:3:rocdevice.cpp :442 : 43557940886 us: [pid:263009 tid:0x7fb0637eb0c0] Initializing HSA stack. :3:comgrctx.cpp :33 : 43557950813 us: [pid:263009 tid:0x7fb0637eb0c0] Loading COMGR library. :3:rocdevice.cpp :208 : 43557950867 us: [pid:263009 tid:0x7fb0637eb0c0] Numa selects cpu agent[0]=0x5573aa210df0(fine=0x5573aa109ff0,coarse=0x5573aa208b60) for gpu agent=0x5573aa20de60 CPU<->GPU XGMI=0 :3:rocdevice.cpp :1680: 43557950995 us: [pid:263009 tid:0x7fb0637eb0c0] Gfx Major/Minor/Stepping: 10/3/1 :3:rocdevice.cpp :1682: 43557950999 us: [pid:263009 tid:0x7fb0637eb0c0] HMM support: 1, XNACK: 0, Direct host access: 0 :3:rocdevice.cpp :1684: 43557951003 us: [pid:263009 tid:0x7fb0637eb0c0] Max SDMA Read Mask: 0x0, Max SDMA Write Mask: 0x0 :4:rocdevice.cpp :2063: 43557951062 us: [pid:263009 tid:0x7fb0637eb0c0] Allocate hsa host memory 0x7fb0638e2000, size 0x38 :4:rocdevice.cpp :2063: 43557951401 us: [pid:263009 tid:0x7fb0637eb0c0] Allocate hsa host memory 0x7fb050b00000, size 0x101000 :4:rocdevice.cpp :2063: 43557951853 us: [pid:263009 tid:0x7fb0637eb0c0] Allocate hsa host memory 0x7fb050900000, size 0x101000 :4:runtime.cpp :83 : 43557951935 us: [pid:263009 tid:0x7fb0637eb0c0] init :3:hip_context.cpp :48 : 43557951938 us: [pid:263009 tid:0x7fb0637eb0c0] Direct Dispatch: 1 :3:hip_memory.cpp :566 : 43557951969 us: [pid:263009 tid:0x7fb0637eb0c0] hipMalloc ( 0x7ffc04ebdd60, 4000000 ) :4:rocdevice.cpp :2191: 43557952006 us: [pid:263009 tid:0x7fb0637eb0c0] Allocate hsa device memory 0x7fb050400000, size 0x3d0900 :3:rocdevice.cpp :2230: 43557952010 us: [pid:263009 tid:0x7fb0637eb0c0] device=0x5573aa24a5c0, freeMem_ = 0x2fec2f700 :3:hip_memory.cpp :568 : 43557952015 us: [pid:263009 tid:0x7fb0637eb0c0] hipMalloc: Returned hipSuccess : 0x7fb050400000: duration: 46 us :3:hip_memory.cpp :566 : 43557952020 us: [pid:263009 tid:0x7fb0637eb0c0] hipMalloc ( 0x7ffc04ebdd58, 4000000 ) :4:rocdevice.cpp :2191: 43557952059 us: [pid:263009 tid:0x7fb0637eb0c0] Allocate hsa device memory 0x7faf4b800000, size 0x3d0900 :3:rocdevice.cpp :2230: 43557952063 us: [pid:263009 tid:0x7fb0637eb0c0] device=0x5573aa24a5c0, freeMem_ = 0x2fe85ee00 :3:hip_memory.cpp :568 : 43557952067 us: [pid:263009 tid:0x7fb0637eb0c0] hipMalloc: Returned hipSuccess : 0x7faf4b800000: duration: 47 us :3:hip_memory.cpp :566 : 43557952072 us: [pid:263009 tid:0x7fb0637eb0c0] hipMalloc ( 0x7ffc04ebdd50, 4000000 ) :4:rocdevice.cpp :2191: 43557952095 us: [pid:263009 tid:0x7fb0637eb0c0] Allocate hsa device memory 0x7faf4b200000, size 0x3d0900 :3:rocdevice.cpp :2230: 43557952099 us: [pid:263009 tid:0x7fb0637eb0c0] device=0x5573aa24a5c0, freeMem_ = 0x2fe48e500 :3:hip_memory.cpp :568 : 43557952103 us: [pid:263009 tid:0x7fb0637eb0c0] hipMalloc: Returned hipSuccess : 0x7faf4b200000: duration: 31 us :3:hip_memory.cpp :641 : 43557955171 us: [pid:263009 tid:0x7fb0637eb0c0] hipMemcpy ( 0x7fb050400000, 0x7fb05242f010, 4000000, hipMemcpyHostToDevice ) :3:rocdevice.cpp :2732: 43557955182 us: [pid:263009 tid:0x7fb0637eb0c0] number of allocated hardware queues with low priority: 0, with normal priority: 0, with high priority: 0, maximum per priority is: 4 :3:rocdevice.cpp :2810: 43557961534 us: [pid:263009 tid:0x7fb0637eb0c0] created hardware queue 0x7fb0638d2000 with size 16384 with priority 1, cooperative: 0 :3:rocdevice.cpp :2902: 43557961542 us: [pid:263009 tid:0x7fb0637eb0c0] acquireQueue refCount: 0x7fb0638d2000 (1) :4:rocdevice.cpp :2063: 43557961865 us: [pid:263009 tid:0x7fb0637eb0c0] Allocate hsa host memory 0x7faf49400000, size 0x100000 :3:devprogram.cpp :2684: 43558136012 us: [pid:263009 tid:0x7fb0637eb0c0] Using Code Object V5. :4:command.cpp :349 : 43558138568 us: [pid:263009 tid:0x7fb0637eb0c0] Command (CopyHostToDevice) enqueued: 0x5573aa4bf820 :4:rocmemory.cpp :966 : 43558138674 us: [pid:263009 tid:0x7fb0637eb0c0] Locking to pool 0x5573aa208b60, size 0x3d1000, HostPtr = 0x7fb05242f000, DevPtr = 0x7fb05242f000 :4:rocblit.cpp :727 : 43558138683 us: [pid:263009 tid:0x7fb0637eb0c0] HSA Async Copy dst=0x7fb050400000, src=0x7fb05242f010, size=4000000, wait_event=0x0, completion_signal=0x7fb0638e6800 :4:rocvirtual.cpp :553 : 43558139303 us: [pid:263009 tid:0x7fb0637eb0c0] Host wait on completion_signal=0x7fb0638e6800 :3:rocvirtual.hpp :66 : 43558139310 us: [pid:263009 tid:0x7fb0637eb0c0] Host active wait for Signal = (0x7fb0638e6800) for -1 ns :4:command.cpp :289 : 43558139634 us: [pid:263009 tid:0x7fb0637eb0c0] Queue marker to command queue: 0x5573aa10b440 :4:command.cpp :349 : 43558139639 us: [pid:263009 tid:0x7fb0637eb0c0] Command (InternalMarker) enqueued: 0x5573aa6b9510 :4:command.cpp :179 : 43558139644 us: [pid:263009 tid:0x7fb0637eb0c0] Command 0x5573aa4bf820 complete :4:command.cpp :173 : 43558139647 us: [pid:263009 tid:0x7fb0637eb0c0] Command 0x5573aa6b9510 complete (Wall: 43558139647, CPU: 0, GPU: 0 us) :4:command.cpp :253 : 43558139653 us: [pid:263009 tid:0x7fb0637eb0c0] Waiting for event 0x5573aa4bf820 to complete, current status 0 :4:command.cpp :268 : 43558139657 us: [pid:263009 tid:0x7fb0637eb0c0] Event 0x5573aa4bf820 wait completed :3:hip_memory.cpp :642 : 43558139662 us: [pid:263009 tid:0x7fb0637eb0c0] hipMemcpy: Returned hipSuccess : : duration: 184491 us :3:hip_memory.cpp :641 : 43558139671 us: [pid:263009 tid:0x7fb0637eb0c0] hipMemcpy ( 0x7faf4b800000, 0x7fb05205e010, 4000000, hipMemcpyHostToDevice ) :4:command.cpp :349 : 43558139678 us: [pid:263009 tid:0x7fb0637eb0c0] Command (CopyHostToDevice) enqueued: 0x5573aa4bf820 :4:rocmemory.cpp :966 : 43558139794 us: [pid:263009 tid:0x7fb0637eb0c0] Locking to pool 0x5573aa208b60, size 0x3d1000, HostPtr = 0x7fb05205e000, DevPtr = 0x7fb05205e000 :4:rocblit.cpp :727 : 43558139801 us: [pid:263009 tid:0x7fb0637eb0c0] HSA Async Copy dst=0x7faf4b800000, src=0x7fb05205e010, size=4000000, wait_event=0x0, completion_signal=0x7fb0638e6780 :4:rocvirtual.cpp :553 : 43558139807 us: [pid:263009 tid:0x7fb0637eb0c0] Host wait on completion_signal=0x7fb0638e6780 :3:rocvirtual.hpp :66 : 43558139811 us: [pid:263009 tid:0x7fb0637eb0c0] Host active wait for Signal = (0x7fb0638e6780) for -1 ns :4:command.cpp :289 : 43558140120 us: [pid:263009 tid:0x7fb0637eb0c0] Queue marker to command queue: 0x5573aa10b440 :4:command.cpp :349 : 43558140124 us: [pid:263009 tid:0x7fb0637eb0c0] Command (InternalMarker) enqueued: 0x5573aa6b9510 :4:command.cpp :179 : 43558140129 us: [pid:263009 tid:0x7fb0637eb0c0] Command 0x5573aa4bf820 complete :4:command.cpp :173 : 43558140133 us: [pid:263009 tid:0x7fb0637eb0c0] Command 0x5573aa6b9510 complete (Wall: 43558140132, CPU: 0, GPU: 0 us) :4:command.cpp :253 : 43558140139 us: [pid:263009 tid:0x7fb0637eb0c0] Waiting for event 0x5573aa4bf820 to complete, current status 0 :4:command.cpp :268 : 43558140144 us: [pid:263009 tid:0x7fb0637eb0c0] Event 0x5573aa4bf820 wait completed :3:hip_memory.cpp :642 : 43558140147 us: [pid:263009 tid:0x7fb0637eb0c0] hipMemcpy: Returned hipSuccess : : duration: 476 us :3:hip_platform.cpp :193 : 43558140161 us: [pid:263009 tid:0x7fb0637eb0c0] __hipPushCallConfiguration ( {3907,1,1}, {256,1,1}, 0, stream: ) :3:hip_platform.cpp :197 : 43558140166 us: [pid:263009 tid:0x7fb0637eb0c0] __hipPushCallConfiguration: Returned hipSuccess : :3:hip_platform.cpp :202 : 43558140173 us: [pid:263009 tid:0x7fb0637eb0c0] __hipPopCallConfiguration ( {2101532160,2209010602,1670549504}, {2827062664,21875,0}, 0x7ffc04ebdd70, 0x7ffc04ebdd68 ) :3:hip_platform.cpp :211 : 43558140177 us: [pid:263009 tid:0x7fb0637eb0c0] __hipPopCallConfiguration: Returned hipSuccess : :3:hip_module.cpp :678 : 43558140187 us: [pid:263009 tid:0x7fb0637eb0c0] hipLaunchKernel ( 0x5573a8818d88, {3907,1,1}, {256,1,1}, 0x7ffc04ebddb0, 0, stream: ) :3:devprogram.cpp :2681: 43558140248 us: [pid:263009 tid:0x7fb0637eb0c0] Using Code Object V4. :4:command.cpp :349 : 43558140484 us: [pid:263009 tid:0x7fb0637eb0c0] Command (KernelExecution) enqueued: 0x5573aa55e660 :3:rocvirtual.cpp :706 : 43558140491 us: [pid:263009 tid:0x7fb0637eb0c0] Arg0: = ptr:0x7fb050400000 obj:[0x7fb050400000-0x7fb0507d0900] :3:rocvirtual.cpp :706 : 43558140495 us: [pid:263009 tid:0x7fb0637eb0c0] Arg1: = ptr:0x7faf4b800000 obj:[0x7faf4b800000-0x7faf4bbd0900] :3:rocvirtual.cpp :706 : 43558140499 us: [pid:263009 tid:0x7fb0637eb0c0] Arg2: = ptr:0x7faf4b200000 obj:[0x7faf4b200000-0x7faf4b5d0900] :3:rocvirtual.cpp :781 : 43558140503 us: [pid:263009 tid:0x7fb0637eb0c0] Arg3: = val:1000000 :3:rocvirtual.cpp :2859: 43558140505 us: [pid:263009 tid:0x7fb0637eb0c0] ShaderName : _Z8vadd_hipPKfS0_Pfi :4:rocvirtual.cpp :865 : 43558140512 us: [pid:263009 tid:0x7fb0637eb0c0] HWq=0x7fb050200000, Dispatch Header = 0x1502 (type=2, barrier=1, acquire=2, release=2), setup=3, grid=[1000192, 1, 1], workgroup=[256, 1, 1], private_seg_size=0, group_seg_size=0, kernel_obj=0x7fb061e7c580, kernarg_address=0x7faf49400000, completion_signal=0x0 :3:hip_module.cpp :679 : 43558140520 us: [pid:263009 tid:0x7fb0637eb0c0] hipLaunchKernel: Returned hipSuccess : :3:hip_memory.cpp :641 : 43558140524 us: [pid:263009 tid:0x7fb0637eb0c0] hipMemcpy ( 0x7fb051c8d010, 0x7faf4b200000, 4000000, hipMemcpyDeviceToHost ) :4:command.cpp :349 : 43558140531 us: [pid:263009 tid:0x7fb0637eb0c0] Command (CopyDeviceToHost) enqueued: 0x5573aa4bf820 :4:rocmemory.cpp :966 : 43558142069 us: [pid:263009 tid:0x7fb0637eb0c0] Locking to pool 0x5573aa208b60, size 0x3d1000, HostPtr = 0x7fb051c8d000, DevPtr = 0x7fb051c8d000 :4:rocvirtual.cpp :1011: 43558142077 us: [pid:263009 tid:0x7fb0637eb0c0] HWq=0x7fb050200000, BarrierAND Header = 0x1503 (type=3, barrier=1, acquire=2, release=2), dep_signal=[0x0, 0x0, 0x0, 0x0, 0x0], completion_signal=0x7fb0638e6700 :3:rocvirtual.hpp :66 : 43558142082 us: [pid:263009 tid:0x7fb0637eb0c0] Host active wait for Signal = (0x7fb0638e6700) for 10000 ns :4:rocblit.cpp :727 : 43558142097 us: [pid:263009 tid:0x7fb0637eb0c0] HSA Async Copy dst=0x7fb051c8d010, src=0x7faf4b200000, size=4000000, wait_event=0x7fb0638e6700, completion_signal=0x7fb0638e6680 :4:rocvirtual.cpp :553 : 43558142819 us: [pid:263009 tid:0x7fb0637eb0c0] Host wait on completion_signal=0x7fb0638e6680 :3:rocvirtual.hpp :66 : 43558142825 us: [pid:263009 tid:0x7fb0637eb0c0] Host active wait for Signal = (0x7fb0638e6680) for -1 ns :4:command.cpp :289 : 43558143151 us: [pid:263009 tid:0x7fb0637eb0c0] Queue marker to command queue: 0x5573aa10b440 :4:command.cpp :349 : 43558143156 us: [pid:263009 tid:0x7fb0637eb0c0] Command (InternalMarker) enqueued: 0x5573aa6b9510 :4:command.cpp :179 : 43558143161 us: [pid:263009 tid:0x7fb0637eb0c0] Command 0x5573aa55e660 complete :4:command.cpp :179 : 43558143165 us: [pid:263009 tid:0x7fb0637eb0c0] Command 0x5573aa4bf820 complete :4:command.cpp :173 : 43558143169 us: [pid:263009 tid:0x7fb0637eb0c0] Command 0x5573aa6b9510 complete (Wall: 43558143168, CPU: 0, GPU: 0 us) :4:command.cpp :253 : 43558143174 us: [pid:263009 tid:0x7fb0637eb0c0] Waiting for event 0x5573aa4bf820 to complete, current status 0 :4:command.cpp :268 : 43558143179 us: [pid:263009 tid:0x7fb0637eb0c0] Event 0x5573aa4bf820 wait completed :3:hip_memory.cpp :642 : 43558143183 us: [pid:263009 tid:0x7fb0637eb0c0] hipMemcpy: Returned hipSuccess : : duration: 2659 us PASSED!