【发布时间】：2019-10-06 02:50:16
【问题描述】：
我按照以下说明在全新安装的 Ubuntu 18.04 上安装了 ROCm、ROCm-Tensorflow 和 PlaidML：
- https://rocm.github.io/ROCmInstall.html
- https://rocm.github.io/QuickStartOCL.html
- https://rocm.github.io/tensorflow.html
- https://github.com/plaidml/plaidml
虽然 /opt/rocm/bin/rocminfo 列出了两个 GPU，但 /opt/rocm/opencl/bin/x86_64/clinfo 或 plaidml-setup 无法识别它们（输出如下）。
导入tensorflow会报如下错误：
>>> import tensorflow
HSA reported error!
In file: unpinned_copy_engine.cpp
At line: 126
HSA reported error!
In file: unpinned_copy_engine.cpp
At line: 126
HSA reported error!
In file: unpinned_copy_engine.cpp
At line: 126
HSA reported error!
In file: unpinned_copy_engine.cpp
At line: 126
HSA reported error!
In file: unpinned_copy_engine.cpp
At line: 126
HSA reported error!
In file: unpinned_copy_engine.cpp
At line: 126
HSA reported error!
In file: unpinned_copy_engine.cpp
At line: 126
HSA reported error!
In file: unpinned_copy_engine.cpp
At line: 126
### HCC STATUS_CHECK Error: HSA_STATUS_ERROR_OUT_OF_RESOURCES (0x1008) at file:mcwamp_hsa.cpp line:1220
Aborted (core dumped)
Rocminfo 列出所有设备：
$ /opt/rocm/bin/rocminfo
=====================
HSA System Attributes
=====================
Runtime Version: 1.1
System Timestamp Freq.: 1000.000000MHz
Sig. Max Wait Duration: 18446744073709551615 (number of timestamp)
Machine Model: LARGE
System Endianness: LITTLE
==========
HSA Agents
==========
*******
Agent 1
*******
Name: AMD Ryzen 3 2200G with Radeon Vega Graphics
Vendor Name: CPU
Feature: None specified
Profile: FULL_PROFILE
Float Round Mode: NEAR
Max Queue Number: 0
Queue Min Size: 0
Queue Max Size: 0
Queue Type: MULTI
Node: 0
Device Type: CPU
Cache Info:
L1: 32KB
Chip ID: 5597
Cacheline Size: 64
Max Clock Frequency (MHz):3850
BDFID: 2560
Compute Unit: 4
Features: None
Pool Info:
Pool 1
Segment: GLOBAL; FLAGS: KERNARG, FINE GRAINED
Size: 16776832KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Alignment: 4KB
Acessible by all: TRUE
ISA Info:
N/A
*******
Agent 2
*******
Name: gfx902
Vendor Name: AMD
Feature: KERNEL_DISPATCH
Profile: FULL_PROFILE
Float Round Mode: NEAR
Max Queue Number: 128
Queue Min Size: 4096
Queue Max Size: 131072
Queue Type: MULTI
Node: 0
Device Type: GPU
Cache Info:
L1: 16KB
Chip ID: 5597
Cacheline Size: 64
Max Clock Frequency (MHz):1100
BDFID: 2560
Compute Unit: 11
Features: KERNEL_DISPATCH
Fast F16 Operation: FALSE
Wavefront Size: 64
Workgroup Max Size: 1024
Workgroup Max Size Per Dimension:
Dim[0]: 67109888
Dim[1]: 167773184
Dim[2]: 0
Grid Max Size: 4294967295
Waves Per CU: 160
Max Work-item Per CU: 10240
Grid Max Size per Dimension:
Dim[0]: 4294967295
Dim[1]: 4294967295
Dim[2]: 4294967295
Max number Of fbarriers Per Workgroup:32
Pool Info:
Pool 1
Segment: GROUP
Size: 64KB
Allocatable: FALSE
Alloc Granule: 0KB
Alloc Alignment: 0KB
Acessible by all: FALSE
ISA Info:
ISA 1
Name: amdgcn-amd-amdhsa--gfx902+xnack
Machine Models: HSA_MACHINE_MODEL_LARGE
Profiles: HSA_PROFILE_BASE
Default Rounding Mode: NEAR
Default Rounding Mode: NEAR
Fast f16: TRUE
Workgroup Max Dimension:
Dim[0]: 67109888
Dim[1]: 1024
Dim[2]: 16777217
Workgroup Max Size: 1024
Grid Max Dimension:
x 4294967295
y 4294967295
z 4294967295
Grid Max Size: 4294967295
FBarrier Max Size: 32
*******
Agent 3
*******
Name: gfx803
Vendor Name: AMD
Feature: KERNEL_DISPATCH
Profile: BASE_PROFILE
Float Round Mode: NEAR
Max Queue Number: 128
Queue Min Size: 4096
Queue Max Size: 131072
Queue Type: MULTI
Node: 1
Device Type: GPU
Cache Info:
L1: 16KB
Chip ID: 26591
Cacheline Size: 64
Max Clock Frequency (MHz):1206
BDFID: 256
Compute Unit: 32
Features: KERNEL_DISPATCH
Fast F16 Operation: FALSE
Wavefront Size: 64
Workgroup Max Size: 1024
Workgroup Max Size Per Dimension:
Dim[0]: 67109888
Dim[1]: 16778240
Dim[2]: 0
Grid Max Size: 4294967295
Waves Per CU: 40
Max Work-item Per CU: 2560
Grid Max Size per Dimension:
Dim[0]: 4294967295
Dim[1]: 4294967295
Dim[2]: 4294967295
Max number Of fbarriers Per Workgroup:32
Pool Info:
Pool 1
Segment: GLOBAL; FLAGS: COARSE GRAINED
Size: 4194304KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Alignment: 4KB
Acessible by all: FALSE
Pool 2
Segment: GROUP
Size: 64KB
Allocatable: FALSE
Alloc Granule: 0KB
Alloc Alignment: 0KB
Acessible by all: FALSE
ISA Info:
ISA 1
Name: amdgcn-amd-amdhsa--gfx803
Machine Models: HSA_MACHINE_MODEL_LARGE
Profiles: HSA_PROFILE_BASE
Default Rounding Mode: NEAR
Default Rounding Mode: NEAR
Fast f16: TRUE
Workgroup Max Dimension:
Dim[0]: 67109888
Dim[1]: 1024
Dim[2]: 16777217
Workgroup Max Size: 1024
Grid Max Dimension:
x 4294967295
y 4294967295
z 4294967295
Grid Max Size: 4294967295
FBarrier Max Size: 32
*** Done ***
CL信息：
$ /opt/rocm/opencl/bin/x86_64/clinfo
Number of platforms: 1
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 1.2 pocl 1.1 None+Asserts, LLVM 6.0.0, SPIR, SLEEF, DISTRO, POCL_DEBUG
Platform Name: Portable Computing Language
Platform Vendor: The pocl project
Platform Extensions: cl_khr_icd
Platform Name: Portable Computing Language
Number of devices: 1
Device Type: CL_DEVICE_TYPE_CPU
Vendor ID: 1022h
Max compute units: 4
Max work items dimensions: 3
Max work items[0]: 4096
Max work items[1]: 4096
Max work items[2]: 4096
Max work group size: 4096
Preferred vector width char: 16
Preferred vector width short: 16
Preferred vector width int: 8
Preferred vector width long: 4
Preferred vector width float: 8
Preferred vector width double: 4
Native vector width char: 16
Native vector width short: 16
Native vector width int: 8
Native vector width long: 4
Native vector width float: 8
Native vector width double: 4
Max clock frequency: 3850Mhz
Address bits: 64
Max memory allocation: 4294967296
Image support: Yes
Max number of images read arguments: 128
Max number of images write arguments: 128
Max image 2D width: 16384
Max image 2D height: 16384
Max image 3D width: 2048
Max image 3D height: 2048
Max image 3D depth: 2048
Max samplers within kernel: 16
Max size of kernel argument: 1024
Alignment (bits) of base address: 1024
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: Yes
Quiet NaNs: Yes
Round to nearest even: Yes
Round to zero: Yes
Round to +ve and infinity: Yes
IEEE754-2008 fused multiply-add: Yes
Cache type: Read/Write
Cache line size: 64
Cache size: 4194304
Global memory size: 12548460544
Constant buffer size: 2097152
Max number of constant args: 8
Local memory type: Global
Local memory size: 2097152
Kernel Preferred work group size multiple: 8
Error correction support: 0
Unified memory for Host and Device: 1
Profiling timer resolution: 1
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: Yes
Queue on Host properties:
Out-of-Order: No
Profiling : Yes
Platform ID: 0x7ff20df56020
Name: pthread-AMD Ryzen 3 2200G with Radeon Vega Graphics
Vendor: AuthenticAMD
Device OpenCL C version: OpenCL C 1.2 pocl
Driver version: 1.1
Profile: FULL_PROFILE
Version: OpenCL 1.2 pocl HSTR: pthread-x86_64-pc-linux-gnu-znver1
Extensions: cl_khr_byte_addressable_store 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_3d_image_writes cl_khr_spir cl_khr_fp64 cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_fp64
格子ML：
$ plaidml-setup
PlaidML Setup (0.5.0)
Thanks for using PlaidML!
Some Notes:
* Bugs and other issues: https://github.com/plaidml/plaidml
* Questions: https://stackoverflow.com/questions/tagged/plaidml
* Say hello: https://groups.google.com/forum/#!forum/plaidml-dev
* PlaidML is licensed under the GNU AGPLv3
Default Config Devices:
No devices.
Experimental Config Devices:
llvm_cpu.0 : CPU (LLVM)
Using experimental devices can cause poor performance, crashes, and other nastiness.
...
系统信息：
- AMD Ryzen 2200g 配备 vega 8 显卡 (iGPU) 和 AMD Radeon rx470 (dGPU)
- Ubuntu 18.04.2
- 内核 4.18.0-20-generic
- ROCm 2.4.25
- Python 3.6.7
- ROCm 张量流：1.13.3
- PlaidML 0.5.0
【问题讨论】：
标签： python tensorflow opencl ubuntu-18.04 amd-rocm