From 1021a0ea618306a42e2b8b22e863692f1506d1e2 Mon Sep 17 00:00:00 2001
From: Vasileios Porpodas <vporpodas@google.com>
Date: Tue, 14 Jan 2025 13:43:37 -0800
Subject: [PATCH] [SandboxVec][Utils] Implement Utils::verifyFunction()

This patch implements a wrapper function for the LLVM IR verifier for functions,
and calls it (flag-guarded) within the bottom-up-vectorizer for finding IR bugs
as soon as they happen.
---
 llvm/include/llvm/SandboxIR/Utils.h            |  9 +++++++++
 .../SandboxVectorizer/Passes/BottomUpVec.cpp   | 18 ++++++++++++++++++
 2 files changed, 27 insertions(+)

diff --git a/llvm/include/llvm/SandboxIR/Utils.h b/llvm/include/llvm/SandboxIR/Utils.h
index d58fe52214395..5c6f0d9edd618 100644
--- a/llvm/include/llvm/SandboxIR/Utils.h
+++ b/llvm/include/llvm/SandboxIR/Utils.h
@@ -17,6 +17,8 @@
 #include "llvm/Analysis/MemoryLocation.h"
 #include "llvm/Analysis/ScalarEvolution.h"
 #include "llvm/Analysis/ValueTracking.h"
+#include "llvm/IR/Verifier.h"
+#include "llvm/SandboxIR/Function.h"
 #include "llvm/SandboxIR/Instruction.h"
 #include <optional>
 
@@ -122,6 +124,13 @@ class Utils {
                              const std::optional<MemoryLocation> &OptLoc) {
     return BatchAA.getModRefInfo(cast<llvm::Instruction>(I->Val), OptLoc);
   }
+
+  /// Equivalent to llvm::verifyFunction().
+  /// \Returns true if the IR is broken.
+  static bool verifyFunction(const Function *F, raw_ostream &OS) {
+    const auto &LLVMF = *cast<llvm::Function>(F->Val);
+    return llvm::verifyFunction(LLVMF, &OS);
+  }
 };
 
 } // namespace llvm::sandboxir
diff --git a/llvm/lib/Transforms/Vectorize/SandboxVectorizer/Passes/BottomUpVec.cpp b/llvm/lib/Transforms/Vectorize/SandboxVectorizer/Passes/BottomUpVec.cpp
index 7cebde335cb4e..b3a477c64a5cc 100644
--- a/llvm/lib/Transforms/Vectorize/SandboxVectorizer/Passes/BottomUpVec.cpp
+++ b/llvm/lib/Transforms/Vectorize/SandboxVectorizer/Passes/BottomUpVec.cpp
@@ -27,6 +27,13 @@ static cl::opt<bool>
     AllowNonPow2("sbvec-allow-non-pow2", cl::init(false), cl::Hidden,
                  cl::desc("Allow non-power-of-2 vectorization."));
 
+#ifndef NDEBUG
+static cl::opt<bool>
+    AlwaysVerify("sbvec-always-verify", cl::init(false), cl::Hidden,
+                 cl::desc("Helps find bugs by verifying the IR whenever we "
+                          "emit new instructions (*very* expensive)."));
+#endif // NDEBUG
+
 namespace sandboxir {
 
 BottomUpVec::BottomUpVec(StringRef Pipeline)
@@ -365,6 +372,17 @@ Value *BottomUpVec::vectorizeRec(ArrayRef<Value *> Bndl,
     break;
   }
   }
+#ifndef NDEBUG
+  if (AlwaysVerify) {
+    // This helps find broken IR by constantly verifying the function. Note that
+    // this is very expensive and should only be used for debugging.
+    Instruction *I0 = isa<Instruction>(Bndl[0])
+                          ? cast<Instruction>(Bndl[0])
+                          : cast<Instruction>(UserBndl[0]);
+    assert(!Utils::verifyFunction(I0->getParent()->getParent(), dbgs()) &&
+           "Broken function!");
+  }
+#endif
   return NewVec;
 }