18 Replies Latest reply on Mar 5, 2012 6:50 PM by antzrhere

    Computer is dead/locked : last SDK !

    spectral

      Hi,

      I have try to run the clpp gpu radix sort on a HD6950 and after 1 sort, it locks !

      To test, you can simply download the last version from SVN (not the packaged one), run it... and you will have to reboot your computer !

      It is a CRITICAL problem... so please do your best to fix it !

      Thanks

        • Computer is dead/locked : last SDK !
          spectral

          Does someone from the AMD Team can test it ?

          My computer is locked each time I start the sort algorithm ! (I know that I'm not the only one to meet this kind of problem !!!)

          You can download the last version from SVN here :

          http://code.google.com/p/clpp/

          • Computer is dead/locked : last SDK !
            MicahVillmow
            viewon01,
            Does the hang occur if all the barriers are commented out? Also, can you set GPU_BARRIER_DETECTION=true to see if that fixes the hang?
            • Computer is dead/locked : last SDK !
              MicahVillmow
              it is an environment variable.
              On windows, use 'set GPU_BARRIER_DETECTION=true' and then run your app from the command line.
              On linux, use 'export GPU_BARRIER_DETECTION=true'
                • Computer is dead/locked : last SDK !
                  spectral

                  Hi Micah,

                  I have do some tests :

                  1) I only test the 'scan' algorithm and the computer is blocked.

                  2) I have put the env var. GPU_BARRIER_DETECTION but it has NO effect

                  3) I have remove all the barriers and this has the computer DOES NOT block. So, the problem is related to a local-barrier

                  What can I do to help you to find the problem ? Maybe someone at AMD can take a closer look ? Tell me what to do ?

                  Thanks

                   

                  BTW: I have also update to Catalyst 11.6 but it change nothing :-(

                    • Computer is dead/locked : last SDK !
                      spectral

                      I have also tested with the Catalyst 11.7 preview, the one delivered with gDebugger.

                      First, I still have the problem and even there are some regressions !!!!

                      I have test my main software with it (This one does not contains any _sync_ operation) and it also block the computer !

                      There is a terrible bug somewhere :-(

                      Tell me how I can help you to debug this ?

                        • Computer is dead/locked : last SDK !
                          spectral

                          I have see that other peoples also have their computer freezing :

                          http://forums.amd.com/devforum/messageview.cfm?catid=390&threadid=150237&enterthread=y

                          And even, I have test my application with Catalyst 11.7 and now even the CPU version crash... I run it and it exit directly !!!!!!!

                            • Computer is dead/locked : last SDK !
                              himanshu.gautam

                              vewon01,

                              I am looking into this issue.I will try to communicate if i find some thing fishy inyour code.

                              Anyways as you said before, the code doesn't crash when you removed the barriers.I would suggest you to incrementely remove barriers one by one and try to figure out which barrier gets stuck.

                              Also have you tried to use gDEBugger, it can be helpful.

                                • Computer is dead/locked : last SDK !
                                  spectral

                                  Thanks,

                                  So I'll wait for your feedback. Thanks for your help.

                                    • Computer is dead/locked : last SDK !
                                      spectral

                                      Hi Himanshu,

                                      Have you find something ? Maybe the problem is somewhere else ?

                                        • Computer is dead/locked : last SDK !
                                          spectral

                                          Still no news ?

                                          I have try to find the bug, but maybe I have miss a specific architecture constraint (Like the one that Micah is talking about). Or it is a driver bug !

                                          Can you help ?

                                          Thanks

                                            • Computer is dead/locked : last SDK !
                                              spectral

                                              Any news ?

                                              How can I help to debug please ?

                                              Thanks

                                                • Computer is dead/locked : last SDK !
                                                  genaganna

                                                   

                                                  Originally posted by: viewon01 Any news ?

                                                   

                                                  How can I help to debug please ?

                                                   

                                                  Thanks

                                                   

                                                  Viewon01,

                                                  It is look like they have not followed OpenCL.  I am getting following error from clBuildProgram. I have tested with SDK2.5 and 11.7 driver.

                                                   

                                                  ==============================================

                                                   

                                                  Platform[AMD Accelerated Parallel Processing] Device[Cypress]

                                                   

                                                   

                                                  --------------- Satish radix sort Key

                                                  Error: Failed to build program executable!

                                                  C:\Users\Naganna\AppData\Local\Temp\OCL850A.tmp.cl(100): error: non-kernel

                                                            function: variable with automatic storage duration cannot be stored

                                                            in a named address space

                                                          __local uint localBuffer[TPG*2];

                                                                       ^

                                                   

                                                  C:\Users\Naganna\AppData\Local\Temp\OCL850A.tmp.cl(104): error: identifier

                                                            "localBuffer" is undefined

                                                          uint4 localBits = inclusive_scan_128(localBuffer, tid, block, lane, init

                                                  ialValue, bitsOnCount);

                                                                                               ^

                                                   

                                                  C:\Users\Naganna\AppData\Local\Temp\OCL850A.tmp.cl(128): error: mixed

                                                            vector-scalar operation not allowed unless

                                                            up-convertable(scalar-type=>vector-element-type)

                                                          localBits += localBuffer[block + 4 - 1];

                                                                       ^

                                                   

                                                  C:\Users\Naganna\AppData\Local\Temp\OCL850A.tmp.cl(308): warning: type

                                                            qualifier is meaningless on cast type

                                                        const int4 tid4 = ((const int4)tid) + (const int4)(0,WGZ,WGZ_x2,WGZ_x3);

                                                   

                                                                            ^

                                                   

                                                  C:\Users\Naganna\AppData\Local\Temp\OCL850A.tmp.cl(309): warning: type

                                                            qualifier is meaningless on cast type

                                                          const int4 gid4 = tid4 + ((const int4)groupId<<2);

                                                                                     ^

                                                   

                                                  3 errors detected in the compilation of "C:\Users\Naganna\AppData\Local\Temp\OCL

                                                  850A.tmp.cl".

                                                  ≡¡Internal error: compiler frontend invocation failed. Make sure ATISTREAMSDKROO

                                                  T is set

                                                  Program build failure

                                                  Assertion failed: clStatus == CL_SUCCESS, file c:\users\naganna\downloads\clpp_v

                                                  1_beta3\clpp\src\clpp\clppprogram.cpp, line 180



                                                  ==============================================

                                                   

                                                  Please ask clpp developers to fix all OpenCL compilation error for AMD OpenCL.

                                                   

                                                    • Computer is dead/locked : last SDK !
                                                      spectral

                                                      Hi,

                                                      The fix have been dones. Can you help to fix for the GPU please ?

                                                      Thanks

                                                        • Computer is dead/locked : last SDK !
                                                          erwincoumans

                                                           

                                                          It looks like the latest drivers, Catalyst 11.9 fixes the problem.

                                                          Can you confirm?

                                                            • Computer is dead/locked : last SDK !
                                                              genaganna

                                                               

                                                              Originally posted by: erwincoumans  

                                                              It looks like the latest drivers, Catalyst 11.9 fixes the problem.

                                                              Can you confirm?

                                                              I still see those errors with internel libraries.  Please ask clpp developer to fix the issue.

                                                              Error log

                                                              ==============================================

                                                              Platform[AMD Accelerated Parallel Processing] Device[Cypress]

                                                               

                                                               

                                                              --------------- Satish radix sort Key

                                                              Error: Failed to build program executable!

                                                              C:\Users\Naganna\AppData\Local\Temp\OCLC91D.tmp.cl(100): error: variable with

                                                                        automatic storage duration cannot be stored in the named address

                                                                        space

                                                                      __local uint localBuffer[TPG*2];

                                                                                   ^

                                                               

                                                              C:\Users\Naganna\AppData\Local\Temp\OCLC91D.tmp.cl(104): error: identifier

                                                                        "localBuffer" is undefined

                                                                      uint4 localBits = inclusive_scan_128(localBuffer, tid, block, lane, initialValue, bitsOnCount);

                                                                                                           ^

                                                               

                                                              C:\Users\Naganna\AppData\Local\Temp\OCLC91D.tmp.cl(128): error: mixed

                                                                        vector-scalar operation not allowed unless

                                                                        up-convertable(scalar-type=>vector-element-type)

                                                                      localBits += localBuffer[block + 4 - 1];

                                                                                   ^

                                                               

                                                              C:\Users\Naganna\AppData\Local\Temp\OCLC91D.tmp.cl(308): warning: type

                                                                        qualifier is meaningless on cast type

                                                                    const int4 tid4 = ((const int4)tid) + (const int4)(0,WGZ,WGZ_x2,WGZ_x3);

                                                                                        ^

                                                               

                                                              C:\Users\Naganna\AppData\Local\Temp\OCLC91D.tmp.cl(309): warning: type

                                                                        qualifier is meaningless on cast type

                                                                      const int4 gid4 = tid4 + ((const int4)groupId<<2);

                                                                                                 ^

                                                               

                                                              3 errors detected in the compilation of "C:\Users\Naganna\AppData\Local\Temp\OCLC91D.tmp.cl".

                                                               

                                                              Internal error: clc compiler invocation failed.

                                                               

                                                              Program build failure

                                                              Assertion failed: clStatus == CL_SUCCESS, file c:\users\naganna\desktop\clpp_v1_beta3\clpp\src\clpp\clppprogram.cpp, line 180