Files
rust/compiler/rustc_data_structures/src/graph/dominators/mod.rs

215 lines
7.3 KiB
Rust
Raw Normal View History

//! Finding the dominators in a control-flow graph.
//!
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
//! Algorithm based on Loukas Georgiadis,
//! "Linear-Time Algorithms for Dominators and Related Problems",
//! ftp://ftp.cs.princeton.edu/techreports/2005/737.pdf
use super::ControlFlowGraph;
2019-12-22 17:42:04 -05:00
use rustc_index::vec::{Idx, IndexVec};
Updates to experimental coverage counter injection This is a combination of 18 commits. Commit #2: Additional examples and some small improvements. Commit #3: fixed mir-opt non-mir extensions and spanview title elements Corrected a fairly recent assumption in runtest.rs that all MIR dump files end in .mir. (It was appending .mir to the graphviz .dot and spanview .html file names when generating blessed output files. That also left outdated files in the baseline alongside the files with the incorrect names, which I've now removed.) Updated spanview HTML title elements to match their content, replacing a hardcoded and incorrect name that was left in accidentally when originally submitted. Commit #4: added more test examples also improved Makefiles with support for non-zero exit status and to force validation of tests unless a specific test overrides it with a specific comment. Commit #5: Fixed rare issues after testing on real-world crate Commit #6: Addressed PR feedback, and removed temporary -Zexperimental-coverage -Zinstrument-coverage once again supports the latest capabilities of LLVM instrprof coverage instrumentation. Also fixed a bug in spanview. Commit #7: Fix closure handling, add tests for closures and inner items And cleaned up other tests for consistency, and to make it more clear where spans start/end by breaking up lines. Commit #8: renamed "typical" test results "expected" Now that the `llvm-cov show` tests are improved to normally expect matching actuals, and to allow individual tests to override that expectation. Commit #9: test coverage of inline generic struct function Commit #10: Addressed review feedback * Removed unnecessary Unreachable filter. * Replaced a match wildcard with remining variants. * Added more comments to help clarify the role of successors() in the CFG traversal Commit #11: refactoring based on feedback * refactored `fn coverage_spans()`. * changed the way I expand an empty coverage span to improve performance * fixed a typo that I had accidently left in, in visit.rs Commit #12: Optimized use of SourceMap and SourceFile Commit #13: Fixed a regression, and synched with upstream Some generated test file names changed due to some new change upstream. Commit #14: Stripping out crate disambiguators from demangled names These can vary depending on the test platform. Commit #15: Ignore llvm-cov show diff on test with generics, expand IO error message Tests with generics produce llvm-cov show results with demangled names that can include an unstable "crate disambiguator" (hex value). The value changes when run in the Rust CI Windows environment. I added a sed filter to strip them out (in a prior commit), but sed also appears to fail in the same environment. Until I can figure out a workaround, I'm just going to ignore this specific test result. I added a FIXME to follow up later, but it's not that critical. I also saw an error with Windows GNU, but the IO error did not specify a path for the directory or file that triggered the error. I updated the error messages to provide more info for next, time but also noticed some other tests with similar steps did not fail. Looks spurious. Commit #16: Modify rust-demangler to strip disambiguators by default Commit #17: Remove std::process::exit from coverage tests Due to Issue #77553, programs that call std::process::exit() do not generate coverage results on Windows MSVC. Commit #18: fix: test file paths exceeding Windows max path len
2020-09-01 16:15:17 -07:00
use std::cmp::Ordering;
#[cfg(test)]
mod tests;
struct PreOrderFrame<Iter> {
pre_order_idx: PreorderIndex,
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
iter: Iter,
}
rustc_index::newtype_index! {
struct PreorderIndex { .. }
}
pub fn dominators<G: ControlFlowGraph>(graph: G) -> Dominators<G::Node> {
// compute the post order index (rank) for each node
2021-01-24 13:32:18 +01:00
let mut post_order_rank = IndexVec::from_elem_n(0, graph.num_nodes());
// We allocate capacity for the full set of nodes, because most of the time
// most of the nodes *are* reachable.
let mut parent: IndexVec<PreorderIndex, PreorderIndex> =
IndexVec::with_capacity(graph.num_nodes());
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
let mut stack = vec![PreOrderFrame {
pre_order_idx: PreorderIndex::new(0),
iter: graph.successors(graph.start_node()),
}];
let mut pre_order_to_real: IndexVec<PreorderIndex, G::Node> =
IndexVec::with_capacity(graph.num_nodes());
let mut real_to_pre_order: IndexVec<G::Node, Option<PreorderIndex>> =
IndexVec::from_elem_n(None, graph.num_nodes());
pre_order_to_real.push(graph.start_node());
parent.push(PreorderIndex::new(0)); // the parent of the root node is the root for now.
real_to_pre_order[graph.start_node()] = Some(PreorderIndex::new(0));
let mut post_order_idx = 0;
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
'recurse: while let Some(frame) = stack.last_mut() {
while let Some(successor) = frame.iter.next() {
if real_to_pre_order[successor].is_none() {
let pre_order_idx = pre_order_to_real.push(successor);
real_to_pre_order[successor] = Some(pre_order_idx);
parent.push(frame.pre_order_idx);
stack.push(PreOrderFrame { pre_order_idx, iter: graph.successors(successor) });
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
continue 'recurse;
}
}
post_order_rank[pre_order_to_real[frame.pre_order_idx]] = post_order_idx;
post_order_idx += 1;
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
stack.pop();
}
let reachable_vertices = pre_order_to_real.len();
let mut idom = IndexVec::from_elem_n(PreorderIndex::new(0), reachable_vertices);
let mut semi = IndexVec::from_fn_n(std::convert::identity, reachable_vertices);
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
let mut label = semi.clone();
let mut bucket = IndexVec::from_elem_n(vec![], reachable_vertices);
let mut lastlinked = None;
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
for w in (PreorderIndex::new(1)..PreorderIndex::new(reachable_vertices)).rev() {
// Optimization: process buckets just once, at the start of the
// iteration. Do not explicitly empty the bucket (even though it will
// not be used again), to save some instructions.
let z = parent[w];
for &v in bucket[z].iter() {
let y = eval(&mut parent, lastlinked, &semi, &mut label, v);
idom[v] = if semi[y] < z { y } else { z };
}
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
semi[w] = w;
for v in graph.predecessors(pre_order_to_real[w]) {
let v = real_to_pre_order[v].unwrap();
let x = eval(&mut parent, lastlinked, &semi, &mut label, v);
semi[w] = std::cmp::min(semi[w], semi[x]);
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
}
// semi[w] is now semidominator(w).
// Optimization: Do not insert into buckets if parent[w] = semi[w], as
// we then immediately know the idom.
if parent[w] != semi[w] {
bucket[semi[w]].push(w);
} else {
idom[w] = parent[w];
}
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
// Optimization: We share the parent array between processed and not
// processed elements; lastlinked represents the divider.
lastlinked = Some(w);
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
}
for w in PreorderIndex::new(1)..PreorderIndex::new(reachable_vertices) {
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
if idom[w] != semi[w] {
idom[w] = idom[idom[w]];
}
}
let mut immediate_dominators = IndexVec::from_elem_n(None, graph.num_nodes());
for (idx, node) in pre_order_to_real.iter_enumerated() {
immediate_dominators[*node] = Some(pre_order_to_real[idom[idx]]);
}
2019-12-22 17:42:04 -05:00
Dominators { post_order_rank, immediate_dominators }
}
#[inline]
fn eval(
ancestor: &mut IndexVec<PreorderIndex, PreorderIndex>,
lastlinked: Option<PreorderIndex>,
semi: &IndexVec<PreorderIndex, PreorderIndex>,
label: &mut IndexVec<PreorderIndex, PreorderIndex>,
node: PreorderIndex,
) -> PreorderIndex {
if is_processed(node, lastlinked) {
compress(ancestor, lastlinked, semi, label, node);
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
label[node]
} else {
node
}
}
#[inline]
fn is_processed(v: PreorderIndex, lastlinked: Option<PreorderIndex>) -> bool {
if let Some(ll) = lastlinked { v >= ll } else { false }
}
#[inline]
fn compress(
ancestor: &mut IndexVec<PreorderIndex, PreorderIndex>,
lastlinked: Option<PreorderIndex>,
semi: &IndexVec<PreorderIndex, PreorderIndex>,
label: &mut IndexVec<PreorderIndex, PreorderIndex>,
v: PreorderIndex,
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
) {
assert!(is_processed(v, lastlinked));
let u = ancestor[v];
if is_processed(u, lastlinked) {
compress(ancestor, lastlinked, semi, label, u);
if semi[label[u]] < semi[label[v]] {
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
label[v] = label[u];
}
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
ancestor[v] = ancestor[u];
}
Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation with the simple variant of Lengauer-Tarjan, which performs better in the general case. Performance on the keccak benchmark is about equivalent between the two, but we don't see regressions (and indeed see improvements) on other benchmarks, even on a partially optimized implementation. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. Implement the simple Lengauer-Tarjan algorithm This replaces the previous implementation (from #34169), which has not been optimized since, with the simple variant of Lengauer-Tarjan which performs better in the general case. A previous attempt -- not kept in commit history -- attempted a replacement with a bitset-based implementation, but this led to regressions on perf.rust-lang.org benchmarks and equivalent wins for the keccak benchmark, so was rejected. The implementation here follows that of the pseudocode in "Linear-Time Algorithms for Dominators and Related Problems" thesis by Loukas Georgiadis. The next few commits will optimize the implementation as suggested in the thesis. Several related works are cited in the comments within the implementation, as well. On the keccak benchmark, we were previously spending 15% of our cycles computing the NCA / intersect function; this function is quite expensive, especially on modern CPUs, as it chases pointers on every iteration in a tight loop. With this commit, we spend ~0.05% of our time in dominator computation.
2021-05-06 17:24:09 -04:00
}
#[derive(Clone, Debug)]
pub struct Dominators<N: Idx> {
post_order_rank: IndexVec<N, usize>,
immediate_dominators: IndexVec<N, Option<N>>,
}
impl<Node: Idx> Dominators<Node> {
2021-01-17 20:20:16 +01:00
pub fn dummy() -> Self {
Self { post_order_rank: IndexVec::new(), immediate_dominators: IndexVec::new() }
}
pub fn is_reachable(&self, node: Node) -> bool {
self.immediate_dominators[node].is_some()
}
pub fn immediate_dominator(&self, node: Node) -> Node {
assert!(self.is_reachable(node), "node {:?} is not reachable", node);
self.immediate_dominators[node].unwrap()
}
2019-02-09 01:36:22 +09:00
pub fn dominators(&self, node: Node) -> Iter<'_, Node> {
assert!(self.is_reachable(node), "node {:?} is not reachable", node);
2019-12-22 17:42:04 -05:00
Iter { dominators: self, node: Some(node) }
}
pub fn is_dominated_by(&self, node: Node, dom: Node) -> bool {
// FIXME -- could be optimized by using post-order-rank
self.dominators(node).any(|n| n == dom)
}
Updates to experimental coverage counter injection This is a combination of 18 commits. Commit #2: Additional examples and some small improvements. Commit #3: fixed mir-opt non-mir extensions and spanview title elements Corrected a fairly recent assumption in runtest.rs that all MIR dump files end in .mir. (It was appending .mir to the graphviz .dot and spanview .html file names when generating blessed output files. That also left outdated files in the baseline alongside the files with the incorrect names, which I've now removed.) Updated spanview HTML title elements to match their content, replacing a hardcoded and incorrect name that was left in accidentally when originally submitted. Commit #4: added more test examples also improved Makefiles with support for non-zero exit status and to force validation of tests unless a specific test overrides it with a specific comment. Commit #5: Fixed rare issues after testing on real-world crate Commit #6: Addressed PR feedback, and removed temporary -Zexperimental-coverage -Zinstrument-coverage once again supports the latest capabilities of LLVM instrprof coverage instrumentation. Also fixed a bug in spanview. Commit #7: Fix closure handling, add tests for closures and inner items And cleaned up other tests for consistency, and to make it more clear where spans start/end by breaking up lines. Commit #8: renamed "typical" test results "expected" Now that the `llvm-cov show` tests are improved to normally expect matching actuals, and to allow individual tests to override that expectation. Commit #9: test coverage of inline generic struct function Commit #10: Addressed review feedback * Removed unnecessary Unreachable filter. * Replaced a match wildcard with remining variants. * Added more comments to help clarify the role of successors() in the CFG traversal Commit #11: refactoring based on feedback * refactored `fn coverage_spans()`. * changed the way I expand an empty coverage span to improve performance * fixed a typo that I had accidently left in, in visit.rs Commit #12: Optimized use of SourceMap and SourceFile Commit #13: Fixed a regression, and synched with upstream Some generated test file names changed due to some new change upstream. Commit #14: Stripping out crate disambiguators from demangled names These can vary depending on the test platform. Commit #15: Ignore llvm-cov show diff on test with generics, expand IO error message Tests with generics produce llvm-cov show results with demangled names that can include an unstable "crate disambiguator" (hex value). The value changes when run in the Rust CI Windows environment. I added a sed filter to strip them out (in a prior commit), but sed also appears to fail in the same environment. Until I can figure out a workaround, I'm just going to ignore this specific test result. I added a FIXME to follow up later, but it's not that critical. I also saw an error with Windows GNU, but the IO error did not specify a path for the directory or file that triggered the error. I updated the error messages to provide more info for next, time but also noticed some other tests with similar steps did not fail. Looks spurious. Commit #16: Modify rust-demangler to strip disambiguators by default Commit #17: Remove std::process::exit from coverage tests Due to Issue #77553, programs that call std::process::exit() do not generate coverage results on Windows MSVC. Commit #18: fix: test file paths exceeding Windows max path len
2020-09-01 16:15:17 -07:00
/// Provide deterministic ordering of nodes such that, if any two nodes have a dominator
/// relationship, the dominator will always precede the dominated. (The relative ordering
/// of two unrelated nodes will also be consistent, but otherwise the order has no
/// meaning.) This method cannot be used to determine if either Node dominates the other.
pub fn rank_partial_cmp(&self, lhs: Node, rhs: Node) -> Option<Ordering> {
self.post_order_rank[lhs].partial_cmp(&self.post_order_rank[rhs])
}
}
2019-02-09 01:36:22 +09:00
pub struct Iter<'dom, Node: Idx> {
dominators: &'dom Dominators<Node>,
node: Option<Node>,
}
impl<'dom, Node: Idx> Iterator for Iter<'dom, Node> {
type Item = Node;
fn next(&mut self) -> Option<Self::Item> {
if let Some(node) = self.node {
let dom = self.dominators.immediate_dominator(node);
if dom == node {
self.node = None; // reached the root
} else {
self.node = Some(dom);
}
Some(node)
} else {
None
}
}
}