Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_1,obj_1,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,Start_Timestamp,End_Timestamp 0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f3d95e2cec0,0,0,64,0x7f6d3ee70ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131082.0,131072.0,131072.0,64,0x7fca6c6bcec0,0,0,0,0,0,0,0,0,0.0,1413317650641624,1413317650661624 1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f3d95e2cec0,0,0,64,0x7f6d3ee70ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131073.0,91356.0,91356.0,64,0x7fca6c6bcec0,0,0,0,0,0,0,0,0,0.0,1413317650753782,1413317650770102 2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f3d95e2cec0,0,0,64,0x7f6d3ee70ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131083.0,91672.0,91672.0,64,0x7fca6c6bcec0,0,0,0,0,0,0,0,0,0.0,1413317650790582,1413317650806102