+ | Max GLES1 profile version: 1.1 | ||
+ | Max GLES[23] profile version: 3.2 | ||
+ | Memory info (GL_ATI_meminfo): | ||
+ | VBO free memory - total: 15158 MB, largest block: 15158 MB | ||
+ | VBO free aux. memory - total: 16286 MB, largest block: 16286 MB | ||
+ | Texture free memory - total: 15158 MB, largest block: 15158 MB | ||
+ | Texture free aux. memory - total: 16286 MB, largest block: 16286 MB | ||
+ | Renderbuffer free memory - total: 15158 MB, largest block: 15158 MB | ||
+ | Renderbuffer free aux. memory - total: 16286 MB, largest block: 16286 MB | ||
+ | Memory info (GL_NVX_gpu_memory_info): | ||
+ | Dedicated video memory: 16384 MB | ||
+ | Total available memory: 32752 MB | ||
+ | Currently available dedicated video memory: 15158 MB | ||
+ | OpenGL vendor string: AMD | ||
+ | OpenGL renderer string: AMD Radeon RX 6800 (SIENNA_CICHLID, DRM 3.42.0, 5.14.0-3-amd64, LLVM 12.0.1) | ||
+ | OpenGL core profile version string: 4.6 (Core Profile) Mesa 21.2.4 | ||
+ | OpenGL core profile shading language version string: 4.60 | ||
+ | OpenGL core profile context flags: (none) | ||
+ | OpenGL core profile profile mask: core profile | ||
+ | |||
+ | OpenGL version string: 4.6 (Compatibility Profile) Mesa 21.2.4 | ||
+ | OpenGL shading language version string: 4.60 | ||
+ | OpenGL context flags: (none) | ||
+ | OpenGL profile mask: compatibility profile | ||
+ | |||
+ | OpenGL ES profile version string: OpenGL ES 3.2 Mesa 21.2.4 | ||
+ | OpenGL ES profile shading language version string: OpenGL ES GLSL ES 3.20 | ||
+ | </code> | ||
+ | |||
+ | OpenCL enfin prêt pour RX6000 (RX6800) noyau 5.15.6 minimum : | ||
+ | clinfo : | ||
+ | <code user>alain@sid:~$ clinfo | ||
+ | Number of platforms 1 | ||
Platform Name AMD Accelerated Parallel Processing | Platform Name AMD Accelerated Parallel Processing | ||
Platform Vendor Advanced Micro Devices, Inc. | Platform Vendor Advanced Micro Devices, Inc. | ||
- | Platform Version OpenCL 2.1 AMD-APP (3075.10) | + | Platform Version OpenCL 2.0 AMD-APP (3314.0) |
Platform Profile FULL_PROFILE | Platform Profile FULL_PROFILE | ||
- | Platform Extensions cl_khr_icd cl_amd_event_callback cl_amd_offline_devices | + | Platform Extensions cl_khr_icd cl_amd_event_callback |
- | Platform Host timer resolution 1ns | + | |
Platform Extensions function suffix AMD | Platform Extensions function suffix AMD | ||
Platform Name AMD Accelerated Parallel Processing | Platform Name AMD Accelerated Parallel Processing | ||
Number of devices 1 | Number of devices 1 | ||
- | Device Name Ellesmere | + | Device Name gfx1030 |
Device Vendor Advanced Micro Devices, Inc. | Device Vendor Advanced Micro Devices, Inc. | ||
Device Vendor ID 0x1002 | Device Vendor ID 0x1002 | ||
- | Device Version OpenCL 1.2 AMD-APP (3075.10) | + | Device Version OpenCL 2.0 |
- | Driver Version 3075.10 | + | Driver Version 3314.0 (HSA1.1,LC) |
- | Device OpenCL C Version OpenCL C 1.2 | + | Device OpenCL C Version OpenCL C 2.0 |
Device Type GPU | Device Type GPU | ||
- | Device Board Name (AMD) Radeon RX 570 Series | + | Device Board Name (AMD) Navi 21 [Radeon RX 6800/6800 XT / 6900 XT] |
- | Device Topology (AMD) PCI-E, 0b:00.0 | + | Device PCI-e ID (AMD) 0x73bf |
+ | Device Topology (AMD) PCI-E, 0000:0a:00.0 | ||
Device Profile FULL_PROFILE | Device Profile FULL_PROFILE | ||
Device Available Yes | Device Available Yes | ||
Compiler Available Yes | Compiler Available Yes | ||
Linker Available Yes | Linker Available Yes | ||
- | Max compute units 32 | + | Max compute units 30 |
SIMD per compute unit (AMD) 4 | SIMD per compute unit (AMD) 4 | ||
- | SIMD width (AMD) 16 | + | SIMD width (AMD) 32 |
SIMD instruction width (AMD) 1 | SIMD instruction width (AMD) 1 | ||
- | Max clock frequency 1244MHz | + | Max clock frequency 2475MHz |
- | Graphics IP (AMD) 8.0 | + | Graphics IP (AMD) 10.3 |
Device Partition (core) | Device Partition (core) | ||
- | Max number of sub-devices 32 | + | Max number of sub-devices 30 |
Supported partition types None | Supported partition types None | ||
Supported affinity domains (n/a) | Supported affinity domains (n/a) | ||
Ligne 740: | Ligne 790: | ||
Preferred work group size (AMD) 256 | Preferred work group size (AMD) 256 | ||
Max work group size (AMD) 1024 | Max work group size (AMD) 1024 | ||
- | Preferred work group size multiple 64 | + | Preferred work group size multiple (kernel) 32 |
- | Wavefront width (AMD) 64 | + | Wavefront width (AMD) 32 |
Preferred / native vector sizes | Preferred / native vector sizes | ||
char 4 / 4 | char 4 / 4 | ||
Ligne 759: | Ligne 809: | ||
Support is emulated in software No | Support is emulated in software No | ||
Single-precision Floating-point support (core) | Single-precision Floating-point support (core) | ||
- | Denormals No | + | Denormals Yes |
Infinity and NANs Yes | Infinity and NANs Yes | ||
Round to nearest Yes | Round to nearest Yes | ||
Ligne 776: | Ligne 826: | ||
Support is emulated in software No | Support is emulated in software No | ||
Address bits 64, Little-Endian | Address bits 64, Little-Endian | ||
- | Global memory size 8022630400 (7.472GiB) | + | Global memory size 17163091968 (15.98GiB) |
- | Global free memory (AMD) 7815016 (7.453GiB) | + | Global free memory (AMD) 16760832 (15.98GiB) 16760832 (15.98GiB) |
Global memory channels (AMD) 8 | Global memory channels (AMD) 8 | ||
- | Global memory banks per channel (AMD) 16 | + | Global memory banks per channel (AMD) 4 |
Global memory bank width (AMD) 256 bytes | Global memory bank width (AMD) 256 bytes | ||
Error Correction support No | Error Correction support No | ||
- | Max memory allocation 4244635648 (3.953GiB) | + | Max memory allocation 14588628168 (13.59GiB) |
Unified memory for Host and Device No | Unified memory for Host and Device No | ||
+ | Shared Virtual Memory (SVM) capabilities (core) | ||
+ | Coarse-grained buffer sharing Yes | ||
+ | Fine-grained buffer sharing Yes | ||
+ | Fine-grained system sharing No | ||
+ | Atomics No | ||
Minimum alignment for any data type 128 bytes | Minimum alignment for any data type 128 bytes | ||
- | Alignment of base address 2048 bits (256 bytes) | + | Alignment of base address 1024 bits (128 bytes) |
+ | Preferred alignment for atomics | ||
+ | SVM 0 bytes | ||
+ | Global 0 bytes | ||
+ | Local 0 bytes | ||
+ | Max size for global variable 14588628168 (13.59GiB) | ||
+ | Preferred total size of global vars 17163091968 (15.98GiB) | ||
Global Memory cache type Read/Write | Global Memory cache type Read/Write | ||
Global Memory cache size 16384 (16KiB) | Global Memory cache size 16384 (16KiB) | ||
Global Memory cache line size 64 bytes | Global Memory cache line size 64 bytes | ||
Image support Yes | Image support Yes | ||
- | Max number of samplers per kernel 16 | + | Max number of samplers per kernel 29631 |
Max size for 1D images from buffer 134217728 pixels | Max size for 1D images from buffer 134217728 pixels | ||
- | Max 1D or 2D image array size 2048 images | + | Max 1D or 2D image array size 8192 images |
Base address alignment for 2D image buffers 256 bytes | Base address alignment for 2D image buffers 256 bytes | ||
Pitch alignment for 2D image buffers 256 pixels | Pitch alignment for 2D image buffers 256 pixels | ||
Max 2D image size 16384x16384 pixels | Max 2D image size 16384x16384 pixels | ||
- | Max 3D image size 2048x2048x2048 pixels | + | Max 3D image size 16384x16384x8192 pixels |
Max number of read image args 128 | Max number of read image args 128 | ||
Max number of write image args 8 | Max number of write image args 8 | ||
+ | Max number of read/write image args 64 | ||
+ | Max number of pipe args 16 | ||
+ | Max active pipe reservations 16 | ||
+ | Max pipe packet size 1703726280 (1.587GiB) | ||
Local memory type Local | Local memory type Local | ||
- | Local memory size 32768 (32KiB) | + | Local memory size 65536 (64KiB) |
- | Local memory syze per CU (AMD) 65536 (64KiB) | + | Local memory size per CU (AMD) 65536 (64KiB) |
Local memory banks (AMD) 32 | Local memory banks (AMD) 32 | ||
Max number of constant args 8 | Max number of constant args 8 | ||
- | Max constant buffer size 4244635648 (3.953GiB) | + | Max constant buffer size 14588628168 (13.59GiB) |
Preferred constant buffer size (AMD) 16384 (16KiB) | Preferred constant buffer size (AMD) 16384 (16KiB) | ||
Max size of kernel argument 1024 | Max size of kernel argument 1024 | ||
- | Queue properties | + | Queue properties (on host) |
Out-of-order execution No | Out-of-order execution No | ||
Profiling Yes | Profiling Yes | ||
+ | Queue properties (on device) | ||
+ | Out-of-order execution Yes | ||
+ | Profiling Yes | ||
+ | Preferred size 262144 (256KiB) | ||
+ | Max size 8388608 (8MiB) | ||
+ | Max queues on device 1 | ||
+ | Max events on device 1024 | ||
Prefer user sync for interop Yes | Prefer user sync for interop Yes | ||
+ | Number of P2P devices (AMD) 0 | ||
Profiling timer resolution 1ns | Profiling timer resolution 1ns | ||
- | Profiling timer offset since Epoch (AMD) 1591853725436918849ns (Thu Jun 11 07:35:25 2020) | + | Profiling timer offset since Epoch (AMD) 0ns (Thu Jan 1 01:00:00 1970) |
Execution capabilities | Execution capabilities | ||
Run OpenCL kernels Yes | Run OpenCL kernels Yes | ||
Run native kernels No | Run native kernels No | ||
- | Thread trace supported (AMD) Yes | + | Thread trace supported (AMD) No |
- | Number of async queues (AMD) 2 | + | Number of async queues (AMD) 8 |
- | Max real-time compute queues (AMD) 0 | + | Max real-time compute queues (AMD) 8 |
- | Max real-time compute units (AMD) 909198854 | + | Max real-time compute units (AMD) 30 |
- | SPIR versions 1.2 | + | |
printf() buffer size 4194304 (4MiB) | printf() buffer size 4194304 (4MiB) | ||
Built-in kernels (n/a) | Built-in kernels (n/a) | ||
- | Device Extensions cl_khr_fp64 cl_amd_fp64 cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_gl_sharing cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_media_ops2 cl_amd_popcnt cl_khr_image2d_from_buffer cl_khr_spir cl_khr_gl_event | + | Device Extensions cl_khr_fp64 cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_gl_sharing cl_amd_device_attribute_query cl_amd_media_ops cl_amd_media_ops2 cl_khr_image2d_from_buffer cl_khr_subgroups cl_khr_depth_images cl_amd_copy_buffer_p2p cl_amd_assembly_program |
NULL platform behavior | NULL platform behavior | ||
- | clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...) No platform | + | clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...) AMD Accelerated Parallel Processing |
- | clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...) No platform | + | clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...) Success [AMD] |
- | clCreateContext(NULL, ...) [default] No platform | + | clCreateContext(NULL, ...) [default] Success [AMD] |
- | clCreateContext(NULL, ...) [other] Success [AMD] | + | |
clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT) Success (1) | clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT) Success (1) | ||
Platform Name AMD Accelerated Parallel Processing | Platform Name AMD Accelerated Parallel Processing | ||
- | Device Name Ellesmere | + | Device Name gfx1030 |
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) No devices found in platform | clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) No devices found in platform | ||
clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) Success (1) | clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) Success (1) | ||
Platform Name AMD Accelerated Parallel Processing | Platform Name AMD Accelerated Parallel Processing | ||
- | Device Name Ellesmere | + | Device Name gfx1030 |
clCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR) No devices found in platform | clCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR) No devices found in platform | ||
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM) No devices found in platform | clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM) No devices found in platform | ||
clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL) Success (1) | clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL) Success (1) | ||
Platform Name AMD Accelerated Parallel Processing | Platform Name AMD Accelerated Parallel Processing | ||
- | Device Name Ellesmere | + | Device Name gfx1030 |
- | </code> | + | |
- | ==== AMD RX 6800 16GB GDDR6 ==== | + | ICD loader properties |
- | lspci -nnkd::0300 | + | ICD loader Name OpenCL ICD Loader |
- | <code user>0a:00.0 VGA compatible controller [0300]: Advanced Micro Devices, Inc. [AMD/ATI] Navi 21 [Radeon RX 6800/6800 XT / 6900 XT] [1002:73bf] (rev c3) | + | ICD loader Vendor OCL Icd free software |
- | Subsystem: Sapphire Technology Limited Navi 21 [Radeon RX 6800/6800 XT / 6900 XT] [1da2:e437] | + | ICD loader Version 2.2.14 |
- | Kernel driver in use: amdgpu | + | ICD loader Profile OpenCL 3.0 |
- | Kernel modules: amdgpu | + | </code> |
- | </code> | + | |
- | + | ||
- | glxinfo -B | + | |
- | <code user>name of display: :0 | + | |
- | display: :0 screen: 0 | + | |
- | direct rendering: Yes | + | |
- | Extended renderer info (GLX_MESA_query_renderer): | + | |
- | Vendor: AMD (0x1002) | + | |
- | Device: AMD Radeon RX 6800 (SIENNA_CICHLID, DRM 3.42.0, 5.14.0-3-amd64, LLVM 12.0.1) (0x73bf) | + | |
- | Version: 21.2.4 | + | |
- | Accelerated: yes | + | |
- | Video memory: 16384MB | + | |
- | Unified memory: no | + | |
- | Preferred profile: core (0x1) | + | |
- | Max core profile version: 4.6 | + | |
- | Max compat profile version: 4.6 | + | |
- | Max GLES1 profile version: 1.1 | + | |
- | Max GLES[23] profile version: 3.2 | + | |
- | Memory info (GL_ATI_meminfo): | + | |
- | VBO free memory - total: 15158 MB, largest block: 15158 MB | + | |
- | VBO free aux. memory - total: 16286 MB, largest block: 16286 MB | + | |
- | Texture free memory - total: 15158 MB, largest block: 15158 MB | + | |
- | Texture free aux. memory - total: 16286 MB, largest block: 16286 MB | + | |
- | Renderbuffer free memory - total: 15158 MB, largest block: 15158 MB | + | |
- | Renderbuffer free aux. memory - total: 16286 MB, largest block: 16286 MB | + | |
- | Memory info (GL_NVX_gpu_memory_info): | + | |
- | Dedicated video memory: 16384 MB | + | |
- | Total available memory: 32752 MB | + | |
- | Currently available dedicated video memory: 15158 MB | + | |
- | OpenGL vendor string: AMD | + | |
- | OpenGL renderer string: AMD Radeon RX 6800 (SIENNA_CICHLID, DRM 3.42.0, 5.14.0-3-amd64, LLVM 12.0.1) | + | |
- | OpenGL core profile version string: 4.6 (Core Profile) Mesa 21.2.4 | + | |
- | OpenGL core profile shading language version string: 4.60 | + | |
- | OpenGL core profile context flags: (none) | + | |
- | OpenGL core profile profile mask: core profile | + | |
- | + | ||
- | OpenGL version string: 4.6 (Compatibility Profile) Mesa 21.2.4 | + | |
- | OpenGL shading language version string: 4.60 | + | |
- | OpenGL context flags: (none) | + | |
- | OpenGL profile mask: compatibility profile | + | |
- | + | ||
- | OpenGL ES profile version string: OpenGL ES 3.2 Mesa 21.2.4 | + | |
- | OpenGL ES profile shading language version string: OpenGL ES GLSL ES 3.20 | + | |
- | </code> | + | |
- | + | ||
- | OpenCL pas prêt pour l'instant : | + | |
- | clinfo : | + | |
- | <code user>Number of platforms 0 </code> | + | |