LoopInfo: introduce Loop::getLocStr; unify debug output

llvm/include/llvm/Analysis/LoopInfo.h

@@ -385,6 +385,11 @@ class LLVM_EXTERNAL_VISIBILITY Loop : public LoopBase<BasicBlock, Loop> {
   /// Return the source code span of the loop.
   LocRange getLocRange() const;
 
+  /// Return a string containing the location of the loop (file name + line
+  /// number if present, otherwise module name). Meant to be used for debug
+  /// printing within LLVM_DEBUG.
+  std::string getLocStr() const;
+
   StringRef getName() const {
     if (BasicBlock *Header = getHeader())
       if (Header->hasName())
@@ -690,7 +695,6 @@ llvm::MDNode *
 makePostTransformationMetadata(llvm::LLVMContext &Context, MDNode *OrigLoopID,
                                llvm::ArrayRef<llvm::StringRef> RemovePrefixes,
                                llvm::ArrayRef<llvm::MDNode *> AddAttrs);
-
 } // namespace llvm
 
 #endif

llvm/lib/Analysis/LoopAccessAnalysis.cpp

@@ -2374,9 +2374,9 @@ void MemoryDepChecker::Dependence::print(
 
 bool LoopAccessInfo::canAnalyzeLoop() {
   // We need to have a loop header.
-  LLVM_DEBUG(dbgs() << "LAA: Found a loop in "
-                    << TheLoop->getHeader()->getParent()->getName() << ": "
-                    << TheLoop->getHeader()->getName() << '\n');
+  LLVM_DEBUG(dbgs() << "\nLAA: Checking a loop in '"
+                    << TheLoop->getHeader()->getParent()->getName() << "' from "
+                    << TheLoop->getLocStr() << "\n");
 
   // We can only analyze innermost loops.
   if (!TheLoop->isInnermost()) {
@@ -2403,6 +2403,8 @@ bool LoopAccessInfo::canAnalyzeLoop() {
     return false;
   }
 
+  LLVM_DEBUG(dbgs() << "LAA: Found a loop: " << TheLoop->getHeader()->getName()
+                    << "\n");
   return true;
 }
 

llvm/lib/Analysis/LoopInfo.cpp

@@ -663,6 +663,17 @@ Loop::LocRange Loop::getLocRange() const {
   return LocRange();
 }
 
+std::string Loop::getLocStr() const {
+  std::string Result;
+  raw_string_ostream OS(Result);
+  if (const DebugLoc LoopDbgLoc = getStartLoc())
+    LoopDbgLoc.print(OS);
+  else
+    // Just print the module name.
+    OS << getHeader()->getParent()->getParent()->getModuleIdentifier();
+  return Result;
+}
+
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
 LLVM_DUMP_METHOD void Loop::dump() const { print(dbgs()); }
 

llvm/lib/Transforms/Scalar/LoopDistribute.cpp

@@ -659,9 +659,9 @@ class LoopDistributeForLoop {
   bool processLoop() {
     assert(L->isInnermost() && "Only process inner loops.");
 
-    LLVM_DEBUG(dbgs() << "\nLDist: In \""
-                      << L->getHeader()->getParent()->getName()
-                      << "\" checking " << *L << "\n");
+    LLVM_DEBUG(dbgs() << "\nLDist: Checking a loop in '"
+                      << L->getHeader()->getParent()->getName() << "' from "
+                      << L->getLocStr() << "\n");
 
     // Having a single exit block implies there's also one exiting block.
     if (!L->getExitBlock())
@@ -686,6 +686,9 @@ class LoopDistributeForLoop {
     if (!Dependences || Dependences->empty())
       return fail("NoUnsafeDeps", "no unsafe dependences to isolate");
 
+    LLVM_DEBUG(dbgs() << "LDist: Found a loop: " << L->getHeader()->getName()
+                      << "\n");
+
     InstPartitionContainer Partitions(L, LI, DT);
 
     // First, go through each memory operation and assign them to consecutive

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -1027,23 +1027,6 @@ static void reportVectorization(OptimizationRemarkEmitter *ORE, Loop *TheLoop,
 
 } // end namespace llvm
 
-#ifndef NDEBUG
-/// \return string containing a file name and a line # for the given loop.
-static std::string getDebugLocString(const Loop *L) {
-  std::string Result;
-  if (L) {
-    raw_string_ostream OS(Result);
-    if (const DebugLoc LoopDbgLoc = L->getStartLoc())
-      LoopDbgLoc.print(OS);
-    else
-      // Just print the module name.
-      OS << L->getHeader()->getParent()->getParent()->getModuleIdentifier();
-    OS.flush();
-  }
-  return Result;
-}
-#endif
-
 namespace llvm {
 
 // Loop vectorization cost-model hints how the scalar epilogue loop should be
@@ -9836,13 +9819,9 @@ bool LoopVectorizePass::processLoop(Loop *L) {
   assert((EnableVPlanNativePath || L->isInnermost()) &&
          "VPlan-native path is not enabled. Only process inner loops.");
 
-#ifndef NDEBUG
-  const std::string DebugLocStr = getDebugLocString(L);
-#endif /* NDEBUG */
-
   LLVM_DEBUG(dbgs() << "\nLV: Checking a loop in '"
                     << L->getHeader()->getParent()->getName() << "' from "
-                    << DebugLocStr << "\n");
+                    << L->getLocStr() << "\n");
 
   LoopVectorizeHints Hints(L, InterleaveOnlyWhenForced, *ORE, TTI);
 
@@ -10112,15 +10091,15 @@ bool LoopVectorizePass::processLoop(Loop *L) {
     });
   } else if (VectorizeLoop && !InterleaveLoop) {
     LLVM_DEBUG(dbgs() << "LV: Found a vectorizable loop (" << VF.Width
-                      << ") in " << DebugLocStr << '\n');
+                      << ") in " << L->getLocStr() << '\n');
     ORE->emit([&]() {
       return OptimizationRemarkAnalysis(LV_NAME, IntDiagMsg.first,
                                         L->getStartLoc(), L->getHeader())
              << IntDiagMsg.second;
     });
   } else if (VectorizeLoop && InterleaveLoop) {
     LLVM_DEBUG(dbgs() << "LV: Found a vectorizable loop (" << VF.Width
-                      << ") in " << DebugLocStr << '\n');
+                      << ") in " << L->getLocStr() << '\n');
     LLVM_DEBUG(dbgs() << "LV: Interleave Count is " << IC << '\n');
   }
 

llvm/test/Analysis/LoopAccessAnalysis/print-order.ll

@@ -6,7 +6,8 @@
 ;    A[i+1] = A[i] + 1;
 ; }
 
-; CHECK: LAA: Found a loop in negative_step: loop
+; CHECK-LABEL: 'negative_step'
+; CHECK: LAA: Found a loop: loop
 ; CHECK: LAA: Checking memory dependencies
 ; CHECK-NEXT: LAA: Src Scev: {(4092 + %A),+,-4}<nw><%loop>Sink Scev: {(4088 + %A)<nuw>,+,-4}<nw><%loop>(Induction step: -1)
 ; CHECK-NEXT: LAA: Distance for   store i32 %add, ptr %gep.A.plus.1, align 4 to   %l = load i32, ptr %gep.A, align 4: -4
@@ -37,7 +38,8 @@ exit:
 ;    A[i-1] = A[i] + 1;
 ; }
 
-; CHECK: LAA: Found a loop in positive_step: loop
+; CHECK-LABEL: 'positive_step'
+; CHECK: LAA: Found a loop: loop
 ; CHECK: LAA: Checking memory dependencies
 ; CHECK-NEXT: LAA: Src Scev: {(4 + %A)<nuw>,+,4}<nuw><%loop>Sink Scev: {%A,+,4}<nw><%loop>(Induction step: 1)
 ; CHECK-NEXT: LAA: Distance for   %l = load i32, ptr %gep.A, align 4 to   store i32 %add, ptr %gep.A.minus.1, align 4: -4

llvm/test/Analysis/LoopAccessAnalysis/scalable-vector-regression-tests.ll

@@ -24,7 +24,8 @@ loop.end:
   ret void
 }
 
-; CHECK-LABEL: LAA: Found a loop in regression_test_loop_access_scalable_typesize
+; CHECK-LABEL: 'regression_test_loop_access_scalable_typesize'
+; CHECK: LAA: Found a loop: vector.body
 ; CHECK: LAA: Bad stride - Scalable object:
 define void @regression_test_loop_access_scalable_typesize(ptr %input_ptr) {
 entry:
@@ -42,7 +43,8 @@ end:
   ret void
 }
 
-; CHECK-LABEL: LAA: Found a loop in regression_test_loop_access_scalable_typesize_nonscalable_object
+; CHECK-LABEL: 'regression_test_loop_access_scalable_typesize_nonscalable_object'
+; CHECK: LAA: Found a loop: vector.body
 ; CHECK: LAA: Bad stride - Scalable object:
 define void @regression_test_loop_access_scalable_typesize_nonscalable_object(ptr %input_ptr) {
 entry:

llvm/test/Transforms/LoopDistribute/debug-print.ll

@@ -0,0 +1,43 @@
+; RUN: opt -passes=loop-distribute -enable-loop-distribute \
+; RUN:   -debug-only=loop-distribute -disable-output 2>&1 %s | FileCheck %s
+
+define void @f(ptr noalias %a, ptr noalias %b, ptr noalias %c, ptr noalias %d, i64 %stride) {
+; CHECK-LABEL: 'f'
+; CHECK:        LDist: Found a loop: for.body
+; CHECK:        Backward dependences:
+; CHECK-NEXT:     Backward:
+; CHECK-NEXT:         %load.a = load i32, ptr %gep.a, align 4 ->
+; CHECK-NEXT:         store i32 %mul.a, ptr %gep.a.plus4, align 4
+; CHECK:        Seeded partitions:
+; CHECK:        Partition 0
+; CHECK:        Partition 1
+; CHECK:        Partition 2
+; CHECK:        Partition 3
+; CHECK:        Distributing loop
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
+  %gep.a = getelementptr inbounds i32, ptr %a, i64 %ind
+  %load.a = load i32, ptr %gep.a, align 4
+  %gep.b = getelementptr inbounds i32, ptr %b, i64 %ind
+  %load.b = load i32, ptr %gep.b, align 4
+  %mul.a = mul i32 %load.b, %load.a
+  %add = add nuw nsw i64 %ind, 1
+  %gep.a.plus4 = getelementptr inbounds i32, ptr %a, i64 %add
+  store i32 %mul.a, ptr %gep.a.plus4, align 4
+  %gep.d = getelementptr inbounds i32, ptr %d, i64 %ind
+  %loadD = load i32, ptr %gep.d, align 4
+  %mul = mul i64 %ind, %stride
+  %gep.strided.a = getelementptr inbounds i32, ptr %a, i64 %mul
+  %load.strided.a = load i32, ptr %gep.strided.a, align 4
+  %mul.c = mul i32 %loadD, %load.strided.a
+  %gep.c = getelementptr inbounds i32, ptr %c, i64 %ind
+  store i32 %mul.c, ptr %gep.c, align 4
+  %exitcond = icmp eq i64 %add, 20
+  br i1 %exitcond, label %exit, label %for.body
+
+exit:                                             ; preds = %for.body
+  ret void
+}

llvm/test/Transforms/LoopVectorize/ARM/mve-hoist-runtime-checks.ll

@@ -18,7 +18,8 @@ target triple = "thumbv8.1m.main-none-unknown-eabi"
 ; NOTE: The strides of the starting address values in the inner loop differ, i.e.
 ; '(i * (n + 1))' vs '(i * n)'.
 
-; DEBUG-LABEL: LAA: Found a loop in diff_checks:
+; DEBUG-LABEL: 'diff_checks'
+; DEBUG:      LAA: Found a loop: inner.loop
 ; DEBUG:      LAA: Not creating diff runtime check, since these  cannot be hoisted out of the outer loop
 ; DEBUG:      LAA: Adding RT check for range:
 ; DEBUG-NEXT: LAA: Expanded RT check for range to include outer loop in order to permit hoisting

llvm/test/Transforms/LoopVectorize/runtime-checks-hoist.ll

@@ -17,7 +17,8 @@ target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
 ; NOTE: The strides of the starting address values in the inner loop differ, i.e.
 ; '(i * (n + 1))' vs '(i * n)'.
 
-; DEBUG-LABEL: LAA: Found a loop in diff_checks:
+; DEBUG-LABEL: 'diff_checks'
+; DEBUG:      LAA: Found a loop: inner.loop
 ; DEBUG:      LAA: Not creating diff runtime check, since these  cannot be hoisted out of the outer loop
 ; DEBUG:      LAA: Adding RT check for range:
 ; DEBUG-NEXT: LAA: Expanded RT check for range to include outer loop in order to permit hoisting
@@ -149,7 +150,8 @@ outer.exit:
 ; We decide to do full runtime checks here (as opposed to diff checks) due to
 ; the additional load of 'dst[(i * n) + j]' in the loop.
 
-; DEBUG-LABEL: LAA: Found a loop in full_checks:
+; DEBUG-LABEL: 'full_checks'
+; DEBUG: LAA: Found a loop: inner.loop
 ; DEBUG-NOT: LAA: Creating diff runtime check for:
 ; DEBUG: LAA: Adding RT check for range:
 ; DEBUG-NEXT: LAA: Expanded RT check for range to include outer loop in order to permit hoisting
@@ -272,7 +274,8 @@ outer.exit:
 ; is accessed with a higher stride compared src, and therefore the inner loop
 ; runtime checks will vary for each outer loop iteration.
 
-; DEBUG-LABEL: LAA: Found a loop in full_checks_diff_strides:
+; DEBUG-LABEL: 'full_checks_diff_strides'
+; DEBUG: LAA: Found a loop: inner.loop
 ; DEBUG-NOT: LAA: Creating diff runtime check for:
 ; DEBUG: LAA: Adding RT check for range:
 ; DEBUG-NEXT: LAA: Expanded RT check for range to include outer loop in order to permit hoisting
@@ -402,7 +405,8 @@ outer.exit:
 ;   }
 ; }
 
-; DEBUG-LABEL: LAA: Found a loop in diff_checks_src_start_invariant:
+; DEBUG-LABEL: 'diff_checks_src_start_invariant'
+; DEBUG: LAA: Found a loop: inner.loop
 ; DEBUG-NOT: LAA: Expanded RT check for range to include outer loop in order to permit hoisting
 
 define void @diff_checks_src_start_invariant(ptr nocapture noundef writeonly %dst, ptr nocapture noundef readonly %src, i32 noundef %m, i32 noundef %n) {
@@ -508,7 +512,8 @@ outer.loop.exit:
 ;   }
 ; }
 
-; DEBUG-LABEL: LAA: Found a loop in full_checks_src_start_invariant:
+; DEBUG-LABEL: 'full_checks_src_start_invariant'
+; DEBUG:      LAA: Found a loop: inner.loop
 ; DEBUG:      LAA: Adding RT check for range:
 ; DEBUG-NEXT: LAA: Expanded RT check for range to include outer loop in order to permit hoisting
 ; DEBUG-NEXT: Start: %dst End: ((4 * (zext i32 %m to i64) * (zext i32 %n to i64)) + %dst)
@@ -629,7 +634,8 @@ outer.loop.exit:
 ; The 'src' access varies with the outermost loop, rather than the parent of the
 ; innermost loop. Hence we don't expand `src`, although in theory we could do.
 
-; DEBUG-LABEL: LAA: Found a loop in triple_nested_loop_mixed_access:
+; DEBUG-LABEL: 'triple_nested_loop_mixed_access'
+; DEBUG:      LAA: Found a loop: inner.loop
 ; DEBUG-NOT:  LAA: Creating diff runtime check for:
 ; DEBUG:      LAA: Adding RT check for range:
 ; DEBUG-NEXT: LAA: Expanded RT check for range to include outer loop in order to permit hoisting
@@ -795,7 +801,8 @@ exit:
 ; }
 ; Outer loop trip count is uncomputable so we shouldn't expand the ranges.
 
-; DEBUG-LABEL: LAA: Found a loop in uncomputable_outer_tc:
+; DEBUG-LABEL: 'uncomputable_outer_tc'
+; DEBUG:      LAA: Found a loop: inner.loop
 ; DEBUG:      LAA: Adding RT check for range:
 ; DEBUG-NEXT: Start: {%dst,+,(4 * (zext i32 (1 + %n) to i64))<nuw><nsw>}<%outer.loop> End: {((4 * (zext i32 %n to i64))<nuw><nsw> + %dst),+,(4 * (zext i32 (1 + %n) to i64))<nuw><nsw>}<%outer.loop>
 ; DEBUG-NEXT: LAA: Adding RT check for range:
@@ -945,7 +952,8 @@ while.end:
 ; Inner IV is decreasing, but this isn't a problem and we can still expand the
 ; runtime checks correctly to cover the whole loop.
 
-; DEBUG-LABEL: LAA: Found a loop in decreasing_inner_iv:
+; DEBUG-LABEL: 'decreasing_inner_iv'
+; DEBUG:      LAA: Found a loop: inner.loop
 ; DEBUG:      LAA: Adding RT check for range:
 ; DEBUG-NEXT: LAA: Expanded RT check for range to include outer loop in order to permit hoisting
 ; DEBUG-NEXT: LAA: ... but need to check stride is positive: (4 * (sext i32 %stride1 to i64))<nsw>
@@ -1111,7 +1119,8 @@ exit:
 ; Outer IV is decreasing, but the direction of memory accesses also depends
 ; upon the signedness of stride1.
 
-; DEBUG-LABEL: LAA: Found a loop in decreasing_outer_iv:
+; DEBUG-LABEL: 'decreasing_outer_iv'
+; DEBUG:      LAA: Found a loop: inner.loop
 ; DEBUG:      LAA: Adding RT check for range:
 ; DEBUG-NEXT: LAA: Expanded RT check for range to include outer loop in order to permit hoisting
 ; DEBUG-NEXT: LAA: ... but need to check stride is positive: (-4 * (sext i32 %stride1 to i64))<nsw>
@@ -1271,7 +1280,8 @@ exit:
 ; }
 
 
-; DEBUG-LABEL: LAA: Found a loop in unknown_inner_stride:
+; DEBUG-LABEL: 'unknown_inner_stride'
+; DEBUG:      LAA: Found a loop: inner.loop
 ; DEBUG:      LAA: Adding RT check for range:
 ; DEBUG-NEXT: LAA: Expanded RT check for range to include outer loop in order to permit hoisting
 ; DEBUG-NEXT: Start: %dst End: ((4 * (zext i32 %n to i64))<nuw><nsw> + (4 * (zext i32 (1 + %n) to i64) * (-1 + (zext i32 %m to i64))<nsw>) + %dst)