diff options
author | Jacques Lucke <jacques@blender.org> | 2021-11-26 13:05:47 +0300 |
---|---|---|
committer | Jacques Lucke <jacques@blender.org> | 2021-11-26 13:06:16 +0300 |
commit | 658fd8df0bd2427cd77e7fc4bcca8a102f67b626 (patch) | |
tree | 574c5a6f4c11db7047a98ca38c6d6f129a4b10e2 /source/blender/functions/intern/multi_function_params.cc | |
parent | 004172de38d5483b715a5b13d06c2aa5dd3de3f5 (diff) |
Geometry Nodes: refactor multi-threading in field evaluation
Previously, there was a fixed grain size for all multi-functions. That was
not sufficient because some functions could benefit a lot from smaller
grain sizes.
This refactors adds a new `MultiFunction::call_auto` method which has the
same effect as just calling `MultiFunction::call` but additionally figures
out how to execute the specific multi-function efficiently. It determines
a good grain size and decides whether the mask indices should be shifted
or not.
Most multi-function evaluations benefit from this, but medium sized work
loads (1000 - 50000 elements) benefit from it the most. Especially when
expensive multi-functions (e.g. noise) is involved. This is because for
smaller work loads, threading is rarely used and for larger work loads
threading worked fine before already.
With this patch, multi-functions can specify execution hints, that allow
the caller to execute it most efficiently. These execution hints still
have to be added to more functions.
Some performance measurements of a field evaluation involving noise and
math nodes, ordered by the number of elements being evaluated:
```
1,000,000: 133 ms -> 120 ms
100,000: 30 ms -> 18 ms
10,000: 20 ms -> 2.7 ms
1,000: 4 ms -> 0.5 ms
100: 0.5 ms -> 0.4 ms
```
Diffstat (limited to 'source/blender/functions/intern/multi_function_params.cc')
-rw-r--r-- | source/blender/functions/intern/multi_function_params.cc | 44 |
1 files changed, 44 insertions, 0 deletions
diff --git a/source/blender/functions/intern/multi_function_params.cc b/source/blender/functions/intern/multi_function_params.cc new file mode 100644 index 00000000000..376c5b2deb7 --- /dev/null +++ b/source/blender/functions/intern/multi_function_params.cc @@ -0,0 +1,44 @@ +/* + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software Foundation, + * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#include "FN_multi_function_params.hh" + +namespace blender::fn { + +GMutableSpan MFParams::ensure_dummy_single_output(int data_index) +{ + /* Lock because we are actually modifying #builder_ and it may be used by multiple threads. */ + std::lock_guard lock{builder_->mutex_}; + + for (const std::pair<int, GMutableSpan> &items : builder_->dummy_output_spans_) { + if (items.first == data_index) { + return items.second; + } + } + + const CPPType &type = builder_->mutable_spans_[data_index].type(); + void *buffer = builder_->scope_.linear_allocator().allocate( + builder_->min_array_size_ * type.size(), type.alignment()); + if (!type.is_trivially_destructible()) { + builder_->scope_.add_destruct_call( + [&type, buffer, mask = builder_->mask_]() { type.destruct_indices(buffer, mask); }); + } + const GMutableSpan span{type, buffer, builder_->min_array_size_}; + builder_->dummy_output_spans_.append({data_index, span}); + return span; +} + +} // namespace blender::fn |