void __device_stub__Z19EvalObjFuncGPUPhaseP6float3S0_ii( vertex_type *__par0, _ZN9cuda_side10color_typeE *__par1, int __par2, int __par3) { __cudaSetupArgSimple(__par0, 0UL); __cudaSetupArgSimple(__par1, 8UL); __cudaSetupArgSimple(__par2, 16UL); __cudaSetupArgSimple(__par3, 20UL); __cudaLaunch(((char *)((void ( *)(vertex_type *, _ZN9cuda_side10color_typeE *, int, int))EvalObjFuncGPUPhase))); }
void __device_stub__Z10EchoKernelv(void){__cudaLaunch(((char *)((void ( *)(void))EchoKernel)));}
void __device_stub__Z9gen_histsPmPfS0_S0_iiP12_gpufi_data_(hist_t *__par0, float *__par1, float *__par2, float *__par3, int __par4, int __par5, struct _gpufi_data_ *__par6){auto struct __T20 *__T24; __cudaInitArgBlock(__T24);__cudaSetupArg(__par0, __T24);__cudaSetupArg(__par1, __T24);__cudaSetupArg(__par2, __T24);__cudaSetupArg(__par3, __T24);__cudaSetupArg(__par4, __T24);__cudaSetupArg(__par5, __T24);__cudaSetupArg(__par6, __T24);__cudaLaunch(((char *)__device_stub_name(__device_stub__Z9gen_histsPmPfS0_S0_iiP12_gpufi_data_,((void ( *)(hist_t *, float *, float *, float *, int, int, struct _gpufi_data_ *))gen_hists__entry))));}
void __device_stub__Z10PreprocessP4int4iPK6uchar3iiif( _ZN9cuda_side16partial_sum_typeE *__par0, int __par1, const _ZN9cuda_side10pixel_typeE *__par2, int __par3, int __par4, int __par5, float __par6) { __cudaSetupArgSimple(__par0, 0UL); __cudaSetupArgSimple(__par1, 8UL); __cudaSetupArgSimple(__par2, 16UL); __cudaSetupArgSimple(__par3, 24UL); __cudaSetupArgSimple(__par4, 28UL); __cudaSetupArgSimple(__par5, 32UL); __cudaSetupArgSimple(__par6, 36UL); __cudaLaunch(((char *)((void ( *)(_ZN9cuda_side16partial_sum_typeE *, int, const _ZN9cuda_side10pixel_typeE *, int, int, int, float))Preprocess))); }
void __device_stub__Z26matrixBellmanErrorAndDerivPfS_S_S_S_S_fS_ii( float *__par0, float *__par1, float *__par2, float *__par3, float *__par4, float *__par5, float __par6, float *__par7, int __par8, int __par9) { __cudaSetupArgSimple(__par0, 0Ui64); __cudaSetupArgSimple(__par1, 8Ui64); __cudaSetupArgSimple(__par2, 16Ui64); __cudaSetupArgSimple(__par3, 24Ui64); __cudaSetupArgSimple(__par4, 32Ui64); __cudaSetupArgSimple(__par5, 40Ui64); __cudaSetupArgSimple(__par6, 48Ui64); __cudaSetupArgSimple(__par7, 56Ui64); __cudaSetupArgSimple(__par8, 64Ui64); __cudaSetupArgSimple(__par9, 68Ui64); __cudaLaunch(((char *)((void ( *)(float *, float *, float *, float *, float *, float *, float, float *, int, int))matrixBellmanErrorAndDeriv))); }
void __device_stub__Z21DqnStanfordEvaluationPfS_S_S_S_i( float *__par0, float *__par1, float *__par2, float *__par3, float *__par4, int __par5) { __cudaSetupArgSimple(__par0, 0Ui64); __cudaSetupArgSimple(__par1, 8Ui64); __cudaSetupArgSimple(__par2, 16Ui64); __cudaSetupArgSimple(__par3, 24Ui64); __cudaSetupArgSimple(__par4, 32Ui64); __cudaSetupArgSimple(__par5, 40Ui64); __cudaLaunch(((char *)((void ( *)(float *, float *, float *, float *, float *, int))DqnStanfordEvaluation))); }
void __device_stub__Z29matrixIncorporateSigmoidDerivPfS_S_ii( float *__par0, float *__par1, float *__par2, int __par3, int __par4) { __cudaSetupArgSimple(__par0, 0Ui64); __cudaSetupArgSimple(__par1, 8Ui64); __cudaSetupArgSimple(__par2, 16Ui64); __cudaSetupArgSimple(__par3, 24Ui64); __cudaSetupArgSimple(__par4, 28Ui64); __cudaLaunch(((char *)((void ( *)(float *, float *, float *, int, int))matrixIncorporateSigmoidDeriv))); }
void __device_stub__Z23matrixCrossEntropyErrorPfS_S_ii( float *__par0, float *__par1, float *__par2, int __par3, int __par4) { __cudaSetupArgSimple(__par0, 0Ui64); __cudaSetupArgSimple(__par1, 8Ui64); __cudaSetupArgSimple(__par2, 16Ui64); __cudaSetupArgSimple(__par3, 24Ui64); __cudaSetupArgSimple(__par4, 28Ui64); __cudaLaunch(((char *)((void ( *)(float *, float *, float *, int, int))matrixCrossEntropyError))); }
void __device_stub__Z18columnwiseMaxIndexPfS_ii( float *__par0, float *__par1, int __par2, int __par3) { __cudaSetupArgSimple(__par0, 0Ui64); __cudaSetupArgSimple(__par1, 8Ui64); __cudaSetupArgSimple(__par2, 16Ui64); __cudaSetupArgSimple(__par3, 20Ui64); __cudaLaunch(((char *)((void ( *)(float *, float *, int, int))columnwiseMaxIndex))); }
void __device_stub__Z13matrixSigmoidPfS_ii( float *__par0, float *__par1, int __par2, int __par3) { __cudaSetupArgSimple(__par0, 0Ui64); __cudaSetupArgSimple(__par1, 8Ui64); __cudaSetupArgSimple(__par2, 16Ui64); __cudaSetupArgSimple(__par3, 20Ui64); __cudaLaunch(((char *)((void ( *)(float *, float *, int, int))matrixSigmoid))); }
void __device_stub__Z14matrixHadamardPfS_fS_fii( float *__par0, float *__par1, float __par2, float *__par3, float __par4, int __par5, int __par6) { __cudaSetupArgSimple(__par0, 0Ui64); __cudaSetupArgSimple(__par1, 8Ui64); __cudaSetupArgSimple(__par2, 16Ui64); __cudaSetupArgSimple(__par3, 24Ui64); __cudaSetupArgSimple(__par4, 32Ui64); __cudaSetupArgSimple(__par5, 36Ui64); __cudaSetupArgSimple(__par6, 40Ui64); __cudaLaunch(((char *)((void ( *)(float *, float *, float, float *, float, int, int))matrixHadamard))); }
void __device_stub__Z8ComputeXP5uint4Pfi(uint4 *__par0, float *__par1, int __par2){auto struct __T20 *__T24; __cudaInitArgBlock(__T24);__cudaSetupArg(__par0, __T24);__cudaSetupArg(__par1, __T24);__cudaSetupArg(__par2, __T24);__cudaLaunch(((char *)__device_stub_name(__device_stub__Z8ComputeXP5uint4Pfi,((void ( *)(uint4 *, float *, int))ComputeX__entry))));}
void __device_stub__Z8cuda_ppeP12interval_gpuIdES1_PVS0_S3_S1_S1_S1_S1_jPVjS5_S5_S5_S5_S5_S5_(I *__par0, I *__par1, volatile I *__par2, volatile I *__par3, I *__par4, I *__par5, I *__par6, I *__par7, unsigned __par8, volatile unsigned *__par9, volatile unsigned *__par10, volatile unsigned *__par11, volatile unsigned *__par12, volatile unsigned *__par13, volatile unsigned *__par14, volatile unsigned *__par15){__cudaSetupArgSimple(__par0, 0UL);__cudaSetupArgSimple(__par1, 8UL);__cudaSetupArgSimple(__par2, 16UL);__cudaSetupArgSimple(__par3, 24UL);__cudaSetupArgSimple(__par4, 32UL);__cudaSetupArgSimple(__par5, 40UL);__cudaSetupArgSimple(__par6, 48UL);__cudaSetupArgSimple(__par7, 56UL);__cudaSetupArgSimple(__par8, 64UL);__cudaSetupArgSimple(__par9, 72UL);__cudaSetupArgSimple(__par10, 80UL);__cudaSetupArgSimple(__par11, 88UL);__cudaSetupArgSimple(__par12, 96UL);__cudaSetupArgSimple(__par13, 104UL);__cudaSetupArgSimple(__par14, 112UL);__cudaSetupArgSimple(__par15, 120UL);__cudaLaunch(((char *)((void ( *)(I *, I *, volatile I *, volatile I *, I *, I *, I *, I *, unsigned, volatile unsigned *, volatile unsigned *, volatile unsigned *, volatile unsigned *, volatile unsigned *, volatile unsigned *, volatile unsigned *))cuda_ppe)));}
void __device_stub__Z6kernelPi(int *__par0){auto struct __T20 *__T21; __cudaInitArgBlock(__T21);__cudaSetupArg(__par0, __T21);__cudaLaunch(((char *)__device_stub_name(__device_stub__Z6kernelPi,((void ( *)(int *))kernel__entry))));}
void __device_stub__Z18K_SYNC_UINT_DEP128PjS_jji(unsigned *__par0, unsigned *__par1, unsigned __par2, unsigned __par3, int __par4){__cudaSetupArgSimple(__par0, 0UL);__cudaSetupArgSimple(__par1, 8UL);__cudaSetupArgSimple(__par2, 16UL);__cudaSetupArgSimple(__par3, 20UL);__cudaSetupArgSimple(__par4, 24UL);__cudaLaunch(((char *)((void ( *)(unsigned *, unsigned *, unsigned, unsigned, int))K_SYNC_UINT_DEP128)));}