digital-drosophila/registry/catalog-20260929/evidence/phase4c-runtime/profiler/kernel-launch-summary.json

{
  "compile-default": {
    "cuda_kernel_launches": 1830,
    "cuda_runtime_events": 4491,
    "duration_ms": 10.0,
    "kernels_per_step": 18.3,
    "steps": 100,
    "top_kernel_launch_counts": [
      [
        "void at_cuda_detail::cub::detail::scan::DeviceCompactInitKernel<at_cuda_detail::cub::ScanTileState<int, true>, int*>(at_cuda_detail::cub::ScanTileState<int, true>, int, int*)",
        200
      ],
      [
        "void at_cuda_detail::cub::detail::select::DeviceSelectSweepKernel<at_cuda_detail::cub::detail::select::policy_hub<long, bool, int, false, (at_cuda_detail::cub::SelectImpl)0>::Policy1000, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::counting_iterator<long, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, long*, int*, at_cuda_detail::cub::ScanTileState<int, true>, at_cuda_detail::cub::NullType, at_cuda_detail::cub::NullType, int, at_cuda_detail::cub::detail::select::streaming_context_t<long, true>, (at_cuda_detail::cub::SelectImpl)0>(thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::counting_iterator<long, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, long*, int*, at_cuda_detail::cub::ScanTileState<int, true>, at_cuda_detail::cub::NullType, at_cuda_detail::cub::NullType, int, int, at_cuda_detail::cub::detail::select::streaming_context_t<long, true>, at_cuda_detail::cub::detail::vsmem_t)",
        200
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::FillFunctor<float>, std::array<char*, 1ul>, false>(int, at::native::FillFunctor<float>, std::array<char*, 1ul>)",
        103
      ],
      [
        "triton_poi_fused_add_bitwise_and_clamp_min_eq_full_like_ge_mul_sub_where_0",
        101
      ],
      [
        "void at::native::(anonymous namespace)::distribution_elementwise_grid_stride_kernel<float, 4, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::(anonymous namespace)::distribution_nullary_kernel<float, float, float4, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2} const&, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(int, float)#1}>(long, at::PhiloxCudaState, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::(anonymous namespace)::distribution_nullary_kernel<float, float, float4, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2} const&, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(int, float)#1})",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul>, false>(int, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul>)",
        100
      ],
      [
        "void at::native::unrolled_elementwise_kernel<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#1}::operator()() const::{lambda(unsigned char)#1}, std::array<char*, 2ul>, 4, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1> >(int, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#1}::operator()() const::{lambda(unsigned char)#1}, std::array<char*, 2ul>, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1>)",
        100
      ],
      [
        "void at::native::unrolled_elementwise_kernel<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#11}::operator()() const::{lambda(bool)#1}, std::array<char*, 2ul>, 4, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1> >(int, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#11}::operator()() const::{lambda(bool)#1}, std::array<char*, 2ul>, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1>)",
        100
      ],
      [
        "void at::native::index_elementwise_kernel<128, 4, at::native::gpu_index_kernel<at::native::index_kernel_impl<at::native::OpaqueType<1> >(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_kernel_impl<at::native::OpaqueType<1> >(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1}>(long, at::native::gpu_index_kernel<at::native::index_kernel_impl<at::native::OpaqueType<1> >(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_kernel_impl<at::native::OpaqueType<1> >(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1})",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::BinaryFunctor<bool, bool, bool, at::native::BitwiseAndFunctor<bool> >, std::array<char*, 3ul>, false>(int, at::native::BinaryFunctor<bool, bool, bool, at::native::BitwiseAndFunctor<bool> >, std::array<char*, 3ul>)",
        100
      ],
      [
        "void at_cuda_detail::cub::detail::reduce::DeviceReduceSingleTileKernel<at_cuda_detail::cub::detail::reduce::policy_hub<int, unsigned long long, cuda::std::__4::plus<void> >::Policy1000, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, int*, unsigned long long, cuda::std::__4::plus<void>, int, int, cuda::std::__4::__identity>(thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, int*, unsigned long long, cuda::std::__4::plus<void>, int, cuda::std::__4::__identity)",
        100
      ],
      [
        "void at_cuda_detail::cub::detail::reduce::DeviceReduceKernel<at_cuda_detail::cub::detail::reduce::policy_hub<int, unsigned long long, cuda::std::__4::plus<void> >::Policy1000, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, unsigned long long, cuda::std::__4::plus<void>, int, cuda::std::__4::__identity>(thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, int*, unsigned long long, at_cuda_detail::cub::GridEvenShare<unsigned long long>, cuda::std::__4::plus<void>, cuda::std::__4::__identity)",
        100
      ],
      [
        "void at_cuda_detail::cub::detail::reduce::DeviceReduceSingleTileKernel<at_cuda_detail::cub::detail::reduce::policy_hub<int, unsigned long long, cuda::std::__4::plus<void> >::Policy1000, int*, int*, int, cuda::std::__4::plus<void>, int, int, cuda::std::__4::__identity>(int*, int*, int, cuda::std::__4::plus<void>, int, cuda::std::__4::__identity)",
        100
      ],
      [
        "void at::native::unrolled_elementwise_kernel<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#3}::operator()() const::{lambda(int)#1}, std::array<char*, 2ul>, 4, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1> >(int, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#3}::operator()() const::{lambda(int)#1}, std::array<char*, 2ul>, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1>)",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::CUDAFunctor_add<int>, std::array<char*, 3ul>, false>(int, at::native::CUDAFunctor_add<int>, std::array<char*, 3ul>)",
        100
      ],
      [
        "void at::native::index_elementwise_kernel<128, 4, at::native::gpu_index_kernel<at::native::index_kernel_impl<at::native::OpaqueType<8> >(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_kernel_impl<at::native::OpaqueType<8> >(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1}>(long, at::native::gpu_index_kernel<at::native::index_kernel_impl<at::native::OpaqueType<8> >(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_kernel_impl<at::native::OpaqueType<8> >(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1})",
        32
      ],
      [
        "void at::native::vectorized_elementwise_kernel<2, at::native::CUDAFunctor_add<long>, std::array<char*, 3ul>, false>(int, at::native::CUDAFunctor_add<long>, std::array<char*, 3ul>)",
        20
      ],
      [
        "void at::native::index_elementwise_kernel<128, 4, at::native::gpu_index_kernel<at::native::index_put_kernel_impl<at::native::OpaqueType<4> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_put_kernel_impl<at::native::OpaqueType<4> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1}>(long, at::native::gpu_index_kernel<at::native::index_put_kernel_impl<at::native::OpaqueType<4> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_put_kernel_impl<at::native::OpaqueType<4> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1})",
        16
      ],
      [
        "void at::native::index_elementwise_kernel<128, 4, at::native::gpu_index_kernel<at::native::index_put_kernel_impl<at::native::OpaqueType<1> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_put_kernel_impl<at::native::OpaqueType<1> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1}>(long, at::native::gpu_index_kernel<at::native::index_put_kernel_impl<at::native::OpaqueType<1> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_put_kernel_impl<at::native::OpaqueType<1> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1})",
        8
      ],
      [
        "void at::native::vectorized_elementwise_kernel<2, at::native::CUDAFunctorOnSelf_add<long>, std::array<char*, 2ul>, false>(int, at::native::CUDAFunctorOnSelf_add<long>, std::array<char*, 2ul>)",
        8
      ]
    ],
    "trace": "/data/digital-drosophila/experiments/phase4c-runtime/profiler/compile-default-10ms-trace.json",
    "trial_metrics": null
  },
  "compile-reduce-overhead": {
    "reason": "torch profiler/CUDAGraph output lifetime conflict; compiler performance and graph-break reports retained",
    "status": "not separately profiled"
  },
  "cudagraph-custom-state": {
    "cuda_kernel_launches": 609,
    "cuda_runtime_events": 1279,
    "duration_ms": 10.0,
    "kernels_per_step": 6.09,
    "steps": 100,
    "top_kernel_launch_counts": [
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::FillFunctor<float>, std::array<char*, 1ul>, false>(int, at::native::FillFunctor<float>, std::array<char*, 1ul>)",
        104
      ],
      [
        "void at::native::(anonymous namespace)::distribution_elementwise_grid_stride_kernel<float, 4, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::(anonymous namespace)::distribution_nullary_kernel<float, float, float4, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2} const&, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(int, float)#1}>(long, at::PhiloxCudaState, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::(anonymous namespace)::distribution_nullary_kernel<float, float, float4, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2} const&, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(int, float)#1})",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul>, false>(int, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul>)",
        100
      ],
      [
        "void at::native::unrolled_elementwise_kernel<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#1}::operator()() const::{lambda(unsigned char)#1}, std::array<char*, 2ul>, 4, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1> >(int, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#1}::operator()() const::{lambda(unsigned char)#1}, std::array<char*, 2ul>, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1>)",
        100
      ],
      [
        "(anonymous namespace)::force_kernel(float*, int*, unsigned char*, int*, long const*, unsigned char const*, int, float, int)",
        100
      ],
      [
        "(anonymous namespace)::fanout_kernel(unsigned char const*, long const*, int const*, float const*, float*, int)",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::FillFunctor<int>, std::array<char*, 1ul>, false>(int, at::native::FillFunctor<int>, std::array<char*, 1ul>)",
        2
      ],
      [
        "(anonymous namespace)::state_kernel(float*, float*, int*, float*, unsigned char*, int*, int, float, float, float, float, float, int)",
        2
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::FillFunctor<unsigned char>, std::array<char*, 1ul>, false>(int, at::native::FillFunctor<unsigned char>, std::array<char*, 1ul>)",
        1
      ]
    ],
    "trace": "/data/digital-drosophila/experiments/phase4c-runtime/profiler/cudagraph-custom-state-10ms-trace.json",
    "trial_metrics": {
      "active_neurons": 8,
      "backend": "cudagraph-custom-state",
      "biological_realtime_speed": 1.1735718655667582,
      "cpu_process_utilization_percent_of_one_core": 99.98462619490603,
      "descending_active_neurons": 0,
      "descending_spikes": 0,
      "duration_ms": 10.0,
      "event_count": 0,
      "event_sha256": null,
      "final_g_sha256": "59bc68b376b730245aa0a6187794bf1b8bb5cf893925f731adc6d454c4034d10",
      "final_voltage_sha256": "6fcb234cad5fb8c919026fb8744cb417110ed1cad7f2943298f154e0cbcae469",
      "mean_firing_rate_hz": 0.004799040191961607,
      "motor_active_neurons": 0,
      "motor_spikes": 0,
      "peak_vram_bytes": 223039488,
      "realtime_factor_wall_over_biological": 0.8520995001163101,
      "resource_sampling": {},
      "spike_counts_sha256": "0b63df6856cb1eb2386ceab5e335edbf3ebd10cea87012d8e42b82165cb2d712",
      "steps": 100,
      "steps_per_second": 11735.71865566758,
      "total_spikes": 8,
      "wall_clock_seconds": 0.0085209950011631
    }
  },
  "custom-cuda": {
    "cuda_kernel_launches": 606,
    "cuda_runtime_events": 923,
    "duration_ms": 10.0,
    "kernels_per_step": 6.06,
    "steps": 100,
    "top_kernel_launch_counts": [
      [
        "void at::native::(anonymous namespace)::distribution_elementwise_grid_stride_kernel<float, 4, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::(anonymous namespace)::distribution_nullary_kernel<float, float, float4, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2} const&, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(int, float)#1}>(long, at::PhiloxCudaState, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::(anonymous namespace)::distribution_nullary_kernel<float, float, float4, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2} const&, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(int, float)#1})",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul>, false>(int, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul>)",
        100
      ],
      [
        "void at::native::unrolled_elementwise_kernel<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#1}::operator()() const::{lambda(unsigned char)#1}, std::array<char*, 2ul>, 4, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1> >(int, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#1}::operator()() const::{lambda(unsigned char)#1}, std::array<char*, 2ul>, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1>)",
        100
      ],
      [
        "(anonymous namespace)::state_kernel(float*, float*, int*, float*, unsigned char*, int*, int, float, float, float, float, float, int)",
        100
      ],
      [
        "(anonymous namespace)::force_kernel(float*, int*, unsigned char*, int*, long const*, unsigned char const*, int, float, int)",
        100
      ],
      [
        "(anonymous namespace)::fanout_kernel(unsigned char const*, long const*, int const*, float const*, float*, int)",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::FillFunctor<float>, std::array<char*, 1ul>, false>(int, at::native::FillFunctor<float>, std::array<char*, 1ul>)",
        3
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::FillFunctor<int>, std::array<char*, 1ul>, false>(int, at::native::FillFunctor<int>, std::array<char*, 1ul>)",
        2
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::FillFunctor<unsigned char>, std::array<char*, 1ul>, false>(int, at::native::FillFunctor<unsigned char>, std::array<char*, 1ul>)",
        1
      ]
    ],
    "trace": "/data/digital-drosophila/experiments/phase4c-runtime/profiler/custom-cuda-10ms-trace.json",
    "trial_metrics": {
      "active_neurons": 8,
      "backend": "custom-cuda",
      "biological_realtime_speed": 2.4314329832463635,
      "cpu_process_utilization_percent_of_one_core": 99.9569150568377,
      "descending_active_neurons": 0,
      "descending_spikes": 0,
      "duration_ms": 10.0,
      "event_count": 0,
      "event_sha256": null,
      "final_g_sha256": "0bfca525d31620f6c66768a307f7dd31b157d323151f4da1d7b45a6d4498eb82",
      "final_voltage_sha256": "39705a277ec277659246d5e8fbb5377d58f2f1c8af231baa197569ec0617e500",
      "mean_firing_rate_hz": 0.004799040191961607,
      "motor_active_neurons": 0,
      "motor_spikes": 0,
      "peak_vram_bytes": 222372352,
      "realtime_factor_wall_over_biological": 0.4112800997972954,
      "resource_sampling": {},
      "spike_counts_sha256": "0b63df6856cb1eb2386ceab5e335edbf3ebd10cea87012d8e42b82165cb2d712",
      "steps": 100,
      "steps_per_second": 24314.329832463634,
      "total_spikes": 8,
      "wall_clock_seconds": 0.004112800997972954
    }
  },
  "eager": {
    "cuda_kernel_launches": 5029,
    "cuda_runtime_events": 13292,
    "duration_ms": 10.0,
    "kernels_per_step": 50.29,
    "steps": 100,
    "top_kernel_launch_counts": [
      [
        "void at_cuda_detail::cub::detail::scan::DeviceCompactInitKernel<at_cuda_detail::cub::ScanTileState<int, true>, int*>(at_cuda_detail::cub::ScanTileState<int, true>, int, int*)",
        600
      ],
      [
        "void at_cuda_detail::cub::detail::select::DeviceSelectSweepKernel<at_cuda_detail::cub::detail::select::policy_hub<long, bool, int, false, (at_cuda_detail::cub::SelectImpl)0>::Policy1000, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::counting_iterator<long, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, long*, int*, at_cuda_detail::cub::ScanTileState<int, true>, at_cuda_detail::cub::NullType, at_cuda_detail::cub::NullType, int, at_cuda_detail::cub::detail::select::streaming_context_t<long, true>, (at_cuda_detail::cub::SelectImpl)0>(thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::counting_iterator<long, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, long*, int*, at_cuda_detail::cub::ScanTileState<int, true>, at_cuda_detail::cub::NullType, at_cuda_detail::cub::NullType, int, int, at_cuda_detail::cub::detail::select::streaming_context_t<long, true>, at_cuda_detail::cub::detail::vsmem_t)",
        600
      ],
      [
        "void at_cuda_detail::cub::detail::reduce::DeviceReduceKernel<at_cuda_detail::cub::detail::reduce::policy_hub<int, unsigned long long, cuda::std::__4::plus<void> >::Policy1000, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, unsigned long long, cuda::std::__4::plus<void>, int, cuda::std::__4::__identity>(thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, int*, unsigned long long, at_cuda_detail::cub::GridEvenShare<unsigned long long>, cuda::std::__4::plus<void>, cuda::std::__4::__identity)",
        500
      ],
      [
        "void at_cuda_detail::cub::detail::reduce::DeviceReduceSingleTileKernel<at_cuda_detail::cub::detail::reduce::policy_hub<int, unsigned long long, cuda::std::__4::plus<void> >::Policy1000, int*, int*, int, cuda::std::__4::plus<void>, int, int, cuda::std::__4::__identity>(int*, int*, int, cuda::std::__4::plus<void>, int, cuda::std::__4::__identity)",
        500
      ],
      [
        "void at::native::index_elementwise_kernel<128, 4, at::native::gpu_index_kernel<at::native::index_kernel_impl<at::native::OpaqueType<4> >(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_kernel_impl<at::native::OpaqueType<4> >(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1}>(long, at::native::gpu_index_kernel<at::native::index_kernel_impl<at::native::OpaqueType<4> >(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_kernel_impl<at::native::OpaqueType<4> >(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1})",
        308
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::CUDAFunctor_add<float>, std::array<char*, 3ul>, false>(int, at::native::CUDAFunctor_add<float>, std::array<char*, 3ul>)",
        300
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul>, false>(int, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul>)",
        200
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::AUnaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 2ul>, false>(int, at::native::AUnaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 2ul>)",
        200
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::BinaryFunctor<bool, bool, bool, at::native::BitwiseAndFunctor<bool> >, std::array<char*, 3ul>, false>(int, at::native::BinaryFunctor<bool, bool, bool, at::native::BitwiseAndFunctor<bool> >, std::array<char*, 3ul>)",
        200
      ],
      [
        "void at::native::index_elementwise_kernel<128, 4, at::native::gpu_index_kernel<at::native::index_put_kernel_impl<at::native::OpaqueType<4> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_put_kernel_impl<at::native::OpaqueType<4> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1}>(long, at::native::gpu_index_kernel<at::native::index_put_kernel_impl<at::native::OpaqueType<4> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_put_kernel_impl<at::native::OpaqueType<4> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1})",
        116
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::FillFunctor<float>, std::array<char*, 1ul>, false>(int, at::native::FillFunctor<float>, std::array<char*, 1ul>)",
        103
      ],
      [
        "void at::native::(anonymous namespace)::distribution_elementwise_grid_stride_kernel<float, 4, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::(anonymous namespace)::distribution_nullary_kernel<float, float, float4, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2} const&, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(int, float)#1}>(long, at::PhiloxCudaState, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::(anonymous namespace)::distribution_nullary_kernel<float, float, float4, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2} const&, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(int, float)#1})",
        100
      ],
      [
        "void at::native::unrolled_elementwise_kernel<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#1}::operator()() const::{lambda(unsigned char)#1}, std::array<char*, 2ul>, 4, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1> >(int, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#1}::operator()() const::{lambda(unsigned char)#1}, std::array<char*, 2ul>, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1>)",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::(anonymous namespace)::launch_clamp_scalar(at::TensorIteratorBase&, c10::Scalar, c10::Scalar, at::native::detail::ClampLimits)::{lambda()#1}::operator()() const::{lambda()#3}::operator()() const::{lambda(int)#1}, std::array<char*, 2ul>, false>(int, at::native::(anonymous namespace)::launch_clamp_scalar(at::TensorIteratorBase&, c10::Scalar, c10::Scalar, at::native::detail::ClampLimits)::{lambda()#1}::operator()() const::{lambda()#3}::operator()() const::{lambda(int)#1}, std::array<char*, 2ul>)",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::CUDAFunctorOnSelf_add<int>, std::array<char*, 2ul>, false>(int, at::native::CUDAFunctorOnSelf_add<int>, std::array<char*, 2ul>)",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::AUnaryFunctor<int, int, bool, at::native::(anonymous namespace)::CompareEqFunctor<int> >, std::array<char*, 2ul>, false>(int, at::native::AUnaryFunctor<int, int, bool, at::native::(anonymous namespace)::CompareEqFunctor<int> >, std::array<char*, 2ul>)",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::CUDAFunctorOnSelf_add<float>, std::array<char*, 2ul>, false>(int, at::native::CUDAFunctorOnSelf_add<float>, std::array<char*, 2ul>)",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::bitwise_not_kernel_cuda(at::TensorIteratorBase&)::{lambda(bool)#1}, std::array<char*, 2ul>, false>(int, at::native::bitwise_not_kernel_cuda(at::TensorIteratorBase&)::{lambda(bool)#1}, std::array<char*, 2ul>)",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::(anonymous namespace)::masked_fill_kernel(at::TensorIterator&, c10::Scalar const&)::{lambda()#1}::operator()() const::{lambda()#7}::operator()() const::{lambda(float, bool)#1}, std::array<char*, 3ul>, false>(int, at::native::(anonymous namespace)::masked_fill_kernel(at::TensorIterator&, c10::Scalar const&)::{lambda()#1}::operator()() const::{lambda()#7}::operator()() const::{lambda(float, bool)#1}, std::array<char*, 3ul>)",
        100
      ],
      [
        "void at::native::unrolled_elementwise_kernel<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#11}::operator()() const::{lambda(bool)#1}, std::array<char*, 2ul>, 4, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1> >(int, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#11}::operator()() const::{lambda(bool)#1}, std::array<char*, 2ul>, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1>)",
        100
      ]
    ],
    "trace": "/data/digital-drosophila/experiments/phase4c-runtime/profiler/eager-10ms-trace.json",
    "trial_metrics": null
  },
  "hybrid-exact": {
    "cuda_kernel_launches": 5010,
    "cuda_runtime_events": 13265,
    "duration_ms": 10.0,
    "kernels_per_step": 50.1,
    "steps": 100,
    "top_kernel_launch_counts": [
      [
        "void at_cuda_detail::cub::detail::scan::DeviceCompactInitKernel<at_cuda_detail::cub::ScanTileState<int, true>, int*>(at_cuda_detail::cub::ScanTileState<int, true>, int, int*)",
        600
      ],
      [
        "void at_cuda_detail::cub::detail::select::DeviceSelectSweepKernel<at_cuda_detail::cub::detail::select::policy_hub<long, bool, int, false, (at_cuda_detail::cub::SelectImpl)0>::Policy1000, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::counting_iterator<long, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, long*, int*, at_cuda_detail::cub::ScanTileState<int, true>, at_cuda_detail::cub::NullType, at_cuda_detail::cub::NullType, int, at_cuda_detail::cub::detail::select::streaming_context_t<long, true>, (at_cuda_detail::cub::SelectImpl)0>(thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::counting_iterator<long, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, long*, int*, at_cuda_detail::cub::ScanTileState<int, true>, at_cuda_detail::cub::NullType, at_cuda_detail::cub::NullType, int, int, at_cuda_detail::cub::detail::select::streaming_context_t<long, true>, at_cuda_detail::cub::detail::vsmem_t)",
        600
      ],
      [
        "void at_cuda_detail::cub::detail::reduce::DeviceReduceKernel<at_cuda_detail::cub::detail::reduce::policy_hub<int, unsigned long long, cuda::std::__4::plus<void> >::Policy1000, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, unsigned long long, cuda::std::__4::plus<void>, int, cuda::std::__4::__identity>(thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, int*, unsigned long long, at_cuda_detail::cub::GridEvenShare<unsigned long long>, cuda::std::__4::plus<void>, cuda::std::__4::__identity)",
        500
      ],
      [
        "void at_cuda_detail::cub::detail::reduce::DeviceReduceSingleTileKernel<at_cuda_detail::cub::detail::reduce::policy_hub<int, unsigned long long, cuda::std::__4::plus<void> >::Policy1000, int*, int*, int, cuda::std::__4::plus<void>, int, int, cuda::std::__4::__identity>(int*, int*, int, cuda::std::__4::plus<void>, int, cuda::std::__4::__identity)",
        500
      ],
      [
        "void at::native::index_elementwise_kernel<128, 4, at::native::gpu_index_kernel<at::native::index_kernel_impl<at::native::OpaqueType<4> >(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_kernel_impl<at::native::OpaqueType<4> >(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1}>(long, at::native::gpu_index_kernel<at::native::index_kernel_impl<at::native::OpaqueType<4> >(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_kernel_impl<at::native::OpaqueType<4> >(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1})",
        308
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::CUDAFunctor_add<float>, std::array<char*, 3ul>, false>(int, at::native::CUDAFunctor_add<float>, std::array<char*, 3ul>)",
        300
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul>, false>(int, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul>)",
        200
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::AUnaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 2ul>, false>(int, at::native::AUnaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 2ul>)",
        200
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::BinaryFunctor<bool, bool, bool, at::native::BitwiseAndFunctor<bool> >, std::array<char*, 3ul>, false>(int, at::native::BinaryFunctor<bool, bool, bool, at::native::BitwiseAndFunctor<bool> >, std::array<char*, 3ul>)",
        200
      ],
      [
        "void at::native::index_elementwise_kernel<128, 4, at::native::gpu_index_kernel<at::native::index_put_kernel_impl<at::native::OpaqueType<4> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_put_kernel_impl<at::native::OpaqueType<4> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1}>(long, at::native::gpu_index_kernel<at::native::index_put_kernel_impl<at::native::OpaqueType<4> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_put_kernel_impl<at::native::OpaqueType<4> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1})",
        116
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::FillFunctor<float>, std::array<char*, 1ul>, false>(int, at::native::FillFunctor<float>, std::array<char*, 1ul>)",
        103
      ],
      [
        "void at::native::(anonymous namespace)::distribution_elementwise_grid_stride_kernel<float, 4, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::(anonymous namespace)::distribution_nullary_kernel<float, float, float4, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2} const&, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(int, float)#1}>(long, at::PhiloxCudaState, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::(anonymous namespace)::distribution_nullary_kernel<float, float, float4, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2}, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_and_transform<float, float, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}>(at::TensorIteratorBase&, at::CUDAGeneratorImpl*, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(curandStatePhilox4_32_10*)#2} const&, at::native::templates::cuda::uniform_kernel<at::CUDAGeneratorImpl*>(at::TensorIteratorBase&, double, double, at::CUDAGeneratorImpl*)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1})::{lambda(int, float)#1})",
        100
      ],
      [
        "void at::native::unrolled_elementwise_kernel<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#1}::operator()() const::{lambda(unsigned char)#1}, std::array<char*, 2ul>, 4, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1> >(int, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#1}::operator()() const::{lambda(unsigned char)#1}, std::array<char*, 2ul>, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1>)",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::(anonymous namespace)::launch_clamp_scalar(at::TensorIteratorBase&, c10::Scalar, c10::Scalar, at::native::detail::ClampLimits)::{lambda()#1}::operator()() const::{lambda()#3}::operator()() const::{lambda(int)#1}, std::array<char*, 2ul>, false>(int, at::native::(anonymous namespace)::launch_clamp_scalar(at::TensorIteratorBase&, c10::Scalar, c10::Scalar, at::native::detail::ClampLimits)::{lambda()#1}::operator()() const::{lambda()#3}::operator()() const::{lambda(int)#1}, std::array<char*, 2ul>)",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::CUDAFunctorOnSelf_add<int>, std::array<char*, 2ul>, false>(int, at::native::CUDAFunctorOnSelf_add<int>, std::array<char*, 2ul>)",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::AUnaryFunctor<int, int, bool, at::native::(anonymous namespace)::CompareEqFunctor<int> >, std::array<char*, 2ul>, false>(int, at::native::AUnaryFunctor<int, int, bool, at::native::(anonymous namespace)::CompareEqFunctor<int> >, std::array<char*, 2ul>)",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::CUDAFunctorOnSelf_add<float>, std::array<char*, 2ul>, false>(int, at::native::CUDAFunctorOnSelf_add<float>, std::array<char*, 2ul>)",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::bitwise_not_kernel_cuda(at::TensorIteratorBase&)::{lambda(bool)#1}, std::array<char*, 2ul>, false>(int, at::native::bitwise_not_kernel_cuda(at::TensorIteratorBase&)::{lambda(bool)#1}, std::array<char*, 2ul>)",
        100
      ],
      [
        "void at::native::vectorized_elementwise_kernel<4, at::native::(anonymous namespace)::masked_fill_kernel(at::TensorIterator&, c10::Scalar const&)::{lambda()#1}::operator()() const::{lambda()#7}::operator()() const::{lambda(float, bool)#1}, std::array<char*, 3ul>, false>(int, at::native::(anonymous namespace)::masked_fill_kernel(at::TensorIterator&, c10::Scalar const&)::{lambda()#1}::operator()() const::{lambda()#7}::operator()() const::{lambda(float, bool)#1}, std::array<char*, 3ul>)",
        100
      ],
      [
        "void at::native::unrolled_elementwise_kernel<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#11}::operator()() const::{lambda(bool)#1}, std::array<char*, 2ul>, 4, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1> >(int, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#11}::operator()() const::{lambda(bool)#1}, std::array<char*, 2ul>, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1>)",
        100
      ]
    ],
    "trace": "/data/digital-drosophila/experiments/phase4c-runtime/profiler/hybrid-exact-10ms-trace.json",
    "trial_metrics": null
  }
}