Lines         Copies      Function name
  -----         ------      -------------
  46689 (100%)  458 (100%)  (TOTAL)
  10626 (22.8%)   2 (0.4%)  matrixmultiply::sgemm_kernel::kernel_x86_avx
   8840 (18.9%)   2 (0.4%)  matrixmultiply::dgemm_kernel::kernel_x86_avx
   3824 (8.2%)    1 (0.2%)  matrixmultiply::sgemm_kernel::kernel_fallback_impl
   3152 (6.8%)    8 (1.7%)  matrixmultiply::gemm::gemm_loop
   2232 (4.8%)   16 (3.5%)  matrixmultiply::threading::RangeChunkParallel<G>::for_each
   2144 (4.6%)   16 (3.5%)  matrixmultiply::gemm::gemm_packed::{{closure}}
   2020 (4.3%)    1 (0.2%)  matrixmultiply::dgemm_kernel::kernel_fallback_impl
   1876 (4.0%)    4 (0.9%)  matrixmultiply::gemm::pack
   1432 (3.1%)    8 (1.7%)  matrixmultiply::gemm::c_to_masked_ab_beta_c
   1112 (2.4%)   16 (3.5%)  matrixmultiply::gemm::gemm_loop::{{closure}}
    944 (2.0%)    8 (1.7%)  matrixmultiply::gemm::gemm_packed
    776 (1.7%)    8 (1.7%)  <matrixmultiply::gemm::GemmParameters<T> as matrixmultiply::kernel::GemmSelect<T>>::select
    776 (1.7%)    8 (1.7%)  matrixmultiply::gemm::ensure_kernel_params
    720 (1.5%)    8 (1.7%)  std::thread::local::LocalKey<T>::try_with
    528 (1.1%)    8 (1.7%)  matrixmultiply::gemm::make_packing_buffer
    512 (1.1%)   16 (3.5%)  matrixmultiply::threading::RangeChunkParallel<G>::thread_local
    360 (0.8%)    8 (1.7%)  matrixmultiply::gemm::masked_kernel
    274 (0.6%)    2 (0.4%)  matrixmultiply::gemm::c_to_beta_c
    200 (0.4%)    8 (1.7%)  matrixmultiply::threading::LoopThreadConfig::new
    157 (0.3%)    3 (0.7%)  core::mem::replace
    115 (0.2%)    1 (0.2%)  matrixmultiply::dgemm_kernel::detect
    115 (0.2%)    1 (0.2%)  matrixmultiply::sgemm_kernel::detect
    104 (0.2%)    8 (1.7%)  rawpointer::PointerExt::stride_offset
     96 (0.2%)    8 (1.7%)  matrixmultiply::gemm::gemm_packed::{{closure}}::{{closure}}
     96 (0.2%)    8 (1.7%)  std::thread::local::LocalKey<T>::with
     89 (0.2%)    1 (0.2%)  std::thread::local::lazy::LazyKeyInner<T>::initialize
     88 (0.2%)    2 (0.4%)  matrixmultiply::aligned_alloc::Alloc<T>::new
     80 (0.2%)    1 (0.2%)  core::cmp::max_by
     80 (0.2%)    1 (0.2%)  core::cmp::min_by
     78 (0.2%)    1 (0.2%)  matrixmultiply::gemm::dgemm
     78 (0.2%)    1 (0.2%)  matrixmultiply::gemm::sgemm
     74 (0.2%)    2 (0.4%)  core::ptr::metadata::from_raw_parts_mut
     66 (0.1%)    1 (0.2%)  std::thread::local::fast::Key<T>::get
     65 (0.1%)    3 (0.7%)  core::ptr::read
     63 (0.1%)    1 (0.2%)  std::thread::local::fast::Key<T>::try_initialize
     62 (0.1%)    1 (0.2%)  core::fmt::Arguments::new_v1
     57 (0.1%)    1 (0.2%)  <matrixmultiply::util::RangeChunk as core::iter::traits::iterator::Iterator>::next
     53 (0.1%)    1 (0.2%)  std_detect::detect::cache::test
     52 (0.1%)    2 (0.4%)  <matrixmultiply::aligned_alloc::Alloc<T> as core::ops::drop::Drop>::drop
     50 (0.1%)    1 (0.2%)  core::result::Result<T,E>::expect
     50 (0.1%)    1 (0.2%)  matrixmultiply::util::round_up_to
     48 (0.1%)    3 (0.7%)  core::ptr::mut_ptr::<impl *mut T>::offset
     45 (0.1%)    1 (0.2%)  std::thread::local::fast::destroy_value
     41 (0.1%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_setr_ps
     40 (0.1%)    5 (1.1%)  core::core_arch::x86::avx::_mm256_permute2f128_pd
     40 (0.1%)    3 (0.7%)  core::intrinsics::copy_nonoverlapping
     40 (0.1%)    1 (0.2%)  core::sync::atomic::atomic_load
     40 (0.1%)    1 (0.2%)  matrixmultiply::gemm::align_ptr
     39 (0.1%)    1 (0.2%)  core::option::Option<T>::unwrap_or_else
     37 (0.1%)    1 (0.2%)  core::cell::Cell<T>::replace
     36 (0.1%)    1 (0.2%)  <core::ops::range::Range<T> as core::iter::range::RangeIteratorImpl>::spec_next
     36 (0.1%)    1 (0.2%)  core::option::Option<T>::ok_or
     36 (0.1%)    1 (0.2%)  std::thread::local::fast::Key<T>::try_register_dtor
     32 (0.1%)    4 (0.9%)  matrixmultiply::ptr::Ptr
     32 (0.1%)    2 (0.4%)  core::ptr::const_ptr::<impl *const T>::offset
     30 (0.1%)    2 (0.4%)  core::ptr::slice_from_raw_parts_mut
     30 (0.1%)    2 (0.4%)  core::slice::raw::from_raw_parts_mut
     30 (0.1%)    1 (0.2%)  <core::result::Result<T,E> as core::ops::try_trait::Try>::branch
     29 (0.1%)    1 (0.2%)  std_detect::detect::cache::Cache::test
     28 (0.1%)    3 (0.7%)  core::mem::maybe_uninit::MaybeUninit<T>::assume_init
     28 (0.1%)    2 (0.4%)  core::core_arch::x86::avx::_mm256_extractf128_pd
     28 (0.1%)    2 (0.4%)  core::core_arch::x86::avx::_mm256_extractf128_ps
     27 (0.1%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelAvx as matrixmultiply::kernel::GemmKernel>::kernel
     27 (0.1%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelFallback as matrixmultiply::kernel::GemmKernel>::kernel
     27 (0.1%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelFma as matrixmultiply::kernel::GemmKernel>::kernel
     27 (0.1%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelSse2 as matrixmultiply::kernel::GemmKernel>::kernel
     27 (0.1%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelAvx as matrixmultiply::kernel::GemmKernel>::kernel
     27 (0.1%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelFallback as matrixmultiply::kernel::GemmKernel>::kernel
     27 (0.1%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelFma as matrixmultiply::kernel::GemmKernel>::kernel
     27 (0.1%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelSse2 as matrixmultiply::kernel::GemmKernel>::kernel
     27 (0.1%)    1 (0.2%)  matrixmultiply::dgemm_kernel::kernel_target_avx
     27 (0.1%)    1 (0.2%)  matrixmultiply::dgemm_kernel::kernel_target_fma
     27 (0.1%)    1 (0.2%)  matrixmultiply::dgemm_kernel::kernel_target_sse2
     27 (0.1%)    1 (0.2%)  matrixmultiply::sgemm_kernel::kernel_target_avx
     27 (0.1%)    1 (0.2%)  matrixmultiply::sgemm_kernel::kernel_target_fma
     27 (0.1%)    1 (0.2%)  matrixmultiply::sgemm_kernel::kernel_target_sse2
     26 (0.1%)    3 (0.7%)  core::ptr::write
     26 (0.1%)    1 (0.2%)  matrixmultiply::threading::<impl matrixmultiply::util::RangeChunk>::parallel
     25 (0.1%)    1 (0.2%)  <matrixmultiply::x86::AvxMulAdd as matrixmultiply::x86::DMultiplyAdd>::multiply_add
     25 (0.1%)    1 (0.2%)  <matrixmultiply::x86::AvxMulAdd as matrixmultiply::x86::SMultiplyAdd>::multiply_add
     24 (0.1%)    3 (0.7%)  core::core_arch::x86::avx::_mm256_permute2f128_ps
     24 (0.1%)    3 (0.7%)  core::core_arch::x86::avx::_mm256_shuffle_pd
     24 (0.1%)    3 (0.7%)  core::slice::<impl [T]>::as_mut_ptr
     24 (0.1%)    2 (0.4%)  <matrixmultiply::ptr::Ptr<*const T> as rawpointer::PointerExt>::offset
     24 (0.1%)    2 (0.4%)  <matrixmultiply::ptr::Ptr<*mut T> as rawpointer::PointerExt>::offset
     24 (0.1%)    1 (0.2%)  core::cmp::impls::<impl core::cmp::Ord for usize>::cmp
     24 (0.1%)    1 (0.2%)  core::option::Option<T>::as_ref
     22 (0.0%)    2 (0.4%)  core::ops::function::FnOnce::call_once
     21 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_setr_pd
     20 (0.0%)    4 (0.9%)  matrixmultiply::ptr::Ptr<T>::ptr
     20 (0.0%)    1 (0.2%)  core::alloc::layout::Layout::from_size_align_unchecked
     20 (0.0%)    1 (0.2%)  matrixmultiply::threading::get_thread_pool
     19 (0.0%)    1 (0.2%)  matrixmultiply::gemm::MASK_BUF::__init
     18 (0.0%)    4 (0.9%)  core::cell::UnsafeCell<T>::get
     18 (0.0%)    2 (0.4%)  <*const T as rawpointer::PointerExt>::offset
     18 (0.0%)    2 (0.4%)  <*mut T as rawpointer::PointerExt>::offset
     18 (0.0%)    2 (0.4%)  core::ptr::const_ptr::<impl *const T>::add
     18 (0.0%)    2 (0.4%)  core::ptr::mut_ptr::<impl *mut T>::add
     18 (0.0%)    2 (0.4%)  matrixmultiply::ptr::Ptr<*mut T>::to_const
     18 (0.0%)    2 (0.4%)  rawpointer::PointerExt::add
     18 (0.0%)    1 (0.2%)  <core::result::Result<T,F> as core::ops::try_trait::FromResidual<core::result::Result<core::convert::Infallible,E>>>::from_residual
     16 (0.0%)    2 (0.4%)  core::slice::<impl [T]>::as_ptr
     16 (0.0%)    2 (0.4%)  rawpointer::PointerExt::inc
     16 (0.0%)    1 (0.2%)  alloc::alloc::dealloc
     16 (0.0%)    1 (0.2%)  core::core_arch::x86::sse2::_mm_storeh_pd
     16 (0.0%)    1 (0.2%)  core::core_arch::x86::sse2::_mm_storel_pd
     16 (0.0%)    1 (0.2%)  core::core_arch::x86::sse::_mm_store_ss
     16 (0.0%)    1 (0.2%)  core::num::<impl usize>::unchecked_add
     16 (0.0%)    1 (0.2%)  core::ptr::mut_ptr::<impl *mut T>::guaranteed_eq
     15 (0.0%)    1 (0.2%)  <matrixmultiply::x86::FusedMulAdd as matrixmultiply::x86::DMultiplyAdd>::multiply_add
     15 (0.0%)    1 (0.2%)  <matrixmultiply::x86::FusedMulAdd as matrixmultiply::x86::SMultiplyAdd>::multiply_add
     14 (0.0%)    3 (0.7%)  core::mem::manually_drop::ManuallyDrop<T>::into_inner
     14 (0.0%)    2 (0.4%)  <I as core::iter::traits::collect::IntoIterator>::into_iter
     14 (0.0%)    2 (0.4%)  core::slice::raw::debug_check_data_len
     14 (0.0%)    1 (0.2%)  core::cell::Cell<T>::set
     14 (0.0%)    1 (0.2%)  core::cell::UnsafeCell<T>::new
     14 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_permute_ps
     14 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm_permute_ps
     13 (0.0%)    3 (0.7%)  core::mem::maybe_uninit::MaybeUninit<T>::as_mut_ptr
     13 (0.0%)    1 (0.2%)  alloc::alloc::alloc
     13 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_loadu_pd
     13 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_loadu_ps
     13 (0.0%)    1 (0.2%)  core::option::Option<T>::take
     13 (0.0%)    1 (0.2%)  matrixmultiply::util::range_chunk
     13 (0.0%)    1 (0.2%)  std_detect::detect::cache::test_bit
     12 (0.0%)    2 (0.4%)  matrixmultiply::aligned_alloc::Alloc<T>::ptr_mut
     12 (0.0%)    1 (0.2%)  core::core_arch::x86::sse::_mm_set1_ps
     12 (0.0%)    1 (0.2%)  core::sync::atomic::AtomicUsize::load
     10 (0.0%)    3 (0.7%)  core::mem::maybe_uninit::MaybeUninit<T>::uninit
     10 (0.0%)    2 (0.4%)  core::ptr::mut_ptr::<impl *mut T>::cast
     10 (0.0%)    1 (0.2%)  <f32 as matrixmultiply::kernel::Element>::add_assign
     10 (0.0%)    1 (0.2%)  <f32 as matrixmultiply::kernel::Element>::mul_assign
     10 (0.0%)    1 (0.2%)  <f64 as matrixmultiply::kernel::Element>::add_assign
     10 (0.0%)    1 (0.2%)  <f64 as matrixmultiply::kernel::Element>::mul_assign
     10 (0.0%)    1 (0.2%)  core::cmp::impls::<impl core::cmp::PartialOrd for usize>::lt
     10 (0.0%)    1 (0.2%)  core::core_arch::x86::fma::_mm256_fmadd_pd
     10 (0.0%)    1 (0.2%)  core::core_arch::x86::fma::_mm256_fmadd_ps
     10 (0.0%)    1 (0.2%)  core::iter::range::<impl core::iter::traits::iterator::Iterator for core::ops::range::Range<A>>::next
     10 (0.0%)    1 (0.2%)  matrixmultiply::dgemm_kernel::at
     10 (0.0%)    1 (0.2%)  matrixmultiply::sgemm_kernel::at
     10 (0.0%)    1 (0.2%)  std_detect::detect::cache::test::{{closure}}
      9 (0.0%)    1 (0.2%)  <usize as core::iter::range::Step>::forward_unchecked
      9 (0.0%)    1 (0.2%)  core::cmp::Ord::max
      9 (0.0%)    1 (0.2%)  core::cmp::Ord::min
      9 (0.0%)    1 (0.2%)  core::cmp::max
      9 (0.0%)    1 (0.2%)  core::cmp::min
      9 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_storeu_pd
      9 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_storeu_ps
      9 (0.0%)    1 (0.2%)  std::thread::local::lazy::LazyKeyInner<T>::get
      9 (0.0%)    1 (0.2%)  std::thread::local::lazy::LazyKeyInner<T>::take
      9 (0.0%)    1 (0.2%)  std_detect::detect::cache::Initializer::test
      9 (0.0%)    1 (0.2%)  std_detect::detect::check_for
      8 (0.0%)    2 (0.4%)  core::mem::drop
      8 (0.0%)    1 (0.2%)  core::alloc::layout::Layout::align
      8 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_add_pd
      8 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_add_ps
      8 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_blend_pd
      8 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_mul_pd
      8 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_mul_ps
      8 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_shuffle_ps
      8 (0.0%)    1 (0.2%)  core::mem::needs_drop
      8 (0.0%)    1 (0.2%)  core::ptr::mut_ptr::<impl *mut T>::is_null
      8 (0.0%)    1 (0.2%)  std_detect::detect::arch::__is_feature_detected::avx
      8 (0.0%)    1 (0.2%)  std_detect::detect::arch::__is_feature_detected::fma
      7 (0.0%)    1 (0.2%)  core::cell::Cell<T>::get
      7 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_broadcast_sd
      7 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_load_pd
      7 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_load_ps
      7 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_movehdup_ps
      7 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_moveldup_ps
      7 (0.0%)    1 (0.2%)  core::num::nonzero::NonZeroUsize::new_unchecked
      7 (0.0%)    1 (0.2%)  matrixmultiply::threading::LoopThreadConfig::num_pack_a
      6 (0.0%)    1 (0.2%)  <f32 as matrixmultiply::kernel::Element>::is_zero
      6 (0.0%)    1 (0.2%)  <f64 as matrixmultiply::kernel::Element>::is_zero
      6 (0.0%)    1 (0.2%)  core::alloc::layout::Layout::size
      6 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_set1_pd
      6 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_set1_ps
      6 (0.0%)    1 (0.2%)  core::ptr::drop_in_place<matrixmultiply::aligned_alloc::Alloc<f32>>
      6 (0.0%)    1 (0.2%)  core::ptr::drop_in_place<matrixmultiply::aligned_alloc::Alloc<f64>>
      5 (0.0%)    5 (1.1%)  core::mem::size_of
      5 (0.0%)    1 (0.2%)  core::clone::impls::<impl core::clone::Clone for usize>::clone
      4 (0.0%)    1 (0.2%)  core::num::nonzero::NonZeroUsize::get
      4 (0.0%)    1 (0.2%)  core::ptr::drop_in_place<std::thread::local::AccessError>
      4 (0.0%)    1 (0.2%)  matrixmultiply::threading::Registry::thread_pool
      4 (0.0%)    1 (0.2%)  matrixmultiply::threading::ThreadPool::top
      3 (0.0%)    1 (0.2%)  <T as core::convert::From<T>>::from
      3 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelFma as matrixmultiply::kernel::GemmKernel>::align_to
      3 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelFma as matrixmultiply::kernel::GemmKernel>::always_masked
      3 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelFma as matrixmultiply::kernel::GemmKernel>::align_to
      3 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelFma as matrixmultiply::kernel::GemmKernel>::always_masked
      3 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelSse2 as matrixmultiply::kernel::GemmKernel>::always_masked
      3 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_setzero_pd
      3 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_setzero_ps
      3 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_undefined_pd
      3 (0.0%)    1 (0.2%)  core::core_arch::x86::avx::_mm256_undefined_ps
      3 (0.0%)    1 (0.2%)  core::core_arch::x86::sse::_mm_undefined_ps
      3 (0.0%)    1 (0.2%)  matrixmultiply::gemm::MASK_BUF::__getit
      2 (0.0%)    2 (0.4%)  core::mem::align_of
      1 (0.0%)    1 (0.2%)  <f32 as matrixmultiply::kernel::Element>::one
      1 (0.0%)    1 (0.2%)  <f32 as matrixmultiply::kernel::Element>::test_value
      1 (0.0%)    1 (0.2%)  <f32 as matrixmultiply::kernel::Element>::zero
      1 (0.0%)    1 (0.2%)  <f64 as matrixmultiply::kernel::Element>::one
      1 (0.0%)    1 (0.2%)  <f64 as matrixmultiply::kernel::Element>::test_value
      1 (0.0%)    1 (0.2%)  <f64 as matrixmultiply::kernel::Element>::zero
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelAvx as matrixmultiply::kernel::GemmKernel>::align_to
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelAvx as matrixmultiply::kernel::GemmKernel>::always_masked
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelAvx as matrixmultiply::kernel::GemmKernel>::kc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelAvx as matrixmultiply::kernel::GemmKernel>::mc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelAvx as matrixmultiply::kernel::GemmKernel>::nc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelFallback as matrixmultiply::kernel::GemmKernel>::align_to
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelFallback as matrixmultiply::kernel::GemmKernel>::always_masked
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelFallback as matrixmultiply::kernel::GemmKernel>::kc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelFallback as matrixmultiply::kernel::GemmKernel>::mc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelFallback as matrixmultiply::kernel::GemmKernel>::nc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelFma as matrixmultiply::kernel::GemmKernel>::kc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelFma as matrixmultiply::kernel::GemmKernel>::mc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelFma as matrixmultiply::kernel::GemmKernel>::nc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelSse2 as matrixmultiply::kernel::GemmKernel>::align_to
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelSse2 as matrixmultiply::kernel::GemmKernel>::always_masked
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelSse2 as matrixmultiply::kernel::GemmKernel>::kc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelSse2 as matrixmultiply::kernel::GemmKernel>::mc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::dgemm_kernel::KernelSse2 as matrixmultiply::kernel::GemmKernel>::nc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelAvx as matrixmultiply::kernel::GemmKernel>::align_to
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelAvx as matrixmultiply::kernel::GemmKernel>::always_masked
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelAvx as matrixmultiply::kernel::GemmKernel>::kc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelAvx as matrixmultiply::kernel::GemmKernel>::mc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelAvx as matrixmultiply::kernel::GemmKernel>::nc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelFallback as matrixmultiply::kernel::GemmKernel>::align_to
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelFallback as matrixmultiply::kernel::GemmKernel>::always_masked
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelFallback as matrixmultiply::kernel::GemmKernel>::kc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelFallback as matrixmultiply::kernel::GemmKernel>::mc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelFallback as matrixmultiply::kernel::GemmKernel>::nc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelFma as matrixmultiply::kernel::GemmKernel>::kc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelFma as matrixmultiply::kernel::GemmKernel>::mc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelFma as matrixmultiply::kernel::GemmKernel>::nc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelSse2 as matrixmultiply::kernel::GemmKernel>::align_to
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelSse2 as matrixmultiply::kernel::GemmKernel>::kc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelSse2 as matrixmultiply::kernel::GemmKernel>::mc
      1 (0.0%)    1 (0.2%)  <matrixmultiply::sgemm_kernel::KernelSse2 as matrixmultiply::kernel::GemmKernel>::nc
      1 (0.0%)    1 (0.2%)  core::hint::unreachable_unchecked
      1 (0.0%)    1 (0.2%)  core::ptr::null_mut
      1 (0.0%)    1 (0.2%)  matrixmultiply::threading::<impl matrixmultiply::util::RangeChunk>::parallel::nop