Closed GoogleCodeExporter closed 9 years ago
Lets see if we can help.
Are you sure you have catalyst driver and AMD APP SDK installed?
Check /opt/AMDAPP/bin/x86_64 there should be a program called clinfo does it
run OK?
Does it report your GPU device? (feel free to send me the output if you would
like me to check for you).
When you first log in does your LD_LIBRARY_PATH var refer to
/opt/AMDAPP/lib/x86_64 ? It should (so that opencl .so's can be located)?
Did you extend LD_LIBRARY_PATH or replace it?
I note that you added two issues for this (#25 and this #26). I will delete #25
and we can track it here.
Gary
Original comment by frost.g...@gmail.com
on 1 Dec 2011 at 1:36
AMD-APP-SDK-v2.5-RC2-lnx64 is installed
yes clinfo is working correctly
LD_LIBRARY_PATH is correctly refer
----
[[krishang@octopus ~]$ echo $LD_LIBRARY_PATH
/usr/local/AMD-APP-SDK-v2.5-RC2-lnx64/lib/x86_64:
/home/krishang/aparapi_2011_09_13:
/usr/local/mpich2-1.0.7/lib:/usr/local/AMD-APP-SDK-v2.4-lnx64/lib/x86_64:
/usr/local/GotoBLAS2:
:/usr/local/AMD-APP-SDK-v2.4-lnx64/lib/x86_64:
---
even i removed usr/local/AMD-APP-SDK-v2.4-lnx64/lib/x86_64: from library path
same warning is coming .
i apologize for reporting is twice .
output of cl info
--------------------------------------------------------------------------
[krishang@octopus ~]$ /usr/local/AMD-APP-SDK-v2.5-RC2-lnx64/bin/x86_64/clinfo
Number of platforms: 1
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 1.1 AMD-APP-SDK-v2.5 (684.213)
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: 2
Device Type: CL_DEVICE_TYPE_GPU
Device ID: 4098
Device Topology: PCI[ B#0, D#0, F#0 ]
Max compute units: 18
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: 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: 0Mhz
Address bits: 32
Max memory allocation: 268435456
Image support: Yes
Max number of images read arguments: 128
Max number of images write arguments: 8
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: 1024
Alignment (bits) of base address: 32768
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: None
Cache line size: 0
Cache size: 0
Global memory size: 1073741824
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Scratchpad
Local memory size: 32768
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 properties:
Out-of-Order: No
Profiling : Yes
Platform ID: 0x2b06a4d2f060
Name: Cypress
Vendor: Advanced Micro Devices, Inc.
Device OpenCL C version: OpenCL C 1.1
Driver version: CAL 1.4.900
Profile: FULL_PROFILE
Version: OpenCL 1.1 AMD-APP-SDK-v2.5 (684.213)
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_3d_image_writes cl_khr_byte_addressable_store cl_khr_gl_sharing cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_popcnt
Device Type: CL_DEVICE_TYPE_CPU
Device ID: 4098
Max compute units: 24
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: 0
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: 0
Max clock frequency: 800Mhz
Address bits: 64
Max memory allocation: 7369785344
Image support: Yes
Max number of images read arguments: 128
Max number of images write arguments: 8
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: No
Cache type: Read/Write
Cache line size: 64
Cache size: 65536
Global memory size: 29479141376
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Global
Local memory size: 32768
Kernel Preferred work group size multiple: 1
Error correction support: 0
Unified memory for Host and Device: 1
Profiling timer resolution: 999848
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: Yes
Queue properties:
Out-of-Order: No
Profiling : Yes
Platform ID: 0x2b06a4d2f060
Name: AMD Opteron(tm) Processor 6168
Vendor: AuthenticAMD
Device OpenCL C version: OpenCL C 1.1
Driver version: 2.0
Profile: FULL_PROFILE
Version: OpenCL 1.1 AMD-APP-SDK-v2.5 (684.213)
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_byte_addressable_store cl_khr_gl_sharing cl_ext_device_fission cl_amd_device_attribute_query cl_amd_vec3 cl_amd_media_ops cl_amd_popcnt cl_amd_printf
--------------------------------------------------------------------------------
-----
Original comment by kri22go...@gmail.com
on 1 Dec 2011 at 2:17
OK so yes looks like Catalyst and APP SDK is installed.
I am not familiar with CentOS (RHEL derivative I think) but I would expect that
/opt/AMDAPP should be the location of these files. Maybe the install process
for CentOS is different. We'll leave that for the moment.
Is this a binary distribution (from
http://code.google.com/p/aparapi/downloads/list)? or did you go through the
build process and build from source?
Also did you encounter this error running any of the samples (mandel?) ?
I assume that you are running from the machine and are *not* remoting in (ssh,
rsh) and that X is up (you are using an X Windows session rather than running
from a Console).
The example scripts (mandel.sh) set the java.library.path to point to the
directory containing aparapi.so. Can you confirm that the directory is correct
and contains the aparapi.so file.
Consider setting -Dcom.amd.aparapi.logLevel=FINE to see if we can extract any
more information at run time.
Original comment by frost.g...@gmail.com
on 1 Dec 2011 at 3:58
ya it is binary distribution.
i am encounter this error to running samples (both mandel and squres).
DISPLAY is perfactly export from server to client machine since mandel output
in JTP mode coming in client machine.
Original comment by kri22go...@gmail.com
on 2 Dec 2011 at 5:08
Make sure that this is not a duplicate of
http://code.google.com/p/aparapi/issues/detail?id=17
In short, "X-Forwarding" enabled on your remote session is incompatible with
OpenCL.
Original comment by ryan.lam...@gmail.com
on 2 Dec 2011 at 5:47
the issue is not with "X-Forwarding" . i directly login to server but issue is
same.
it is not able to load shared lib aparapi_x86 library. even it is in the path.
detail out put of mandel with -Dcom.amd.aparapi.logLevel=FINE is below.
----------------------------------------------------------------------
[krishang@octopus mandel]$ source mandel.sh
Dec 5, 2011 11:08:16 AM com.amd.aparapi.Kernel$EXECUTION_MODE <clinit>
FINE: arch = i386
Dec 5, 2011 11:08:16 AM com.amd.aparapi.Kernel$EXECUTION_MODE <clinit>
FINE: attempting to load shared lib aparapi_x86
Dec 5, 2011 11:08:16 AM com.amd.aparapi.Kernel$EXECUTION_MODE <clinit>
WARNING: Check your environment. Failed to load aparapi native library
aparapi_x86 or possibly failed to locate opencl native library
(opencl.dll/opencl.so). Ensure that both are in your PATH (windows) or in
LD_LIBRARY_PATH (linux).
Dec 5, 2011 11:08:16 AM com.amd.aparapi.Kernel$EXECUTION_MODE
getDefaultExecutionMode
FINE: default execution mode = JTP
Dec 5, 2011 11:08:16 AM com.amd.aparapi.KernelRunner executeJava
FINE: executeJava: _globalSize=589824
Dec 5, 2011 11:08:16 AM com.amd.aparapi.KernelRunner
getJTPLocalSizeForGlobalSize
FINE: executeJava: picking localSize=48 for globalSize=589824
Dec 5, 2011 11:08:16 AM com.amd.aparapi.KernelRunner executeJava
FINE: executeJava: localSize=48, numThreads=48, numThreadSets=1, numGroups=12288
Execution mode=JTP
-----------------------------------------------------------------------
Original comment by kri22go...@gmail.com
on 5 Dec 2011 at 5:51
So is a 64 bit Linux distro?
Is the JVM also 64 bit?
Aparapi is trying to load aparapi_x86.so and should be trying to load
aparapi_x86_64 if this machine is a 64 bit machine.
Can you confirm bitness of the OS and the JVM?
You may need to install 64 bit JVM.
Gary
Original comment by frost.g...@gmail.com
on 5 Dec 2011 at 2:56
thnx frost..
after install 64 bit JVM it is working .
Original comment by kri22go...@gmail.com
on 7 Dec 2011 at 2:48
Excellent. Glad we got it working for you.
I will close this issue
Original comment by frost.g...@gmail.com
on 7 Dec 2011 at 3:56
Original issue reported on code.google.com by
kri22go...@gmail.com
on 1 Dec 2011 at 11:24