blas_problem03.stats.csv

"Name","Calls","TotalDurationNs","AverageNs","Percentage"
"void at::native::(anonymous namespace)::CatArrayBatchedCopy<c10::Half, unsigned int, 3, 64, 64>(c10::Half*, at::native::(anonymous namespace)::CatArrInputTensorMetadata<c10::Half, unsigned int, 64, 64>, at::native::(anonymous namespace)::TensorSizeStride<unsigned int, 4u>, int, unsigned int) [clone .kd]",71280,89908224355,1261338,25.397590230924248
"Cijk_Ailk_Bljk_HHS_BH_MT16x16x128_MI16x16x16x1_SN_1LDSB0_APM1_AF0EM1_AF1EM1_AMAS0_ASGT_ASLT_ASAE01_ASCE01_ASEM1_BL1_BS1_CLR0_DTVA0_DTVB0_EPS1_ELFLR0_EMLL0_FSSC11_FL0_GRVW8_GSU1_GSUASB_GLS0_ISA942_IU1_K1_KLA_LBSPPA0_LBSPPB256_LPA8_LPB8_LRVW4_MIAV1_MKFGSU256_NTA0_NTB0_NTC3_NTD3_NEPBS4_NLCA1_NLCB1_ONLL1_PK0_PGR2_PLR1_SIA3_SS1_SU0_SUM0_SUS0_SPO1_SRVW0_SSO2_SVW1_TSGRA0_TSGRB0_TT1_16_TLDS1_UMLDSA0_UMLDSB1_USFGROn1_VAW1_VSn1_VW1_VFLRP0_WSGRA0_WSGRB0_WG16_4_1_WGM1.kd",71280,52526832957,736908,14.83796381410688
"Cijk_Alik_Bljk_HHS_BH_MT256x256x32_MI32x32x8x1_SN_1LDSB1_APM1_AF0EM1_AF1EM1_AMAS3_ASGT_ASLT_ASAE01_ASCE01_ASEM1_BL1_BS1_CLR0_DTVA0_DTVB0_EPS1_ELFLR0_EMLL0_FSSC10_FL2_GRVW8_GSU1_GSUASB_GLS1_ISA942_IU1_K1_KLA_LBSPPA128_LBSPPB128_LPA8_LPB8_LRVW8_MIAV0_MKFGSU256_NTA0_NTB0_NTC2_NTD2_NEPBS0_NLCA1_NLCB1_ONLL1_PK0_PGR2_PLR5_SIA3_SS1_SU32_SUM0_SUS128_SPO0_SRVW0_SSO8_SVW2_TSGRA0_TSGRB0_TT2_256_TLDS1_UMLDSA1_UMLDSB1_USFGROn1_VAW1_VSn1_VW2_VFLRP0_WSGRA0_WSGRB0_WG128_2_1_WGM19.kd",35640,30009885190,842028,8.477297515333653
"void at::native::(anonymous namespace)::cunn_SoftMaxForward<4, float, float, float, at::native::(anonymous namespace)::SoftMaxForwardEpilogue>(float*, float const*, int) [clone .kd]",36000,27994451833,777623,7.907970839091989
"Cijk_Ailk_Bljk_HHS_BH_MT16x32x128_MI16x16x16x1_SN_1LDSB0_APM1_AF0EM1_AF1EM1_AMAS3_ASGT_ASLT_ASAE01_ASCE01_ASEM1_BL1_BS1_CLR0_DTVA0_DTVB0_EPS1_ELFLR0_EMLL0_FSSC11_FL0_GRVW8_GSU1_GSUASB_GLS0_ISA942_IU1_K1_KLA_LBSPPA0_LBSPPB256_LPA8_LPB8_LRVW4_MIAV0_MKFGSU256_NTA0_NTB0_NTC3_NTD3_NEPBS4_NLCA1_NLCB1_ONLL1_PK0_PGR2_PLR1_SIA3_SS0_SU0_SUM0_SUS0_SPO1_SRVW0_SSO2_SVW4_TSGRA0_TSGRB0_TT1_16_TLDS1_UMLDSA0_UMLDSB1_USFGROn1_VAW1_VSn1_VW2_VFLRP0_WSGRA0_WSGRB1_WG16_8_1_WGM1.kd",720,26120804048,36278894,7.378696248008794
"Cijk_Alik_Bljk_HHS_BH_MT256x256x32_MI32x32x8x1_SN_1LDSB1_APM1_AF0EM1_AF1EM1_AMAS3_ASGT_ASLT_ASAE01_ASCE01_ASEM1_BL1_BS1_CLR0_DTVA0_DTVB0_EPS1_ELFLR0_EMLL0_FSSC10_FL2_GRVW8_GSU1_GSUASB_GLS0_ISA942_IU1_K1_KLA_LBSPPA128_LBSPPB128_LPA8_LPB8_LRVW8_MIAV0_MKFGSU256_NTA0_NTB0_NTC3_NTD2_NEPBS0_NLCA1_NLCB1_ONLL2_PK0_PGR2_PLR5_SIA3_SS1_SU32_SUM0_SUS128_SPO0_SRVW0_SSO6_SVW2_TSGRA0_TSGRB0_TT2_256_TLDS1_UMLDSA1_UMLDSB1_USFGROn1_VAW1_VSn1_VW2_VFLRP0_WSGRA0_WSGRB0_WG128_2_1_WGM19.kd",1080,21225444318,19653189,5.995837879406237
"Cijk_Alik_Bljk_HHS_BH_MT256x256x32_MI32x32x8x1_SN_1LDSB1_APM1_AF0EM1_AF1EM1_AMAS3_ASGT_ASLT_ASAE01_ASCE01_ASEM1_BL1_BS1_CLR0_DTVA0_DTVB0_EPS1_ELFLR0_EMLL0_FSSC10_FL0_GRVW8_GSU1_GSUASB_GLS1_ISA942_IU1_K1_KLA_LBSPPA128_LBSPPB128_LPA8_LPB8_LRVW8_MIAV0_MKFGSU256_NTA0_NTB0_NTC3_NTD2_NEPBS0_NLCA1_NLCB1_ONLL1_PK0_PGR2_PLR5_SIA3_SS1_SU32_SUM0_SUS128_SPO1_SRVW0_SSO6_SVW2_TSGRA0_TSGRB0_TT2_256_TLDS1_UMLDSA1_UMLDSB1_USFGROn1_VAW1_VSn1_VW2_VFLRP0_WSGRA0_WSGRB0_WG128_2_1_WGM19.kd",71280,19570776243,274561,5.528421444052009
"void at::native::legacy::elementwise_kernel<128, 4, at::native::gpu_kernel_impl<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#10}::operator()() const::{lambda(c10::Half)#1}>(at::TensorIteratorBase&, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#10}::operator()() const::{lambda(c10::Half)#1} const&)::{lambda(int)#4}>(int, at::native::gpu_kernel_impl<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#10}::operator()() const::{lambda(c10::Half)#1}>(at::TensorIteratorBase&, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#10}::operator()() const::{lambda(c10::Half)#1} const&)::{lambda(int)#4}) [clone .kd]",148680,12575717957,84582,3.5524328705508426
"Cijk_Alik_Bljk_HHS_BH_MT256x256x32_MI32x32x8x1_SN_1LDSB1_APM1_AF0EM1_AF1EM1_AMAS3_ASGT_ASLT_ASAE01_ASCE01_ASEM1_BL1_BS1_CLR0_DTVA0_DTVB0_EPS1_ELFLR0_EMLL0_FSSC10_FL0_GRVW8_GSU1_GSUASB_GLS1_ISA942_IU1_K1_KLA_LBSPPA128_LBSPPB128_LPA8_LPB8_LRVW8_MIAV0_MKFGSU256_NTA0_NTB0_NTC3_NTD2_NEPBS0_NLCA1_NLCB1_ONLL2_PK0_PGR2_PLR5_SIA3_SS1_SU32_SUM0_SUS128_SPO1_SRVW0_SSO8_SVW2_TSGRA0_TSGRB0_TT2_256_TLDS1_UMLDSA1_UMLDSB1_USFGROn1_VAW1_VSn1_VW2_VFLRP0_WSGRA0_WSGRB0_WG128_2_1_WGM18.kd",35640,10855783071,304595,3.0665796377473393
"Cijk_Alik_Bljk_HHS_BH_MT256x256x32_MI32x32x8x1_SN_1LDSB1_APM1_AF0EM1_AF1EM1_AMAS3_ASGT_ASLT_ASAE01_ASCE01_ASEM1_BL1_BS1_CLR0_DTVA0_DTVB0_EPS1_ELFLR0_EMLL0_FSSC10_FL2_GRVW8_GSU1_GSUASB_GLS1_ISA942_IU1_K1_KLA_LBSPPA128_LBSPPB128_LPA8_LPB8_LRVW8_MIAV0_MKFGSU256_NTA0_NTB0_NTC3_NTD3_NEPBS0_NLCA1_NLCB1_ONLL0_PK0_PGR2_PLR5_SIA3_SS1_SU32_SUM0_SUS128_SPO1_SRVW0_SSO10_SVW2_TSGRA0_TSGRB0_TT2_256_TLDS1_UMLDSA1_UMLDSB1_USFGROn1_VAW1_VSn1_VW2_VFLRP0_WSGRA0_WSGRB0_WG128_2_1_WGM19.kd",360,10684788150,29679967,3.018276393341359
"Cijk_Alik_Bljk_HHS_BH_MT256x256x32_MI32x32x8x1_SN_1LDSB1_APM1_AF0EM8_AF1EM8_AMAS3_ASGT_ASLT_ASAE01_ASCE01_ASEM1_BL1_BS1_CLR0_DTVA0_DTVB0_EPS1_ELFLR0_EMLL0_FSSC10_FL0_GRVW8_GSU1_GSUASB_GLS0_ISA942_IU1_K1_KLA_LBSPPA128_LBSPPB128_LPA8_LPB8_LRVW8_MIAV0_MKFGSU256_NTA0_NTB0_NTC0_NTD0_NEPBS0_NLCA1_NLCB1_ONLL1_PK0_PGR2_PLR5_SIA3_SS1_SU32_SUM0_SUS64_SPO0_SRVW0_SSO8_SVW2_TSGRA0_TSGRB0_TT2_256_TLDS1_UMLDSA1_UMLDSB1_USFGROn1_VAW1_VSn1_VW2_VFLRP0_WSGRA0_WSGRB0_WG128_2_1_WGM12.kd",1200,7362088333,6135073,2.0796685071559176
"__amd_rocclr_copyBuffer.kd",73212,7045629013,96235,1.9902739696508518
"void at::native::legacy::elementwise_kernel<128, 4, at::native::gpu_kernel_impl<at::native::(anonymous namespace)::masked_fill_kernel(at::TensorIterator&, c10::Scalar const&)::{lambda()#1}::operator()() const::{lambda()#7}::operator()() const::{lambda(float, bool)#1}>(at::TensorIteratorBase&, at::native::(anonymous namespace)::masked_fill_kernel(at::TensorIterator&, c10::Scalar const&)::{lambda()#1}::operator()() const::{lambda()#7}::operator()() const::{lambda(float, bool)#1} const&)::{lambda(int)#4}>(int, at::native::gpu_kernel_impl<at::native::(anonymous namespace)::masked_fill_kernel(at::TensorIterator&, c10::Scalar const&)::{lambda()#1}::operator()() const::{lambda()#7}::operator()() const::{lambda(float, bool)#1}>(at::TensorIteratorBase&, at::native::(anonymous namespace)::masked_fill_kernel(at::TensorIterator&, c10::Scalar const&)::{lambda()#1}::operator()() const::{lambda()#7}::operator()() const::{lambda(float, bool)#1} const&)::{lambda(int)#4}) [clone .kd]",41400,6882150367,166235,1.9440939489419518
"void at::native::legacy::elementwise_kernel<512, 1, at::native::gpu_kernel_impl<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#7}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#7}::operator()() const::{lambda(float)#1} const&)::{lambda(int)#1}>(int, at::native::gpu_kernel_impl<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#7}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#7}::operator()() const::{lambda(float)#1} const&)::{lambda(int)#1}) [clone .kd]",41400,6187852577,149465,1.747966276583181
"void at::native::legacy::elementwise_kernel<512, 1, at::native::gpu_kernel_impl<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#10}::operator()() const::{lambda(c10::Half)#1}>(at::TensorIteratorBase&, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#10}::operator()() const::{lambda(c10::Half)#1} const&)::{lambda(int)#1}>(int, at::native::gpu_kernel_impl<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#10}::operator()() const::{lambda(c10::Half)#1}>(at::TensorIteratorBase&, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#10}::operator()() const::{lambda(c10::Half)#1} const&)::{lambda(int)#1}) [clone .kd]",42600,5905788186,138633,1.668287739132955
"void at::native::modern::elementwise_kernel<at::native::AUnaryFunctor<c10::Half, c10::Half, c10::Half, at::native::binary_internal::MulFunctor<float> >, at::detail::Array<char*, 2> >(int, at::native::AUnaryFunctor<c10::Half, c10::Half, c10::Half, at::native::binary_internal::MulFunctor<float> >, at::detail::Array<char*, 2>) [clone .kd]",109080,4859821292,44552,1.3728193461188376
"void at::native::modern::elementwise_kernel<at::native::BinaryFunctor<c10::Half, c10::Half, c10::Half, at::native::binary_internal::MulFunctor<float> >, at::detail::Array<char*, 3> >(int, at::native::BinaryFunctor<c10::Half, c10::Half, c10::Half, at::native::binary_internal::MulFunctor<float> >, at::detail::Array<char*, 3>) [clone .kd]",109080,4843272428,44401,1.3681445650331858
"void at::native::modern::elementwise_kernel<at::native::CUDAFunctorOnSelf_add<c10::Half>, at::detail::Array<char*, 2> >(int, at::native::CUDAFunctorOnSelf_add<c10::Half>, at::detail::Array<char*, 2>) [clone .kd]",72720,3192123875,43896,0.9017223365850117
"void at::native::(anonymous namespace)::vectorized_layer_norm_kernel<c10::Half, float>(int, float, c10::Half const*, c10::Half const*, c10::Half const*, float*, float*, c10::Half*) [clone .kd]",74400,1976795885,26569,0.5584122277754137
"void at::native::modern::elementwise_kernel<at::native::CUDAFunctor_add<c10::Half>, at::detail::Array<char*, 3> >(int, at::native::CUDAFunctor_add<c10::Half>, at::detail::Array<char*, 3>) [clone .kd]",72000,1897321157,26351,0.5359619281511178
"void at::native::modern::elementwise_kernel<at::native::tanh_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#3}::operator()() const::{lambda(c10::Half)#1}, at::detail::Array<char*, 2> >(int, at::native::tanh_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#3}::operator()() const::{lambda(c10::Half)#1}, at::detail::Array<char*, 2>) [clone .kd]",36360,1684960465,46341,0.47597353581811347
"void at::native::reduce_kernel<512, 1, at::native::ReduceOp<c10::Half, at::native::ArgMaxOps<float>, unsigned int, long, 4> >(at::native::ReduceOp<c10::Half, at::native::ArgMaxOps<float>, unsigned int, long, 4>) [clone .kd]",1380,284349431,206050,0.08032402355561422
"void at::native::legacy::elementwise_kernel<128, 4, at::native::gpu_kernel_impl<at::native::BinaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> > >(at::TensorIteratorBase&, at::native::BinaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> > const&)::{lambda(int)#3}>(int, at::native::gpu_kernel_impl<at::native::BinaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> > >(at::TensorIteratorBase&, at::native::BinaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> > const&)::{lambda(int)#3}) [clone .kd]",1200,88829701,74024,0.025092925174737445
"void at::native::(anonymous namespace)::indexSelectLargeIndex<c10::Half, long, unsigned int, -1, -1, -1, true>(at::cuda::detail::TensorInfo<c10::Half, unsigned int>, at::cuda::detail::TensorInfo<c10::Half, unsigned int>, at::cuda::detail::TensorInfo<long, unsigned int>, int, int, unsigned int, unsigned int, long) [clone .kd]",1188,57135469,48093,0.016139827471000165
"void at::native::(anonymous namespace)::CatArrayBatchedCopy_aligned16_contig<long, unsigned int, 2, 128, 1>(long*, at::native::(anonymous namespace)::CatArrInputTensorMetadata<long, unsigned int, 128, 1>, at::native::(anonymous namespace)::TensorSizeStride<unsigned int, 4u>, int, unsigned int) [clone .kd]",2400,47136752,19640,0.013315354859926362
"void at::native::tensor_kernel_scan_innermost_dim<long, std::plus<long> >(long*, long const*, unsigned int, unsigned int, unsigned int, long, std::plus<long>) [clone .kd]",1200,35945422,29954,0.0101539887500056
"void at::native::modern::elementwise_kernel<at::native::BinaryFunctor<long, long, long, at::native::binary_internal::MulFunctor<long> >, at::detail::Array<char*, 3> >(int, at::native::BinaryFunctor<long, long, long, at::native::binary_internal::MulFunctor<long> >, at::detail::Array<char*, 3>) [clone .kd]",3600,21728964,6035,0.006138073883380105
"void at::native::legacy::elementwise_kernel<512, 1, at::native::gpu_kernel_impl<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#11}::operator()() const::{lambda(bool)#1}>(at::TensorIteratorBase&, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#11}::operator()() const::{lambda(bool)#1} const&)::{lambda(int)#1}>(int, at::native::gpu_kernel_impl<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#11}::operator()() const::{lambda(bool)#1}>(at::TensorIteratorBase&, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#11}::operator()() const::{lambda(bool)#1} const&)::{lambda(int)#1}) [clone .kd]",1200,18591407,15492,0.005251765788833286
"void at::native::modern::elementwise_kernel<at::native::CUDAFunctorOnSelf_add<long>, at::detail::Array<char*, 2> >(int, at::native::CUDAFunctorOnSelf_add<long>, at::detail::Array<char*, 2>) [clone .kd]",1200,17162608,14302,0.004848153641171777
"void at::native::legacy::elementwise_kernel<512, 1, at::native::gpu_kernel_impl<at::native::(anonymous namespace)::pow_tensor_tensor_kernel(at::TensorIteratorBase&)::{lambda()#1}::operator()() const::{lambda()#7}::operator()() const::{lambda(float, float)#1}>(at::TensorIteratorBase&, at::native::(anonymous namespace)::pow_tensor_tensor_kernel(at::TensorIteratorBase&)::{lambda()#1}::operator()() const::{lambda()#7}::operator()() const::{lambda(float, float)#1} const&)::{lambda(int)#1}>(int, at::native::gpu_kernel_impl<at::native::(anonymous namespace)::pow_tensor_tensor_kernel(at::TensorIteratorBase&)::{lambda()#1}::operator()() const::{lambda()#7}::operator()() const::{lambda(float, float)#1}>(at::TensorIteratorBase&, at::native::(anonymous namespace)::pow_tensor_tensor_kernel(at::TensorIteratorBase&)::{lambda()#1}::operator()() const::{lambda()#7}::operator()() const::{lambda(float, float)#1} const&)::{lambda(int)#1}) [clone .kd]",1200,17087539,14239,0.004826947887029451
"void at::native::modern::elementwise_kernel<at::native::bitwise_not_kernel_cuda(at::TensorIteratorBase&)::{lambda(bool)#1}, at::detail::Array<char*, 2> >(int, at::native::bitwise_not_kernel_cuda(at::TensorIteratorBase&)::{lambda(bool)#1}, at::detail::Array<char*, 2>) [clone .kd]",1200,14085320,11737,0.003978870544911919
"void at::native::(anonymous namespace)::indexSelectLargeIndex<c10::Half, long, unsigned int, 2, 2, -2, true>(at::cuda::detail::TensorInfo<c10::Half, unsigned int>, at::cuda::detail::TensorInfo<c10::Half, unsigned int>, at::cuda::detail::TensorInfo<long, unsigned int>, int, int, unsigned int, unsigned int, long) [clone .kd]",12,13334731,1111227,0.0037668415343225328
"reduction_prod_kernel.kd",1200,12254077,10211,0.003461574606070903
"__amd_rocclr_fillBufferAligned.kd",1476,8577640,5811,0.002423041801028182
"void at::native::legacy::elementwise_kernel<512, 1, at::native::gpu_kernel_impl<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#4}::operator()() const::{lambda(long)#1}>(at::TensorIteratorBase&, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#4}::operator()() const::{lambda(long)#1} const&)::{lambda(int)#1}>(int, at::native::gpu_kernel_impl<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#4}::operator()() const::{lambda(long)#1}>(at::TensorIteratorBase&, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#4}::operator()() const::{lambda(long)#1} const&)::{lambda(int)#1}) [clone .kd]",1212,7889413,6509,0.0022286290266990863
"void (anonymous namespace)::elementwise_kernel_with_index<int, at::native::arange_cuda_out(c10::Scalar const&, c10::Scalar const&, c10::Scalar const&, at::Tensor&)::{lambda()#1}::operator()() const::{lambda()#3}::operator()() const::{lambda(long)#1}>(int, at::native::arange_cuda_out(c10::Scalar const&, c10::Scalar const&, c10::Scalar const&, at::Tensor&)::{lambda()#1}::operator()() const::{lambda()#3}::operator()() const::{lambda(long)#1}, function_traits<at::native::arange_cuda_out(c10::Scalar const&, c10::Scalar const&, c10::Scalar const&, at::Tensor&)::{lambda()#1}::operator()() const::{lambda()#3}::operator()() const::{lambda(long)#1}>::result_type*) [clone .kd]",1200,7632641,6360,0.0021560951724765255
"void at::native::modern::elementwise_kernel<at::native::CUDAFunctor_add<long>, at::detail::Array<char*, 3> >(int, at::native::CUDAFunctor_add<long>, at::detail::Array<char*, 3>) [clone .kd]",1200,6136582,5113,0.0017334831843534028
"void at::native::legacy::elementwise_kernel<512, 1, at::native::gpu_kernel_impl<at::native::BinaryFunctor<long, long, bool, at::native::(anonymous namespace)::CompareEqFunctor<long> > >(at::TensorIteratorBase&, at::native::BinaryFunctor<long, long, bool, at::native::(anonymous namespace)::CompareEqFunctor<long> > const&)::{lambda(int)#2}>(int, at::native::gpu_kernel_impl<at::native::BinaryFunctor<long, long, bool, at::native::(anonymous namespace)::CompareEqFunctor<long> > >(at::TensorIteratorBase&, at::native::BinaryFunctor<long, long, bool, at::native::(anonymous namespace)::CompareEqFunctor<long> > const&)::{lambda(int)#2}) [clone .kd]",1200,6013682,5011,0.001698765961743645
"void at::native::modern::elementwise_kernel<at::native::AUnaryFunctor<long, long, long, at::native::binary_internal::MulFunctor<long> >, at::detail::Array<char*, 2> >(int, at::native::AUnaryFunctor<long, long, long, at::native::binary_internal::MulFunctor<long> >, at::detail::Array<char*, 2>) [clone .kd]",1200,5901905,4918,0.0016671908031459972
"void at::native::modern::elementwise_kernel<at::native::CUDAFunctorOnOther_add<long>, at::detail::Array<char*, 2> >(int, at::native::CUDAFunctorOnOther_add<long>, at::detail::Array<char*, 2>) [clone .kd]",1200,5820212,4850,0.0016441138782748912
"void at::native::modern::elementwise_kernel<at::native::FillFunctor<long>, at::detail::Array<char*, 1> >(int, at::native::FillFunctor<long>, at::detail::Array<char*, 1>) [clone .kd]",1212,5721018,4720,0.0016160932096048151
"void at::native::reduce_kernel<512, 1, at::native::ReduceOp<long, at::native::func_wrapper_t<long, at::native::MaxNanFunctor<long> >, unsigned int, long, 4> >(at::native::ReduceOp<long, at::native::func_wrapper_t<long, at::native::MaxNanFunctor<long> >, unsigned int, long, 4>) [clone .kd]",1200,4065034,3387,0.0011483050471459276
"void at::native::legacy::elementwise_kernel<128, 4, at::native::gpu_kernel_impl<at::native::BinaryFunctor<bool, bool, bool, at::native::BitwiseOrFunctor<bool> > >(at::TensorIteratorBase&, at::native::BinaryFunctor<bool, bool, bool, at::native::BitwiseOrFunctor<bool> > const&)::{lambda(int)#4}>(int, at::native::gpu_kernel_impl<at::native::BinaryFunctor<bool, bool, bool, at::native::BitwiseOrFunctor<bool> > >(at::TensorIteratorBase&, at::native::BinaryFunctor<bool, bool, bool, at::native::BitwiseOrFunctor<bool> > const&)::{lambda(int)#4}) [clone .kd]",12,3688795,307399,0.0010420237361819513
"void at::native::legacy::elementwise_kernel<128, 4, at::native::gpu_kernel_impl<at::native::AUnaryFunctor<long, long, bool, at::native::(anonymous namespace)::CompareEqFunctor<long> > >(at::TensorIteratorBase&, at::native::AUnaryFunctor<long, long, bool, at::native::(anonymous namespace)::CompareEqFunctor<long> > const&)::{lambda(int)#4}>(int, at::native::gpu_kernel_impl<at::native::AUnaryFunctor<long, long, bool, at::native::(anonymous namespace)::CompareEqFunctor<long> > >(at::TensorIteratorBase&, at::native::AUnaryFunctor<long, long, bool, at::native::(anonymous namespace)::CompareEqFunctor<long> > const&)::{lambda(int)#4}) [clone .kd]",1200,2444785,2037,0.0006906114326932215
"void at::native::legacy::elementwise_kernel<128, 4, at::native::gpu_kernel_impl<at::native::(anonymous namespace)::CompareFunctor<long> >(at::TensorIteratorBase&, at::native::(anonymous namespace)::CompareFunctor<long> const&)::{lambda(int)#4}>(int, at::native::gpu_kernel_impl<at::native::(anonymous namespace)::CompareFunctor<long> >(at::TensorIteratorBase&, at::native::(anonymous namespace)::CompareFunctor<long> const&)::{lambda(int)#4}) [clone .kd]",12,522325,43527,0.00014754819609147097
"void at::native::reduce_kernel<512, 1, at::native::ReduceOp<long, at::native::func_wrapper_t<long, at::native::sum_functor<long, long, long>::operator()(at::TensorIterator&)::{lambda(long, long)#1}>, unsigned int, long, 4> >(at::native::ReduceOp<long, at::native::func_wrapper_t<long, at::native::sum_functor<long, long, long>::operator()(at::TensorIterator&)::{lambda(long, long)#1}>, unsigned int, long, 4>) [clone .kd]",12,197683,16473,5.5842186470014375e-05
"void (anonymous namespace)::elementwise_kernel_with_index<int, at::native::arange_cuda_out(c10::Scalar const&, c10::Scalar const&, c10::Scalar const&, at::Tensor&)::{lambda()#1}::operator()() const::{lambda()#4}::operator()() const::{lambda(long)#1}>(int, at::native::arange_cuda_out(c10::Scalar const&, c10::Scalar const&, c10::Scalar const&, at::Tensor&)::{lambda()#1}::operator()() const::{lambda()#4}::operator()() const::{lambda(long)#1}, function_traits<at::native::arange_cuda_out(c10::Scalar const&, c10::Scalar const&, c10::Scalar const&, at::Tensor&)::{lambda()#1}::operator()() const::{lambda()#4}::operator()() const::{lambda(long)#1}>::result_type*) [clone .kd]",12,71880,5990,2.0304914248896635e-05
"void at::native::legacy::elementwise_kernel<512, 1, at::native::gpu_kernel_impl<at::native::AUnaryFunctor<long, long, bool, at::native::(anonymous namespace)::CompareEqFunctor<long> > >(at::TensorIteratorBase&, at::native::AUnaryFunctor<long, long, bool, at::native::(anonymous namespace)::CompareEqFunctor<long> > const&)::{lambda(int)#2}>(int, at::native::gpu_kernel_impl<at::native::AUnaryFunctor<long, long, bool, at::native::(anonymous namespace)::CompareEqFunctor<long> > >(at::TensorIteratorBase&, at::native::AUnaryFunctor<long, long, bool, at::native::(anonymous namespace)::CompareEqFunctor<long> > const&)::{lambda(int)#2}) [clone .kd]",12,71561,5963,2.0214802011203282e-05
"void at::native::legacy::elementwise_kernel<128, 4, at::native::gpu_kernel_impl<at::native::compare_scalar_kernel<long>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, long)::{lambda(long)#1}>(at::TensorIteratorBase&, at::native::compare_scalar_kernel<long>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, long)::{lambda(long)#1} const&)::{lambda(int)#4}>(int, at::native::gpu_kernel_impl<at::native::compare_scalar_kernel<long>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, long)::{lambda(long)#1}>(at::TensorIteratorBase&, at::native::compare_scalar_kernel<long>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, long)::{lambda(long)#1} const&)::{lambda(int)#4}) [clone .kd]",12,64200,5350,1.813544094016644e-05