[llvm] [LoopInterchange] Bail out early if minimum loop nest is not met (PR #115128)

[Madhur Amilkanthwar via llvm-commits]

https://github.com/madhur13490 updated https://github.com/llvm/llvm-project/pull/115128

>From 347b15832d4e1d44170a5b357c5bf8fe5eb10edb Mon Sep 17 00:00:00 2001
From: Madhur Amilkanthwar <madhura at nvidia.com>
Date: Mon, 4 Nov 2024 15:37:51 +0530
Subject: [PATCH] [LoopInterchange] Bail out early if minimum loop nest is not
 met

This patch bails out early if minimum depth
is not met. As it stands today, the pass computes
CacheCost before it attempts to do the transform.
This is not needed if minimum depth is not met.
This handles basic cases where depth is typically 1.

As the patch avoids unnecessary computation, it is aimed
to improve compile-time.
---
 .../lib/Transforms/Scalar/LoopInterchange.cpp | 22 +++++--
 .../LoopInterchange/bail-out-one-loop.ll      | 65 +++++++++++++++++++
 2 files changed, 83 insertions(+), 4 deletions(-)
 create mode 100644 llvm/test/Transforms/LoopInterchange/bail-out-one-loop.ll

diff --git a/llvm/lib/Transforms/Scalar/LoopInterchange.cpp b/llvm/lib/Transforms/Scalar/LoopInterchange.cpp
index db63bda1e6b926..80b6c0132d1ba2 100644
--- a/llvm/lib/Transforms/Scalar/LoopInterchange.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopInterchange.cpp
@@ -234,6 +234,14 @@ static void populateWorklist(Loop &L, LoopVector &LoopList) {
   LoopList.push_back(CurrentLoop);
 }
 
+static bool hasMinimumLoopDepth(SmallVectorImpl<Loop *> &LoopList) {
+  unsigned LoopNestDepth = LoopList.size();
+  if (LoopNestDepth < 2) {
+    LLVM_DEBUG(dbgs() << "Loop doesn't contain minimum nesting level.\n");
+    return false;
+  }
+  return true;
+}
 namespace {
 
 /// LoopInterchangeLegality checks if it is legal to interchange the loop.
@@ -416,11 +424,11 @@ struct LoopInterchange {
 
   bool processLoopList(SmallVectorImpl<Loop *> &LoopList) {
     bool Changed = false;
-    unsigned LoopNestDepth = LoopList.size();
-    if (LoopNestDepth < 2) {
-      LLVM_DEBUG(dbgs() << "Loop doesn't contain minimum nesting level.\n");
+
+    if (!hasMinimumLoopDepth(LoopList))
       return false;
-    }
+
+    unsigned LoopNestDepth = LoopList.size();
     if (LoopNestDepth > MaxLoopNestDepth) {
       LLVM_DEBUG(dbgs() << "Cannot handle loops of depth greater than "
                         << MaxLoopNestDepth << "\n");
@@ -1713,6 +1721,12 @@ PreservedAnalyses LoopInterchangePass::run(LoopNest &LN,
                                            LPMUpdater &U) {
   Function &F = *LN.getParent();
 
+  SmallVector<Loop *, 8> LoopList(LN.getLoops());
+
+  // Ensure minimum depth of the loop nest to do the interchange.
+  if (!hasMinimumLoopDepth(LoopList))
+    return PreservedAnalyses::all();
+
   DependenceInfo DI(&F, &AR.AA, &AR.SE, &AR.LI);
   std::unique_ptr<CacheCost> CC =
       CacheCost::getCacheCost(LN.getOutermostLoop(), AR, DI);
diff --git a/llvm/test/Transforms/LoopInterchange/bail-out-one-loop.ll b/llvm/test/Transforms/LoopInterchange/bail-out-one-loop.ll
new file mode 100644
index 00000000000000..4a532e1a862e60
--- /dev/null
+++ b/llvm/test/Transforms/LoopInterchange/bail-out-one-loop.ll
@@ -0,0 +1,65 @@
+; REQUIRES: asserts
+
+; RUN: opt < %s -passes=loop-interchange -debug -disable-output | FileCheck %s
+
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128-Fn32"
+
+ at N = dso_local global i32 0, align 4
+ at a = dso_local global ptr null, align 8
+ at b = dso_local global ptr null, align 8
+ at c = dso_local global ptr null, align 8
+
+; Loop interchange should not run delinearization
+; for one loop case and should bail out early.
+
+; CHECK-NOT: Delinearizing
+; CHECK-NOT: Strides:
+; CHECK-NOT: Terms:
+; CHECK: Loop doesn't contain minimum nesting level.
+
+define void @foo() {
+entry:
+  %retval = alloca i32, align 4
+  %i = alloca i32, align 4
+  store i32 0, ptr %retval, align 4
+  store i32 0, ptr %i, align 4
+  br label %for.cond
+
+for.cond:                                         ; preds = %for.inc, %entry
+  %0 = load i32, ptr %i, align 4
+  %1 = load i32, ptr @N, align 4
+  %cmp = icmp ult i32 %0, %1
+  br i1 %cmp, label %for.body, label %for.cond.cleanup
+
+for.cond.cleanup:                                 ; preds = %for.cond
+  br label %for.end
+
+for.body:                                         ; preds = %for.cond
+  %2 = load ptr, ptr @b, align 8
+  %3 = load i32, ptr %i, align 4
+  %idxprom = zext i32 %3 to i64
+  %arrayidx = getelementptr inbounds nuw i32, ptr %2, i64 %idxprom
+  %4 = load i32, ptr %arrayidx, align 4
+  %5 = load ptr, ptr @c, align 8
+  %6 = load i32, ptr %i, align 4
+  %idxprom1 = zext i32 %6 to i64
+  %arrayidx2 = getelementptr inbounds nuw i32, ptr %5, i64 %idxprom1
+  %7 = load i32, ptr %arrayidx2, align 4
+  %add = add nsw i32 %4, %7
+  %8 = load ptr, ptr @a, align 8
+  %9 = load i32, ptr %i, align 4
+  %idxprom3 = zext i32 %9 to i64
+  %arrayidx4 = getelementptr inbounds nuw i32, ptr %8, i64 %idxprom3
+  store i32 %add, ptr %arrayidx4, align 4
+  br label %for.inc
+
+for.inc:                                          ; preds = %for.body
+  %10 = load i32, ptr %i, align 4
+  %inc = add i32 %10, 1
+  store i32 %inc, ptr %i, align 4
+  br label %for.cond
+
+for.end:                                          ; preds = %for.cond.cleanup
+  ret void
+}
+