diff --git a/llvm/lib/Target/AArch64/SVEInstrFormats.td b/llvm/lib/Target/AArch64/SVEInstrFormats.td
--- a/llvm/lib/Target/AArch64/SVEInstrFormats.td
+++ b/llvm/lib/Target/AArch64/SVEInstrFormats.td
@@ -1019,6 +1019,30 @@
                   (!cast<Instruction>(NAME # _D) ZPR64:$Zd, FPR64asZPR:$Dn, 0), 2>;
   def : InstAlias<"mov $Zd, $Qn",
                   (!cast<Instruction>(NAME # _Q) ZPR128:$Zd, FPR128asZPR:$Qn, 0), 2>;
+
+  // Duplicate extracted element of vector into all vector elements
+  def : Pat<(nxv16i8 (AArch64dup (i32 (vector_extract (nxv16i8 ZPR:$vec), sve_elm_idx_extdup_b:$index)))),
+            (!cast<Instruction>(NAME # _B) ZPR:$vec, sve_elm_idx_extdup_b:$index)>;
+  def : Pat<(nxv8i16 (AArch64dup (i32 (vector_extract (nxv8i16 ZPR:$vec), sve_elm_idx_extdup_h:$index)))),
+            (!cast<Instruction>(NAME # _H) ZPR:$vec, sve_elm_idx_extdup_h:$index)>;
+  def : Pat<(nxv4i32 (AArch64dup (i32 (vector_extract (nxv4i32 ZPR:$vec), sve_elm_idx_extdup_s:$index)))),
+            (!cast<Instruction>(NAME # _S) ZPR:$vec, sve_elm_idx_extdup_s:$index)>;
+  def : Pat<(nxv2i64 (AArch64dup (i64 (vector_extract (nxv2i64 ZPR:$vec), sve_elm_idx_extdup_d:$index)))),
+            (!cast<Instruction>(NAME # _D) ZPR:$vec, sve_elm_idx_extdup_d:$index)>;
+  def : Pat<(nxv8f16 (AArch64dup (f16 (vector_extract (nxv8f16 ZPR:$vec), sve_elm_idx_extdup_h:$index)))),
+            (!cast<Instruction>(NAME # _H) ZPR:$vec, sve_elm_idx_extdup_h:$index)>;
+  def : Pat<(nxv8bf16 (AArch64dup (bf16 (vector_extract (nxv8bf16 ZPR:$vec), sve_elm_idx_extdup_h:$index)))),
+            (!cast<Instruction>(NAME # _H) ZPR:$vec, sve_elm_idx_extdup_h:$index)>;
+  def : Pat<(nxv4f16 (AArch64dup (f16 (vector_extract (nxv4f16 ZPR:$vec), sve_elm_idx_extdup_s:$index)))),
+            (!cast<Instruction>(NAME # _S) ZPR:$vec, sve_elm_idx_extdup_s:$index)>;
+  def : Pat<(nxv2f16 (AArch64dup (f16 (vector_extract (nxv2f16 ZPR:$vec), sve_elm_idx_extdup_d:$index)))),
+            (!cast<Instruction>(NAME # _D) ZPR:$vec, sve_elm_idx_extdup_d:$index)>;
+  def : Pat<(nxv4f32 (AArch64dup (f32 (vector_extract (nxv4f32 ZPR:$vec), sve_elm_idx_extdup_s:$index)))),
+            (!cast<Instruction>(NAME # _S) ZPR:$vec, sve_elm_idx_extdup_s:$index)>;
+  def : Pat<(nxv2f32 (AArch64dup (f32 (vector_extract (nxv2f32 ZPR:$vec), sve_elm_idx_extdup_d:$index)))),
+            (!cast<Instruction>(NAME # _D) ZPR:$vec, sve_elm_idx_extdup_d:$index)>;
+  def : Pat<(nxv2f64 (AArch64dup (f64 (vector_extract (nxv2f64 ZPR:$vec), sve_elm_idx_extdup_d:$index)))),
+            (!cast<Instruction>(NAME # _D) ZPR:$vec, sve_elm_idx_extdup_d:$index)>;
 }
 
 class sve_int_perm_tbl<bits<2> sz8_64, bits<2> opc, string asm, ZPRRegOp zprty,
diff --git a/llvm/test/CodeGen/AArch64/aarch64-dup-extract-scalable.ll b/llvm/test/CodeGen/AArch64/aarch64-dup-extract-scalable.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/aarch64-dup-extract-scalable.ll
@@ -0,0 +1,126 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple aarch64-none-linux-gnu -mattr=+sve | FileCheck %s
+
+define <vscale x 16 x i8> @dup_extract_i8(<vscale x 16 x i8> %data) {
+; CHECK-LABEL: dup_extract_i8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    mov z0.b, z0.b[1]
+; CHECK-NEXT:    ret
+  %1 = extractelement <vscale x 16 x i8> %data, i8 1
+  %.splatinsert = insertelement <vscale x 16 x i8> poison, i8 %1, i32 0
+  %.splat = shufflevector <vscale x 16 x i8> %.splatinsert, <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+  ret <vscale x 16 x i8> %.splat
+}
+
+define <vscale x 8 x i16> @dup_extract_i16(<vscale x 8 x i16> %data) {
+; CHECK-LABEL: dup_extract_i16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    mov z0.h, z0.h[1]
+; CHECK-NEXT:    ret
+  %1 = extractelement <vscale x 8 x i16> %data, i16 1
+  %.splatinsert = insertelement <vscale x 8 x i16> poison, i16 %1, i32 0
+  %.splat = shufflevector <vscale x 8 x i16> %.splatinsert, <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+  ret <vscale x 8 x i16> %.splat
+}
+
+define <vscale x 4 x i32> @dup_extract_i32(<vscale x 4 x i32> %data) {
+; CHECK-LABEL: dup_extract_i32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    mov z0.s, z0.s[1]
+; CHECK-NEXT:    ret
+  %1 = extractelement <vscale x 4 x i32> %data, i32 1
+  %.splatinsert = insertelement <vscale x 4 x i32> poison, i32 %1, i32 0
+  %.splat = shufflevector <vscale x 4 x i32> %.splatinsert, <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+  ret <vscale x 4 x i32> %.splat
+}
+
+define <vscale x 2 x i64> @dup_extract_i64(<vscale x 2 x i64> %data) {
+; CHECK-LABEL: dup_extract_i64:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    mov z0.d, z0.d[1]
+; CHECK-NEXT:    ret
+  %1 = extractelement <vscale x 2 x i64> %data, i64 1
+  %.splatinsert = insertelement <vscale x 2 x i64> poison, i64 %1, i32 0
+  %.splat = shufflevector <vscale x 2 x i64> %.splatinsert, <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+  ret <vscale x 2 x i64> %.splat
+}
+
+define <vscale x 8 x half> @dup_extract_f16(<vscale x 8 x half> %data) {
+; CHECK-LABEL: dup_extract_f16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    mov z0.h, z0.h[1]
+; CHECK-NEXT:    ret
+  %1 = extractelement <vscale x 8 x half> %data, i16 1
+  %.splatinsert = insertelement <vscale x 8 x half> poison, half %1, i32 0
+  %.splat = shufflevector <vscale x 8 x half> %.splatinsert, <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+  ret <vscale x 8 x half> %.splat
+}
+
+define <vscale x 4 x half> @dup_extract_f16_4(<vscale x 4 x half> %data) {
+; CHECK-LABEL: dup_extract_f16_4:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    mov z0.s, z0.s[1]
+; CHECK-NEXT:    ret
+  %1 = extractelement <vscale x 4 x half> %data, i16 1
+  %.splatinsert = insertelement <vscale x 4 x half> poison, half %1, i32 0
+  %.splat = shufflevector <vscale x 4 x half> %.splatinsert, <vscale x 4 x half> poison, <vscale x 4 x i32> zeroinitializer
+  ret <vscale x 4 x half> %.splat
+}
+
+define <vscale x 2 x half> @dup_extract_f16_2(<vscale x 2 x half> %data) {
+; CHECK-LABEL: dup_extract_f16_2:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    mov z0.d, z0.d[1]
+; CHECK-NEXT:    ret
+  %1 = extractelement <vscale x 2 x half> %data, i16 1
+  %.splatinsert = insertelement <vscale x 2 x half> poison, half %1, i32 0
+  %.splat = shufflevector <vscale x 2 x half> %.splatinsert, <vscale x 2 x half> poison, <vscale x 2 x i32> zeroinitializer
+  ret <vscale x 2 x half> %.splat
+}
+
+define <vscale x 8 x bfloat> @dup_extract_bf16(<vscale x 8 x bfloat> %data) #0 {
+; CHECK-LABEL: dup_extract_bf16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    mov z0.h, z0.h[1]
+; CHECK-NEXT:    ret
+  %1 = extractelement <vscale x 8 x bfloat> %data, i16 1
+  %.splatinsert = insertelement <vscale x 8 x bfloat> poison, bfloat %1, i32 0
+  %.splat = shufflevector <vscale x 8 x bfloat> %.splatinsert, <vscale x 8 x bfloat> poison, <vscale x 8 x i32> zeroinitializer
+  ret <vscale x 8 x bfloat> %.splat
+}
+
+define <vscale x 4 x float> @dup_extract_f32(<vscale x 4 x float> %data) {
+; CHECK-LABEL: dup_extract_f32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    mov z0.s, z0.s[1]
+; CHECK-NEXT:    ret
+  %1 = extractelement <vscale x 4 x float> %data, i32 1
+  %.splatinsert = insertelement <vscale x 4 x float> poison, float %1, i32 0
+  %.splat = shufflevector <vscale x 4 x float> %.splatinsert, <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+  ret <vscale x 4 x float> %.splat
+}
+
+define <vscale x 2 x float> @dup_extract_f32_2(<vscale x 2 x float> %data) {
+; CHECK-LABEL: dup_extract_f32_2:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    mov z0.d, z0.d[1]
+; CHECK-NEXT:    ret
+  %1 = extractelement <vscale x 2 x float> %data, i32 1
+  %.splatinsert = insertelement <vscale x 2 x float> poison, float %1, i32 0
+  %.splat = shufflevector <vscale x 2 x float> %.splatinsert, <vscale x 2 x float> poison, <vscale x 2 x i32> zeroinitializer
+  ret <vscale x 2 x float> %.splat
+}
+
+define <vscale x 2 x double> @dup_extract_f64(<vscale x 2 x double> %data) {
+; CHECK-LABEL: dup_extract_f64:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    mov z0.d, z0.d[1]
+; CHECK-NEXT:    ret
+  %1 = extractelement <vscale x 2 x double> %data, i64 1
+  %.splatinsert = insertelement <vscale x 2 x double> poison, double %1, i32 0
+  %.splat = shufflevector <vscale x 2 x double> %.splatinsert, <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+  ret <vscale x 2 x double> %.splat
+}
+
+; +bf16 is required for the bfloat version.
+attributes #0 = { "target-features"="+sve,+bf16" }
diff --git a/llvm/test/CodeGen/AArch64/sve-ld-post-inc.ll b/llvm/test/CodeGen/AArch64/sve-ld-post-inc.ll
--- a/llvm/test/CodeGen/AArch64/sve-ld-post-inc.ll
+++ b/llvm/test/CodeGen/AArch64/sve-ld-post-inc.ll
@@ -29,8 +29,8 @@
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    ldr d0, [x0]
 ; CHECK-NEXT:    add x8, x0, x2, lsl #3
-; CHECK-NEXT:    mov z0.d, d0
 ; CHECK-NEXT:    str x8, [x1]
+; CHECK-NEXT:    mov z0.d, d0
 ; CHECK-NEXT:    ret
   %load = load double, double* %a
   %dup = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double %load)