diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -4350,7 +4350,6 @@
   // entire expression in the smaller type.
   if (VF.isVector() && PhiTy != RdxDesc.getRecurrenceType()) {
     assert(!IsInLoopReductionPhi && "Unexpected truncated inloop reduction!");
-    assert(!VF.isScalable() && "scalable vectors not yet supported.");
     Type *RdxVecTy = VectorType::get(RdxDesc.getRecurrenceType(), VF);
     Builder.SetInsertPoint(
         LI->getLoopFor(LoopVectorBody)->getLoopLatch()->getTerminator());
diff --git a/llvm/test/Transforms/LoopVectorize/sve-reduction-inloop.ll b/llvm/test/Transforms/LoopVectorize/sve-reduction-inloop.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/sve-reduction-inloop.ll
@@ -0,0 +1,47 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -loop-vectorize -mtriple aarch64-unknown-linux-gnu -mattr=+sve  -S | FileCheck %s
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+
+define i8 @reduction_add_trunc(i8* noalias nocapture %A) {
+; CHECK-LABEL: @reduction_add_trunc(
+; CHECK: vector.body:
+; CHECK:  %[[MUL:.*]] = mul i32 %{{.*}}, 16
+; CHECK-NEXT:  %[[INDEXNEXT:.*]] = add i32 %index, %[[MUL]]
+; CHECK-NEXT:  %[[ICMP1:.*]] = icmp eq i32 %[[INDEXNEXT]], %{{.*}}
+; CHECK-NEXT:  %[[TRUNC1:.*]] = trunc <vscale x 8 x i32> %{{.*}} to <vscale x 8 x i8>
+; CHECK-NEXT:  %[[ZEXT1:.*]] = zext <vscale x 8 x i8> %[[TRUNC1]] to <vscale x 8 x i32>
+; CHECK-NEXT:  %[[TRUNC2:.*]] = trunc <vscale x 8 x i32> %{{.*}} to <vscale x 8 x i8>
+; CHECK-NEXT:  %[[ZEXT2:.*]] = zext <vscale x 8 x i8> %[[TRUNC2]] to <vscale x 8 x i32>
+; CHECK: middle.block:
+; CHECK-NEXT:  %[[TRUNC3:.*]] = trunc <vscale x 8 x i32> %[[ZEXT1]] to <vscale x 8 x i8>
+; CHECK-NEXT:  %[[TRUNC4:.*]] = trunc <vscale x 8 x i32> %[[ZEXT2]] to <vscale x 8 x i8>
+; CHECK-NEXT:  %[[BINRDX:.*]] = add <vscale x 8 x i8> %[[TRUNC4]], %[[TRUNC3]]
+; CHECK-NEXT:  %[[REDUCEADD:.*]] = call i8 @llvm.vector.reduce.add.nxv8i8(<vscale x 8 x i8> %[[BINRDX]])
+;
+entry:
+  br label %.lr.ph
+
+.lr.ph:                                           ; preds = %entry, %.lr.ph
+  %indvars.iv = phi i32 [ %indvars.iv.next, %.lr.ph ], [ 0, %entry ]
+  %sum.02p = phi i32 [ %l9, %.lr.ph ], [ 255, %entry ]
+  %sum.02 = and i32 %sum.02p, 255
+  %l2 = getelementptr inbounds i8, i8* %A, i32 %indvars.iv
+  %l3 = load i8, i8* %l2, align 4
+  %l3e = zext i8 %l3 to i32
+  %l9 = add i32 %sum.02, %l3e
+  %indvars.iv.next = add i32 %indvars.iv, 1
+  %exitcond = icmp eq i32 %indvars.iv.next, 256
+  br i1 %exitcond, label %._crit_edge, label %.lr.ph, !llvm.loop !0
+
+._crit_edge:                                      ; preds = %.lr.ph
+  %sum.0.lcssa = phi i32 [ %l9, %.lr.ph ]
+  %ret = trunc i32 %sum.0.lcssa to i8
+  ret i8 %ret
+}
+
+!0 = distinct !{!0, !1, !2, !3, !4}
+!1 = !{!"llvm.loop.vectorize.width", i32 8}
+!2 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
+!3 = !{!"llvm.loop.interleave.count", i32 2}
+!4 = !{!"llvm.loop.vectorize.enable", i1 true}