system spec

[mpekalski]

I started to set up a system from a scratch and now I am having a bit of a problem setting up clBLAS like in which order should I install different dependencies, which versions are proffered over the others etc. It compiles, but then when I run test-functional or test-correctness it does not go far. So I would be grateful if somebody who has clBLAS running could run a couple of commands below and provide me with an output. It basically gives the version of drivers, system, libraries and their location.

I am trying to set it up on lubuntu 15.04 with Radeon 290. Or maybe some other system is more friendly with AMD's drivers?

uname -a

env | grep -i 'LD_\|AMD\|BLAS\|OPENCL\|LAPACK\|/CL'

dpkg -l fglrx fglrx-core fglrx-dev fglrx-amdcccle

lsmod | grep fglrx

fglrxinfo

clinfo

/usr/bin/g++ --version

/usr/bin/gcc --version

#assuming clBLAS installation path
file /opt/clBLAS/bin/test-functional | awk -F: '$2 ~ "dynamically linked" {print $1}' | xargs ldd

ldconfig -p | grep -i 'OPENCL\|amd\|blas\|lapack'  

ldconfig -p | grep -i 'OPENCL\|amd\|blas\|lapack'     | grep "=> /" | awk '{print $4}'  | xargs ls -la

ldconfig -p | grep -i 'OPENCL\|amd\|blas\|lapack'     | grep "=> /" | awk '{print $4}'  | xargs ls -la | grep " -> " | awk '{print $11}' | xargs locate

# in case one uses alternatives and not soft links
update-alternatives --display libOpenCL.so
update-alternatives --display libOpenCL.so.1

EDIT: I had OpenCL-caffe and clBLAS repos opened in two tabs and I posted this in the wrong one. My mistake, sorry for that.

[nathan-sixnines]

I've tried a bunch of different drivers but the only ones that seem to work for me are the 2:15.200 versions from sudo apt-get install fglrx-updates fglrx-updates-core fglrx-updates-dev fglrx-amdcccle-updates.

One other thing to try that helped for me was I ran "make install" after "make all" when building clBLAS before running the tests. With my current setup I'm just using the precompiled 2.4 binaries anyway though, so that's not a factor. I have Tahiti cards, and I think the improvements after 2.4 are mostly targeted at Hawaii and Fiji.

I'll hop on that computer and edit in those outputs in a minute.

uname -a

Linux 10 3.19.0-25-generic #26~14.04.1-Ubuntu SMP Fri Jul 24 21:16:20 UTC 2015 x86_64 x86_64 x86_64 GNU/Linux

env | grep -i 'LD_|AMD|BLAS|OPENCL|LAPACK|/CL'

LD_LIBRARY_PATH=/opt/AMDAPPSDK-3.0/lib/x86_64/:/usr/lib32:/home/nathan/Downloads/acml/y/ifort64/lib:/home/nathan/Downloads/clBLAS-2.4.0-Linux-x64/lib:/home/nathan/Downloads/clBLAS-2.4.0-Linux-x64/lib64:/home/nathan/Downloads/acml/y/ifort64_mp/lib/libacml_mp.so
AMDAPPSDKROOT=/opt/AMDAPPSDK-3.0
PWD=//home/nathan/Downloads/clBLAS-2.4.0-Linux-x64/bin

dpkg -l fglrx fglrx-core fglrx-dev fglrx-amdcccle

Desired=Unknown/Install/Remove/Purge/Hold
| Status=Not/Inst/Conf-files/Unpacked/halF-conf/Half-inst/trig-aWait/Trig-pend
|/ Err?=(none)/Reinst-required (Status,Err: uppercase=bad)
||/ Name Version Architecture Description
+++-===========================-==================-==================-============================================================
un fglrx-amdcccle (no description available)
un fglrx-dev (no description available)
dpkg-query: no packages found matching fglrx
dpkg-query: no packages found matching fglrx-core

dpkg -l fglrx* (this might be a bit more interesting than the previous output)

Desired=Unknown/Install/Remove/Purge/Hold
| Status=Not/Inst/Conf-files/Unpacked/halF-conf/Half-inst/trig-aWait/Trig-pend
|/ Err?=(none)/Reinst-required (Status,Err: uppercase=bad)
||/ Name Version Architecture Description
+++-===========================-==================-==================-============================================================
un fglrx-amdcccle (no description available)
ii fglrx-amdcccle-updates 2:15.200-0ubuntu0. amd64 Catalyst Control Center for the AMD graphics accelerators
un fglrx-control (no description available)
un fglrx-control-qt2 (no description available)
un fglrx-dev (no description available)
un fglrx-driver (no description available)
un fglrx-driver-core (no description available)
un fglrx-driver-dev (no description available)
un fglrx-glx (no description available)
ii fglrx-updates 2:15.200-0ubuntu0. amd64 Video driver for the AMD graphics accelerators
ii fglrx-updates-core 2:15.200-0ubuntu0. amd64 Minimal video driver for the AMD graphics accelerators
ii fglrx-updates-dev 2:15.200-0ubuntu0. amd64 Video driver for the AMD graphics accelerators (devel files)

lsmod | grep fglrx

fglrx 12460032 358
amd_iommu_v2 20480 1 fglrx

fglrxinfo

display: :0 screen: 0
OpenGL vendor string: Advanced Micro Devices, Inc.
OpenGL renderer string: AMD Radeon HD 7900 Series
OpenGL version string: 4.4.13374 Compatibility Profile Context 15.20.1013

clinfo

Number of platforms: 1
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 2.0 AMD-APP (1729.3)
Platform Name: AMD Accelerated Parallel Processing
Platform Vendor: Advanced Micro Devices, Inc.
Platform Extensions: cl_khr_icd cl_amd_event_callback cl_amd_offline_devices

Platform Name: AMD Accelerated Parallel Processing
Number of devices: 5
Device Type: CL_DEVICE_TYPE_GPU
Vendor ID: 1002h
Board name: AMD Radeon HD 7900 Series
Device Topology: PCI[ B#2, D#0, F#0 ]
Max compute units: 28
Max work items dimensions: 3
Max work items[0]: 256
Max work items[1]: 256
Max work items[2]: 256
Max work group size: 256
Preferred vector width char: 4
Preferred vector width short: 2
Preferred vector width int: 1
Preferred vector width long: 1
Preferred vector width float: 1
Preferred vector width double: 1
Native vector width char: 4
Native vector width short: 2
Native vector width int: 1
Native vector width long: 1
Native vector width float: 1
Native vector width double: 1
Max clock frequency: 880Mhz
Address bits: 32
Max memory allocation: 1889796096
Image support: Yes
Max number of images read arguments: 128
Max number of images write arguments: 8
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: 2048
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: No
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: 16384
Global memory size: 2837446656
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Scratchpad
Local memory size: 32768
Max pipe arguments: 0
Max pipe active reservations: 0
Max pipe packet size: 0
Max global variable size: 0
Max global variable preferred total size: 0
Max read/write image args: 0
Max on device events: 0
Queue on device max size: 0
Max on device queues: 0
Queue on device preferred size: 0
SVM capabilities:
Coarse grain buffer: No
Fine grain buffer: No
Fine grain system: No
Atomics: No
Preferred platform atomic alignment: 0
Preferred global atomic alignment: 0
Preferred local atomic alignment: 0
Kernel Preferred work group size multiple: 64
Error correction support: 0
Unified memory for Host and Device: 0
Profiling timer resolution: 1
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: No
Queue on Host properties:
Out-of-Order: No
Profiling : Yes
Queue on Device properties:
Out-of-Order: No
Profiling : No
Platform ID: 0x7f9ac13a88f0
Name: Tahiti
Vendor: Advanced Micro Devices, Inc.
Device OpenCL C version: OpenCL C 1.2
Driver version: 1729.3 (VM)
Profile: FULL_PROFILE
Version: OpenCL 1.2 AMD-APP (1729.3)
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_gl_sharing cl_ext_atomic_counters_32 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 Type: CL_DEVICE_TYPE_GPU
Vendor ID: 1002h
Board name:
Device Topology: PCI[ B#2, D#0, F#0 ]
Max compute units: 28
Max work items dimensions: 3
Max work items[0]: 256
Max work items[1]: 256
Max work items[2]: 256
Max work group size: 256
Preferred vector width char: 4
Preferred vector width short: 2
Preferred vector width int: 1
Preferred vector width long: 1
Preferred vector width float: 1
Preferred vector width double: 1
Native vector width char: 4
Native vector width short: 2
Native vector width int: 1
Native vector width long: 1
Native vector width float: 1
Native vector width double: 1
Max clock frequency: 880Mhz
Address bits: 32
Max memory allocation: 2204368896
Image support: Yes
Max number of images read arguments: 128
Max number of images write arguments: 8
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: 2048
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: No
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: 16384
Global memory size: 3181379584
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Scratchpad
Local memory size: 32768
Max pipe arguments: 0
Max pipe active reservations: 0
Max pipe packet size: 0
Max global variable size: 0
Max global variable preferred total size: 0
Max read/write image args: 0
Max on device events: 0
Queue on device max size: 0
Max on device queues: 0
Queue on device preferred size: 0
SVM capabilities:
Coarse grain buffer: No
Fine grain buffer: No
Fine grain system: No
Atomics: No
Preferred platform atomic alignment: 0
Preferred global atomic alignment: 0
Preferred local atomic alignment: 0
Kernel Preferred work group size multiple: 64
Error correction support: 0
Unified memory for Host and Device: 0
Profiling timer resolution: 1
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: No
Queue on Host properties:
Out-of-Order: No
Profiling : Yes
Queue on Device properties:
Out-of-Order: No
Profiling : No
Platform ID: 0x7f9ac13a88f0
Name: Tahiti
Vendor: Advanced Micro Devices, Inc.
Device OpenCL C version: OpenCL C 1.2
Driver version: 1729.3 (VM)
Profile: FULL_PROFILE
Version: OpenCL 1.2 AMD-APP (1729.3)
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_gl_sharing cl_ext_atomic_counters_32 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 Type: CL_DEVICE_TYPE_GPU
Vendor ID: 1002h
Board name:
Device Topology: PCI[ B#2, D#0, F#0 ]
Max compute units: 28
Max work items dimensions: 3
Max work items[0]: 256
Max work items[1]: 256
Max work items[2]: 256
Max work group size: 256
Preferred vector width char: 4
Preferred vector width short: 2
Preferred vector width int: 1
Preferred vector width long: 1
Preferred vector width float: 1
Preferred vector width double: 1
Native vector width char: 4
Native vector width short: 2
Native vector width int: 1
Native vector width long: 1
Native vector width float: 1
Native vector width double: 1
Max clock frequency: 880Mhz
Address bits: 32
Max memory allocation: 2204368896
Image support: Yes
Max number of images read arguments: 128
Max number of images write arguments: 8
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: 2048
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: No
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: 16384
Global memory size: 3181379584
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Scratchpad
Local memory size: 32768
Max pipe arguments: 0
Max pipe active reservations: 0
Max pipe packet size: 0
Max global variable size: 0
Max global variable preferred total size: 0
Max read/write image args: 0
Max on device events: 0
Queue on device max size: 0
Max on device queues: 0
Queue on device preferred size: 0
SVM capabilities:
Coarse grain buffer: No
Fine grain buffer: No
Fine grain system: No
Atomics: No
Preferred platform atomic alignment: 0
Preferred global atomic alignment: 0
Preferred local atomic alignment: 0
Kernel Preferred work group size multiple: 64
Error correction support: 0
Unified memory for Host and Device: 0
Profiling timer resolution: 1
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: No
Queue on Host properties:
Out-of-Order: No
Profiling : Yes
Queue on Device properties:
Out-of-Order: No
Profiling : No
Platform ID: 0x7f9ac13a88f0
Name: Tahiti
Vendor: Advanced Micro Devices, Inc.
Device OpenCL C version: OpenCL C 1.2
Driver version: 1729.3 (VM)
Profile: FULL_PROFILE
Version: OpenCL 1.2 AMD-APP (1729.3)
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_gl_sharing cl_ext_atomic_counters_32 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 Type: CL_DEVICE_TYPE_GPU
Vendor ID: 1002h
Board name:
Device Topology: PCI[ B#2, D#0, F#0 ]
Max compute units: 28
Max work items dimensions: 3
Max work items[0]: 256
Max work items[1]: 256
Max work items[2]: 256
Max work group size: 256
Preferred vector width char: 4
Preferred vector width short: 2
Preferred vector width int: 1
Preferred vector width long: 1
Preferred vector width float: 1
Preferred vector width double: 1
Native vector width char: 4
Native vector width short: 2
Native vector width int: 1
Native vector width long: 1
Native vector width float: 1
Native vector width double: 1
Max clock frequency: 880Mhz
Address bits: 32
Max memory allocation: 2204368896
Image support: Yes
Max number of images read arguments: 128
Max number of images write arguments: 8
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: 2048
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: No
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: 16384
Global memory size: 3181379584
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Scratchpad
Local memory size: 32768
Max pipe arguments: 0
Max pipe active reservations: 0
Max pipe packet size: 0
Max global variable size: 0
Max global variable preferred total size: 0
Max read/write image args: 0
Max on device events: 0
Queue on device max size: 0
Max on device queues: 0
Queue on device preferred size: 0
SVM capabilities:
Coarse grain buffer: No
Fine grain buffer: No
Fine grain system: No
Atomics: No
Preferred platform atomic alignment: 0
Preferred global atomic alignment: 0
Preferred local atomic alignment: 0
Kernel Preferred work group size multiple: 64
Error correction support: 0
Unified memory for Host and Device: 0
Profiling timer resolution: 1
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: No
Queue on Host properties:
Out-of-Order: No
Profiling : Yes
Queue on Device properties:
Out-of-Order: No
Profiling : No
Platform ID: 0x7f9ac13a88f0
Name: Tahiti
Vendor: Advanced Micro Devices, Inc.
Device OpenCL C version: OpenCL C 1.2
Driver version: 1729.3 (VM)
Profile: FULL_PROFILE
Version: OpenCL 1.2 AMD-APP (1729.3)
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_gl_sharing cl_ext_atomic_counters_32 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 Type: CL_DEVICE_TYPE_CPU
Vendor ID: 1002h
Board name:
Max compute units: 2
Max work items dimensions: 3
Max work items[0]: 1024
Max work items[1]: 1024
Max work items[2]: 1024
Max work group size: 1024
Preferred vector width char: 16
Preferred vector width short: 8
Preferred vector width int: 4
Preferred vector width long: 2
Preferred vector width float: 4
Preferred vector width double: 2
Native vector width char: 16
Native vector width short: 8
Native vector width int: 4
Native vector width long: 2
Native vector width float: 4
Native vector width double: 2
Max clock frequency: 2700Mhz
Address bits: 64
Max memory allocation: 2147483648
Image support: Yes
Max number of images read arguments: 128
Max number of images write arguments: 64
Max image 2D width: 8192
Max image 2D height: 8192
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: 4096
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: 32768
Global memory size: 4072837120
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Global
Local memory size: 32768
Max pipe arguments: 16
Max pipe active reservations: 16
Max pipe packet size: 2147483648
Max global variable size: 1879048192
Max global variable preferred total size: 1879048192
Max read/write image args: 64
Max on device events: 0
Queue on device max size: 0
Max on device queues: 0
Queue on device preferred size: 0
SVM capabilities:
Coarse grain buffer: No
Fine grain buffer: No
Fine grain system: No
Atomics: No
Preferred platform atomic alignment: 0
Preferred global atomic alignment: 0
Preferred local atomic alignment: 0
Kernel Preferred work group size multiple: 1
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
Queue on Device properties:
Out-of-Order: No
Profiling : No
Platform ID: 0x7f9ac13a88f0
Name: Intel(R) Celeron(R) CPU G1620 @ 2.70GHz
Vendor: GenuineIntel
Device OpenCL C version: OpenCL C 1.2
Driver version: 1729.3 (sse2)
Profile: FULL_PROFILE
Version: OpenCL 1.2 AMD-APP (1729.3)
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_gl_sharing cl_ext_device_fission cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_media_ops2 cl_amd_popcnt cl_khr_spir cl_khr_gl_event

/usr/bin/g++ --version

g++ (Ubuntu 4.8.4-2ubuntu1~14.04) 4.8.4

/usr/bin/gcc --version

gcc (Ubuntu 4.8.4-2ubuntu1~14.04) 4.8.4

file //home/nathan/Downloads/clBLAS-2.4.0-Linux-x64/bin/test-functional | awk -F: '$2 ~ "dynamically linked" {print $1}' | xargs ldd

linux-vdso.so.1 =>  (0x00007ffdd31f3000)
librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007fba6e6fa000)
libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007fba6e4dc000)
libclBLAS.so.2 => /home/nathan/Downloads/clBLAS-2.4.0-Linux-x64/lib64/libclBLAS.so.2 (0x00007fba6e1fc000)
libOpenCL.so.1 => /usr/lib/x86_64-linux-gnu/libOpenCL.so.1 (0x00007fba6dff3000)
libstdc++.so.6 => /usr/lib/x86_64-linux-gnu/libstdc++.so.6 (0x00007fba6dcef000)
libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007fba6d9e9000)
libgcc_s.so.1 => /lib/x86_64-linux-gnu/libgcc_s.so.1 (0x00007fba6d7d3000)
libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007fba6d40e000)
/lib64/ld-linux-x86-64.so.2 (0x00007fba6e902000)
libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007fba6d20a000)

ldconfig -p | grep -i 'OPENCL|amd|blas|lapack'

libsamdb.so.0 (libc6,x86-64) => /usr/lib/x86_64-linux-gnu/libsamdb.so.0
liblapack_atlas.so.3 (libc6,x86-64) => /usr/lib/liblapack_atlas.so.3
liblapack_atlas.so (libc6,x86-64) => /usr/lib/liblapack_atlas.so
liblapack.so.3 (libc6,x86-64) => /usr/lib/liblapack.so.3
liblapack.so (libc6,x86-64) => /usr/lib/liblapack.so
libf77blas.so.3 (libc6,x86-64) => /usr/lib/libf77blas.so.3
libf77blas.so (libc6,x86-64) => /usr/lib/libf77blas.so
libcolamd.so.2.8.0 (libc6,x86-64) => /usr/lib/x86_64-linux-gnu/libcolamd.so.2.8.0
libcblas.so.3 (libc6,x86-64) => /usr/lib/libcblas.so.3
libcblas.so (libc6,x86-64) => /usr/lib/libcblas.so
libblas.so.3 (libc6,x86-64) => /usr/lib/libblas.so.3
libblas.so (libc6,x86-64) => /usr/lib/libblas.so
libamdocl64.so (libc6,x86-64) => /usr/lib/libamdocl64.so
libamdocl32.so (libc6) => /usr/lib32/libamdocl32.so
libamdocl12cl64.so (libc6,x86-64) => /usr/lib/libamdocl12cl64.so
libamdocl12cl32.so (libc6) => /usr/lib32/libamdocl12cl32.so
libamdhsasc64.so (libc6,x86-64) => /usr/lib/libamdhsasc64.so
libamdhsasc32.so (libc6) => /usr/lib32/libamdhsasc32.so
libOpenCL.so.1 (libc6,x86-64) => /usr/lib/x86_64-linux-gnu/libOpenCL.so.1
libOpenCL.so.1 (libc6,x86-64) => /usr/lib/libOpenCL.so.1
libOpenCL.so.1 (libc6) => /usr/lib32/libOpenCL.so.1
libOpenCL.so (libc6,x86-64) => /usr/lib/x86_64-linux-gnu/libOpenCL.so
libOpenCL.so (libc6,x86-64) => /usr/lib/libOpenCL.so
libAMDXvBA.so.1 (libc6,x86-64) => /usr/lib/libAMDXvBA.so.1
libAMDXvBA.so.1 (libc6) => /usr/lib32/fglrx/libAMDXvBA.so.1
libAMDXvBA.so.1 (libc6) => /usr/lib32/libAMDXvBA.so.1
libAMDXvBA.so (libc6,x86-64) => /usr/lib/libAMDXvBA.so
libAMDXvBA.so (libc6) => /usr/lib32/fglrx/libAMDXvBA.so

ldconfig -p | grep -i 'OPENCL|amd|blas|lapack' | grep "=> /" | awk '{print $4}' | xargs ls -la

lrwxrwxrwx 1 root root 15 Aug 18 06:12 /usr/lib32/fglrx/libAMDXvBA.so -> libAMDXvBA.so.1
lrwxrwxrwx 1 root root 17 Jan 12 23:19 /usr/lib32/fglrx/libAMDXvBA.so.1 -> libAMDXvBA.so.1.0
-rw-r--r-- 1 root root 10839656 Aug 18 06:12 /usr/lib32/libamdhsasc32.so
-rw-r--r-- 1 root root 54673864 Aug 18 06:12 /usr/lib32/libamdocl12cl32.so
-rw-r--r-- 1 root root 60111220 Aug 18 06:12 /usr/lib32/libamdocl32.so
lrwxrwxrwx 1 root root 17 Jan 12 23:19 /usr/lib32/libAMDXvBA.so.1 -> libAMDXvBA.so.1.0
-rw-r--r-- 1 root root 29152 Aug 18 06:12 /usr/lib32/libOpenCL.so.1
-rw-r--r-- 1 root root 12209920 Aug 18 06:12 /usr/lib/libamdhsasc64.so
-rw-r--r-- 1 root root 55936064 Aug 18 06:12 /usr/lib/libamdocl12cl64.so
-rw-r--r-- 1 root root 61057960 Aug 18 06:12 /usr/lib/libamdocl64.so
lrwxrwxrwx 1 root root 15 Aug 18 06:12 /usr/lib/libAMDXvBA.so -> libAMDXvBA.so.1
lrwxrwxrwx 1 root root 17 Aug 18 06:12 /usr/lib/libAMDXvBA.so.1 -> libAMDXvBA.so.1.0
lrwxrwxrwx 1 root root 28 Jan 13 05:17 /usr/lib/libblas.so -> /etc/alternatives/libblas.so
lrwxrwxrwx 1 root root 30 Jan 13 05:17 /usr/lib/libblas.so.3 -> /etc/alternatives/libblas.so.3
lrwxrwxrwx 1 root root 22 Feb 3 2014 /usr/lib/libcblas.so -> atlas-base/libcblas.so
lrwxrwxrwx 1 root root 24 Feb 3 2014 /usr/lib/libcblas.so.3 -> atlas-base/libcblas.so.3
lrwxrwxrwx 1 root root 24 Feb 3 2014 /usr/lib/libf77blas.so -> atlas-base/libf77blas.so
lrwxrwxrwx 1 root root 26 Feb 3 2014 /usr/lib/libf77blas.so.3 -> atlas-base/libf77blas.so.3
lrwxrwxrwx 1 root root 29 Feb 3 2014 /usr/lib/liblapack_atlas.so -> atlas-base/liblapack_atlas.so
lrwxrwxrwx 1 root root 31 Feb 3 2014 /usr/lib/liblapack_atlas.so.3 -> atlas-base/liblapack_atlas.so.3
lrwxrwxrwx 1 root root 30 Jan 13 05:17 /usr/lib/liblapack.so -> /etc/alternatives/liblapack.so
lrwxrwxrwx 1 root root 32 Jan 13 05:17 /usr/lib/liblapack.so.3 -> /etc/alternatives/liblapack.so.3
lrwxrwxrwx 1 root root 14 Aug 18 06:12 /usr/lib/libOpenCL.so -> libOpenCL.so.1
-rw-r--r-- 1 root root 27328 Aug 18 06:12 /usr/lib/libOpenCL.so.1
-rw-r--r-- 1 root root 26592 Dec 17 2013 /usr/lib/x86_64-linux-gnu/libcolamd.so.2.8.0
lrwxrwxrwx 1 root root 18 Mar 15 2014 /usr/lib/x86_64-linux-gnu/libOpenCL.so -> libOpenCL.so.1.0.0
lrwxrwxrwx 1 root root 18 Mar 15 2014 /usr/lib/x86_64-linux-gnu/libOpenCL.so.1 -> libOpenCL.so.1.0.0
lrwxrwxrwx 1 root root 17 Jan 12 22:55 /usr/lib/x86_64-linux-gnu/libsamdb.so.0 -> libsamdb.so.0.0.1

ldconfig -p | grep -i 'OPENCL|amd|blas|lapack' | grep "=> /" | awk '{print $4}' | xargs ls -la | grep " -> " | awk '{print $11}' | xargs locate

/etc/alternatives/libblas.so
/etc/alternatives/libblas.so.3
/etc/alternatives/libblas.so.3gf
/etc/alternatives/liblapack.so
/etc/alternatives/liblapack.so.3
/etc/alternatives/liblapack.so.3gf
/opt/AMDAPPSDK-3.0/lib/x86/libOpenCL.so.1
/opt/AMDAPPSDK-3.0/lib/x86_64/sdk/libOpenCL.so.1
/usr/lib/libAMDXvBA.so.1
/usr/lib/libAMDXvBA.so.1.0
/usr/lib/libOpenCL.so.1
/usr/lib/atlas-base/libcblas.so
/usr/lib/atlas-base/libcblas.so.3
/usr/lib/atlas-base/libcblas.so.3.0
/usr/lib/atlas-base/libf77blas.so
/usr/lib/atlas-base/libf77blas.so.3
/usr/lib/atlas-base/libf77blas.so.3.0
/usr/lib/atlas-base/liblapack_atlas.so
/usr/lib/atlas-base/liblapack_atlas.so.3
/usr/lib/atlas-base/liblapack_atlas.so.3.0
/usr/lib/x86_64-linux-gnu/libOpenCL.so.1
/usr/lib/x86_64-linux-gnu/libOpenCL.so.1.0.0
/usr/lib/x86_64-linux-gnu/libsamdb.so.0.0.1
/usr/lib32/libAMDXvBA.so.1
/usr/lib32/libAMDXvBA.so.1.0
/usr/lib32/libOpenCL.so.1
/usr/lib32/fglrx/libAMDXvBA.so.1
/usr/lib32/fglrx/libAMDXvBA.so.1.0

update-alternatives --display libOpenCL.so

update-alternatives: error: no alternatives for libOpenCL.so

update-alternatives --display libOpenCL.so.1

update-alternatives: error: no alternatives for libOpenCL.so.1

I am still having issues with caffe but with this configuration for me it does successfully complete clBLAS's test-functional.

[gujunli]

@mpekalski sorry that I came to your question late. what is your current status?

[mpekalski]

I managed to set up everything. Some tests of clBLAS are still failing. For OpenCL I only managed to run quick-test for cifar10 and it seems to work fine. Anyway, thanks for having a look.