[LV] Check isPredInst instead of isScalarWithPred in uniform analysis.

Any instruction marked as uniform will result in a uniform
VPReplicateRecipe. If it requires predication, it will be placed in a
replicate region, even if isScalarWithPredication returns false.

Check isPredicatedInst instead of isScalarWithPredication to avoid
generating uniform VPReplicateRecipes placed inside a replicate region.
This fixes an assertion when using scalable VFs.

Fixes #80416.
Fixes #94328.

Author: fhahn

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -3907,7 +3907,7 @@ void LoopVectorizationCostModel::collectLoopUniforms(ElementCount VF) {
   SetVector<Instruction *> Worklist;
 
   // Add uniform instructions demanding lane 0 to the worklist. Instructions
-  // that are scalar with predication must not be considered uniform after
+  // that are require predication must not be considered uniform after
   // vectorization, because that would create an erroneous replicating region
   // where only a single instance out of VF should be formed.
   // TODO: optimize such seldom cases if found important, see PR40816.
@@ -3917,9 +3917,10 @@ void LoopVectorizationCostModel::collectLoopUniforms(ElementCount VF) {
                         << *I << "\n");
       return;
     }
-    if (isScalarWithPredication(I, VF)) {
-      LLVM_DEBUG(dbgs() << "LV: Found not uniform being ScalarWithPredication: "
-                        << *I << "\n");
+    if (isPredicatedInst(I)) {
+      LLVM_DEBUG(
+          dbgs() << "LV: Found not uniform due to requiring predication: " << *I
+                 << "\n");
       return;
     }
     LLVM_DEBUG(dbgs() << "LV: Found uniform instruction: " << *I << "\n");

llvm/test/Transforms/LoopVectorize/AArch64/divs-with-scalable-vfs.ll

@@ -0,0 +1,92 @@
+; RUN: opt -p loop-vectorize -mtriple aarch64 -mcpu=neoverse-v1 -S %s | FileCheck %s
+
+; Test case for https://github.com/llvm/llvm-project/issues/94328.
+define void @sdiv_feeding_gep(ptr %dst, i32 %x, i64 %M, i64 %conv6, i64 %N) {
+entry:
+  %conv61 = zext i32 %x to i64
+  br label %loop
+
+loop:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
+  %div18 = sdiv i64 %M, %conv6
+  %conv20 = trunc i64 %div18 to i32
+  %mul30 = mul i64 %div18, %conv61
+  %sub31 = sub i64 %iv, %mul30
+  %conv34 = trunc i64 %sub31 to i32
+  %mul35 = mul i32 %x, %conv20
+  %add36 = add i32 %mul35, %conv34
+  %idxprom = sext i32 %add36 to i64
+  %gep = getelementptr double, ptr %dst, i64 %idxprom
+  store double 0.000000e+00, ptr %gep, align 8
+  %iv.next = add i64 %iv, 1
+  %ec = icmp eq i64 %iv.next, %N
+  br i1 %ec, label %exit, label %loop
+
+exit:
+  ret void
+}
+
+define void @sdiv_feeding_gep_predicated(ptr %dst, i32 %x, i64 %M, i64 %conv6, i64 %N) {
+entry:
+  %conv61 = zext i32 %x to i64
+  br label %loop
+
+loop:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop.latch ]
+  %c = icmp ule i64 %iv, %M
+  br i1 %c, label %then, label %loop.latch
+
+then:
+  %div18 = sdiv i64 %M, %conv6
+  %conv20 = trunc i64 %div18 to i32
+  %mul30 = mul i64 %div18, %conv61
+  %sub31 = sub i64 %iv, %mul30
+  %conv34 = trunc i64 %sub31 to i32
+  %mul35 = mul i32 %x, %conv20
+  %add36 = add i32 %mul35, %conv34
+  %idxprom = sext i32 %add36 to i64
+  %gep = getelementptr double, ptr %dst, i64 %idxprom
+  store double 0.000000e+00, ptr %gep, align 8
+  br label %loop.latch
+
+loop.latch:
+  %iv.next = add i64 %iv, 1
+  %ec = icmp eq i64 %iv.next, %N
+  br i1 %ec, label %exit, label %loop
+
+exit:
+  ret void
+}
+
+; Test case for https://github.com/llvm/llvm-project/issues/80416.
+define void @udiv_urem_feeding_gep(i64 %x, ptr %dst, i64 %N) {
+entry:
+  %mul.1.i = mul i64 %x, %x
+  %mul.2.i = mul i64 %mul.1.i, %x
+  br label %loop
+
+loop:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
+  %div.i = udiv i64 %iv, %mul.2.i
+  %rem.i = urem i64 %iv, %mul.2.i
+  %div.1.i = udiv i64 %rem.i, %mul.1.i
+  %rem.1.i = urem i64 %rem.i, %mul.1.i
+  %div.2.i = udiv i64 %rem.1.i, %x
+  %rem.2.i = urem i64 %rem.1.i, %x
+  %mul.i = mul i64 %x, %div.i
+  %add.i = add i64 %mul.i, %div.1.i
+  %mul.1.i9 = mul i64 %add.i, %x
+  %add.1.i = add i64 %mul.1.i9, %div.2.i
+  %mul.2.i11 = mul i64 %add.1.i, %x
+  %add.2.i = add i64 %mul.2.i11, %rem.2.i
+  %sext.i = shl i64 %add.2.i, 32
+  %conv6.i = ashr i64 %sext.i, 32
+  %gep = getelementptr i64, ptr %dst, i64 %conv6.i
+  store i64 %div.i, ptr %gep, align 4
+  %iv.next = add i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv, %N
+  br i1 %exitcond.not, label %exit, label %loop
+
+exit:
+  ret void
+}