To use this example with TAU, please configure TAU with the -level_zero=<dir> option (-opencl=<dir> is optional): 

source /opt/intel/oneapi/setvars.sh
./configure -level_zero=/usr -bfd=download -unwind=download -dwarf=download -iowrapper -otf=download -opencl=/opt/intel/oneapi/compiler/2021.1-beta10/linux
make install
cd examples/gpu/oneapi/complex_mult
make 
tau_exec -T serial,level_zero -l0 ./complex_mult.exe
Target Device: Intel(R) Graphics Gen12LP [0x9a49]
****************************************Multiplying Complex numbers in Parallel********************************************************
[0] (2 : 4i) * (4 : 6i) = (-16 : 28i)
[1] (3 : 5i) * (5 : 7i) = (-20 : 46i)
[2] (4 : 6i) * (6 : 8i) = (-24 : 68i)
[3] (5 : 7i) * (7 : 9i) = (-28 : 94i)
[4] (6 : 8i) * (8 : 10i) = (-32 : 124i)
...
[9999] (10001 : 10003i) * (10003 : 10005i) = (-40012 : 200120014i)
Complex multiplication successfully run on the device

pprof -a
Reading Profile files in profile.*

NODE 0;CONTEXT 0;THREAD 0:
---------------------------------------------------------------------------------------
%Time    Exclusive    Inclusive       #Call      #Subrs  Inclusive Name
              msec   total msec                          usec/call 
---------------------------------------------------------------------------------------
100.0          113          113           1           1     113572 .TAU application
  0.0        0.023        0.023           1           0         23 pthread_create

NODE 0;CONTEXT 0;THREAD 1:
---------------------------------------------------------------------------------------
%Time    Exclusive    Inclusive       #Call      #Subrs  Inclusive Name
              msec   total msec                          usec/call 
---------------------------------------------------------------------------------------
100.0           82           82           1           5      82778 .TAU application
  0.0       0.0405       0.0405           4           0         10 zeCommandListAppendMemoryCopy
  0.0        0.008        0.008           1           0          8 _ZTSZZ13DpcppParallelRN2cl4sycl5queueERSt6vectorI8Complex2SaIS4_EES7_S7_ENKUlRT_E64_12clINS0_7handlerEEEDaS9_EUlS8_E70_23

NODE 0;CONTEXT 0;THREAD 2:
---------------------------------------------------------------------------------------
%Time    Exclusive    Inclusive       #Call      #Subrs  Inclusive Name
              msec   total msec                          usec/call 
---------------------------------------------------------------------------------------
100.0            1           84           1         136      84291 .TAU application
 96.6           81           81           1           0      81404 zeModuleCreate
  0.8        0.698        0.698           4           0        175 zeCommandListAppendMemoryCopy
  0.3        0.281        0.281           6           0         47 zeEventHostSynchronize
  0.2        0.142        0.142           1           0        142 zeCommandListCreateImmediate
  0.1        0.122        0.122           2           0         61 zeCommandQueueExecuteCommandLists
  0.1       0.0907       0.0907           1           0         91 zeCommandQueueCreate
  0.1       0.0505       0.0505           2           0         25 zeCommandListReset
  0.1        0.045        0.045           3           0         15 zeMemAllocDevice
  0.0       0.0155       0.0155           1           0         16 zeCommandListCreate
  0.0       0.0135       0.0135           1           0         14 zeCommandListDestroy
  0.0        0.013        0.013           3           0          4 zeMemFree
  0.0       0.0125       0.0125           1           0         12 zeModuleDestroy
  0.0         0.01         0.01           1           0         10 zeKernelCreate
  0.0       0.0075       0.0075           1           0          8 zeCommandListAppendLaunchKernel
  0.0      0.00725      0.00725           1           0          7 zeCommandQueueDestroy
  0.0        0.006        0.006          12           0          0 zeKernelSetArgumentValue
  0.0       0.0045       0.0045          10           0          0 zeDeviceGetModuleProperties
  0.0      0.00425      0.00425           3           0          1 zeDeviceGet
  0.0        0.003        0.003           1           0          3 zeEventPoolCreate
  0.0        0.003        0.003           1           0          3 zeFenceDestroy
  0.0      0.00275      0.00275           1           0          3 zeDeviceGetProperties
  0.0       0.0025       0.0025           1           0          2 zeFenceCreate
  0.0      0.00225      0.00225           1           0          2 zeKernelDestroy
  0.0        0.002        0.002          10           0          0 zeDeviceGetImageProperties
  0.0      0.00175      0.00175          20           0          0 zeDeviceGetMemoryProperties
  0.0      0.00175      0.00175           2           0          1 zeEventCreate
  0.0       0.0015       0.0015           2           0          1 zeCommandListClose
  0.0       0.0015       0.0015           2           0          1 zeDeviceGetCommandQueueGroupProperties
  0.0       0.0015       0.0015           1           0          2 zeInit
  0.0       0.0015       0.0015           1           0          2 zeKernelSuggestGroupSize
  0.0        0.001        0.001           1           0          1 zeCommandListAppendWaitOnEvents
  0.0        0.001        0.001          20           0          0 zeDeviceGetCacheProperties
  0.0        0.001        0.001           1           0          1 zeDriverGetProperties
  0.0      0.00075      0.00075           2           0          0 zeDriverGet
  0.0      0.00075      0.00075           1           0          1 zeKernelSetGroupSize
  0.0       0.0005       0.0005           1           0          0 zeContextCreate
  0.0       0.0005       0.0005           2           0          0 zeContextDestroy
  0.0       0.0005       0.0005           1           0          0 zeDeviceGetComputeProperties
  0.0       0.0005       0.0005           2           0          0 zeEventDestroy
  0.0       0.0005       0.0005           1           0          0 zeKernelGetProperties
  0.0      0.00025      0.00025           1           0          0 zeDriverGetApiVersion
  0.0      0.00025      0.00025           2           0          0 zeFenceQueryStatus
  0.0      0.00025      0.00025           2           0          0 zeFenceReset
  0.0      0.00025      0.00025           1           0          0 zeKernelSetIndirectAccess
  0.0      0.00025      0.00025           1           0          0 zeModuleBuildLogDestroy

NODE 0;CONTEXT 0;THREAD 3:
---------------------------------------------------------------------------------------
%Time    Exclusive    Inclusive       #Call      #Subrs  Inclusive Name
              msec   total msec                          usec/call 
---------------------------------------------------------------------------------------
100.0            2           92           1           1      92971 .TAU application
 97.7           90           90           1           0      90871 NEO::DrmGemCloseWorker::worker(void*) [{} {0, 0}]


