cancel
Showing results for 
Search instead for 
Did you mean: 

OpenCL

TheRealLoki
Journeyman III

OpenCl reports two devices with a 6900 XT

Hi,

I am trying to get my OpenCl program running with one 6900XT (it works fine with one and two 2080ti). The problem is, that clGetDeviceIDs reports two devices, and clGetDeviceInfo says both are "gfx 1030". Is this correct? Is the GPU logically split into two devices? I found no information about that. Further observations are:

- clGetDeviceInfo reports 40 compute units for each device. The 6900XT should have 80. That would support the theory of two logical devices
- geekbench allows to select two 6900XT with OpenCl, but only one device with Vulkan
- the performance of the GPU is what can be expected (tested with furmark)
- My code runs fine with one "gfx 1030" device (no matter with which of both), but the performance is what I would expect from a "half" 6900XT; it crashes if I try to use both simultaneously.

I am using a i9-7900X with 64gb ram, Windows 10, driver version 22.1.2.

Regards,
        loki

0 Likes
12 Replies
dipak
Staff

Hi @TheRealLoki ,

Thank you for reporting it. I've whitelisted you and moved the post to the OpenCL forum.

Can you please share the clinfo output?

Thanks.

0 Likes

Hi,

here is the clinfo output:

 

 

Number of platforms 1
Platform Name AMD Accelerated Parallel Processing
Platform Vendor Advanced Micro Devices, Inc.
Platform Version OpenCL 2.1 AMD-APP (3354.13)
Platform Profile FULL_PROFILE
Platform Extensions cl_khr_icd cl_khr_d3d10_sharing cl_khr_d3d11_sharing cl_khr_dx9_media_sharing cl_amd_event_callback cl_amd_offline_devices
Platform Extensions function suffix AMD
Platform Host timer resolution 100ns

Platform Name AMD Accelerated Parallel Processing
Number of devices 2
Device Name gfx1030
Device Vendor Advanced Micro Devices, Inc.
Device Vendor ID 0x1002
Device Version OpenCL 1.2 AMD-APP (3354.13)
Driver Version 3354.13 (PAL,LC)
Device OpenCL C Version OpenCL C 1.2
Device Type GPU
Device Board Name (AMD) AMD Radeon RX 6900 XT
Device PCI-e ID (AMD) 0x73bf
Device Topology (AMD) PCI-E, 0000:67:00.0
Device Profile FULL_PROFILE
Device Available Yes
Compiler Available Yes
Linker Available Yes
Max compute units 40
SIMD per compute unit (AMD) 4
SIMD width (AMD) 32
SIMD instruction width (AMD) 1
Max clock frequency 2015MHz
Graphics IP (AMD) 10.3
Device Partition (core)
Max number of sub-devices 40
Supported partition types None
Supported affinity domains (n/a)
Max work item dimensions 3
Max work item sizes 1024x1024x1024
Max work group size 256
Preferred work group size (AMD) 256
Max work group size (AMD) 1024
Preferred work group size multiple (kernel) 32
Wavefront width (AMD) 32
Preferred / native vector sizes
char 4 / 4
short 2 / 2
int 1 / 1
long 1 / 1
half 1 / 1 (cl_khr_fp16)
float 1 / 1
double 1 / 1 (cl_khr_fp64)
Half-precision Floating-point support (cl_khr_fp16)
Denormals No
Infinity and NANs No
Round to nearest No
Round to zero No
Round to infinity No
IEEE754-2008 fused multiply-add No
Support is emulated in software No
Single-precision Floating-point support (core)
Denormals Yes
Infinity and NANs Yes
Round to nearest Yes
Round to zero Yes
Round to infinity Yes
IEEE754-2008 fused multiply-add Yes
Support is emulated in software No
Correctly-rounded divide and sqrt operations Yes
Double-precision Floating-point support (cl_khr_fp64)
Denormals Yes
Infinity and NANs Yes
Round to nearest Yes
Round to zero Yes
Round to infinity Yes
IEEE754-2008 fused multiply-add Yes
Support is emulated in software No
Address bits 64, Little-Endian
Global memory size 3221225472 (3GiB)
Global free memory (AMD) 3080192 (14.69EiB) 0 (0B)
Global memory channels (AMD) 8
Global memory banks per channel (AMD) 4
Global memory bank width (AMD) 256 bytes
Error Correction support No
Max memory allocation 3221225472 (3GiB)
Unified memory for Host and Device No
Minimum alignment for any data type 128 bytes
Alignment of base address 2048 bits (256 bytes)
Global Memory cache type Read/Write
Global Memory cache size 16384 (16KiB)
Global Memory cache line size 64 bytes
Image support Yes
Max number of samplers per kernel 16
Max size for 1D images from buffer 201326592 pixels
Max 1D or 2D image array size 2048 images
Base address alignment for 2D image buffers 256 bytes
Pitch alignment for 2D image buffers 256 pixels
Max 2D image size 16384x16384 pixels
Max 3D image size 2048x2048x2048 pixels
Max number of read image args 128
Max number of write image args 8
Local memory type Local
Local memory size 65536 (64KiB)
Local memory size per CU (AMD) 65536 (64KiB)
Local memory banks (AMD) 32
Max number of constant args 8
Max constant buffer size 3221225472 (3GiB)
Preferred constant buffer size (AMD) <printDeviceInfo:153: get CL_DEVICE_PREFERRED_CONSTANT_BUFFER_SIZE_AMD : error -30>
Max size of kernel argument 1024
Queue properties
Out-of-order execution No
Profiling Yes
Prefer user sync for interop Yes
Number of P2P devices (AMD) 0
Profiling timer resolution 1ns
Profiling timer offset since Epoch (AMD) 1643379365406121600ns (Fri Jan 28 15:16:05 2022)
Execution capabilities
Run OpenCL kernels Yes
Run native kernels No
Thread trace supported (AMD) Yes
Number of async queues (AMD) 2
Max real-time compute queues (AMD) 3
Max real-time compute units (AMD) 16
printf() buffer size 4194304 (4MiB)
Built-in kernels (n/a)
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_d3d10_sharing cl_khr_d3d11_sharing cl_khr_dx9_media_sharing cl_khr_image2d_from_buffer cl_khr_gl_event cl_amd_liquid_flash cl_amd_copy_buffer_p2p

Device Name gfx1030
Device Vendor Advanced Micro Devices, Inc.
Device Vendor ID 0x1002
Device Version OpenCL 1.2 AMD-APP (3354.13)
Driver Version 3354.13 (PAL,LC)
Device OpenCL C Version OpenCL C 1.2
Device Type GPU
Device Board Name (AMD) AMD Radeon RX 6900 XT
Device PCI-e ID (AMD) 0x73bf
Device Topology (AMD) PCI-E, 0000:67:00.0
Device Profile FULL_PROFILE
Device Available Yes
Compiler Available Yes
Linker Available Yes
Max compute units 40
SIMD per compute unit (AMD) 4
SIMD width (AMD) 32
SIMD instruction width (AMD) 1
Max clock frequency 2015MHz
Graphics IP (AMD) 10.3
Device Partition (core)
Max number of sub-devices 40
Supported partition types None
Supported affinity domains (n/a)
Max work item dimensions 3
Max work item sizes 1024x1024x1024
Max work group size 256
Preferred work group size (AMD) 256
Max work group size (AMD) 1024
Preferred work group size multiple (kernel) 32
Wavefront width (AMD) 32
Preferred / native vector sizes
char 4 / 4
short 2 / 2
int 1 / 1
long 1 / 1
half 1 / 1 (cl_khr_fp16)
float 1 / 1
double 1 / 1 (cl_khr_fp64)
Half-precision Floating-point support (cl_khr_fp16)
Denormals No
Infinity and NANs No
Round to nearest No
Round to zero No
Round to infinity No
IEEE754-2008 fused multiply-add No
Support is emulated in software No
Single-precision Floating-point support (core)
Denormals Yes
Infinity and NANs Yes
Round to nearest Yes
Round to zero Yes
Round to infinity Yes
IEEE754-2008 fused multiply-add Yes
Support is emulated in software No
Correctly-rounded divide and sqrt operations Yes
Double-precision Floating-point support (cl_khr_fp64)
Denormals Yes
Infinity and NANs Yes
Round to nearest Yes
Round to zero Yes
Round to infinity Yes
IEEE754-2008 fused multiply-add Yes
Support is emulated in software No
Address bits 64, Little-Endian
Global memory size 3221225472 (3GiB)
Global free memory (AMD) 3080192 (14.69EiB) 0 (0B)
Global memory channels (AMD) 8
Global memory banks per channel (AMD) 4
Global memory bank width (AMD) 256 bytes
Error Correction support No
Max memory allocation 3221225472 (3GiB)
Unified memory for Host and Device No
Minimum alignment for any data type 128 bytes
Alignment of base address 2048 bits (256 bytes)
Global Memory cache type Read/Write
Global Memory cache size 16384 (16KiB)
Global Memory cache line size 64 bytes
Image support Yes
Max number of samplers per kernel 16
Max size for 1D images from buffer 201326592 pixels
Max 1D or 2D image array size 2048 images
Base address alignment for 2D image buffers 256 bytes
Pitch alignment for 2D image buffers 256 pixels
Max 2D image size 16384x16384 pixels
Max 3D image size 2048x2048x2048 pixels
Max number of read image args 128
Max number of write image args 8
Local memory type Local
Local memory size 65536 (64KiB)
Local memory size per CU (AMD) 65536 (64KiB)
Local memory banks (AMD) 32
Max number of constant args 8
Max constant buffer size 3221225472 (3GiB)
Preferred constant buffer size (AMD) <printDeviceInfo:153: get CL_DEVICE_PREFERRED_CONSTANT_BUFFER_SIZE_AMD : error -30>
Max size of kernel argument 1024
Queue properties
Out-of-order execution No
Profiling Yes
Prefer user sync for interop Yes
Number of P2P devices (AMD) 0
Profiling timer resolution 1ns
Profiling timer offset since Epoch (AMD) 1643379365406121600ns (Fri Jan 28 15:16:05 2022)
Execution capabilities
Run OpenCL kernels Yes
Run native kernels No
Thread trace supported (AMD) Yes
Number of async queues (AMD) 2
Max real-time compute queues (AMD) 3
Max real-time compute units (AMD) 16
printf() buffer size 4194304 (4MiB)
Built-in kernels (n/a)
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_d3d10_sharing cl_khr_d3d11_sharing cl_khr_dx9_media_sharing cl_khr_image2d_from_buffer cl_khr_gl_event cl_amd_liquid_flash cl_amd_copy_buffer_p2p

NULL platform behavior
clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...) No platform
clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...) No platform
clCreateContext(NULL, ...) [default] No platform
clCreateContext(NULL, ...) [other] Success [AMD]
clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT) Success (1)
Platform Name AMD Accelerated Parallel Processing
Device Name gfx1030
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) Success (2)
Platform Name AMD Accelerated Parallel Processing
Device Name gfx1030
Device Name gfx1030
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_ALL) Success (2)
Platform Name AMD Accelerated Parallel Processing
Device Name gfx1030
Device Name gfx1030
NOTE: your OpenCL library only supports OpenCL 1.0,
but some installed platforms support OpenCL 2.1.
Programs using 2.1 features may crash
or behave unexpectedly

 

 

bye,

         loki

0 Likes

Hi,

here is the clinfo output:

Number of platforms                               1
  Platform Name                                   AMD Accelerated Parallel Processing
  Platform Vendor                                 Advanced Micro Devices, Inc.
  Platform Version                                OpenCL 2.1 AMD-APP (3354.13)
  Platform Profile                                FULL_PROFILE
  Platform Extensions                             cl_khr_icd cl_khr_d3d10_sharing cl_khr_d3d11_sharing cl_khr_dx9_media_sharing cl_amd_event_callback cl_amd_offline_devices
  Platform Extensions function suffix             AMD
  Platform Host timer resolution                  100ns

  Platform Name                                   AMD Accelerated Parallel Processing
Number of devices                                 2
  Device Name                                     gfx1030
  Device Vendor                                   Advanced Micro Devices, Inc.
  Device Vendor ID                                0x1002
  Device Version                                  OpenCL 1.2 AMD-APP (3354.13)
  Driver Version                                  3354.13 (PAL,LC)
  Device OpenCL C Version                         OpenCL C 1.2
  Device Type                                     GPU
  Device Board Name (AMD)                         AMD Radeon RX 6900 XT
  Device PCI-e ID (AMD)                           0x73bf
  Device Topology (AMD)                           PCI-E, 0000:67:00.0
  Device Profile                                  FULL_PROFILE
  Device Available                                Yes
  Compiler Available                              Yes
  Linker Available                                Yes
  Max compute units                               40
  SIMD per compute unit (AMD)                     4
  SIMD width (AMD)                                32
  SIMD instruction width (AMD)                    1
  Max clock frequency                             2015MHz
  Graphics IP (AMD)                               10.3
  Device Partition                                (core)
    Max number of sub-devices                     40
    Supported partition types                     None
    Supported affinity domains                    (n/a)
  Max work item dimensions                        3
  Max work item sizes                             1024x1024x1024
  Max work group size                             256
  Preferred work group size (AMD)                 256
  Max work group size (AMD)                       1024
  Preferred work group size multiple (kernel)     32
  Wavefront width (AMD)                           32
  Preferred / native vector sizes
    char                                                 4 / 4
    short                                                2 / 2
    int                                                  1 / 1
    long                                                 1 / 1
    half                                                 1 / 1        (cl_khr_fp16)
    float                                                1 / 1
    double                                               1 / 1        (cl_khr_fp64)
  Half-precision Floating-point support           (cl_khr_fp16)
    Denormals                                     No
    Infinity and NANs                             No
    Round to nearest                              No
    Round to zero                                 No
    Round to infinity                             No
    IEEE754-2008 fused multiply-add               No
    Support is emulated in software               No
  Single-precision Floating-point support         (core)
    Denormals                                     Yes
    Infinity and NANs                             Yes
    Round to nearest                              Yes
    Round to zero                                 Yes
    Round to infinity                             Yes
    IEEE754-2008 fused multiply-add               Yes
    Support is emulated in software               No
    Correctly-rounded divide and sqrt operations  Yes
  Double-precision Floating-point support         (cl_khr_fp64)
    Denormals                                     Yes
    Infinity and NANs                             Yes
    Round to nearest                              Yes
    Round to zero                                 Yes
    Round to infinity                             Yes
    IEEE754-2008 fused multiply-add               Yes
    Support is emulated in software               No
  Address bits                                    64, Little-Endian
  Global memory size                              3221225472 (3GiB)
  Global free memory (AMD)                        3080192 (14.69EiB) 0 (0B)
  Global memory channels (AMD)                    8
  Global memory banks per channel (AMD)           4
  Global memory bank width (AMD)                  256 bytes
  Error Correction support                        No
  Max memory allocation                           3221225472 (3GiB)
  Unified memory for Host and Device              No
  Minimum alignment for any data type             128 bytes
  Alignment of base address                       2048 bits (256 bytes)
  Global Memory cache type                        Read/Write
  Global Memory cache size                        16384 (16KiB)
  Global Memory cache line size                   64 bytes
  Image support                                   Yes
    Max number of samplers per kernel             16
    Max size for 1D images from buffer            201326592 pixels
    Max 1D or 2D image array size                 2048 images
    Base address alignment for 2D image buffers   256 bytes
    Pitch alignment for 2D image buffers          256 pixels
    Max 2D image size                             16384x16384 pixels
    Max 3D image size                             2048x2048x2048 pixels
    Max number of read image args                 128
    Max number of write image args                8
  Local memory type                               Local
  Local memory size                               65536 (64KiB)
  Local memory size per CU (AMD)                  65536 (64KiB)
  Local memory banks (AMD)                        32
  Max number of constant args                     8
  Max constant buffer size                        3221225472 (3GiB)
  Preferred constant buffer size (AMD)            <printDeviceInfo:153: get CL_DEVICE_PREFERRED_CONSTANT_BUFFER_SIZE_AMD : error -30>
  Max size of kernel argument                     1024
  Queue properties
    Out-of-order execution                        No
    Profiling                                     Yes
  Prefer user sync for interop                    Yes
  Number of P2P devices (AMD)                     0
  Profiling timer resolution                      1ns
  Profiling timer offset since Epoch (AMD)        1643379365406121600ns (Fri Jan 28 15:16:05 2022)
  Execution capabilities
    Run OpenCL kernels                            Yes
    Run native kernels                            No
    Thread trace supported (AMD)                  Yes
    Number of async queues (AMD)                  2
    Max real-time compute queues (AMD)            3
    Max real-time compute units (AMD)             16
  printf() buffer size                            4194304 (4MiB)
  Built-in kernels                                (n/a)
  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_d3d10_sharing cl_khr_d3d11_sharing cl_khr_dx9_media_sharing cl_khr_image2d_from_buffer cl_khr_gl_event cl_amd_liquid_flash cl_amd_copy_buffer_p2p

  Device Name                                     gfx1030
  Device Vendor                                   Advanced Micro Devices, Inc.
  Device Vendor ID                                0x1002
  Device Version                                  OpenCL 1.2 AMD-APP (3354.13)
  Driver Version                                  3354.13 (PAL,LC)
  Device OpenCL C Version                         OpenCL C 1.2
  Device Type                                     GPU
  Device Board Name (AMD)                         AMD Radeon RX 6900 XT
  Device PCI-e ID (AMD)                           0x73bf
  Device Topology (AMD)                           PCI-E, 0000:67:00.0
  Device Profile                                  FULL_PROFILE
  Device Available                                Yes
  Compiler Available                              Yes
  Linker Available                                Yes
  Max compute units                               40
  SIMD per compute unit (AMD)                     4
  SIMD width (AMD)                                32
  SIMD instruction width (AMD)                    1
  Max clock frequency                             2015MHz
  Graphics IP (AMD)                               10.3
  Device Partition                                (core)
    Max number of sub-devices                     40
    Supported partition types                     None
    Supported affinity domains                    (n/a)
  Max work item dimensions                        3
  Max work item sizes                             1024x1024x1024
  Max work group size                             256
  Preferred work group size (AMD)                 256
  Max work group size (AMD)                       1024
  Preferred work group size multiple (kernel)     32
  Wavefront width (AMD)                           32
  Preferred / native vector sizes
    char                                                 4 / 4
    short                                                2 / 2
    int                                                  1 / 1
    long                                                 1 / 1
    half                                                 1 / 1        (cl_khr_fp16)
    float                                                1 / 1
    double                                               1 / 1        (cl_khr_fp64)
  Half-precision Floating-point support           (cl_khr_fp16)
    Denormals                                     No
    Infinity and NANs                             No
    Round to nearest                              No
    Round to zero                                 No
    Round to infinity                             No
    IEEE754-2008 fused multiply-add               No
    Support is emulated in software               No
  Single-precision Floating-point support         (core)
    Denormals                                     Yes
    Infinity and NANs                             Yes
    Round to nearest                              Yes
    Round to zero                                 Yes
    Round to infinity                             Yes
    IEEE754-2008 fused multiply-add               Yes
    Support is emulated in software               No
    Correctly-rounded divide and sqrt operations  Yes
  Double-precision Floating-point support         (cl_khr_fp64)
    Denormals                                     Yes
    Infinity and NANs                             Yes
    Round to nearest                              Yes
    Round to zero                                 Yes
    Round to infinity                             Yes
    IEEE754-2008 fused multiply-add               Yes
    Support is emulated in software               No
  Address bits                                    64, Little-Endian
  Global memory size                              3221225472 (3GiB)
  Global free memory (AMD)                        3080192 (14.69EiB) 0 (0B)
  Global memory channels (AMD)                    8
  Global memory banks per channel (AMD)           4
  Global memory bank width (AMD)                  256 bytes
  Error Correction support                        No
  Max memory allocation                           3221225472 (3GiB)
  Unified memory for Host and Device              No
  Minimum alignment for any data type             128 bytes
  Alignment of base address                       2048 bits (256 bytes)
  Global Memory cache type                        Read/Write
  Global Memory cache size                        16384 (16KiB)
  Global Memory cache line size                   64 bytes
  Image support                                   Yes
    Max number of samplers per kernel             16
    Max size for 1D images from buffer            201326592 pixels
    Max 1D or 2D image array size                 2048 images
    Base address alignment for 2D image buffers   256 bytes
    Pitch alignment for 2D image buffers          256 pixels
    Max 2D image size                             16384x16384 pixels
    Max 3D image size                             2048x2048x2048 pixels
    Max number of read image args                 128
    Max number of write image args                8
  Local memory type                               Local
  Local memory size                               65536 (64KiB)
  Local memory size per CU (AMD)                  65536 (64KiB)
  Local memory banks (AMD)                        32
  Max number of constant args                     8
  Max constant buffer size                        3221225472 (3GiB)
  Preferred constant buffer size (AMD)            <printDeviceInfo:153: get CL_DEVICE_PREFERRED_CONSTANT_BUFFER_SIZE_AMD : error -30>
  Max size of kernel argument                     1024
  Queue properties
    Out-of-order execution                        No
    Profiling                                     Yes
  Prefer user sync for interop                    Yes
  Number of P2P devices (AMD)                     0
  Profiling timer resolution                      1ns
  Profiling timer offset since Epoch (AMD)        1643379365406121600ns (Fri Jan 28 15:16:05 2022)
  Execution capabilities
    Run OpenCL kernels                            Yes
    Run native kernels                            No
    Thread trace supported (AMD)                  Yes
    Number of async queues (AMD)                  2
    Max real-time compute queues (AMD)            3
    Max real-time compute units (AMD)             16
  printf() buffer size                            4194304 (4MiB)
  Built-in kernels                                (n/a)
  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_d3d10_sharing cl_khr_d3d11_sharing cl_khr_dx9_media_sharing cl_khr_image2d_from_buffer cl_khr_gl_event cl_amd_liquid_flash cl_amd_copy_buffer_p2p

NULL platform behavior
  clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...)  No platform
  clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...)   No platform
  clCreateContext(NULL, ...) [default]            No platform
  clCreateContext(NULL, ...) [other]              Success [AMD]
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT)  Success (1)
    Platform Name                                 AMD Accelerated Parallel Processing
    Device Name                                   gfx1030
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU)  Success (2)
    Platform Name                                 AMD Accelerated Parallel Processing
    Device Name                                   gfx1030
    Device Name                                   gfx1030
  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_ALL)  Success (2)
    Platform Name                                 AMD Accelerated Parallel Processing
    Device Name                                   gfx1030
    Device Name                                   gfx1030
        NOTE:   your OpenCL library only supports OpenCL 1.0,
                but some installed platforms support OpenCL 2.1.
                Programs using 2.1 features may crash
                or behave unexpectedly

bye,

         loki

0 Likes

Hi,

if I paste the clinfo output here, my post is regarded as spam...

bye,

       loki

0 Likes

Yes, that post was marked as "spam" and it was moved to spam folder. I've unmarked the "spam" flag. Now I can see the post here. Please check.

And, thanks for sharing the clinfo output. I'll check with the concerned team and get back to you.

Thanks.

0 Likes

clGetDeviceInfo reports 40 compute units for each device. The 6900XT should have 80. That would support the theory of two logical devices

It looks like 40CU is correctly reported by the clGetDeviceInfo or clinfo. Please note, here CU represents dual compute unit which is the fundamental computational building block of the RDNA architecture.  As mentioned in the RDNA Whitepaper:

"The new dual compute unit design is the essence of the RDNA architecture and replaces the GCN compute unit as the fundamental computational building block of the GPU. As Figure 2 illustrates, the dual compute unit still comprises four SIMDs that operate independently."

 

The problem is, that clGetDeviceIDs reports two devices, and clGetDeviceInfo says both are "gfx 1030"

The OpenCL team wants to know whether it is remote desktop connection or not. Because, a similar issue was reported earlier where remote desktop was detected as another GPU.

Thanks.

0 Likes

Thanks for the info regarding the compute units.

Yes, I'm using RDC to connect to the computer with the 6900 (let's call it Eddie). I already hat the idea that this might be a problem, so I did the following: I connected to a different computer (Marvin) via RDC, and from Marvin to Eddie via KVM switch (Aten KN2116VA), so when I ran clinfo, there was no active RDC connection to Eddie (I can't connect directly from my machine at home to Eddie via KVM). Again, two devices were reported.

Regards,

      loki

0 Likes

Thanks for the above information. I've shared it with the OpenCL team. I'll let you know once I get their feedback on this.

Thanks.

0 Likes

As I've come to know, the latest driver already has the fix for a similar RDC issue which was reported earlier. So not sure if this is related to that old issue or a new one. Usually this happens when PAL-KMD reports two devices as the result of incorrect registry settings or some registry detection. Maybe previous uninstall wasn't done properly. So, can you please do a clean installation of the latest driver available here  to see if it resolves the issue? 

Thanks.

0 Likes

Driver 22.2.1 doesn't resolve the issue, still two devices are reported.

Regards,

       loki

0 Likes

The GPU was installed in a different computer. Now only one device is reported, even via RDC and an older driver version. So the problem was the previous machine, or the combination GPU/computer.

bye,
      loki

0 Likes

Thank you for the update. As the issue is not reproducible on your current setup with the same gpu and the latest driver, may I assume that the issue has been resolved now? 

Thanks.

 

0 Likes