✨ Add pass and patterns for Classical Control Replacement#1756
Draft
DRovara wants to merge 37 commits into
Draft
✨ Add pass and patterns for Classical Control Replacement#1756DRovara wants to merge 37 commits into
DRovara wants to merge 37 commits into
Conversation
DRovara
added
feature
Collaborator
Author
|
@CodeRabbit full review |
Contributor
✅ Actions performedFull review triggered. |
Contributor
📝 WalkthroughSummary by CodeRabbit
WalkthroughThis PR adds QCO measurement-lifting and classical-control-replacement passes, introduces a boolean constant builder helper, registers new optimization tests, and updates changelog references. ChangesQCO Optimization Passes
Estimated code review effort: 4 (Complex) | ~45 minutes Sequence Diagram(s)sequenceDiagram
participant ModuleOp
participant QCOOptimizationPass
participant RewritePatterns
participant QCOOperations
participant ArithOperations
ModuleOp->>QCOOptimizationPass: run optimization
QCOOptimizationPass->>RewritePatterns: apply patterns greedily
RewritePatterns->>QCOOperations: reorder or replace QCO operations
RewritePatterns->>ArithOperations: create boolean constants and conditions
RewritePatterns-->>ModuleOp: updated QCO module
Possibly related PRs
Suggested reviewers: Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches⚔️ Resolve merge conflicts
✨ Simplify code
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 5
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
mlir/include/mlir/Dialect/QCO/IR/QCOOps.td (1)
1071-1077:⚠️ Potential issue | 🟠 Major | ⚡ Quick winDrop
Purefromqco.ctrl,qco.inv, andqco.if(region wrappers).
Purein MLIR expands toAlwaysSpeculatable+NoMemoryEffect(viaAlwaysSpeculatableImplTrait), which asserts speculatability and no memory effects. These wrapper ops already model their effects viaRecursiveMemoryEffects, so keepingPureoverstates effects independently of what’s inside the nested region. KeepRecursiveMemoryEffects, but removePurefromCtrlOp,InvOp, andIfOp(incl. ranges covering the corresponding defs around 1071-1077, 1150-1154, and 1223-1232).🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@mlir/include/mlir/Dialect/QCO/IR/QCOOps.td` around lines 1071 - 1077, The QCO region wrapper ops declare the Pure trait which expands to AlwaysSpeculatable + NoMemoryEffect and incorrectly duplicates/overrides the region-modelled effects; remove the Pure trait from the op definitions for CtrlOp, InvOp, and IfOp (the TD defs named CtrlOp, InvOp, IfOp) so they only keep RecursiveMemoryEffects (and other existing traits like UnitaryOpInterface, AttrSizedOperandSegments, AttrSizedResultSegments, SameOperandsAndResultType, SameOperandsAndResultShape, SingleBlockImplicitTerminator) to ensure effects are solely driven by the nested region.mlir/lib/Dialect/QCO/Builder/QCOProgramBuilder.cpp (1)
1105-1165:⚠️ Potential issue | 🟠 Major | ⚡ Quick winEnforce the configured
mainreturn signature before finalizing.After
initialize(TypeRange), the no-argfinalize()still hardcodes ani64zero, andfinalize(ValueRange)never checks arity/types againstmain.initialize({})or any non-i64signature now silently builds an invalidfunc.return.Suggested fix
OwningOpRef<ModuleOp> QCOProgramBuilder::finalize() { checkFinalized(); - - auto exitCode = intConstant(0); - return finalize({exitCode}); + func::FuncOp mainFunc = nullptr; + for (auto op : cast<ModuleOp>(module).getOps<func::FuncOp>()) { + if (op.getName() == "main") { + mainFunc = op; + break; + } + } + if (!mainFunc) { + llvm::reportFatalUsageError("Could not find main function"); + } + + auto resultTypes = mainFunc.getFunctionType().getResults(); + if (resultTypes.empty()) { + return finalize({}); + } + if (resultTypes.size() == 1 && resultTypes.front().isSignlessInteger(64)) { + auto exitCode = intConstant(0); + return finalize({exitCode}); + } + llvm::reportFatalUsageError( + "Use finalize(returnValues) when main has custom return types"); } OwningOpRef<ModuleOp> QCOProgramBuilder::finalize(ValueRange returnValues) { checkFinalized(); @@ if (!mainFunc) { llvm::reportFatalUsageError("Could not find main function"); } + + auto resultTypes = mainFunc.getFunctionType().getResults(); + if (returnValues.size() != resultTypes.size()) { + llvm::reportFatalUsageError( + "Return values must match the main function return arity"); + } + for (auto [value, type] : llvm::zip_equal(returnValues, resultTypes)) { + if (value.getType() != type) { + llvm::reportFatalUsageError( + "Return values must match the main function return types"); + } + } @@ func::ReturnOp::create(*this, returnValues);🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@mlir/lib/Dialect/QCO/Builder/QCOProgramBuilder.cpp` around lines 1105 - 1165, The finalize paths currently emit a func::ReturnOp without validating or matching the main function's declared result types (initialize(TypeRange) may set a non-i64 or different arity), so update QCOProgramBuilder::finalize() and QCOProgramBuilder::finalize(ValueRange) to first query mainFunc.getType().getResults(), assert that returnValues.size() equals that result list size and that each returnValues[i].getType() == expectedResults[i], and if the no-arg finalize() is used produce appropriate default constants per expectedResults type (not always an i64 zero) instead of unconditionally calling intConstant(0); then create the func::ReturnOp with validated/matched values (and emit a clear error via llvm::reportFatalUsageError if arity/types mismatch). Ensure references: finalize(), finalize(ValueRange), initialize(TypeRange), func::ReturnOp::create, mainFunc.getType().getResults(), and intConstant are used when implementing the checks and per-type default constant construction.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@CHANGELOG.md`:
- Line 14: Replace the incorrect changelog bullet "✨ Add Dead Gate Elimination
Pattern ([`#1755`]) ([**`@DRovara`**])" with an entry that references this PR
(`#1756`) and accurately describes the implemented feature (measurement lifting /
classical-control replacement), e.g., update the PR number to 1756 and change
the description to mention "Measurement lifting and classical-control
replacement" so the released notes match the actual code changes.
In `@mlir/include/mlir/Dialect/QCO/QCOUtils.h`:
- Around line 240-276: The header's inline function checkAndRemoveDeadGate uses
QCO-specific types (SinkOp, UnitaryOpInterface, MeasureOp, IfOp, Reset) but
doesn't include their declarations, making the header order-dependent; fix by
making the header self-contained: add a direct include of the QCO ops/declaring
header (e.g., include "mlir/Dialect/QCO/QCOOps.h") at the top of
mlir/include/mlir/Dialect/QCO/QCOUtils.h so dyn_cast/isa and method calls
resolve, or alternatively move the implementation of checkAndRemoveDeadGate out
of the header into a .cpp that includes QCOOps.h if you prefer to avoid
additional header dependencies.
In `@mlir/lib/Dialect/QCO/Transforms/Optimizations/ReplaceClassicalControls.cpp`:
- Around line 143-155: The lambda passed to IfOp::create currently always builds
a CtrlOp (via CtrlOp::create) even when newControls (derived from toKeep.size())
is empty, which yields invalid IR because qco::CtrlOp requires >=1 control;
modify the lambda to branch on newControls.empty(): if non-empty, keep the
existing flow (create CtrlOp, inline newCtrl.getRegion() into op.getRegion(),
return newCtrl.getOutputQubits()); if empty, instead directly clone or move the
original unitary body into the IfOp region (use rewriter to inline/clone the
original region/body into the new IfOp region) and return the appropriate output
qubits, ensuring no zero-control CtrlOp is constructed (affects
ReplaceClassicalControls.cpp paths like replaceClassicalControlsOnlyControl and
replaceClassicalControlsTwoOfTwoControls).
- Around line 58-63: The isDiagonal predicate omits RzOp so controlled-rz paths
are not recognized; update the isDiagonal function (the dyn_cast<InvOp> branch
and the isa<> return) to include RzOp among the recognized diagonal ops (i.e.,
add RzOp to the isa<ZOp, SOp, TOp, POp, SdgOp, TdgOp, IdOp> list) so
controlled-`rz` will take the diagonal-swap path.
In
`@mlir/unittests/Dialect/QCO/Transforms/Optimizations/test_qco_replace_classical_controls.cpp`:
- Around line 377-380: Remove the leftover debug printing by deleting the
module->dump() call at the end of the test in
test_qco_replace_classical_controls.cpp; keep the existing assertions
runReplaceClassicalControlsPass(module.get()).succeeded() and
runCanonicalizerPass(reference.get()).succeeded() but remove the module->dump()
line so the test no longer prints the transformed module to CI logs.
---
Outside diff comments:
In `@mlir/include/mlir/Dialect/QCO/IR/QCOOps.td`:
- Around line 1071-1077: The QCO region wrapper ops declare the Pure trait which
expands to AlwaysSpeculatable + NoMemoryEffect and incorrectly
duplicates/overrides the region-modelled effects; remove the Pure trait from the
op definitions for CtrlOp, InvOp, and IfOp (the TD defs named CtrlOp, InvOp,
IfOp) so they only keep RecursiveMemoryEffects (and other existing traits like
UnitaryOpInterface, AttrSizedOperandSegments, AttrSizedResultSegments,
SameOperandsAndResultType, SameOperandsAndResultShape,
SingleBlockImplicitTerminator) to ensure effects are solely driven by the nested
region.
In `@mlir/lib/Dialect/QCO/Builder/QCOProgramBuilder.cpp`:
- Around line 1105-1165: The finalize paths currently emit a func::ReturnOp
without validating or matching the main function's declared result types
(initialize(TypeRange) may set a non-i64 or different arity), so update
QCOProgramBuilder::finalize() and QCOProgramBuilder::finalize(ValueRange) to
first query mainFunc.getType().getResults(), assert that returnValues.size()
equals that result list size and that each returnValues[i].getType() ==
expectedResults[i], and if the no-arg finalize() is used produce appropriate
default constants per expectedResults type (not always an i64 zero) instead of
unconditionally calling intConstant(0); then create the func::ReturnOp with
validated/matched values (and emit a clear error via llvm::reportFatalUsageError
if arity/types mismatch). Ensure references: finalize(), finalize(ValueRange),
initialize(TypeRange), func::ReturnOp::create, mainFunc.getType().getResults(),
and intConstant are used when implementing the checks and per-type default
constant construction.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: 404b26d5-75c2-4dfc-86eb-990ccae1574b
📒 Files selected for processing (17)
CHANGELOG.mdmlir/include/mlir/Dialect/QCO/Builder/QCOProgramBuilder.hmlir/include/mlir/Dialect/QCO/IR/QCODialect.tdmlir/include/mlir/Dialect/QCO/IR/QCOOps.tdmlir/include/mlir/Dialect/QCO/QCOUtils.hmlir/include/mlir/Dialect/QCO/Transforms/Passes.tdmlir/lib/Dialect/QCO/Builder/QCOProgramBuilder.cppmlir/lib/Dialect/QCO/IR/Operations/MeasureOp.cppmlir/lib/Dialect/QCO/IR/Operations/ResetOp.cppmlir/lib/Dialect/QCO/IR/QCOOps.cppmlir/lib/Dialect/QCO/IR/SCF/IfOp.cppmlir/lib/Dialect/QCO/Transforms/Optimizations/MeasurementLifting.cppmlir/lib/Dialect/QCO/Transforms/Optimizations/ReplaceClassicalControls.cppmlir/unittests/Dialect/QCO/IR/test_qco_ir.cppmlir/unittests/Dialect/QCO/Transforms/Optimizations/CMakeLists.txtmlir/unittests/Dialect/QCO/Transforms/Optimizations/test_qco_measurement_lifting.cppmlir/unittests/Dialect/QCO/Transforms/Optimizations/test_qco_replace_classical_controls.cpp
Codecov Report❌ Patch coverage is
📢 Thoughts on this report? Let us know! |
11 tasks
…toolkit/core into mlir/measurement-lifting
DRovara
force-pushed
the
mlir/replace-classical-controls
branch
from
July 14, 2026 04:51
ad1be84 to
febb216
Compare
Collaborator
Author
|
@coderabbitai full review |
Contributor
✅ Action performedFull review finished. |
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In
`@mlir/unittests/Dialect/QCO/Transforms/Optimizations/test_qco_measurement_lifting.cpp`:
- Around line 534-574: Correct the expected module in
dontLiftMeasurementMultipleGatesInControl by keeping the control region before
measuring its control qubit, matching the transformed program’s operation order.
Update the referenceBuilder sequence so r0S0 is passed through ctrl first, then
measure the resulting control state, while preserving the multi-gate z/x control
body and final comparison.
In
`@mlir/unittests/Dialect/QCO/Transforms/Optimizations/test_qco_replace_classical_controls.cpp`:
- Line 137: Remove the const qualifier from the ValueRange parameters in all
five lambdas, including those in the QCO optimization test locations identified
by the symbols or surrounding lambda signatures. Keep the parameter types as
ValueRange and change only the signature qualifiers.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: 74274d8e-01d5-487e-9595-db52fcb37ce0
📒 Files selected for processing (9)
CHANGELOG.mdmlir/include/mlir/Dialect/QCO/Builder/QCOProgramBuilder.hmlir/include/mlir/Dialect/QCO/Transforms/Passes.tdmlir/lib/Dialect/QCO/Builder/QCOProgramBuilder.cppmlir/lib/Dialect/QCO/Transforms/Optimizations/MeasurementLifting.cppmlir/lib/Dialect/QCO/Transforms/Optimizations/ReplaceClassicalControls.cppmlir/unittests/Dialect/QCO/Transforms/Optimizations/CMakeLists.txtmlir/unittests/Dialect/QCO/Transforms/Optimizations/test_qco_measurement_lifting.cppmlir/unittests/Dialect/QCO/Transforms/Optimizations/test_qco_replace_classical_controls.cpp
Comment on lines
+534
to
+574
| TEST_F(QCOMeasurementLiftingTest, dontLiftMeasurementMultipleGatesInControl) { | ||
| programBuilder.initialize( | ||
| {programBuilder.getI1Type(), referenceBuilder.getI1Type()}); | ||
| auto q0S0 = programBuilder.allocQubit(); | ||
| auto q1S0 = programBuilder.allocQubit(); | ||
|
|
||
| auto [q0S1, q1S1] = programBuilder.ctrl({q0S0}, q1S0, [&](Value target) { | ||
| auto t = programBuilder.z(target); | ||
| return programBuilder.x(t); | ||
| }); | ||
|
|
||
| auto [q0S2, c0] = programBuilder.measure(q0S1); | ||
| auto [q1S2, c1] = programBuilder.measure(q1S1); | ||
|
|
||
| programBuilder.sink(q0S2); | ||
| programBuilder.sink(q1S2); | ||
| module = programBuilder.finalize({c0, c1}); | ||
|
|
||
| referenceBuilder.initialize( | ||
| {referenceBuilder.getI1Type(), referenceBuilder.getI1Type()}); | ||
| auto r0S0 = referenceBuilder.allocQubit(); | ||
| auto r1S0 = referenceBuilder.allocQubit(); | ||
|
|
||
| auto [r0S1, cr0] = referenceBuilder.measure(r0S0); | ||
|
|
||
| auto [r0S2, r1S1] = referenceBuilder.ctrl({r0S1}, r1S0, [&](Value target) { | ||
| auto t = referenceBuilder.z(target); | ||
| return referenceBuilder.x(t); | ||
| }); | ||
|
|
||
| auto [r1S2, cr1] = referenceBuilder.measure(r1S1); | ||
|
|
||
| referenceBuilder.sink(r0S2); | ||
| referenceBuilder.sink(r1S2); | ||
| reference = referenceBuilder.finalize({cr0, cr1}); | ||
|
|
||
| ASSERT_TRUE(runMeasurementLiftingPass(module.get()).succeeded()); | ||
| ASSERT_TRUE(runCanonicalizerPass(reference.get()).succeeded()); | ||
|
|
||
| EXPECT_TRUE( | ||
| areModulesEquivalentWithPermutations(module.get(), reference.get())); |
Contributor
There was a problem hiding this comment.
🎯 Functional Correctness | 🟠 Major | ⚡ Quick win
Keep the measurement after the multi-gate control region.
This test says lifting must not occur, but the reference measures r0S0 before ctrl, thereby expecting the forbidden transformation. A correct implementation that leaves the measurement in place will fail this test.
Proposed correction
- auto [r0S1, cr0] = referenceBuilder.measure(r0S0);
-
- auto [r0S2, r1S1] = referenceBuilder.ctrl({r0S1}, r1S0, [&](Value target) {
+ auto [r0S1, r1S1] = referenceBuilder.ctrl({r0S0}, r1S0, [&](Value target) {
auto t = referenceBuilder.z(target);
return referenceBuilder.x(t);
});
+ auto [r0S2, cr0] = referenceBuilder.measure(r0S1);
auto [r1S2, cr1] = referenceBuilder.measure(r1S1);📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| TEST_F(QCOMeasurementLiftingTest, dontLiftMeasurementMultipleGatesInControl) { | |
| programBuilder.initialize( | |
| {programBuilder.getI1Type(), referenceBuilder.getI1Type()}); | |
| auto q0S0 = programBuilder.allocQubit(); | |
| auto q1S0 = programBuilder.allocQubit(); | |
| auto [q0S1, q1S1] = programBuilder.ctrl({q0S0}, q1S0, [&](Value target) { | |
| auto t = programBuilder.z(target); | |
| return programBuilder.x(t); | |
| }); | |
| auto [q0S2, c0] = programBuilder.measure(q0S1); | |
| auto [q1S2, c1] = programBuilder.measure(q1S1); | |
| programBuilder.sink(q0S2); | |
| programBuilder.sink(q1S2); | |
| module = programBuilder.finalize({c0, c1}); | |
| referenceBuilder.initialize( | |
| {referenceBuilder.getI1Type(), referenceBuilder.getI1Type()}); | |
| auto r0S0 = referenceBuilder.allocQubit(); | |
| auto r1S0 = referenceBuilder.allocQubit(); | |
| auto [r0S1, cr0] = referenceBuilder.measure(r0S0); | |
| auto [r0S2, r1S1] = referenceBuilder.ctrl({r0S1}, r1S0, [&](Value target) { | |
| auto t = referenceBuilder.z(target); | |
| return referenceBuilder.x(t); | |
| }); | |
| auto [r1S2, cr1] = referenceBuilder.measure(r1S1); | |
| referenceBuilder.sink(r0S2); | |
| referenceBuilder.sink(r1S2); | |
| reference = referenceBuilder.finalize({cr0, cr1}); | |
| ASSERT_TRUE(runMeasurementLiftingPass(module.get()).succeeded()); | |
| ASSERT_TRUE(runCanonicalizerPass(reference.get()).succeeded()); | |
| EXPECT_TRUE( | |
| areModulesEquivalentWithPermutations(module.get(), reference.get())); | |
| TEST_F(QCOMeasurementLiftingTest, dontLiftMeasurementMultipleGatesInControl) { | |
| programBuilder.initialize( | |
| {programBuilder.getI1Type(), referenceBuilder.getI1Type()}); | |
| auto q0S0 = programBuilder.allocQubit(); | |
| auto q1S0 = programBuilder.allocQubit(); | |
| auto [q0S1, q1S1] = programBuilder.ctrl({q0S0}, q1S0, [&](Value target) { | |
| auto t = programBuilder.z(target); | |
| return programBuilder.x(t); | |
| }); | |
| auto [q0S2, c0] = programBuilder.measure(q0S1); | |
| auto [q1S2, c1] = programBuilder.measure(q1S1); | |
| programBuilder.sink(q0S2); | |
| programBuilder.sink(q1S2); | |
| module = programBuilder.finalize({c0, c1}); | |
| referenceBuilder.initialize( | |
| {referenceBuilder.getI1Type(), referenceBuilder.getI1Type()}); | |
| auto r0S0 = referenceBuilder.allocQubit(); | |
| auto r1S0 = referenceBuilder.allocQubit(); | |
| auto [r0S1, r1S1] = referenceBuilder.ctrl({r0S0}, r1S0, [&](Value target) { | |
| auto t = referenceBuilder.z(target); | |
| return referenceBuilder.x(t); | |
| }); | |
| auto [r0S2, cr0] = referenceBuilder.measure(r0S1); | |
| auto [r1S2, cr1] = referenceBuilder.measure(r1S1); | |
| referenceBuilder.sink(r0S2); | |
| referenceBuilder.sink(r1S2); | |
| reference = referenceBuilder.finalize({cr0, cr1}); | |
| ASSERT_TRUE(runMeasurementLiftingPass(module.get()).succeeded()); | |
| ASSERT_TRUE(runCanonicalizerPass(reference.get()).succeeded()); | |
| EXPECT_TRUE( | |
| areModulesEquivalentWithPermutations(module.get(), reference.get())); | |
| } |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In
`@mlir/unittests/Dialect/QCO/Transforms/Optimizations/test_qco_measurement_lifting.cpp`
around lines 534 - 574, Correct the expected module in
dontLiftMeasurementMultipleGatesInControl by keeping the control region before
measuring its control qubit, matching the transformed program’s operation order.
Update the referenceBuilder sequence so r0S0 is passed through ctrl first, then
measure the resulting control state, while preserving the multi-gate z/x control
body and final comparison.
|
|
||
| auto [q01S1, q2S1] = | ||
| programBuilder.ctrl({q0S1, q1S0}, {q2S0}, | ||
| [&](const ValueRange targets) -> SmallVector<Value> { |
Contributor
There was a problem hiding this comment.
📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick win
Remove const from the ValueRange parameters.
Core MLIR handle types should not be const-qualified in signatures.
Proposed fix
- [&](const ValueRange targets) -> SmallVector<Value> {
+ [&](ValueRange targets) -> SmallVector<Value> {Apply this replacement at all five locations.
Based on learnings, avoid const qualifiers on core MLIR types in function and lambda signatures.
Also applies to: 193-193, 251-251, 395-395, 446-446
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In
`@mlir/unittests/Dialect/QCO/Transforms/Optimizations/test_qco_replace_classical_controls.cpp`
at line 137, Remove the const qualifier from the ValueRange parameters in all
five lambdas, including those in the QCO optimization test locations identified
by the symbols or surrounding lambda signatures. Keep the parameter types as
ValueRange and change only the signature qualifiers.
Source: Learnings
Signed-off-by: Damian Rovara <93778306+DRovara@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Part 2 out of 3 of the Qubit Reuse Implementation
This PR ports the previous implementation of the Classical Control Replacement pass to the new dialect infrastructure.
This path has the goal of replacing controlled gates with "classically controlled gates" whenever a classical value for the control qubit is available because it has just been measured.
In those cases, we remove the control from the
CtrlOpand instead introduce aqco.ifOp.This is one of 3 PRs that will, in total, constitute qubit reuse:
Requires #1705 to be merged first.
AI Notice: Gemini 3.1 and Claude Sonnet 4.6 were used for the generation of some code.
Checklist
If PR contains AI-assisted content:
Assisted-by: [Model Name] via [Tool Name]footer.