Files
carbon-lang/toolchain/parse/tree.cpp
T
Jon Ross-PerkinsandChandler Carruth 08f24551ec Add bit packing to NodeImpl (#4651)
Just a small packing optimization. We currently have 222 `NodeKinds`, so
this reduces us to just 30ish more we can add without needing to pack
more. However, if we did, there would be a couple options for bringing
the count down by reusing `NodeKinds` and disambiguating based on the
token kind (the 29 infix operators as an example). Or we could just undo
this.

I'm expecting this to yield a small improvement. I'll see if I can get
better numbers since my machine's not really reliable, but here are some
basic values.

Also suggesting to draw the use of `::RawEnumType` for `TokenKind`,
since bit packing appears to work without it. Hoping the `static_assert`
is easier for people to understand the size of the field.

With the change:

```
----------------------------------------------------------------------------------------------------------------------------
Benchmark                                                 Time             CPU   Iterations      Bytes      Lines     Tokens
----------------------------------------------------------------------------------------------------------------------------
BM_CompileAPIFileDenseDecls<Phase::Parse>/256         50399 ns        50359 ns        14336 104.588M/s 3.87217M/s 21.8629M/s
BM_CompileAPIFileDenseDecls<Phase::Parse>/1024       237823 ns       237629 ns         3072 136.721M/s 4.11986M/s 24.2058M/s
BM_CompileAPIFileDenseDecls<Phase::Parse>/4096       997645 ns       996771 ns          768 142.343M/s 4.04105M/s 23.9363M/s
BM_CompileAPIFileDenseDecls<Phase::Parse>/16384     4020308 ns      4018319 ns          192 152.041M/s 4.05966M/s 24.0874M/s
BM_CompileAPIFileDenseDecls<Phase::Parse>/65536    16691390 ns     16683058 ns           48 151.317M/s 3.92374M/s 23.2936M/s
BM_CompileAPIFileDenseDecls<Phase::Parse>/262144   75265735 ns     75233476 ns            8 135.842M/s 3.48421M/s 20.6862M/s
```

Without the change:
```
----------------------------------------------------------------------------------------------------------------------------
Benchmark                                                 Time             CPU   Iterations      Bytes      Lines     Tokens
----------------------------------------------------------------------------------------------------------------------------
BM_CompileAPIFileDenseDecls<Phase::Parse>/256         51515 ns        51480 ns        13312 102.312M/s 3.78789M/s  21.387M/s
BM_CompileAPIFileDenseDecls<Phase::Parse>/1024       241040 ns       240900 ns         3072 134.865M/s 4.06392M/s 23.8771M/s
BM_CompileAPIFileDenseDecls<Phase::Parse>/4096       985593 ns       984657 ns          768 144.094M/s 4.09077M/s 24.2308M/s
BM_CompileAPIFileDenseDecls<Phase::Parse>/16384     4109327 ns      4105496 ns          192 148.813M/s 3.97345M/s  23.576M/s
BM_CompileAPIFileDenseDecls<Phase::Parse>/65536    17459655 ns     17446006 ns           48   144.7M/s 3.75215M/s  22.275M/s
BM_CompileAPIFileDenseDecls<Phase::Parse>/262144   80802815 ns     80737489 ns            8 126.581M/s 3.24668M/s  19.276M/s
```

---------

Co-authored-by: Chandler Carruth <chandlerc@gmail.com>
2024-12-17 00:58:54 +00:00

90 lines
3.0 KiB
C++

// Part of the Carbon Language project, under the Apache License v2.0 with LLVM
// Exceptions. See /LICENSE for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#include "toolchain/parse/tree.h"
#include "common/check.h"
#include "common/error.h"
#include "llvm/ADT/Sequence.h"
#include "llvm/ADT/SmallVector.h"
#include "toolchain/lex/tokenized_buffer.h"
#include "toolchain/parse/node_kind.h"
#include "toolchain/parse/tree_and_subtrees.h"
#include "toolchain/parse/typed_nodes.h"
namespace Carbon::Parse {
auto Tree::postorder() const -> llvm::iterator_range<PostorderIterator> {
return llvm::iterator_range<PostorderIterator>(
PostorderIterator(NodeId(0)),
PostorderIterator(NodeId(node_impls_.size())));
}
auto Tree::node_token(NodeId n) const -> Lex::TokenIndex {
CARBON_CHECK(n.is_valid());
return node_impls_[n.index].token();
}
auto Tree::Print(llvm::raw_ostream& output) const -> void {
TreeAndSubtrees(*tokens_, *this).Print(output);
}
auto Tree::Verify() const -> ErrorOr<Success> {
llvm::SmallVector<NodeId> nodes;
// Traverse the tree in postorder.
for (NodeId n : postorder()) {
if (node_has_error(n) && !has_errors()) {
return Error(llvm::formatv(
"Node {0} has errors, but the tree is not marked as having any.", n));
}
if (node_kind(n) == NodeKind::Placeholder) {
return Error(llvm::formatv(
"Node {0} is a placeholder node that wasn't replaced.", n));
}
}
// Not every token that can produce a virtual node will, so we only check that
// the number of nodes is in a range.
int32_t num_nodes = size();
if (!has_errors() && num_nodes > tokens_->expected_max_parse_tree_size()) {
return Error(llvm::formatv(
"Tree has {0} nodes and no errors, but "
"Lex::TokenizedBuffer expected up to {1} nodes for {2} tokens.",
num_nodes, tokens_->expected_max_parse_tree_size(), tokens_->size()));
}
if (!has_errors() && num_nodes < tokens_->size()) {
return Error(
llvm::formatv("Tree has {0} nodes and no errors, but expected at least "
"{1} nodes to match the number of tokens.",
num_nodes, tokens_->size()));
}
#ifndef NDEBUG
TreeAndSubtrees subtrees(*tokens_, *this);
CARBON_RETURN_IF_ERROR(subtrees.Verify());
#endif // NDEBUG
return Success();
}
auto Tree::CollectMemUsage(MemUsage& mem_usage, llvm::StringRef label) const
-> void {
mem_usage.Collect(MemUsage::ConcatLabel(label, "node_impls_"), node_impls_);
mem_usage.Collect(MemUsage::ConcatLabel(label, "imports_"), imports_);
}
auto Tree::PostorderIterator::MakeRange(NodeId begin, NodeId end)
-> llvm::iterator_range<PostorderIterator> {
CARBON_CHECK(begin.is_valid() && end.is_valid());
return llvm::iterator_range<PostorderIterator>(
PostorderIterator(begin), PostorderIterator(NodeId(end.index + 1)));
}
auto Tree::PostorderIterator::Print(llvm::raw_ostream& output) const -> void {
output << node_;
}
} // namespace Carbon::Parse