barrbrain
commented
11 months ago See https://github.com/xiph/rav1e/pull/3295#issuecomment-1837299284 for a perf trace from before this PR. Here is the same workload after this PR:
# Samples: 190K of event 'cycles'
# Event count (approx.): 106225872817
#
# Overhead Command / Shared Object / Symbol
# .............. ...............................................................................................................................................................................................................
#
100.00% rav1e
92.23% rav1e
11.33% [.] rav1e_satd8x8_hbd_neon
|
|--6.71%--rav1e::api::internal::ContextInner<T>::receive_packet
| rav1e::api::internal::ContextInner<T>::compute_block_importances (inlined)
| <core::slice::iter::Iter<T> as core::iter::traits::iterator::Iterator>::for_each (inlined)
| rav1e::api::internal::ContextInner<T>::compute_block_importances::{{closure}} (inlined)
| rav1e::api::internal::ContextInner<T>::update_block_importances (inlined)
| core::iter::traits::iterator::Iterator::for_each (inlined)
| <core::iter::adapters::flatten::FlatMap<I,U,F> as core::iter::traits::iterator::Iterator>::fold (inlined)
| <core::iter::adapters::flatten::FlattenCompat<I,U> as core::iter::traits::iterator::Iterator>::fold (inlined)
| core::iter::adapters::flatten::FlattenCompat<I,U>::iter_fold (inlined)
| <core::iter::adapters::fuse::Fuse<I> as core::iter::traits::iterator::Iterator>::fold (inlined)
| <core::iter::adapters::map::Map<I,F> as core::iter::traits::iterator::Iterator>::fold
| <core::iter::adapters::enumerate::Enumerate<I> as core::iter::traits::iterator::Iterator>::fold (inlined)
| core::iter::traits::iterator::Iterator::fold (inlined)
| <core::iter::adapters::enumerate::Enumerate<I> as core::iter::traits::iterator::Iterator>::fold::enumerate::{{closure}} (inlined)
| core::iter::adapters::map::map_fold::{{closure}} (inlined)
| core::iter::adapters::flatten::FlattenCompat<I,U>::iter_fold::flatten::{{closure}} (inlined)
| <core::iter::adapters::flatten::FlattenCompat<I,U> as core::iter::traits::iterator::Iterator>::fold::flatten::{{closure}} (inlined)
| <core::iter::adapters::map::Map<I,F> as core::iter::traits::iterator::Iterator>::fold
| <core::iter::adapters::enumerate::Enumerate<I> as core::iter::traits::iterator::Iterator>::fold (inlined)
| core::iter::traits::iterator::Iterator::fold (inlined)
| <core::iter::adapters::enumerate::Enumerate<I> as core::iter::traits::iterator::Iterator>::fold::enumerate::{{closure}} (inlined)
| core::iter::adapters::map::map_fold::{{closure}} (inlined)
| rav1e::api::internal::ContextInner<T>::update_block_importances::{{closure}}::{{closure}} (inlined)
| rav1e::asm::aarch64::dist::get_satd (inlined)
| satd8x8_hbd_neon (inlined)
|
|--3.63%--rav1e::me::estimate_motion
| |
| --3.25%--rav1e::me::sub_pixel_me (inlined)
| rav1e::me::subpel_diamond_search (inlined)
| rav1e::me::get_subpel_mv_rd (inlined)
| rav1e::me::compute_mv_rd (inlined)
| satd8x8_hbd_neon (inlined)
|
--0.59%--core::ops::function::impls::<impl core::ops::function::FnOnce<A> for &mut F>::call_once
core::ops::function::impls::<impl core::ops::function::FnMut<A> for &F>::call_mut (inlined)
rav1e::encoder::encode_tile_group::{{closure}} (inlined)
rav1e::encoder::encode_tile (inlined)
7.83% [.] put_8tap_neon
|
|--6.49%--rav1e::me::estimate_motion
| rav1e::me::sub_pixel_me (inlined)
| rav1e::me::subpel_diamond_search (inlined)
| rav1e::me::get_subpel_mv_rd (inlined)
| put_8tap_neon
|
--0.66%--put_8tap_neon
put_8tap_neon
4.80% [.] <core::iter::adapters::map::Map<I,F> as core::iter::traits::iterator::Iterator>::fold
|
---rav1e::api::internal::ContextInner<T>::receive_packet
rav1e::api::internal::ContextInner<T>::compute_block_importances (inlined)
<core::slice::iter::Iter<T> as core::iter::traits::iterator::Iterator>::for_each (inlined)
rav1e::api::internal::ContextInner<T>::compute_block_importances::{{closure}} (inlined)
rav1e::api::internal::ContextInner<T>::update_block_importances (inlined)
core::iter::traits::iterator::Iterator::for_each (inlined)
<core::iter::adapters::flatten::FlatMap<I,U,F> as core::iter::traits::iterator::Iterator>::fold (inlined)
<core::iter::adapters::flatten::FlattenCompat<I,U> as core::iter::traits::iterator::Iterator>::fold (inlined)
core::iter::adapters::flatten::FlattenCompat<I,U>::iter_fold (inlined)
<core::iter::adapters::fuse::Fuse<I> as core::iter::traits::iterator::Iterator>::fold (inlined)
<core::iter::adapters::map::Map<I,F> as core::iter::traits::iterator::Iterator>::fold
<core::iter::adapters::enumerate::Enumerate<I> as core::iter::traits::iterator::Iterator>::fold (inlined)
core::iter::traits::iterator::Iterator::fold (inlined)
<core::iter::adapters::enumerate::Enumerate<I> as core::iter::traits::iterator::Iterator>::fold::enumerate::{{closure}} (inlined)
core::iter::adapters::map::map_fold::{{closure}} (inlined)
core::iter::adapters::flatten::FlattenCompat<I,U>::iter_fold::flatten::{{closure}} (inlined)
<core::iter::adapters::flatten::FlattenCompat<I,U> as core::iter::traits::iterator::Iterator>::fold::flatten::{{closure}} (inlined)
<core::iter::adapters::map::Map<I,F> as core::iter::traits::iterator::Iterator>::fold
|
--4.78%--<core::iter::adapters::enumerate::Enumerate<I> as core::iter::traits::iterator::Iterator>::fold (inlined)
core::iter::traits::iterator::Iterator::fold (inlined)
|
--4.73%--<core::iter::adapters::enumerate::Enumerate<I> as core::iter::traits::iterator::Iterator>::fold::enumerate::{{closure}} (inlined)
|
--4.73%--core::iter::adapters::map::map_fold::{{closure}} (inlined)
|
--4.68%--rav1e::api::internal::ContextInner<T>::update_block_importances::{{closure}}::{{closure}} (inlined)
|
--1.33%--<v_frame::plane::Plane<T> as rav1e::frame::plane::AsRegion<T>>::region (inlined)
|
--0.83%--rav1e::tiling::plane_region::PlaneRegion<T>::new (inlined)
rav1e::tiling::plane_region::PlaneRegion<T>::from_slice (inlined)
4.25% [.] rav1e::asm::aarch64::transform::forward::daala_fdct32
|
---rav1e::asm::aarch64::transform::forward::forward_transform_neon
rav1e::asm::aarch64::transform::forward::daala_fdct32
|
--3.47%--rav1e::asm::aarch64::transform::forward::daala_fdct_ii_32 (inlined)
|
--2.35%--rav1e::asm::aarch64::transform::forward::daala_fdst_iv_16_asym (inlined)
|
--0.56%--rav1e::asm::aarch64::transform::forward::RotateKernel::half_kernel (inlined)
3.85% [.] rav1e::rdo::compute_distortion
|
--3.82%--rav1e::rdo::rdo_mode_decision
|
--3.72%--rav1e::rdo::inter_frame_rdo_mode_decision (inlined)
<core::iter::adapters::take::Take<I> as core::iter::traits::iterator::Iterator>::for_each (inlined)
core::iter::traits::iterator::Iterator::try_fold (inlined)
<core::iter::adapters::take::Take<I> as core::iter::traits::iterator::Iterator>::for_each::check::{{closure}} (inlined)
rav1e::rdo::inter_frame_rdo_mode_decision::{{closure}} (inlined)
rav1e::rdo::luma_chroma_mode_rdo
rav1e::rdo::luma_chroma_mode_rdo::{{closure}}
rav1e::rdo::compute_distortion
|
|--2.17%--rav1e::rdo::cdef_dist_wxh (inlined)
| |
| |--1.12%--rav1e::asm::aarch64::dist::cdef_dist::cdef_dist_kernel (inlined)
| | |
| | --0.85%--rav1e::activity::apply_ssim_boost (inlined)
| | |
| | --0.74%--rav1e::activity::ssim_boost_rsqrt (inlined)
| |
| --0.66%--rav1e::rdo::compute_distortion::{{closure}} (inlined)
| |
| --0.50%--rav1e::rdo::distortion_scale (inlined)
|
--1.12%--rav1e::rdo::sse_wxh (inlined)
|
--0.87%--rav1e::rdo::compute_distortion::{{closure}} (inlined)
|
--0.61%--rav1e::rdo::distortion_scale (inlined)
3.80% [.] rav1e::asm::aarch64::transform::forward::daala_fdct64
|
---rav1e::asm::aarch64::transform::forward::forward_transform_neon
rav1e::asm::aarch64::transform::forward::daala_fdct64
|
|--2.04%--rav1e::asm::aarch64::transform::forward::daala_fdst_iv_32_asym (inlined)
|
--0.67%--rav1e::asm::aarch64::transform::forward::daala_fdct64::butterfly_pair (inlined)
3.37% [.] rav1e::asm::aarch64::transform::forward::forward_transform_neon
|
--3.33%--rav1e::asm::aarch64::transform::forward::forward_transform_neon
|
|--0.71%--<core::iter::adapters::zip::Zip<A,B> as core::iter::traits::iterator::Iterator>::next (inlined)
| <core::iter::adapters::zip::Zip<A,B> as core::iter::adapters::zip::ZipImpl<A,B>>::next (inlined)
|
--0.54%--rav1e::asm::aarch64::transform::forward::transpose_8x8_neon (inlined)
3.23% [.] rav1e::encoder::encode_block_post_cdef
|
--2.59%--rav1e::encoder::encode_partition_topdown
rav1e::rdo::rdo_partition_decision
|
|--1.44%--rav1e::rdo::rdo_partition_simple (inlined)
| rav1e::rdo::rdo_mode_decision
| |
| --1.39%--rav1e::rdo::inter_frame_rdo_mode_decision (inlined)
| <core::iter::adapters::take::Take<I> as core::iter::traits::iterator::Iterator>::for_each (inlined)
| core::iter::traits::iterator::Iterator::try_fold (inlined)
| <core::iter::adapters::take::Take<I> as core::iter::traits::iterator::Iterator>::for_each::check::{{closure}} (inlined)
| rav1e::rdo::inter_frame_rdo_mode_decision::{{closure}} (inlined)
| rav1e::rdo::luma_chroma_mode_rdo
| rav1e::rdo::luma_chroma_mode_rdo::{{closure}}
| rav1e::encoder::encode_block_post_cdef
|
--1.15%--rav1e::rdo::rdo_partition_none (inlined)
rav1e::rdo::rdo_mode_decision
|
--1.12%--rav1e::rdo::inter_frame_rdo_mode_decision (inlined)
<core::iter::adapters::take::Take<I> as core::iter::traits::iterator::Iterator>::for_each (inlined)
core::iter::traits::iterator::Iterator::try_fold (inlined)
<core::iter::adapters::take::Take<I> as core::iter::traits::iterator::Iterator>::for_each::check::{{closure}} (inlined)
rav1e::rdo::inter_frame_rdo_mode_decision::{{closure}} (inlined)
rav1e::rdo::luma_chroma_mode_rdo
rav1e::rdo::luma_chroma_mode_rdo::{{closure}}
rav1e::encoder::encode_block_post_cdef
2.64% [.] rav1e_sad32x32_hbd_neon
|
|--1.56%--rav1e::api::internal::ContextInner<T>::send_frame
| rav1e::api::internal::ContextInner<T>::compute_frame_invariants (inlined)
| rav1e::api::internal::ContextInner<T>::compute_lookahead_motion_vectors (inlined)
| rav1e::api::lookahead::compute_motion_vectors
| rayon::iter::ParallelIterator::for_each (inlined)
| rayon::iter::for_each::for_each (inlined)
| <rayon::vec::IntoIter<T> as rayon::iter::ParallelIterator>::drive_unindexed (inlined)
| rayon::iter::plumbing::bridge (inlined)
| <rayon::vec::IntoIter<T> as rayon::iter::IndexedParallelIterator>::with_producer
| <rayon::vec::Drain<T> as rayon::iter::IndexedParallelIterator>::with_producer (inlined)
| <rayon::iter::plumbing::bridge::Callback<C> as rayon::iter::plumbing::ProducerCallback<I>>::callback (inlined)
| rayon::iter::plumbing::bridge_producer_consumer (inlined)
| rayon::iter::plumbing::bridge_producer_consumer::helper
| rayon::iter::plumbing::Producer::fold_with (inlined)
| <rayon::iter::for_each::ForEachConsumer<F> as rayon::iter::plumbing::Folder<T>>::consume_iter (inlined)
| core::iter::traits::iterator::Iterator::for_each (inlined)
| core::iter::traits::iterator::Iterator::fold (inlined)
| core::iter::traits::iterator::Iterator::for_each::call::{{closure}} (inlined)
| core::ops::function::impls::<impl core::ops::function::FnMut<A> for &F>::call_mut
| rav1e::api::lookahead::compute_motion_vectors::{{closure}} (inlined)
| rav1e::me::estimate_tile_motion
| rav1e::me::refine_subsampled_sb_motion (inlined)
| rav1e::me::refine_subsampled_motion_estimate (inlined)
| rav1e::me::full_search
| rav1e::me::compute_mv_rd (inlined)
| rav1e::asm::aarch64::dist::get_sad (inlined)
| sad32x32_hbd_neon (inlined)
|
--1.08%--rav1e::me::estimate_motion
rav1e::me::full_pixel_me (inlined)
rav1e::me::full_pixel_me::{{closure}}
|
|--0.55%--rav1e::me::fullpel_diamond_search (inlined)
| rav1e::me::get_fullpel_mv_rd
| rav1e::me::compute_mv_rd (inlined)
| sad32x32_hbd_neon (inlined)
|
--0.53%--rav1e::me::get_best_predictor (inlined)
rav1e::me::get_fullpel_mv_rd
rav1e::me::compute_mv_rd (inlined)
sad32x32_hbd_neon (inlined)
2.10% [.] rav1e::asm::aarch64::transform::forward::daala_fdct_ii_16
|
---rav1e::asm::aarch64::transform::forward::forward_transform_neon
|
|--1.42%--rav1e::asm::aarch64::transform::forward::daala_fdct16
| rav1e::asm::aarch64::transform::forward::daala_fdct_ii_16
| |
| |--0.57%--rav1e::asm::aarch64::transform::forward::daala_fdst_iv_8_asym (inlined)
| |
| --0.56%--rav1e::asm::aarch64::transform::forward::daala_fdct_ii_8_asym (inlined)
|
--0.68%--rav1e::asm::aarch64::transform::forward::daala_fdct64
rav1e::asm::aarch64::transform::forward::daala_fdct_ii_32_asym (inlined)
rav1e::asm::aarch64::transform::forward::daala_fdct_ii_16
2.10% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_coeffs_lv_map
|
---rav1e::encoder::encode_tx_block
rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_coeffs_lv_map
|
|--0.87%--rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::encode_coeffs (inlined)
|
--0.63%--rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::encode_coeff_signs (inlined)
2.08% [.] core::ops::function::impls::<impl core::ops::function::FnMut<A> for &mut F>::call_mut
|
---rav1e::api::internal::ContextInner<T>::receive_packet
rav1e::api::internal::ContextInner<T>::compute_block_importances (inlined)
<core::slice::iter::Iter<T> as core::iter::traits::iterator::Iterator>::for_each (inlined)
rav1e::api::internal::ContextInner<T>::compute_block_importances::{{closure}} (inlined)
rav1e::api::internal::ContextInner<T>::update_block_importances (inlined)
core::iter::traits::iterator::Iterator::for_each (inlined)
<core::iter::adapters::flatten::FlatMap<I,U,F> as core::iter::traits::iterator::Iterator>::fold (inlined)
<core::iter::adapters::flatten::FlattenCompat<I,U> as core::iter::traits::iterator::Iterator>::fold (inlined)
core::iter::adapters::flatten::FlattenCompat<I,U>::iter_fold (inlined)
<core::iter::adapters::fuse::Fuse<I> as core::iter::traits::iterator::Iterator>::fold (inlined)
<core::iter::adapters::map::Map<I,F> as core::iter::traits::iterator::Iterator>::fold
<core::iter::adapters::enumerate::Enumerate<I> as core::iter::traits::iterator::Iterator>::fold (inlined)
core::iter::traits::iterator::Iterator::fold (inlined)
<core::iter::adapters::enumerate::Enumerate<I> as core::iter::traits::iterator::Iterator>::fold::enumerate::{{closure}} (inlined)
core::iter::adapters::map::map_fold::{{closure}} (inlined)
core::iter::adapters::flatten::FlattenCompat<I,U>::iter_fold::flatten::{{closure}} (inlined)
<core::iter::adapters::flatten::FlattenCompat<I,U> as core::iter::traits::iterator::Iterator>::fold::flatten::{{closure}} (inlined)
<core::iter::adapters::map::Map<I,F> as core::iter::traits::iterator::Iterator>::fold
<core::iter::adapters::enumerate::Enumerate<I> as core::iter::traits::iterator::Iterator>::fold (inlined)
core::iter::traits::iterator::Iterator::fold (inlined)
<core::iter::adapters::enumerate::Enumerate<I> as core::iter::traits::iterator::Iterator>::fold::enumerate::{{closure}} (inlined)
core::iter::adapters::map::map_fold::{{closure}} (inlined)
core::ops::function::impls::<impl core::ops::function::FnMut<A> for &mut F>::call_mut
|
--2.03%--core::iter::traits::iterator::Iterator::for_each::call::{{closure}} (inlined)
rav1e::api::internal::ContextInner<T>::update_block_importances::{{closure}} (inlined)
|
--0.77%--rav1e::api::internal::ContextInner<T>::update_block_importances::{{closure}}::{{closure}} (inlined)
2.06% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
|
--2.01%--rav1e::encoder::encode_tx_block
rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_coeffs_lv_map
rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::encode_coeffs (inlined)
<rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
|
|--0.80%--rav1e::context::cdf_context::CDFContextLog::push (inlined)
| rav1e::context::cdf_context::CDFContextLogPartition<_>::push (inlined)
|
--0.55%--<rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol (inlined)
1.98% [.] rav1e::quantize::QuantizationContext::quantize
|
--1.95%--rav1e::encoder::encode_tx_block
rav1e::quantize::QuantizationContext::quantize
|
--0.79%--core::iter::traits::iterator::Iterator::max (inlined)
core::iter::traits::iterator::Iterator::max_by (inlined)
core::iter::traits::iterator::Iterator::reduce (inlined)
|
--0.78%--<core::iter::adapters::map::Map<I,F> as core::iter::traits::iterator::Iterator>::fold (inlined)
core::iter::traits::iterator::Iterator::fold (inlined)
1.95% [.] rav1e_cdef_dist_kernel_8x8_hbd_neon
|
--1.92%--rav1e::rdo::rdo_mode_decision
|
--1.88%--rav1e::rdo::inter_frame_rdo_mode_decision (inlined)
<core::iter::adapters::take::Take<I> as core::iter::traits::iterator::Iterator>::for_each (inlined)
core::iter::traits::iterator::Iterator::try_fold (inlined)
<core::iter::adapters::take::Take<I> as core::iter::traits::iterator::Iterator>::for_each::check::{{closure}} (inlined)
rav1e::rdo::inter_frame_rdo_mode_decision::{{closure}} (inlined)
rav1e::rdo::luma_chroma_mode_rdo
rav1e::rdo::luma_chroma_mode_rdo::{{closure}}
rav1e::rdo::compute_distortion
rav1e::rdo::cdef_dist_wxh (inlined)
rav1e::asm::aarch64::dist::cdef_dist::cdef_dist_kernel (inlined)
cdef_dist_kernel_8x8_hbd_neon (inlined)
1.59% [.] rav1e::encoder::encode_tx_block
|
--1.55%--rav1e::encoder::encode_tx_block
|
--1.06%--rav1e::encoder::diff (inlined)
|
--0.61%--<core::iter::adapters::zip::Zip<A,B> as core::iter::traits::iterator::Iterator>::next (inlined)
<core::iter::adapters::zip::Zip<A,B> as core::iter::adapters::zip::ZipImpl<A,B>>::next (inlined)
1.23% [.] rav1e::quantize::rust::dequantize
|
--1.22%--rav1e::encoder::encode_tx_block
rav1e::quantize::rust::dequantize
|
--0.95%--<core::iter::adapters::enumerate::Enumerate<I> as core::iter::traits::iterator::Iterator>::next (inlined)
<core::iter::adapters::zip::Zip<A,B> as core::iter::traits::iterator::Iterator>::next (inlined)
<core::iter::adapters::zip::Zip<A,B> as core::iter::adapters::zip::ZipImpl<A,B>>::next (inlined)
1.13% [.] rav1e_sad16x16_hbd_neon
|
---rav1e::me::estimate_motion
rav1e::me::full_pixel_me (inlined)
|
--1.07%--rav1e::me::full_pixel_me::{{closure}}
|
--0.57%--rav1e::me::get_best_predictor (inlined)
rav1e::me::get_fullpel_mv_rd
rav1e::me::compute_mv_rd (inlined)
sad16x16_hbd_neon (inlined)
1.12% [.] rav1e::cdef::cdef_filter_superblock
|
--1.05%--rav1e::encoder::encode_frame
rav1e::encoder::encode_tile_group (inlined)
rav1e::encoder::FrameState<T>::apply_tile_state_mut (inlined)
rav1e::encoder::encode_tile_group::{{closure}} (inlined)
rav1e::cdef::cdef_filter_tile
rav1e::cdef::cdef_filter_superblock
1.05% [.] prep_neon
|
--0.76%--rav1e::rdo::rdo_partition_decision
1.02% [.] rav1e::asm::aarch64::transform::forward::daala_fdct_ii_8
|
---rav1e::asm::aarch64::transform::forward::forward_transform_neon
|
--0.86%--rav1e::asm::aarch64::transform::forward::daala_fdct32
rav1e::asm::aarch64::transform::forward::daala_fdct_ii_32 (inlined)
rav1e::asm::aarch64::transform::forward::daala_fdct_ii_16_asym (inlined)
rav1e::asm::aarch64::transform::forward::daala_fdct_ii_8
1.02% [.] rav1e::lrf::rust::sgrproj_box_ab_r1
|
|--0.51%--rav1e::lrf::sgrproj_stripe_filter
| rav1e::lrf::rust::sgrproj_box_ab_r1
| |
| --0.51%--rav1e::lrf::rust::sgrproj_box_ab_internal (inlined)
|
--0.50%--rav1e::lrf::sgrproj_solve
rav1e::lrf::rust::sgrproj_box_ab_r1
|
--0.50%--rav1e::lrf::rust::sgrproj_box_ab_internal (inlined)
0.99% [.] rav1e::rdo::luma_chroma_mode_rdo::{{closure}}
|
--0.77%--rav1e::encoder::encode_partition_topdown
rav1e::rdo::rdo_partition_decision
|
--0.56%--rav1e::rdo::rdo_partition_simple (inlined)
rav1e::rdo::rdo_mode_decision
|
--0.51%--rav1e::rdo::inter_frame_rdo_mode_decision (inlined)
<core::iter::adapters::take::Take<I> as core::iter::traits::iterator::Iterator>::for_each (inlined)
core::iter::traits::iterator::Iterator::try_fold (inlined)
<core::iter::adapters::take::Take<I> as core::iter::traits::iterator::Iterator>::for_each::check::{{closure}} (inlined)
rav1e::rdo::inter_frame_rdo_mode_decision::{{closure}} (inlined)
rav1e::rdo::luma_chroma_mode_rdo
rav1e::rdo::luma_chroma_mode_rdo::{{closure}}
0.98% [.] rav1e::me::get_fullpel_mv_rd
|
---rav1e::me::estimate_motion
|
--0.96%--rav1e::me::full_pixel_me (inlined)
|
--0.93%--rav1e::me::full_pixel_me::{{closure}}
|
--0.50%--rav1e::me::get_best_predictor (inlined)
rav1e::me::get_fullpel_mv_rd
0.87% [.] rav1e::asm::aarch64::transform::forward::daala_fdst_iv_16
|
---rav1e::asm::aarch64::transform::forward::forward_transform_neon
|
--0.84%--rav1e::asm::aarch64::transform::forward::daala_fdct64
rav1e::asm::aarch64::transform::forward::daala_fdct_ii_32_asym (inlined)
rav1e::asm::aarch64::transform::forward::daala_fdst_iv_16
0.86% [.] rav1e_sad64x64_hbd_neon
|
---rav1e::me::estimate_motion
rav1e::me::full_pixel_me (inlined)
rav1e::me::full_pixel_me::{{closure}}
0.81% [.] rav1e::context::transform_unit::<impl rav1e::context::cdf_context::ContextWriter>::get_nz_map_contexts
|
--0.80%--rav1e::encoder::encode_tx_block
rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_coeffs_lv_map
rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::encode_coeffs (inlined)
rav1e::context::transform_unit::<impl rav1e::context::cdf_context::ContextWriter>::get_nz_map_contexts
|
--0.76%--rav1e::context::transform_unit::<impl rav1e::context::cdf_context::ContextWriter>::get_nz_map_ctx (inlined)
|
--0.59%--rav1e::context::transform_unit::<impl rav1e::context::cdf_context::ContextWriter>::get_nz_map_ctx_from_stats (inlined)
0.77% [.] rav1e::deblock::sse_size14
0.76% [.] rav1e::asm::aarch64::transform::forward::daala_fdst_iv_8
|
---rav1e::asm::aarch64::transform::forward::forward_transform_neon
|
--0.76%--rav1e::asm::aarch64::transform::forward::daala_fdct32
rav1e::asm::aarch64::transform::forward::daala_fdct_ii_32 (inlined)
rav1e::asm::aarch64::transform::forward::daala_fdct_ii_16_asym (inlined)
rav1e::asm::aarch64::transform::forward::daala_fdst_iv_8
0.70% [.] rav1e_avg_16bpc_neon
|
--0.51%--rav1e::encoder::encode_partition_topdown
|
--0.50%--rav1e::rdo::rdo_partition_decision
0.67% [.] rav1e::context::transform_unit::<impl rav1e::context::cdf_context::ContextWriter>::get_nz_mag
|
--0.66%--rav1e::encoder::encode_tx_block
rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_coeffs_lv_map
rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::encode_coeffs (inlined)
rav1e::context::transform_unit::<impl rav1e::context::cdf_context::ContextWriter>::get_nz_map_contexts
rav1e::context::transform_unit::<impl rav1e::context::cdf_context::ContextWriter>::get_nz_map_ctx (inlined)
rav1e::context::transform_unit::<impl rav1e::context::cdf_context::ContextWriter>::get_nz_mag
0.66% [.] rav1e::me::full_pixel_me::{{closure}}
|
---rav1e::me::estimate_motion
rav1e::me::full_pixel_me (inlined)
rav1e::me::full_pixel_me::{{closure}}
0.64% [.] put_neon
0.56% [.] rav1e::lrf::rust::sgrproj_box_f_r1
0.53% [.] rav1e::asm::aarch64::transform::forward::daala_fdct16
|
---rav1e::asm::aarch64::transform::forward::forward_transform_neon
rav1e::asm::aarch64::transform::forward::daala_fdct16
0.52% [.] rav1e::predict::PredictionMode::predict_inter
0.51% [.] rav1e::predict::PredictionMode::predict_inter_single
0.49% [.] rav1e::me::get_subset_predictors
0.46% [.] prep_8tap_neon
0.45% [.] <core::iter::adapters::map::Map<I,F> as core::iter::traits::iterator::Iterator>::fold
0.42% [.] rav1e::deblock::sse_size6
0.42% [.] rav1e::deblock::filter_v_edge
0.42% [.] rav1e::me::estimate_motion
0.42% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.42% [.] rav1e::partition::BlockSize::from_width_and_height_opt
0.38% [.] rav1e::deblock::filter_h_edge
0.36% [.] rav1e::encoder::encode_block_pre_cdef
0.35% [.] rav1e::lrf::rust::sgrproj_box_ab_r2
0.32% [.] rav1e_weighted_sse_32x32_hbd_neon
0.31% [.] rav1e_weighted_sse_16x16_hbd_neon
0.29% [.] rav1e::deblock::sse_v_edge
0.28% [.] rav1e::encoder::write_tx_tree
0.27% [.] rav1e::rdo::rdo_mode_decision
0.26% [.] rav1e::context::block_unit::BlockContext::get_txb_ctx
0.26% [.] rav1e::encoder::motion_compensate
0.25% [.] rav1e::encoder::encode_block_post_cdef
0.24% [.] rav1e::deblock::filter_wide14_12
0.23% [.] rav1e::deblock::sse_h_edge
0.22% [.] rav1e::partition::BlockSize::largest_chroma_tx_size
0.21% [.] rav1e::api::lookahead::estimate_importance_block_difference
0.19% [.] rav1e::me::estimate_tile_motion
0.18% [.] rav1e::deblock::deblock_size14_inner
0.17% [.] rav1e::lrf::rust::sgrproj_box_f_r2
0.17% [.] inv_dct_4s_x16_neon
0.17% [.] rav1e::context::partition_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_segmentation
0.16% [.] rav1e::me::full_search
0.16% [.] rav1e::lrf::sgrproj_solve
0.16% [.] rav1e::partition::get_intra_edges
0.16% [.] rav1e::context::frame_header::<impl rav1e::context::cdf_context::ContextWriter>::write_ref_frames
0.16% [.] rav1e::context::block_unit::FrameBlocks::new
0.15% [.] rav1e::rdo::rdo_tx_size_type
0.15% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::fill_neighbours_ref_counts
0.14% [.] inv_dct32_odd_4s_x16_neon
0.13% [.] rav1e::partition::BlockSize::from_width_and_height_opt
0.13% [.] rav1e::quantize::QuantizationContext::update
0.12% [.] rav1e::context::transform_unit::<impl rav1e::context::cdf_context::ContextWriter>::get_br_ctx
0.12% [.] rav1e::lrf::sgrproj_stripe_filter
0.12% [.] rav1e::deblock::deblock_size6_inner
0.12% [.] rav1e_inv_dct32_odd_8h_x16_neon
0.12% [.] rav1e_inv_dct_8h_x16_neon
0.12% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::find_mvrefs
0.11% [.] rav1e::activity::variance_8x8
0.11% [.] rav1e::context::partition_unit::<impl rav1e::context::cdf_context::ContextWriter>::get_segment_pred
0.10% [.] inv_txfm_horz_dct_32x4_neon
0.10% [.] rav1e::transform::forward_shared::Txfm2DFlipCfg::fwd
0.10% [.] rav1e::deblock::deblock_size
0.10% [.] rav1e::rdo::rdo_loop_plane_error
0.08% [.] rav1e::context::block_unit::BlockContext::intra_inter_context
0.08% [.] rav1e::rdo::spatiotemporal_scale
0.08% [.] inv_txfm_add_vert_dct_8x32_neon
0.08% [.] rav1e::tiling::plane_region::PlaneRegionMut<T>::scratch_copy
0.08% [.] <v_frame::frame::Frame<T> as rav1e::frame::FrameAlloc>::new
0.08% [.] rav1e::context::partition_unit::<impl rav1e::context::block_unit::BlockContext>::reset_skip_context
0.08% [.] v_frame::plane::Plane<T>::downsampled
0.08% [.] memset@plt
0.07% [.] rav1e::rdo::rdo_loop_decision
0.07% [.] rav1e_sad64x32_hbd_neon
0.07% [.] rav1e::context::block_unit::BlockContext::set_coeff_context
0.07% [.] rav1e::lrf::setup_integral_image
0.06% [.] rav1e::partition::BlockSize::from_width_and_height_opt
0.06% [.] memcpy@plt
0.06% [.] <core::iter::adapters::map::Map<I,F> as core::iter::traits::iterator::Iterator>::fold
0.06% [.] rav1e::me::MotionEstimationSubsets::all_mvs
0.06% [.] rav1e::context::partition_unit::<impl rav1e::context::block_unit::BlockContext>::skip_context
0.06% [.] rav1e::asm::aarch64::transform::forward::daala_fdct8
0.06% [.] rav1e::api::lookahead::estimate_inter_costs
0.05% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::encode_eob
0.05% [.] inv_dct64_step1_neon
0.05% [.] rav1e::deblock::deblock_filter_optimize
0.05% [.] rav1e::rdo::clip_visible_bsize
0.05% [.] rav1e_ipred_z2_fill1_16bpc_neon
0.05% [.] core::ops::function::impls::<impl core::ops::function::FnMut<A> for &F>::call_mut
0.05% [.] core::ops::function::impls::<impl core::ops::function::FnOnce<A> for &mut F>::call_once
0.05% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::scan_row_mbmi
0.05% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::add_ref_mv_candidate
0.05% [.] rav1e::asm::aarch64::mc::mc_avg
0.05% [.] inv_txfm_add_vert_dct_8x64_neon
0.05% [.] rav1e::predict::PredictionMode::predict_intra
0.04% [.] rav1e::rdo::luma_chroma_mode_rdo
0.04% [.] rav1e::api::internal::ContextInner<T>::receive_packet
0.04% [.] rav1e::api::lookahead::estimate_intra_costs
0.04% [.] inv_txfm_horz_dct_64x4_neon
0.04% [.] core::cmp::PartialOrd::lt
0.04% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.04% [.] rav1e_weighted_sse_4x4_hbd_neon
0.04% [.] rav1e::encoder::save_block_motion
0.04% [.] <core::iter::adapters::map::Map<I,F> as core::iter::traits::iterator::Iterator>::fold
0.04% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::scan_col_mbmi
0.04% [.] rav1e::ec::rust::update_cdf
0.04% [.] __aarch64_ldadd4_rel
0.04% [.] inv_dct64_step2_neon
0.03% [.] inv_dct64_step2_neon
0.03% [.] rav1e::context::transform_unit::get_tx_set
0.03% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.03% [.] rav1e::context::partition_unit::<impl rav1e::context::block_unit::BlockContext>::partition_plane_context
0.03% [.] rav1e::context::partition_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_partition
0.03% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_coeffs_lv_map
0.03% [.] inv_dct64_step1_neon
0.03% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::get_comp_ref_type_ctx
0.03% [.] rav1e::encoder::encode_block_with_modes
0.03% [.] rav1e::asm::aarch64::transform::forward::daala_fdct4
0.03% [.] rav1e::encoder::encode_block_pre_cdef
0.03% [.] rav1e::partition::BlockSize::from_width_and_height
0.03% [.] v_frame::plane::Plane<T>::pad
0.03% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.03% [.] inv_txfm_dct_clear_4s_x64_neon
0.03% [.] rav1e::context::partition_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_segmentation
0.03% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.03% [.] rav1e::ec::rust::update_cdf
0.03% [.] rav1e::encoder::encode_partition_topdown
0.03% [.] rav1e::encoder::CodedFrameData<T>::compute_spatiotemporal_scores
0.03% [.] rav1e::cdef::cdef_analyze_superblock
0.03% [.] rav1e::asm::aarch64::transform::inverse::inverse_transform_add
0.02% [.] inv_txfm_add_vert_8x16_neon
0.02% [.] rav1e::deblock::sse_size8
0.02% [.] rav1e::encoder::encode_partition_bottomup
0.02% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.02% [.] rav1e::encoder::write_tx_blocks
0.02% [.] inv_txfm_horz_16x4_neon
0.02% [.] <arrayvec::arrayvec::ArrayVec<T,_> as core::iter::traits::collect::FromIterator<T>>::from_iter
0.02% [.] rav1e_weighted_sse_8x8_hbd_neon
0.02% [.] rav1e_sad8x8_hbd_neon
0.02% [.] rav1e::rdo::rdo_cfl_alpha::{{closure}}::{{closure}}
0.02% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::get_comp_mode_ctx
0.02% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_inter_mode
0.02% [.] __aarch64_cas4_acq
0.02% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_compound_mode
0.02% [.] rav1e::partition::BlockSize::largest_chroma_tx_size
0.02% [.] rav1e_inv_txfm_dct_8h_x64_neon
0.02% [.] rav1e_ipred_paeth_16bpc_neon
0.02% [.] rav1e::rdo::rdo_partition_decision
0.02% [.] <core::iter::adapters::map::Map<I,F> as core::iter::traits::iterator::Iterator>::fold
0.02% [.] core::cmp::PartialOrd::ge
0.02% [.] rav1e::encoder::encode_tx_block
0.02% [.] rav1e::partition::has_tr
0.02% [.] rav1e_cdef_find_dir_16bpc_neon
0.02% [.] rav1e::context::frame_header::<impl rav1e::context::cdf_context::ContextWriter>::write_ref_frames
0.02% [.] rav1e::asm::aarch64::dist::cdef_dist::cdef_dist_kernel
0.02% [.] rav1e_inv_txfm_add_dct_dct_32x32_16bpc_neon
0.02% [.] rav1e_ipred_z3_fill1_16bpc_neon
0.02% [.] rav1e::activity::ActivityMask::fill_scales
0.02% [.] rav1e_ipred_cfl_128_16bpc_neon
0.02% [.] rav1e::deblock::sse_size4
0.02% [.] cdef_filter8_pri_16bpc_neon
0.01% [.] rav1e_ipred_smooth_16bpc_neon
0.01% [.] rav1e::asm::aarch64::cdef::cdef_filter_block
0.01% [.] rav1e_ipred_z1_fill1_16bpc_neon
0.01% [.] core::slice::sort::merge_sort
0.01% [.] rav1e::context::<impl rav1e::context::cdf_context::ContextWriter>::encode_mv_component
0.01% [.] inv_txfm_add_8x8_neon
0.01% [.] cdef_filter4_sec_16bpc_neon
0.01% [.] core::slice::sort::insertion_sort_shift_left
0.01% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_mv
0.01% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.01% [.] inv_dct_4s_x8_neon
0.01% [.] <T as alloc::vec::spec_from_elem::SpecFromElem>::from_elem
0.01% [.] rav1e::lrf::rust::sgrproj_box_f_r0
0.01% [.] rav1e::context::transform_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_tx_type
0.01% [.] rav1e_ipred_dc_128_16bpc_neon
0.01% [.] rav1e::deblock::deblock_adjusted_level
0.01% [.] rav1e_cdef_padding4_16bpc_neon
0.01% [.] rav1e::ec::rust::update_cdf
0.01% [.] rav1e_inv_dct_8h_x8_neon
0.01% [.] rav1e::encoder::check_lf_queue
0.01% [.] <rav1e::ec::WriterBase<rav1e::ec::WriterEncoder> as rav1e::ec::StorageBackend>::store
0.01% [.] cdef_filter8_sec_16bpc_neon
0.01% [.] rav1e::deblock::deblock_size8_inner
0.01% [.] crossbeam_deque::deque::Stealer<T>::steal
0.01% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.01% [.] core::ops::function::impls::<impl core::ops::function::FnOnce<A> for &mut F>::call_once
0.01% [.] rav1e::context::block_unit::BlockContext::checkpoint
0.01% [.] rav1e_put_8tap_regular_16bpc_neon
0.01% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::encode_eob
0.01% [.] rav1e_ipred_smooth_h_16bpc_neon
0.01% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.01% [.] rav1e::activity::ActivityMask::from_plane
0.01% [.] rav1e::deblock::deblock_size4_inner
0.01% [.] arrayvec::arrayvec::ArrayVec<T,_>::push
0.01% [.] rav1e::asm::aarch64::predict::ipred_z1
0.01% [.] rav1e::context::partition_unit::<impl rav1e::context::block_unit::BlockContext>::update_partition_context
0.01% [.] idct_dc_w32_neon
0.01% [.] rav1e::asm::aarch64::transform::forward::daala_fdst16
0.01% [.] inv_adst_4s_x16_neon
0.01% [.] alloc::raw_vec::RawVec<T,A>::reserve_for_push
0.01% [.] rav1e::ec::rust::update_cdf
0.01% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.01% [.] core::slice::sort::insertion_sort_shift_left
0.01% [.] <arrayvec::arrayvec::ArrayVec<T,_> as core::clone::Clone>::clone
0.01% [.] rav1e::api::internal::ContextInner<T>::send_frame
0.00% [.] rav1e::dist::rust::get_weighted_sse
0.00% [.] rav1e::ec::rust::update_cdf
0.00% [.] rav1e::partition::supersample_chroma_bsize
0.00% [.] rav1e::context::frame_header::<impl rav1e::context::cdf_context::ContextWriter>::write_lrf
0.00% [.] core::cmp::PartialOrd::ge
0.00% [.] rayon_core::registry::WorkerThread::wait_until_cold
0.00% [.] rav1e_ipred_z1_filter_edge_16bpc_neon
0.00% [.] inv_txfm_add_16x16_neon
0.00% [.] rav1e::context::partition_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_partition
0.00% [.] rav1e_inv_txfm_add_dct_dct_64x64_16bpc_neon
0.00% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.00% [.] crossbeam_epoch::default::with_handle
0.00% [.] rav1e::partition::BlockSize::subsize
0.00% [.] alloc::collections::btree::node::Handle<alloc::collections::btree::node::NodeRef<alloc::collections::btree::node::marker::Mut,K,V,alloc::collections::btree::node::marker::Leaf>,alloc::collections::btree::node::marker::Edge>::insert_recursing
0.00% [.] rav1e_cdef_padding8_16bpc_neon
0.00% [.] rav1e::asm::aarch64::predict::ipred_z2
0.00% [.] core::slice::sort::insertion_sort_shift_left
0.00% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.00% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_inter_mode
0.00% [.] realloc@plt
0.00% [.] crossbeam_deque::deque::Worker<T>::pop
0.00% [.] inv_txfm_add_4x4_neon
0.00% [.] rav1e_ipred_cfl_16bpc_neon
0.00% [.] rav1e_ipred_z2_fill2_16bpc_neon
0.00% [.] rav1e_inv_adst_8h_x16_neon
0.00% [.] rav1e_ipred_h_16bpc_neon
0.00% [.] rav1e_ipred_dc_16bpc_neon
0.00% [.] core::cmp::PartialOrd::gt
0.00% [.] rav1e::predict::rust::dr_intra_derivative
0.00% [.] rav1e::predict::luma_ac
0.00% [.] rav1e::tiling::tile_state::TileStateMut<T>::new
0.00% [.] idct_dc_w64_neon
0.00% [.] cdef_filter4_pri_16bpc_neon
0.00% [.] core::cmp::PartialOrd::le
0.00% [.] inv_txfm_dct_clear_scale_4s_x64_neon
0.00% [.] idct_dc_w8_neon
0.00% [.] rav1e_ipred_v_16bpc_neon
0.00% [.] rav1e_satd32x32_hbd_neon
0.00% [.] rav1e_ipred_smooth_v_16bpc_neon
0.00% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.00% [.] rav1e::asm::aarch64::transform::forward::daala_fdst8
0.00% [.] rav1e::util::logexp::blog32_q11
0.00% [.] alloc::collections::btree::remove::<impl alloc::collections::btree::node::Handle<alloc::collections::btree::node::NodeRef<alloc::collections::btree::node::marker::Mut,K,V,alloc::collections::btree::node::marker::LeafOrInternal>,alloc::collections::btree::node::marker::KV>>::remove_kv_tracking
0.00% [.] idct_dc_w16_neon
0.00% [.] <core::iter::adapters::chain::Chain<A,B> as core::iter::traits::iterator::Iterator>::try_fold
0.00% [.] __aarch64_ldadd8_rel
0.00% [.] rayon_core::sleep::Sleep::sleep
0.00% [.] rav1e::asm::aarch64::transform::forward::daala_fdst_vii_4
0.00% [.] alloc::raw_vec::finish_grow
0.00% [.] rav1e_inv_txfm_add_dct_dct_64x32_16bpc_neon
0.00% [.] rav1e::recon_intra::has_bottom_left
0.00% [.] alloc::collections::btree::map::entry::VacantEntry<K,V,A>::insert
0.00% [.] core::slice::sort::insertion_sort_shift_left
0.00% [.] pow@plt
0.00% [.] std::sys::unix::locks::futex_mutex::Mutex::lock_contended
0.00% [.] core::slice::sort::merge_sort
0.00% [.] rav1e::ec::rust::update_cdf
0.00% [.] crossbeam_deque::deque::Injector<T>::steal
0.00% [.] rayon_core::registry::global_registry
0.00% [.] <alloc::boxed::Box<[I]> as core::iter::traits::collect::FromIterator<I>>::from_iter
0.00% [.] rav1e::encoder::encode_frame
0.00% [.] __aarch64_cas8_acq_rel
0.00% [.] rav1e::do_encode
0.00% [.] <alloc::collections::btree::map::Iter<K,V> as core::iter::traits::iterator::Iterator>::next
0.00% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.00% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_intra_mode_kf
0.00% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.00% [.] rav1e::asm::aarch64::predict::pred_cfl_ac
0.00% [.] rav1e::partition::BlockSize::largest_chroma_tx_size
0.00% [.] rav1e::recon_intra::has_top_right
0.00% [.] rav1e::context::<impl rav1e::context::cdf_context::ContextWriter>::encode_mv_component
0.00% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::write_golomb
0.00% [.] alloc::collections::btree::map::entry::OccupiedEntry<K,V,A>::remove_kv
0.00% [.] <alloc::vec::Vec<T> as alloc::vec::spec_from_iter::SpecFromIter<T,I>>::from_iter
0.00% [.] memmove@plt
0.00% [.] inv_txfm_horz_scale_16x4_neon
0.00% [.] rav1e::cdef::cdef_filter_tile
0.00% [.] rav1e::util::logexp::bexp64
0.00% [.] core::ptr::drop_in_place<rav1e::encoder::ReferenceFramesSet<u16>>
0.00% [.] rav1e::stats::build_frame_summary
0.00% [.] rav1e::lrf::RestorationState::lrf_filter_frame
0.00% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_bits
0.00% [.] <core::panic::unwind_safe::AssertUnwindSafe<F> as core::ops::function::FnOnce<()>>::call_once
0.00% [.] __aarch64_ldadd8_relax
0.00% [.] malloc@plt
0.00% [.] crossbeam_epoch::internal::Global::try_advance
0.00% [.] __aarch64_ldadd8_acq_rel
0.00% [.] rav1e::context::transform_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_tx_type
0.00% [.] crossbeam_deque::deque::Injector<T>::push
0.00% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_mv
0.00% [.] rav1e::rate::QuantizerParameters::new_from_log_q
0.00% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.00% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.00% [.] rav1e_satd64x32_hbd_neon
0.00% [.] rav1e::ec::rust::update_cdf
0.00% [.] rav1e_satd64x64_hbd_neon
0.00% [.] inv_txfm_horz_scale_dct_32x4_neon
0.00% [.] rav1e_inv_dct_4h_x4_neon
0.00% [.] rav1e_sad16x4_hbd_neon
0.00% [.] y4m::Decoder<R>::read_frame
0.00% [.] core::option::Option<&T>::cloned
0.00% [.] rav1e_ipred_z3_fill2_16bpc_neon
0.00% [.] rav1e::context::block_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_compound_mode
0.00% [.] rav1e::util::kmeans::scan
0.00% [.] rav1e_inv_txfm_add_dct_dct_8x8_16bpc_neon
0.00% [.] core::fmt::write
0.00% [.] core::fmt::num::imp::<impl core::fmt::Display for usize>::fmt
0.00% [.] <rav1e::stats::FrameSummary as core::fmt::Display>::fmt
0.00% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.00% [.] <rayon::iter::plumbing::bridge::Callback<C> as rayon::iter::plumbing::ProducerCallback<I>>::callback
0.00% [.] rav1e::encoder::Sequence::get_skip_mode_allowed
0.00% [.] rav1e::encoder::FrameState<T>::new_with_frame
0.00% [.] <bitstream_io::write::BitWriter<W,E> as bitstream_io::write::BitWrite>::write
0.00% [.] rav1e::encoder::FrameInvariants<T>::new_inter_frame
0.00% [.] rav1e::rate::RCState::calc_flat_quantizer
0.00% [.] rav1e::api::internal::ContextInner<T>::compute_keyframe_placement
0.00% [.] rav1e::encoder::FrameState<T>::new_with_frame_and_me_stats_and_rec
0.00% [.] <rayon_core::job::StackJob<L,F,R> as rayon_core::job::Job>::execute
0.00% [.] <rayon_core::latch::LatchRef<L> as rayon_core::latch::Latch>::set
0.00% [.] crossbeam_epoch::sync::queue::Queue<T>::try_pop_if
0.00% [.] crossbeam_epoch::internal::Global::collect
0.00% [.] core::ptr::drop_in_place<rav1e::encoder::CodedFrameData<u16>>
0.00% [.] <rayon_core::job::StackJob<L,F,R> as rayon_core::job::Job>::execute
0.00% [.] v_frame::plane::Plane<T>::copy_from_raw_u8
0.00% [.] <bitstream_io::write::BitWriter<W,bitstream_io::BigEndian> as rav1e::header::UncompressedHeader>::write_delta_q
0.00% [.] core::slice::sort::merge_sort
0.00% [.] rav1e_satd16x16_hbd_neon
0.00% [.] rav1e_sad16x8_hbd_neon
0.00% [.] rav1e_ipred_z1_fill2_16bpc_neon
0.00% [.] rav1e::ec::WriterBase<rav1e::ec::WriterEncoder>::done
0.00% [.] rav1e_prep_8tap_regular_16bpc_neon
0.00% [.] rav1e::context::partition_unit::<impl rav1e::context::cdf_context::ContextWriter>::write_cfl_alphas
0.00% [.] rav1e_inv_txfm_add_dct_dct_4x4_16bpc_neon
0.00% [.] free@plt
0.00% [.] <fern::log_impl::Dispatch as log::Log>::log
0.00% [.] rav1e::asm::aarch64::predict::ipred_z3
0.00% [.] rav1e::cdef::cdef_analyze_superblock_range
0.00% [.] rav1e_ipred_z1_upsample_edge_16bpc_neon
0.00% [.] inv_adst_4s_x4_neon
0.00% [.] core::ops::function::impls::<impl core::ops::function::FnMut<A> for &F>::call_mut
0.00% [.] exp@plt
0.00% [.] rayon::math::simplify_range
0.00% [.] core::ptr::drop_in_place<rayon::vec::Drain<rav1e::tiling::tiler::TileContextMut<u16>>>
0.00% [.] __aarch64_cas8_acq
0.00% [.] rav1e_inv_txfm_add_dct_dct_32x16_16bpc_neon
0.00% [.] <arrayvec::arrayvec::ArrayVec<T,_> as core::iter::traits::collect::FromIterator<T>>::from_iter
0.00% [.] rav1e_sad32x64_hbd_neon
0.00% [.] <rayon::vec::IntoIter<T> as rayon::iter::IndexedParallelIterator>::with_producer
0.00% [.] inv_adst_4s_x8_neon
0.00% [.] rav1e::encoder::FrameInvariants<T>::set_quantizers
0.00% [.] core::cmp::PartialOrd::ge
0.00% [.] alloc::collections::btree::node::Handle<alloc::collections::btree::node::NodeRef<alloc::collections::btree::node::marker::Mut,K,V,alloc::collections::btree::node::marker::Leaf>,alloc::collections::btree::node::marker::Edge>::insert_recursing
0.00% [.] rav1e::quantize::select_dc_qi
0.00% [.] <v_frame::frame::Frame<T> as core::clone::Clone>::clone
0.00% [.] rav1e::rate::RCState::select_qi
0.00% [.] inv_dct_4s_x4_neon
0.00% [.] rav1e_inv_adst_8h_x8_neon
0.00% [.] std::io::Write::write_fmt
0.00% [.] rav1e_ipred_z2_fill3_16bpc_neon
0.00% [.] rav1e::api::lookahead::compute_motion_vectors
0.00% [.] alloc::raw_vec::RawVec<T,A>::reserve::do_reserve_and_handle
0.00% [.] rayon::iter::plumbing::bridge_producer_consumer::helper
0.00% [.] rav1e_satd32x16_hbd_neon
0.00% [.] alloc::raw_vec::RawVec<T,A>::reserve_for_push
0.00% [.] rav1e_ipred_reverse_16bpc_neon
0.00% [.] <rav1e::tiling::tiler::TileContextIterMut<T> as core::iter::traits::iterator::Iterator>::next
0.00% [.] core::fmt::Formatter::pad_integral::write_prefix
0.00% [.] rav1e::segmentation::segmentation_optimize
0.00% [.] alloc::collections::vec_deque::VecDeque<T,A>::grow
0.00% [.] alloc::collections::btree::remove::<impl alloc::collections::btree::node::Handle<alloc::collections::btree::node::NodeRef<alloc::collections::btree::node::marker::Mut,K,V,alloc::collections::btree::node::marker::Leaf>,alloc::collections::btree::node::marker::KV>>::remove_leaf_kv
0.00% [.] <alloc::borrow::Cow<B> as core::fmt::Display>::fmt
0.00% [.] <bitstream_io::write::BitWriter<W,bitstream_io::BigEndian> as rav1e::header::UncompressedHeader>::write_deblock_filter_a
0.00% [.] alloc::collections::btree::remove::<impl alloc::collections::btree::node::Handle<alloc::collections::btree::node::NodeRef<alloc::collections::btree::node::marker::Mut,K,V,alloc::collections::btree::node::marker::LeafOrInternal>,alloc::collections::btree::node::marker::KV>>::remove_kv_tracking
0.00% [.] core::ptr::drop_in_place<rav1e::encoder::ReferenceFrame<u16>>
0.00% [.] <bitstream_io::write::BitWriter<W,bitstream_io::BigEndian> as rav1e::header::UncompressedHeader>::write_segment_data
0.00% [.] <alloc::vec::Vec<T> as alloc::vec::spec_from_iter::SpecFromIter<T,I>>::from_iter
0.00% [.] rav1e::decoder::y4m::<impl rav1e::decoder::Decoder for y4m::Decoder<alloc::boxed::Box<dyn std::io::Read+core::marker::Send>>>::read_frame
0.00% [.] <bitstream_io::write::BitWriter<W,E> as bitstream_io::write::BitWrite>::write
0.00% [.] rav1e::lrf::RestorationPlane::restoration_unit_by_stripe
0.00% [.] fern::log_impl::LevelConfiguration::find_exact
0.00% [.] core::fmt::float::<impl core::fmt::Display for f64>::fmt
0.00% [.] <rav1e::stats::ProgressInfo as core::fmt::Display>::fmt
0.00% [.] <bitstream_io::write::BitWriter<W,bitstream_io::BigEndian> as rav1e::header::ULEB128Writer>::write_uleb128
0.00% [.] rayon::iter::collect::collect_with_consumer
0.00% [.] alloc::sync::Arc<T,A>::drop_slow
0.00% [.] alloc::collections::btree::map::BTreeMap<K,V,A>::get
0.00% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.00% [.] rav1e::context::cdf_context::CDFContext::reset_counts
0.00% [.] <bitstream_io::write::BitWriter<W,E> as bitstream_io::write::BitWrite>::write
0.00% [.] <v_frame::frame::Frame<T> as rav1e::frame::FramePad>::pad
0.00% [.] <alloc::vec::Vec<T> as alloc::vec::spec_from_iter::SpecFromIter<T,I>>::from_iter
0.00% [.] rav1e::stats::ProgressInfo::print_chroma_prediction_mode_summary_by_frame_type
0.00% [.] <bitstream_io::write::BitWriter<W,bitstream_io::BigEndian> as rav1e::header::UncompressedHeader>::write_frame_header_obu
0.00% [.] rayon_core::join::join_context::{{closure}}
0.00% [.] core::num::flt2dec::strategy::dragon::format_exact
0.00% [.] <core::iter::adapters::map::Map<I,F> as core::iter::traits::iterator::Iterator>::fold
0.00% [.] alloc::collections::btree::map::entry::OccupiedEntry<K,V,A>::remove_kv
0.00% [.] sched_yield@plt
0.00% [.] <rav1e::ec::WriterBase<S> as rav1e::ec::Writer>::symbol_with_update
0.00% [.] rav1e::context::cdf_context::CDFContext::new
0.00% [.] <core::panic::unwind_safe::AssertUnwindSafe<F> as core::ops::function::FnOnce<()>>::call_once
0.00% [.] rav1e_inv_adst_4h_x4_neon
0.00% [.] <alloc::collections::btree::map::Keys<K,V> as core::iter::traits::iterator::Iterator>::last
0.00% [.] <T as alloc::vec::spec_from_elem::SpecFromElem>::from_elem
0.00% [.] core::ptr::drop_in_place<rav1e::encoder::FrameState<u16>>
0.00% [.] <std::io::buffered::bufreader::BufReader<R> as std::io::Read>::read
0.00% [.] <rayon::iter::unzip::UnzipFolder<OP,FA,FB> as rayon::iter::plumbing::Folder<T>>::consume
0.00% [.] <rav1e::cpu_features::aarch64::CpuFeatureLevel as core::default::Default>::default
0.00% [.] alloc::sync::Arc<T,A>::make_mut
0.00% [.] <std::io::stdio::StdinLock as std::io::Read>::read_exact
0.00% [.] core::ptr::drop_in_place<rayon::vec::DrainProducer<rav1e::tiling::tiler::TileContextMut<u16>>>
0.00% [.] rayon_core::join::join_context::{{closure}}
0.00% [.] rav1e::encoder::FrameInvariants<T>::new_key_frame
0.00% [.] rav1e::util::logexp::blog64
0.00% [.] v_frame::plane::Plane<T>::probe_padding
0.00% [.] rav1e::encoder::FrameInvariants<T>::set_ref_frame_sign_bias
0.00% [.] std::env::_var_os
0.00% [.] rayon_core::registry::Registry::in_worker_cold
0.00% [.] clap_builder::parser::arg_matcher::ArgMatcher::fill_in_global_values
0.00% [.] clap_builder::builder::command::Command::arg
6.87% libc.so.6
2.13% [.] 0x0000000000099e50
|
--1.98%--rav1e::asm::aarch64::transform::forward::forward_transform_neon
rav1e::asm::aarch64::transform::forward::daala_fdct64
0xffff82369e50
2.08% [.] 0x0000000000099e48
|
--1.95%--rav1e::asm::aarch64::transform::forward::forward_transform_neon
rav1e::asm::aarch64::transform::forward::daala_fdct64
0xffff82369e48
Codecov Report
All modified and coverable lines are covered by tests :white_check_mark:
Additional details and impacted files
```diff @@ Coverage Diff @@ ## master #3302 +/- ## ======================================= Coverage 88.24% 88.24% ======================================= Files 88 88 Lines 28210 28210 ======================================= Hits 24893 24893 Misses 3317 3317 ```:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.