[llvm-branch-commits] [clang] [KeyInstr][Clang] For stmt atom (PR #134646)

[Orlando Cazalet-Hyams via llvm-branch-commits]

https://github.com/OCHyams created https://github.com/llvm/llvm-project/pull/134646

This patch is part of a stack that teaches Clang to generate Key Instructions
metadata for C and C++.

The Key Instructions project is introduced, including a "quick summary" section
at the top which adds context for this PR, here:
https://discourse.llvm.org/t/rfc-improving-is-stmt-placement-for-better-interactive-debugging/82668

The feature is only functional in LLVM if LLVM is built with CMake flag
LLVM_EXPERIMENTAL_KEY_INSTRUCTIONs. Eventually that flag will be removed.

The Clang-side work is demoed here:
https://github.com/llvm/llvm-project/pull/130943

>From 375ca9f7b756d01da82772f9316ab20b56214d91 Mon Sep 17 00:00:00 2001
From: Orlando Cazalet-Hyams <orlando.hyams at sony.com>
Date: Thu, 3 Apr 2025 19:12:47 +0100
Subject: [PATCH] [KeyInstr][Clang] For stmt atom

This patch is part of a stack that teaches Clang to generate Key Instructions
metadata for C and C++.

The Key Instructions project is introduced, including a "quick summary" section
at the top which adds context for this PR, here:
https://discourse.llvm.org/t/rfc-improving-is-stmt-placement-for-better-interactive-debugging/82668

The feature is only functional in LLVM if LLVM is built with CMake flag
LLVM_EXPERIMENTAL_KEY_INSTRUCTIONs. Eventually that flag will be removed.

The Clang-side work is demoed here:
https://github.com/llvm/llvm-project/pull/130943
---
 clang/lib/CodeGen/CGStmt.cpp     | 18 ++++++++++++++--
 clang/test/KeyInstructions/for.c | 37 ++++++++++++++++++++++++++++++++
 2 files changed, 53 insertions(+), 2 deletions(-)
 create mode 100644 clang/test/KeyInstructions/for.c

diff --git a/clang/lib/CodeGen/CGStmt.cpp b/clang/lib/CodeGen/CGStmt.cpp
index d9fd406ad64ee..65b71c39d86c4 100644
--- a/clang/lib/CodeGen/CGStmt.cpp
+++ b/clang/lib/CodeGen/CGStmt.cpp
@@ -1324,6 +1324,7 @@ void CodeGenFunction::EmitForStmt(const ForStmt &S,
     Continue = getJumpDestInCurrentScope("for.inc");
   BreakContinueStack.push_back(BreakContinue(LoopExit, Continue));
 
+  llvm::BasicBlock *ForBody = nullptr;
   if (S.getCond()) {
     // If the for statement has a condition scope, emit the local variable
     // declaration.
@@ -1348,7 +1349,7 @@ void CodeGenFunction::EmitForStmt(const ForStmt &S,
       ExitBlock = createBasicBlock("for.cond.cleanup");
 
     // As long as the condition is true, iterate the loop.
-    llvm::BasicBlock *ForBody = createBasicBlock("for.body");
+    ForBody = createBasicBlock("for.body");
 
     // C99 6.8.5p2/p4: The first substatement is executed if the expression
     // compares unequal to 0.  The condition must be a scalar type.
@@ -1362,7 +1363,14 @@ void CodeGenFunction::EmitForStmt(const ForStmt &S,
       BoolCondVal = emitCondLikelihoodViaExpectIntrinsic(
           BoolCondVal, Stmt::getLikelihood(S.getBody()));
 
-    Builder.CreateCondBr(BoolCondVal, ForBody, ExitBlock, Weights);
+    auto *I = Builder.CreateCondBr(BoolCondVal, ForBody, ExitBlock, Weights);
+    // Key Instructions: Emit the condition and branch as separate atoms to
+    // match existing loop stepping behaviour. FIXME: We could have the branch
+    // as the backup location for the condition, which would probably be a
+    // better experience (no jumping to the brace).
+    if (auto *I = dyn_cast<llvm::Instruction>(BoolCondVal))
+      addInstToNewSourceAtom(I, nullptr);
+    addInstToNewSourceAtom(I, nullptr);
 
     if (ExitBlock != LoopExit.getBlock()) {
       EmitBlock(ExitBlock);
@@ -1416,6 +1424,12 @@ void CodeGenFunction::EmitForStmt(const ForStmt &S,
 
   if (CGM.shouldEmitConvergenceTokens())
     ConvergenceTokenStack.pop_back();
+
+  if (ForBody) {
+    // Key Instructions: We want the for closing brace to be step-able on to
+    // match existing behaviour.
+    addInstToNewSourceAtom(ForBody->getTerminator(), nullptr);
+  }
 }
 
 void
diff --git a/clang/test/KeyInstructions/for.c b/clang/test/KeyInstructions/for.c
new file mode 100644
index 0000000000000..3221ece69a717
--- /dev/null
+++ b/clang/test/KeyInstructions/for.c
@@ -0,0 +1,37 @@
+// RUN: %clang -gkey-instructions -x c++ %s -gmlt -S -emit-llvm -o - \
+// RUN: | FileCheck %s --implicit-check-not atomGroup --implicit-check-not atomRank
+
+// RUN: %clang -gkey-instructions -x c %s -gmlt -S -emit-llvm -o -  \
+// RUN: | FileCheck %s --implicit-check-not atomGroup --implicit-check-not atomRank
+
+// Perennial quesiton: should the inc be its own source atom or not
+// (currently it is).
+
+// FIXME: See do.c and while.c regarding cmp and cond br groups.
+
+void a(int A) {
+// CHECK: entry:
+// CHECK: store i32 0, ptr %i{{.*}}, !dbg [[G1R1:!.*]]
+// CHECK: for.cond:
+// CHECK: %cmp = icmp slt i32 %0, %1, !dbg [[G2R1:!.*]]
+// CHECK: br i1 %cmp, label %for.body, label %for.end, !dbg [[G3R1:!.*]]
+
+// FIXME: Added uncond br group here which is useful for O0, which we're
+// no longer targeting. With optimisations loop rotate puts the condition
+// into for.inc and simplifycfg smooshes that and for.body together, so
+// it's not clear whether it adds any value.
+// CHECK: for.body:
+// CHECK: br label %for.inc, !dbg [[G5R1:!.*]]
+
+// CHECK: for.inc:
+// CHECK: %inc = add{{.*}}, !dbg [[G4R2:!.*]]
+// CHECK: store i32 %inc, ptr %i{{.*}}, !dbg [[G4R1:!.*]]
+    for (int i = 0; i < A; ++i) { }
+}
+
+// CHECK: [[G1R1]] = !DILocation({{.*}}, atomGroup: 1, atomRank: 1)
+// CHECK: [[G2R1]] = !DILocation({{.*}}, atomGroup: 2, atomRank: 1)
+// CHECK: [[G3R1]] = !DILocation({{.*}}, atomGroup: 3, atomRank: 1)
+// CHECK: [[G5R1]] = !DILocation({{.*}}, atomGroup: 5, atomRank: 1)
+// CHECK: [[G4R2]] = !DILocation({{.*}}, atomGroup: 4, atomRank: 2)
+// CHECK: [[G4R1]] = !DILocation({{.*}}, atomGroup: 4, atomRank: 1)