Index: llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -1125,6 +1125,26 @@
 
   KnownBits Known2;
   switch (Op.getOpcode()) {
+  case ISD::VSCALE: {
+    Function const &F = TLO.DAG.getMachineFunction().getFunction();
+    Attribute const &Attr = F.getFnAttribute(Attribute::VScaleRange);
+    if (!Attr.isValid())
+      return false;
+    std::optional<unsigned> MaxVScale = Attr.getVScaleRangeMax();
+    if (!MaxVScale.has_value())
+      return false;
+    APInt Multiplier = Op.getConstantOperandAPInt(0);
+    unsigned Width = Multiplier.getActiveBits() + Log2_32(*MaxVScale) + 1;
+    APInt VScaleResultUpperbound =
+        APInt(Width, *MaxVScale) * Multiplier.sextOrTrunc(Width);
+    bool Negative = VScaleResultUpperbound.isNegative();
+    if (Negative)
+      VScaleResultUpperbound = ~VScaleResultUpperbound;
+    unsigned RequiredBits = VScaleResultUpperbound.getActiveBits();
+    if (RequiredBits < BitWidth)
+      (Negative ? Known.One : Known.Zero).setHighBits(BitWidth - RequiredBits);
+    return false;
+  }
   case ISD::SCALAR_TO_VECTOR: {
     if (VT.isScalableVector())
       return false;
Index: llvm/test/CodeGen/AArch64/vscale-and-sve-cnt-demandedbits.ll
===================================================================
--- llvm/test/CodeGen/AArch64/vscale-and-sve-cnt-demandedbits.ll
+++ llvm/test/CodeGen/AArch64/vscale-and-sve-cnt-demandedbits.ll
@@ -14,9 +14,8 @@
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    rdvl x8, #1
 ; CHECK-NEXT:    lsr x8, x8, #4
-; CHECK-NEXT:    and w9, w8, #0x1f
-; CHECK-NEXT:    and w8, w8, #0xfffffffc
-; CHECK-NEXT:    add w0, w9, w8
+; CHECK-NEXT:    and w9, w8, #0x1c
+; CHECK-NEXT:    add w0, w8, w9
 ; CHECK-NEXT:    ret
   %vscale = call i32 @llvm.vscale.i32()
   %and_redundant = and i32 %vscale, 31
@@ -85,8 +84,7 @@
 ; CHECK-LABEL: vscale_trunc_zext:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    rdvl x8, #1
-; CHECK-NEXT:    lsr x8, x8, #4
-; CHECK-NEXT:    and x0, x8, #0xffffffff
+; CHECK-NEXT:    lsr x0, x8, #4
 ; CHECK-NEXT:    ret
   %vscale = call i32 @llvm.vscale.i32()
   %zext = zext i32 %vscale to i64
@@ -97,8 +95,7 @@
 ; CHECK-LABEL: vscale_trunc_sext:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    rdvl x8, #1
-; CHECK-NEXT:    lsr x8, x8, #4
-; CHECK-NEXT:    sxtw x0, w8
+; CHECK-NEXT:    lsr x0, x8, #4
 ; CHECK-NEXT:    ret
   %vscale = call i32 @llvm.vscale.i32()
   %sext = sext i32 %vscale to i64
@@ -200,9 +197,8 @@
 ; CHECK-NEXT:    mov w9, #5
 ; CHECK-NEXT:    lsr x8, x8, #4
 ; CHECK-NEXT:    mul x8, x8, x9
-; CHECK-NEXT:    and w9, w8, #0x7f
-; CHECK-NEXT:    and w8, w8, #0x3f
-; CHECK-NEXT:    add w0, w9, w8
+; CHECK-NEXT:    and w9, w8, #0x3f
+; CHECK-NEXT:    add w0, w8, w9
 ; CHECK-NEXT:    ret
   %vscale = call i32 @llvm.vscale.i32()
   %mul = mul i32 %vscale, 5
@@ -219,9 +215,8 @@
 ; CHECK-NEXT:    mov x9, #-5
 ; CHECK-NEXT:    lsr x8, x8, #4
 ; CHECK-NEXT:    mul x8, x8, x9
-; CHECK-NEXT:    orr w9, w8, #0xffffff80
-; CHECK-NEXT:    and w8, w8, #0xffffffc0
-; CHECK-NEXT:    add w0, w9, w8
+; CHECK-NEXT:    and w9, w8, #0xffffffc0
+; CHECK-NEXT:    add w0, w8, w9
 ; CHECK-NEXT:    ret
   %vscale = call i32 @llvm.vscale.i32()
   %mul = mul i32 %vscale, -5
@@ -231,6 +226,22 @@
   ret i32 %result
 }
 
+define i32 @pow2_vscale_with_negative_multiplier() vscale_range(1,16) {
+; CHECK-LABEL: pow2_vscale_with_negative_multiplier:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    cntd x8
+; CHECK-NEXT:    neg x8, x8
+; CHECK-NEXT:    orr w9, w8, #0xfffffff0
+; CHECK-NEXT:    add w0, w8, w9
+; CHECK-NEXT:    ret
+  %vscale = call i32 @llvm.vscale.i32()
+  %mul = mul i32 %vscale, -2
+  %or_redundant = or i32 %mul, 4294967264
+  %or_required = or i32 %mul, 4294967280
+  %result = add i32 %or_redundant, %or_required
+  ret i32 %result
+}
+
 declare i32 @llvm.vscale.i32()
 declare i64 @llvm.aarch64.sve.cntb(i32 %pattern)
 declare i64 @llvm.aarch64.sve.cnth(i32 %pattern)
Index: llvm/test/CodeGen/RISCV/vscale-demanded-bits.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/RISCV/vscale-demanded-bits.ll
@@ -0,0 +1,72 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple riscv64 -mattr +v -filetype asm -o - %s | FileCheck %s
+
+define dso_local void @f(ptr nocapture noundef writeonly %buffer, i32 noundef signext %n) local_unnamed_addr #0 {
+; CHECK-LABEL: f:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li a2, 0
+; CHECK-NEXT:    slli a1, a1, 32
+; CHECK-NEXT:    srli a1, a1, 32
+; CHECK-NEXT:    csrr a3, vlenb
+; CHECK-NEXT:    add a4, a3, a1
+; CHECK-NEXT:    addi a4, a4, -1
+; CHECK-NEXT:    neg a5, a3
+; CHECK-NEXT:    and a4, a4, a5
+; CHECK-NEXT:    vsetvli a5, zero, e8, m1, ta, ma
+; CHECK-NEXT:    vid.v v8
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vid.v v16
+; CHECK-NEXT:  .LBB0_1: # %vector.body
+; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vsaddu.vx v24, v16, a2
+; CHECK-NEXT:    vmsltu.vx v0, v24, a1
+; CHECK-NEXT:    add a5, a0, a2
+; CHECK-NEXT:    vse8.v v8, (a5), v0.t
+; CHECK-NEXT:    add a2, a2, a3
+; CHECK-NEXT:    vsetvli zero, zero, e8, m1, ta, ma
+; CHECK-NEXT:    vadd.vx v8, v8, a3
+; CHECK-NEXT:    bne a4, a2, .LBB0_1
+; CHECK-NEXT:  # %bb.2: # %exit
+; CHECK-NEXT:    ret
+entry:
+  %wide.trip.count = zext i32 %n to i64
+  %0 = tail call i64 @llvm.vscale.i64()
+  %1 = shl nuw nsw i64 %0, 3
+  %2 = add nsw i64 %1, -1
+  %n.rnd.up = add nsw i64 %2, %wide.trip.count
+  %n.mod.vf = urem i64 %n.rnd.up, %1
+  %n.vec = sub nsw i64 %n.rnd.up, %n.mod.vf
+  %3 = tail call <vscale x 8 x i8> @llvm.experimental.stepvector.nxv8i8()
+  %4 = tail call i8 @llvm.vscale.i8()
+  %5 = shl i8 %4, 3
+  %.splatinsert = insertelement <vscale x 8 x i8> poison, i8 %5, i64 0
+  %.splat = shufflevector <vscale x 8 x i8> %.splatinsert, <vscale x 8 x i8> poison, <vscale x 8 x i32> zeroinitializer
+  br label %vector.body
+
+vector.body:
+  %index = phi i64 [ 0, %entry ], [ %index.next, %vector.body ]
+  %vec.ind = phi <vscale x 8 x i8> [ %3, %entry ], [ %vec.ind.next, %vector.body ]
+  %active.lane.mask = tail call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 %index, i64 %wide.trip.count)
+  %6 = getelementptr inbounds i8, ptr %buffer, i64 %index
+  tail call void @llvm.masked.store.nxv8i8.p0(<vscale x 8 x i8> %vec.ind, ptr %6, i32 1, <vscale x 8 x i1> %active.lane.mask)
+  %index.next = add i64 %index, %1
+  %vec.ind.next = add <vscale x 8 x i8> %vec.ind, %.splat
+  %7 = icmp eq i64 %index.next, %n.vec
+  br i1 %7, label %exit, label %vector.body
+
+exit:
+  ret void
+}
+
+declare i64 @llvm.vscale.i64()
+
+declare <vscale x 8 x i8> @llvm.experimental.stepvector.nxv8i8()
+
+declare i8 @llvm.vscale.i8()
+
+declare <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64, i64)
+
+declare void @llvm.masked.store.nxv8i8.p0(<vscale x 8 x i8>, ptr nocapture, i32 immarg, <vscale x 8 x i1>)
+
+attributes #0 = { vscale_range(2,1024) }