diff --git a/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td b/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
--- a/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
@@ -1891,13 +1891,18 @@
   defm : pred_store<nxv4i32, nxv4i1,  non_temporal_store, STNT1W_ZRR, STNT1W_ZRI, am_sve_regreg_lsl2>;
   defm : pred_store<nxv2i64, nxv2i1,  non_temporal_store, STNT1D_ZRR, STNT1D_ZRI, am_sve_regreg_lsl3>;
 
-  multiclass unpred_store<PatFrag Store, ValueType Ty, Instruction RegImmInst,
-                          Instruction PTrue> {
+  multiclass unpred_store<PatFrag Store, ValueType Ty, Instruction RegRegInst,
+                          Instruction RegImmInst, Instruction PTrue,
+                          ComplexPattern AddrCP> {
     let AddedComplexity = 1 in {
+      def _reg : Pat<(Store (Ty ZPR:$val), (AddrCP GPR64sp:$base, GPR64:$offset)),
+                     (RegRegInst ZPR:$val, (PTrue 31), GPR64sp:$base, GPR64:$offset)>;
+    }
+    let AddedComplexity = 2 in {
       def _imm : Pat<(Store (Ty ZPR:$val), (am_sve_indexed_s4 GPR64sp:$base, simm4s1:$offset)),
                      (RegImmInst ZPR:$val, (PTrue 31), GPR64sp:$base, simm4s1:$offset)>;
     }
-    let AddedComplexity = 2 in {
+    let AddedComplexity = 3 in {
       def _fi : Pat<(Store (Ty ZPR:$val), (am_sve_fi GPR64sp:$base, simm4s1:$offset)),
                     (RegImmInst ZPR:$val, (PTrue 31), GPR64sp:$base, simm4s1:$offset)>;
     }
@@ -1906,32 +1911,36 @@
               (RegImmInst ZPR:$val, (PTrue 31), GPR64:$base, (i64 0))>;
   }
 
-  defm : unpred_store<         store, nxv16i8,   ST1B_IMM, PTRUE_B>;
-  defm : unpred_store< truncstorevi8, nxv8i16, ST1B_H_IMM, PTRUE_H>;
-  defm : unpred_store< truncstorevi8, nxv4i32, ST1B_S_IMM, PTRUE_S>;
-  defm : unpred_store< truncstorevi8, nxv2i64, ST1B_D_IMM, PTRUE_D>;
-  defm : unpred_store<         store, nxv8i16,   ST1H_IMM, PTRUE_H>;
-  defm : unpred_store<truncstorevi16, nxv4i32, ST1H_S_IMM, PTRUE_S>;
-  defm : unpred_store<truncstorevi16, nxv2i64, ST1H_D_IMM, PTRUE_D>;
-  defm : unpred_store<         store, nxv4i32,   ST1W_IMM, PTRUE_S>;
-  defm : unpred_store<truncstorevi32, nxv2i64, ST1W_D_IMM, PTRUE_D>;
-  defm : unpred_store<         store, nxv2i64,   ST1D_IMM, PTRUE_D>;
-  defm : unpred_store<         store, nxv8f16,   ST1H_IMM, PTRUE_H>;
-  defm : unpred_store<         store, nxv8bf16,  ST1H_IMM, PTRUE_H>;
-  defm : unpred_store<         store, nxv4f16, ST1H_S_IMM, PTRUE_S>;
-  defm : unpred_store<         store, nxv2f16, ST1H_D_IMM, PTRUE_D>;
-  defm : unpred_store<         store, nxv4f32,   ST1W_IMM, PTRUE_S>;
-  defm : unpred_store<         store, nxv2f32, ST1W_D_IMM, PTRUE_D>;
-  defm : unpred_store<         store, nxv2f64,   ST1D_IMM, PTRUE_D>;
-
-  multiclass unpred_load<PatFrag Load, ValueType Ty, Instruction RegImmInst,
-                         Instruction PTrue> {
+  defm : unpred_store<         store, nxv16i8,   ST1B,   ST1B_IMM, PTRUE_B, am_sve_regreg_lsl0>;
+  defm : unpred_store< truncstorevi8, nxv8i16, ST1B_H, ST1B_H_IMM, PTRUE_H, am_sve_regreg_lsl0>;
+  defm : unpred_store< truncstorevi8, nxv4i32, ST1B_S, ST1B_S_IMM, PTRUE_S, am_sve_regreg_lsl0>;
+  defm : unpred_store< truncstorevi8, nxv2i64, ST1B_D, ST1B_D_IMM, PTRUE_D, am_sve_regreg_lsl0>;
+  defm : unpred_store<         store, nxv8i16,   ST1H,   ST1H_IMM, PTRUE_H, am_sve_regreg_lsl1>;
+  defm : unpred_store<truncstorevi16, nxv4i32, ST1H_S, ST1H_S_IMM, PTRUE_S, am_sve_regreg_lsl1>;
+  defm : unpred_store<truncstorevi16, nxv2i64, ST1H_D, ST1H_D_IMM, PTRUE_D, am_sve_regreg_lsl1>;
+  defm : unpred_store<         store, nxv4i32,   ST1W,   ST1W_IMM, PTRUE_S, am_sve_regreg_lsl2>;
+  defm : unpred_store<truncstorevi32, nxv2i64, ST1W_D, ST1W_D_IMM, PTRUE_D, am_sve_regreg_lsl2>;
+  defm : unpred_store<         store, nxv2i64,   ST1D,   ST1D_IMM, PTRUE_D, am_sve_regreg_lsl3>;
+  defm : unpred_store<         store, nxv8f16,   ST1H,   ST1H_IMM, PTRUE_H, am_sve_regreg_lsl1>;
+  defm : unpred_store<         store, nxv8bf16,  ST1H,   ST1H_IMM, PTRUE_H, am_sve_regreg_lsl1>;
+  defm : unpred_store<         store, nxv4f16, ST1H_S, ST1H_S_IMM, PTRUE_S, am_sve_regreg_lsl1>;
+  defm : unpred_store<         store, nxv2f16, ST1H_D, ST1H_D_IMM, PTRUE_D, am_sve_regreg_lsl1>;
+  defm : unpred_store<         store, nxv4f32,   ST1W,   ST1W_IMM, PTRUE_S, am_sve_regreg_lsl2>;
+  defm : unpred_store<         store, nxv2f32, ST1W_D, ST1W_D_IMM, PTRUE_D, am_sve_regreg_lsl2>;
+  defm : unpred_store<         store, nxv2f64,   ST1D,   ST1D_IMM, PTRUE_D, am_sve_regreg_lsl3>;
+
+  multiclass unpred_load<PatFrag Load, ValueType Ty, Instruction RegRegInst,
+                         Instruction RegImmInst, Instruction PTrue,
+                         ComplexPattern AddrCP> {
     let AddedComplexity = 1 in {
+      def _reg: Pat<(Ty (Load  (AddrCP GPR64sp:$base, GPR64:$offset))),
+                    (RegRegInst (PTrue 31), GPR64sp:$base, GPR64:$offset)>;
+    }
+    let AddedComplexity = 2 in {
       def _imm: Pat<(Ty (Load  (am_sve_indexed_s4 GPR64sp:$base, simm4s1:$offset))),
                     (RegImmInst (PTrue 31), GPR64sp:$base, simm4s1:$offset)>;
     }
-
-    let AddedComplexity = 2 in {
+    let AddedComplexity = 3 in {
       def _fi : Pat<(Ty (Load  (am_sve_fi GPR64sp:$base, simm4s1:$offset))),
                     (RegImmInst (PTrue 31), GPR64sp:$base, simm4s1:$offset)>;
     }
@@ -1940,35 +1949,35 @@
               (RegImmInst (PTrue 31), GPR64:$base, (i64 0))>;
   }
 
-  defm : unpred_load<        load, nxv16i8,    LD1B_IMM, PTRUE_B>;
-  defm : unpred_load< zextloadvi8, nxv8i16,  LD1B_H_IMM, PTRUE_H>;
-  defm : unpred_load< zextloadvi8, nxv4i32,  LD1B_S_IMM, PTRUE_S>;
-  defm : unpred_load< zextloadvi8, nxv2i64,  LD1B_D_IMM, PTRUE_D>;
-  defm : unpred_load<  extloadvi8, nxv8i16,  LD1B_H_IMM, PTRUE_H>;
-  defm : unpred_load<  extloadvi8, nxv4i32,  LD1B_S_IMM, PTRUE_S>;
-  defm : unpred_load<  extloadvi8, nxv2i64,  LD1B_D_IMM, PTRUE_D>;
-  defm : unpred_load< sextloadvi8, nxv8i16, LD1SB_H_IMM, PTRUE_H>;
-  defm : unpred_load< sextloadvi8, nxv4i32, LD1SB_S_IMM, PTRUE_S>;
-  defm : unpred_load< sextloadvi8, nxv2i64, LD1SB_D_IMM, PTRUE_D>;
-  defm : unpred_load<        load, nxv8i16,    LD1H_IMM, PTRUE_H>;
-  defm : unpred_load<zextloadvi16, nxv4i32,  LD1H_S_IMM, PTRUE_S>;
-  defm : unpred_load<zextloadvi16, nxv2i64,  LD1H_D_IMM, PTRUE_D>;
-  defm : unpred_load< extloadvi16, nxv4i32,  LD1H_S_IMM, PTRUE_S>;
-  defm : unpred_load< extloadvi16, nxv2i64,  LD1H_D_IMM, PTRUE_D>;
-  defm : unpred_load<sextloadvi16, nxv4i32, LD1SH_S_IMM, PTRUE_S>;
-  defm : unpred_load<sextloadvi16, nxv2i64, LD1SH_D_IMM, PTRUE_D>;
-  defm : unpred_load<        load, nxv4i32,    LD1W_IMM, PTRUE_S>;
-  defm : unpred_load<zextloadvi32, nxv2i64,  LD1W_D_IMM, PTRUE_D>;
-  defm : unpred_load< extloadvi32, nxv2i64,  LD1W_D_IMM, PTRUE_D>;
-  defm : unpred_load<sextloadvi32, nxv2i64, LD1SW_D_IMM, PTRUE_D>;
-  defm : unpred_load<        load, nxv2i64,    LD1D_IMM, PTRUE_D>;
-  defm : unpred_load<        load, nxv8f16,    LD1H_IMM, PTRUE_H>;
-  defm : unpred_load<        load, nxv8bf16,   LD1H_IMM, PTRUE_H>;
-  defm : unpred_load<        load, nxv4f16,  LD1H_S_IMM, PTRUE_S>;
-  defm : unpred_load<        load, nxv2f16,  LD1H_D_IMM, PTRUE_D>;
-  defm : unpred_load<        load, nxv4f32,    LD1W_IMM, PTRUE_S>;
-  defm : unpred_load<        load, nxv2f32,  LD1W_D_IMM, PTRUE_D>;
-  defm : unpred_load<        load, nxv2f64,    LD1D_IMM, PTRUE_D>;
+  defm : unpred_load<        load, nxv16i8,    LD1B,    LD1B_IMM, PTRUE_B, am_sve_regreg_lsl0>;
+  defm : unpred_load< zextloadvi8, nxv8i16,  LD1B_H,  LD1B_H_IMM, PTRUE_H, am_sve_regreg_lsl0>;
+  defm : unpred_load< zextloadvi8, nxv4i32,  LD1B_S,  LD1B_S_IMM, PTRUE_S, am_sve_regreg_lsl0>;
+  defm : unpred_load< zextloadvi8, nxv2i64,  LD1B_D,  LD1B_D_IMM, PTRUE_D, am_sve_regreg_lsl0>;
+  defm : unpred_load<  extloadvi8, nxv8i16,  LD1B_H,  LD1B_H_IMM, PTRUE_H, am_sve_regreg_lsl0>;
+  defm : unpred_load<  extloadvi8, nxv4i32,  LD1B_S,  LD1B_S_IMM, PTRUE_S, am_sve_regreg_lsl0>;
+  defm : unpred_load<  extloadvi8, nxv2i64,  LD1B_D,  LD1B_D_IMM, PTRUE_D, am_sve_regreg_lsl0>;
+  defm : unpred_load< sextloadvi8, nxv8i16, LD1SB_H, LD1SB_H_IMM, PTRUE_H, am_sve_regreg_lsl0>;
+  defm : unpred_load< sextloadvi8, nxv4i32, LD1SB_S, LD1SB_S_IMM, PTRUE_S, am_sve_regreg_lsl0>;
+  defm : unpred_load< sextloadvi8, nxv2i64, LD1SB_D, LD1SB_D_IMM, PTRUE_D, am_sve_regreg_lsl0>;
+  defm : unpred_load<        load, nxv8i16,    LD1H,    LD1H_IMM, PTRUE_H, am_sve_regreg_lsl1>;
+  defm : unpred_load<zextloadvi16, nxv4i32,  LD1H_S,  LD1H_S_IMM, PTRUE_S, am_sve_regreg_lsl1>;
+  defm : unpred_load<zextloadvi16, nxv2i64,  LD1H_D,  LD1H_D_IMM, PTRUE_D, am_sve_regreg_lsl1>;
+  defm : unpred_load< extloadvi16, nxv4i32,  LD1H_S,  LD1H_S_IMM, PTRUE_S, am_sve_regreg_lsl1>;
+  defm : unpred_load< extloadvi16, nxv2i64,  LD1H_D,  LD1H_D_IMM, PTRUE_D, am_sve_regreg_lsl1>;
+  defm : unpred_load<sextloadvi16, nxv4i32, LD1SH_S, LD1SH_S_IMM, PTRUE_S, am_sve_regreg_lsl1>;
+  defm : unpred_load<sextloadvi16, nxv2i64, LD1SH_D, LD1SH_D_IMM, PTRUE_D, am_sve_regreg_lsl1>;
+  defm : unpred_load<        load, nxv4i32,    LD1W,    LD1W_IMM, PTRUE_S, am_sve_regreg_lsl2>;
+  defm : unpred_load<zextloadvi32, nxv2i64,  LD1W_D,  LD1W_D_IMM, PTRUE_D, am_sve_regreg_lsl2>;
+  defm : unpred_load< extloadvi32, nxv2i64,  LD1W_D,  LD1W_D_IMM, PTRUE_D, am_sve_regreg_lsl2>;
+  defm : unpred_load<sextloadvi32, nxv2i64, LD1SW_D, LD1SW_D_IMM, PTRUE_D, am_sve_regreg_lsl2>;
+  defm : unpred_load<        load, nxv2i64,    LD1D,    LD1D_IMM, PTRUE_D, am_sve_regreg_lsl3>;
+  defm : unpred_load<        load, nxv8f16,    LD1H,    LD1H_IMM, PTRUE_H, am_sve_regreg_lsl1>;
+  defm : unpred_load<        load, nxv8bf16,   LD1H,    LD1H_IMM, PTRUE_H, am_sve_regreg_lsl1>;
+  defm : unpred_load<        load, nxv4f16,  LD1H_S,  LD1H_S_IMM, PTRUE_S, am_sve_regreg_lsl1>;
+  defm : unpred_load<        load, nxv2f16,  LD1H_D,  LD1H_D_IMM, PTRUE_D, am_sve_regreg_lsl1>;
+  defm : unpred_load<        load, nxv4f32,    LD1W,    LD1W_IMM, PTRUE_S, am_sve_regreg_lsl2>;
+  defm : unpred_load<        load, nxv2f32,  LD1W_D,  LD1W_D_IMM, PTRUE_D, am_sve_regreg_lsl2>;
+  defm : unpred_load<        load, nxv2f64,    LD1D,    LD1D_IMM, PTRUE_D, am_sve_regreg_lsl3>;
 
   multiclass unpred_store_predicate<ValueType Ty, Instruction Store> {
     def _fi : Pat<(store (Ty PPR:$val), (am_sve_fi GPR64sp:$base, simm9:$offset)),
diff --git a/llvm/test/CodeGen/AArch64/named-vector-shuffles-sve.ll b/llvm/test/CodeGen/AArch64/named-vector-shuffles-sve.ll
--- a/llvm/test/CodeGen/AArch64/named-vector-shuffles-sve.ll
+++ b/llvm/test/CodeGen/AArch64/named-vector-shuffles-sve.ll
@@ -14,14 +14,13 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    rdvl x9, #1
 ; CHECK-NEXT:    sub x9, x9, #1 // =1
-; CHECK-NEXT:    cmp x9, #0 // =0
 ; CHECK-NEXT:    ptrue p0.b
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x9, xzr, lo
+; CHECK-NEXT:    cmp x9, #0 // =0
 ; CHECK-NEXT:    st1b { z0.b }, p0, [sp]
 ; CHECK-NEXT:    st1b { z1.b }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9
-; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x9, xzr, lo
+; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x8, x9]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -36,15 +35,14 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    rdvl x9, #1
 ; CHECK-NEXT:    sub x9, x9, #1 // =1
-; CHECK-NEXT:    mov w10, #15
-; CHECK-NEXT:    cmp x9, #15 // =15
 ; CHECK-NEXT:    ptrue p0.b
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x9, x10, lo
+; CHECK-NEXT:    mov w10, #15
+; CHECK-NEXT:    cmp x9, #15 // =15
 ; CHECK-NEXT:    st1b { z0.b }, p0, [sp]
 ; CHECK-NEXT:    st1b { z1.b }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9
-; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x9, x10, lo
+; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x8, x9]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -60,15 +58,14 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    rdvl x9, #1
 ; CHECK-NEXT:    sub x9, x9, #1 // =1
-; CHECK-NEXT:    mov w10, #16
-; CHECK-NEXT:    cmp x9, #16 // =16
 ; CHECK-NEXT:    ptrue p0.b
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x9, x10, lo
+; CHECK-NEXT:    mov w10, #16
+; CHECK-NEXT:    cmp x9, #16 // =16
 ; CHECK-NEXT:    st1b { z0.b }, p0, [sp]
 ; CHECK-NEXT:    st1b { z1.b }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9
-; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x9, x10, lo
+; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x8, x9]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -83,14 +80,13 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cnth x9
 ; CHECK-NEXT:    sub x9, x9, #1 // =1
-; CHECK-NEXT:    cmp x9, #0 // =0
 ; CHECK-NEXT:    ptrue p0.h
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x9, xzr, lo
+; CHECK-NEXT:    cmp x9, #0 // =0
 ; CHECK-NEXT:    st1h { z0.h }, p0, [sp]
 ; CHECK-NEXT:    st1h { z1.h }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #1
-; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x9, xzr, lo
+; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x8, x9, lsl #1]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -105,15 +101,14 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cnth x10
 ; CHECK-NEXT:    sub x10, x10, #1 // =1
-; CHECK-NEXT:    mov w9, #7
-; CHECK-NEXT:    cmp x10, #7 // =7
 ; CHECK-NEXT:    ptrue p0.h
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    mov w9, #7
+; CHECK-NEXT:    cmp x10, #7 // =7
 ; CHECK-NEXT:    st1h { z0.h }, p0, [sp]
 ; CHECK-NEXT:    st1h { z1.h }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #1
-; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x8, x9, lsl #1]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -129,15 +124,14 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cnth x10
 ; CHECK-NEXT:    sub x10, x10, #1 // =1
-; CHECK-NEXT:    mov w9, #8
-; CHECK-NEXT:    cmp x10, #8 // =8
 ; CHECK-NEXT:    ptrue p0.h
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    mov w9, #8
+; CHECK-NEXT:    cmp x10, #8 // =8
 ; CHECK-NEXT:    st1h { z0.h }, p0, [sp]
 ; CHECK-NEXT:    st1h { z1.h }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #1
-; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x8, x9, lsl #1]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -152,14 +146,13 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cntw x9
 ; CHECK-NEXT:    sub x9, x9, #1 // =1
-; CHECK-NEXT:    cmp x9, #0 // =0
 ; CHECK-NEXT:    ptrue p0.s
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x9, xzr, lo
+; CHECK-NEXT:    cmp x9, #0 // =0
 ; CHECK-NEXT:    st1w { z0.s }, p0, [sp]
 ; CHECK-NEXT:    st1w { z1.s }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #2
-; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x9, xzr, lo
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8, x9, lsl #2]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -174,15 +167,14 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cntw x10
 ; CHECK-NEXT:    sub x10, x10, #1 // =1
-; CHECK-NEXT:    mov w9, #3
-; CHECK-NEXT:    cmp x10, #3 // =3
 ; CHECK-NEXT:    ptrue p0.s
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    mov w9, #3
+; CHECK-NEXT:    cmp x10, #3 // =3
 ; CHECK-NEXT:    st1w { z0.s }, p0, [sp]
 ; CHECK-NEXT:    st1w { z1.s }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #2
-; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8, x9, lsl #2]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -198,15 +190,14 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cntw x10
 ; CHECK-NEXT:    sub x10, x10, #1 // =1
-; CHECK-NEXT:    mov w9, #4
-; CHECK-NEXT:    cmp x10, #4 // =4
 ; CHECK-NEXT:    ptrue p0.s
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    mov w9, #4
+; CHECK-NEXT:    cmp x10, #4 // =4
 ; CHECK-NEXT:    st1w { z0.s }, p0, [sp]
 ; CHECK-NEXT:    st1w { z1.s }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #2
-; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8, x9, lsl #2]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -221,14 +212,13 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cntd x9
 ; CHECK-NEXT:    sub x9, x9, #1 // =1
-; CHECK-NEXT:    cmp x9, #0 // =0
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x9, xzr, lo
+; CHECK-NEXT:    cmp x9, #0 // =0
 ; CHECK-NEXT:    st1d { z0.d }, p0, [sp]
 ; CHECK-NEXT:    st1d { z1.d }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #3
-; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x9, xzr, lo
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8, x9, lsl #3]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -243,14 +233,13 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cntd x9
 ; CHECK-NEXT:    sub x9, x9, #1 // =1
-; CHECK-NEXT:    cmp x9, #1 // =1
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csinc x9, x9, xzr, lo
+; CHECK-NEXT:    cmp x9, #1 // =1
 ; CHECK-NEXT:    st1d { z0.d }, p0, [sp]
 ; CHECK-NEXT:    st1d { z1.d }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #3
-; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8]
+; CHECK-NEXT:    csinc x9, x9, xzr, lo
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8, x9, lsl #3]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -266,15 +255,14 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cntd x10
 ; CHECK-NEXT:    sub x10, x10, #1 // =1
-; CHECK-NEXT:    mov w9, #2
-; CHECK-NEXT:    cmp x10, #2 // =2
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    mov w9, #2
+; CHECK-NEXT:    cmp x10, #2 // =2
 ; CHECK-NEXT:    st1d { z0.d }, p0, [sp]
 ; CHECK-NEXT:    st1d { z1.d }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #3
-; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8, x9, lsl #3]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -289,14 +277,13 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cnth x9
 ; CHECK-NEXT:    sub x9, x9, #1 // =1
-; CHECK-NEXT:    cmp x9, #0 // =0
 ; CHECK-NEXT:    ptrue p0.h
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x9, xzr, lo
+; CHECK-NEXT:    cmp x9, #0 // =0
 ; CHECK-NEXT:    st1h { z0.h }, p0, [sp]
 ; CHECK-NEXT:    st1h { z1.h }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #1
-; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x9, xzr, lo
+; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x8, x9, lsl #1]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -311,15 +298,14 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cnth x10
 ; CHECK-NEXT:    sub x10, x10, #1 // =1
-; CHECK-NEXT:    mov w9, #7
-; CHECK-NEXT:    cmp x10, #7 // =7
 ; CHECK-NEXT:    ptrue p0.h
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    mov w9, #7
+; CHECK-NEXT:    cmp x10, #7 // =7
 ; CHECK-NEXT:    st1h { z0.h }, p0, [sp]
 ; CHECK-NEXT:    st1h { z1.h }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #1
-; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x8, x9, lsl #1]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -335,15 +321,14 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cnth x10
 ; CHECK-NEXT:    sub x10, x10, #1 // =1
-; CHECK-NEXT:    mov w9, #8
-; CHECK-NEXT:    cmp x10, #8 // =8
 ; CHECK-NEXT:    ptrue p0.h
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    mov w9, #8
+; CHECK-NEXT:    cmp x10, #8 // =8
 ; CHECK-NEXT:    st1h { z0.h }, p0, [sp]
 ; CHECK-NEXT:    st1h { z1.h }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #1
-; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x8, x9, lsl #1]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -358,14 +343,13 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cntw x9
 ; CHECK-NEXT:    sub x9, x9, #1 // =1
-; CHECK-NEXT:    cmp x9, #0 // =0
 ; CHECK-NEXT:    ptrue p0.s
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x9, xzr, lo
+; CHECK-NEXT:    cmp x9, #0 // =0
 ; CHECK-NEXT:    st1w { z0.s }, p0, [sp]
 ; CHECK-NEXT:    st1w { z1.s }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #2
-; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x9, xzr, lo
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8, x9, lsl #2]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -380,15 +364,14 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cntw x10
 ; CHECK-NEXT:    sub x10, x10, #1 // =1
-; CHECK-NEXT:    mov w9, #3
-; CHECK-NEXT:    cmp x10, #3 // =3
 ; CHECK-NEXT:    ptrue p0.s
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    mov w9, #3
+; CHECK-NEXT:    cmp x10, #3 // =3
 ; CHECK-NEXT:    st1w { z0.s }, p0, [sp]
 ; CHECK-NEXT:    st1w { z1.s }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #2
-; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8, x9, lsl #2]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -404,15 +387,14 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cntw x10
 ; CHECK-NEXT:    sub x10, x10, #1 // =1
-; CHECK-NEXT:    mov w9, #4
-; CHECK-NEXT:    cmp x10, #4 // =4
 ; CHECK-NEXT:    ptrue p0.s
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    mov w9, #4
+; CHECK-NEXT:    cmp x10, #4 // =4
 ; CHECK-NEXT:    st1w { z0.s }, p0, [sp]
 ; CHECK-NEXT:    st1w { z1.s }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #2
-; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8, x9, lsl #2]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -427,14 +409,13 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cntd x9
 ; CHECK-NEXT:    sub x9, x9, #1 // =1
-; CHECK-NEXT:    cmp x9, #0 // =0
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x9, xzr, lo
+; CHECK-NEXT:    cmp x9, #0 // =0
 ; CHECK-NEXT:    st1d { z0.d }, p0, [sp]
 ; CHECK-NEXT:    st1d { z1.d }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #3
-; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x9, xzr, lo
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8, x9, lsl #3]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -449,14 +430,13 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cntd x9
 ; CHECK-NEXT:    sub x9, x9, #1 // =1
-; CHECK-NEXT:    cmp x9, #1 // =1
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csinc x9, x9, xzr, lo
+; CHECK-NEXT:    cmp x9, #1 // =1
 ; CHECK-NEXT:    st1d { z0.d }, p0, [sp]
 ; CHECK-NEXT:    st1d { z1.d }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #3
-; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8]
+; CHECK-NEXT:    csinc x9, x9, xzr, lo
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8, x9, lsl #3]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -472,15 +452,14 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cntd x10
 ; CHECK-NEXT:    sub x10, x10, #1 // =1
-; CHECK-NEXT:    mov w9, #2
-; CHECK-NEXT:    cmp x10, #2 // =2
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    mov w9, #2
+; CHECK-NEXT:    cmp x10, #2 // =2
 ; CHECK-NEXT:    st1d { z0.d }, p0, [sp]
 ; CHECK-NEXT:    st1d { z1.d }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #3
-; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8, x9, lsl #3]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -495,17 +474,16 @@
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cntd x9
-; CHECK-NEXT:    sub x9, x9, #1 // =1
 ; CHECK-NEXT:    mov z0.d, p0/z, #1 // =0x1
 ; CHECK-NEXT:    ptrue p0.d
-; CHECK-NEXT:    cmp x9, #1 // =1
+; CHECK-NEXT:    sub x9, x9, #1 // =1
 ; CHECK-NEXT:    st1d { z0.d }, p0, [sp]
 ; CHECK-NEXT:    mov z0.d, p1/z, #1 // =0x1
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csinc x9, x9, xzr, lo
+; CHECK-NEXT:    cmp x9, #1 // =1
 ; CHECK-NEXT:    st1d { z0.d }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #3
-; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8]
+; CHECK-NEXT:    csinc x9, x9, xzr, lo
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8, x9, lsl #3]
 ; CHECK-NEXT:    and z0.d, z0.d, #0x1
 ; CHECK-NEXT:    cmpne p0.d, p0/z, z0.d, #0
 ; CHECK-NEXT:    addvl sp, sp, #2
@@ -522,18 +500,17 @@
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cntw x10
-; CHECK-NEXT:    sub x10, x10, #1 // =1
 ; CHECK-NEXT:    mov z0.s, p0/z, #1 // =0x1
 ; CHECK-NEXT:    ptrue p0.s
-; CHECK-NEXT:    mov w9, #2
-; CHECK-NEXT:    cmp x10, #2 // =2
+; CHECK-NEXT:    sub x10, x10, #1 // =1
 ; CHECK-NEXT:    st1w { z0.s }, p0, [sp]
 ; CHECK-NEXT:    mov z0.s, p1/z, #1 // =0x1
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    mov w9, #2
+; CHECK-NEXT:    cmp x10, #2 // =2
 ; CHECK-NEXT:    st1w { z0.s }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #2
-; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8, x9, lsl #2]
 ; CHECK-NEXT:    and z0.s, z0.s, #0x1
 ; CHECK-NEXT:    cmpne p0.s, p0/z, z0.s, #0
 ; CHECK-NEXT:    addvl sp, sp, #2
@@ -550,18 +527,17 @@
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cnth x10
-; CHECK-NEXT:    sub x10, x10, #1 // =1
 ; CHECK-NEXT:    mov z0.h, p0/z, #1 // =0x1
 ; CHECK-NEXT:    ptrue p0.h
-; CHECK-NEXT:    mov w9, #4
-; CHECK-NEXT:    cmp x10, #4 // =4
+; CHECK-NEXT:    sub x10, x10, #1 // =1
 ; CHECK-NEXT:    st1h { z0.h }, p0, [sp]
 ; CHECK-NEXT:    mov z0.h, p1/z, #1 // =0x1
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    mov w9, #4
+; CHECK-NEXT:    cmp x10, #4 // =4
 ; CHECK-NEXT:    st1h { z0.h }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #1
-; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x8, x9, lsl #1]
 ; CHECK-NEXT:    and z0.h, z0.h, #0x1
 ; CHECK-NEXT:    cmpne p0.h, p0/z, z0.h, #0
 ; CHECK-NEXT:    addvl sp, sp, #2
@@ -578,18 +554,17 @@
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    rdvl x9, #1
-; CHECK-NEXT:    sub x9, x9, #1 // =1
 ; CHECK-NEXT:    mov z0.b, p0/z, #1 // =0x1
 ; CHECK-NEXT:    ptrue p0.b
-; CHECK-NEXT:    mov w10, #8
-; CHECK-NEXT:    cmp x9, #8 // =8
+; CHECK-NEXT:    sub x9, x9, #1 // =1
 ; CHECK-NEXT:    st1b { z0.b }, p0, [sp]
 ; CHECK-NEXT:    mov z0.b, p1/z, #1 // =0x1
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x9, x10, lo
+; CHECK-NEXT:    mov w10, #8
+; CHECK-NEXT:    cmp x9, #8 // =8
 ; CHECK-NEXT:    st1b { z0.b }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9
-; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x8]
+; CHECK-NEXT:    csel x9, x9, x10, lo
+; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x8, x9]
 ; CHECK-NEXT:    and z0.b, z0.b, #0x1
 ; CHECK-NEXT:    cmpne p0.b, p0/z, z0.b, #0
 ; CHECK-NEXT:    addvl sp, sp, #2
@@ -607,14 +582,13 @@
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    cntd x9
 ; CHECK-NEXT:    sub x9, x9, #1 // =1
-; CHECK-NEXT:    cmp x9, #1 // =1
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csinc x9, x9, xzr, lo
+; CHECK-NEXT:    cmp x9, #1 // =1
 ; CHECK-NEXT:    st1d { z0.d }, p0, [sp]
 ; CHECK-NEXT:    st1d { z1.d }, p0, [x8, #1, mul vl]
-; CHECK-NEXT:    add x8, x8, x9, lsl #3
-; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8]
+; CHECK-NEXT:    csinc x9, x9, xzr, lo
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8, x9, lsl #3]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -657,11 +631,10 @@
 ; CHECK-NEXT:    addvl sp, sp, #-8
 ; CHECK-NEXT:    rdvl x10, #1
 ; CHECK-NEXT:    sub x10, x10, #1 // =1
-; CHECK-NEXT:    mov w9, #16
-; CHECK-NEXT:    cmp x10, #16 // =16
 ; CHECK-NEXT:    ptrue p0.s
 ; CHECK-NEXT:    mov x8, sp
-; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    mov w9, #16
+; CHECK-NEXT:    cmp x10, #16 // =16
 ; CHECK-NEXT:    st1w { z3.s }, p0, [x8, #3, mul vl]
 ; CHECK-NEXT:    st1w { z2.s }, p0, [x8, #2, mul vl]
 ; CHECK-NEXT:    st1w { z1.s }, p0, [x8, #1, mul vl]
@@ -670,8 +643,9 @@
 ; CHECK-NEXT:    st1w { z4.s }, p0, [x8, #4, mul vl]
 ; CHECK-NEXT:    st1w { z5.s }, p0, [x8, #5, mul vl]
 ; CHECK-NEXT:    st1w { z6.s }, p0, [x8, #6, mul vl]
+; CHECK-NEXT:    csel x9, x10, x9, lo
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8, x9, lsl #2]
 ; CHECK-NEXT:    add x8, x8, x9, lsl #2
-; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8]
 ; CHECK-NEXT:    ld1w { z1.s }, p0/z, [x8, #1, mul vl]
 ; CHECK-NEXT:    ld1w { z2.s }, p0/z, [x8, #2, mul vl]
 ; CHECK-NEXT:    ld1w { z3.s }, p0/z, [x8, #3, mul vl]
@@ -696,8 +670,8 @@
 ; CHECK-NEXT:    st1b { z0.b }, p0, [sp]
 ; CHECK-NEXT:    st1b { z1.b }, p0, [x8, #1, mul vl]
 ; CHECK-NEXT:    addvl x8, x8, #1
-; CHECK-NEXT:    sub x8, x8, #16 // =16
-; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x8]
+; CHECK-NEXT:    mov x9, #-16
+; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x8, x9]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -715,8 +689,8 @@
 ; CHECK-NEXT:    st1b { z0.b }, p0, [sp]
 ; CHECK-NEXT:    st1b { z1.b }, p0, [x8, #1, mul vl]
 ; CHECK-NEXT:    addvl x8, x8, #1
-; CHECK-NEXT:    sub x8, x8, #1 // =1
-; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x8]
+; CHECK-NEXT:    mov x9, #-1
+; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x8, x9]
 ; CHECK-NEXT:    addvl sp, sp, #2
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -1205,8 +1179,8 @@
 ; CHECK-NEXT:    st1b { z0.b }, p0, [sp]
 ; CHECK-NEXT:    st1b { z1.b }, p0, [x8, #1, mul vl]
 ; CHECK-NEXT:    addvl x8, x8, #1
-; CHECK-NEXT:    sub x8, x8, #1 // =1
-; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x8]
+; CHECK-NEXT:    mov x9, #-1
+; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x8, x9]
 ; CHECK-NEXT:    and z0.b, z0.b, #0x1
 ; CHECK-NEXT:    cmpne p0.b, p0/z, z0.b, #0
 ; CHECK-NEXT:    addvl sp, sp, #2
diff --git a/llvm/test/CodeGen/AArch64/sve-fold-vscale.ll b/llvm/test/CodeGen/AArch64/sve-fold-vscale.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/sve-fold-vscale.ll
@@ -0,0 +1,74 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -disable-lsr < %s 2>%t | FileCheck %s
+; RUN: FileCheck --check-prefix=WARN --allow-empty %s <%t
+
+; If this check fails please read test/CodeGen/AArch64/README for instructions on how to resolve it.
+; WARN-NOT: warning
+
+; Check that vscale call is recognised by load/store reg/reg pattern and
+; partially folded, with the rest pulled out of the loop. This requires LSR to
+; be disabled, which is something that will be addressed at a later date.
+
+define void @ld1w_reg_loop([32000 x i32]* %addr) {
+; CHECK-LABEL: ld1w_reg_loop:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    mov x8, xzr
+; CHECK-NEXT:    cntw x9
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:  .LBB0_1: // %vector.body
+; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0, x8, lsl #2]
+; CHECK-NEXT:    adds x8, x8, x9
+; CHECK-NEXT:    b.ne .LBB0_1
+; CHECK-NEXT:  // %bb.2: // %for.cond.cleanup
+; CHECK-NEXT:    ret
+entry:
+  %0 = call i64 @llvm.vscale.i64()
+  %1 = shl i64 %0, 2
+  br label %vector.body
+
+vector.body:
+  %index = phi i64 [ 0, %entry ], [ %index.next, %vector.body ]
+  %2 = getelementptr inbounds [32000 x i32], [32000 x i32]* %addr, i64 0, i64 %index
+  %3 = bitcast i32* %2 to <vscale x 4 x i32>*
+  %load = load volatile <vscale x 4 x i32>, <vscale x 4 x i32>* %3, align 16
+  %index.next = add i64 %index, %1
+  %4 = icmp eq i64 %index.next, 0
+  br i1 %4, label %for.cond.cleanup, label %vector.body
+
+for.cond.cleanup:
+  ret void
+}
+
+define void @st1w_reg_loop([32000 x i32]* %addr, <vscale x 4 x i32> %val) {
+; CHECK-LABEL: st1w_reg_loop:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    mov x8, xzr
+; CHECK-NEXT:    cntw x9
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:  .LBB1_1: // %vector.body
+; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    st1w { z0.s }, p0, [x0, x8, lsl #2]
+; CHECK-NEXT:    adds x8, x8, x9
+; CHECK-NEXT:    b.ne .LBB1_1
+; CHECK-NEXT:  // %bb.2: // %for.cond.cleanup
+; CHECK-NEXT:    ret
+entry:
+  %0 = call i64 @llvm.vscale.i64()
+  %1 = shl i64 %0, 2
+  br label %vector.body
+
+vector.body:
+  %index = phi i64 [ 0, %entry ], [ %index.next, %vector.body ]
+  %2 = getelementptr inbounds [32000 x i32], [32000 x i32]* %addr, i64 0, i64 %index
+  %3 = bitcast i32* %2 to <vscale x 4 x i32>*
+  store volatile <vscale x 4 x i32> %val, <vscale x 4 x i32>* %3, align 16
+  %index.next = add i64 %index, %1
+  %4 = icmp eq i64 %index.next, 0
+  br i1 %4, label %for.cond.cleanup, label %vector.body
+
+for.cond.cleanup:
+  ret void
+}
+
+declare i64 @llvm.vscale.i64()
diff --git a/llvm/test/CodeGen/AArch64/sve-ld1-addressing-mode-reg-imm.ll b/llvm/test/CodeGen/AArch64/sve-ld1-addressing-mode-reg-imm.ll
--- a/llvm/test/CodeGen/AArch64/sve-ld1-addressing-mode-reg-imm.ll
+++ b/llvm/test/CodeGen/AArch64/sve-ld1-addressing-mode-reg-imm.ll
@@ -43,9 +43,9 @@
 define <vscale x 16 x i8> @ld1b_out_of_upper_bound(<vscale x 16 x i8>* %a) {
 ; CHECK-LABEL: ld1b_out_of_upper_bound:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    addvl x8, x0, #8
+; CHECK-NEXT:    rdvl x8, #8
 ; CHECK-NEXT:    ptrue p0.b
-; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x8]
+; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x0, x8]
 ; CHECK-NEXT:    ret
   %base = getelementptr <vscale x 16 x i8>, <vscale x 16 x i8>* %a, i64 8
   %load = load <vscale x 16 x i8>, <vscale x 16 x i8>* %base
@@ -55,9 +55,9 @@
 define <vscale x 16 x i8> @ld1b_out_of_lower_bound(<vscale x 16 x i8>* %a) {
 ; CHECK-LABEL: ld1b_out_of_lower_bound:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    addvl x8, x0, #-9
+; CHECK-NEXT:    rdvl x8, #-9
 ; CHECK-NEXT:    ptrue p0.b
-; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x8]
+; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x0, x8]
 ; CHECK-NEXT:    ret
   %base = getelementptr <vscale x 16 x i8>, <vscale x 16 x i8>* %a, i64 -9
   %load = load <vscale x 16 x i8>, <vscale x 16 x i8>* %base
@@ -138,4 +138,3 @@
   %val = load volatile <vscale x 12 x half>, <vscale x 12 x half>* %a
   ret void
 }
-
diff --git a/llvm/test/CodeGen/AArch64/sve-ld1-addressing-mode-reg-reg.ll b/llvm/test/CodeGen/AArch64/sve-ld1-addressing-mode-reg-reg.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/sve-ld1-addressing-mode-reg-reg.ll
@@ -0,0 +1,302 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve,+bf16 < %s 2>%t | FileCheck %s
+; RUN: FileCheck --check-prefix=WARN --allow-empty %s <%t
+
+; If this check fails please read test/CodeGen/AArch64/README for instructions on how to resolve it.
+; WARN-NOT: warning
+
+; LD1B
+
+define <vscale x 16 x i8> @ld1_nxv16i8(i8* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv16i8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.b
+; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x0, x1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i8, i8* %addr, i64 %off
+  %ptrcast = bitcast i8* %ptr to <vscale x 16 x i8>*
+  %val = load volatile <vscale x 16 x i8>, <vscale x 16 x i8>* %ptrcast
+  ret <vscale x 16 x i8> %val
+}
+
+define <vscale x 8 x i16> @ld1_nxv8i16_zext8(i8* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv8i16_zext8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.h
+; CHECK-NEXT:    ld1b { z0.h }, p0/z, [x0, x1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i8, i8* %addr, i64 %off
+  %ptrcast = bitcast i8* %ptr to <vscale x 8 x i8>*
+  %val = load volatile <vscale x 8 x i8>, <vscale x 8 x i8>* %ptrcast
+  %zext = zext <vscale x 8 x i8> %val to <vscale x 8 x i16>
+  ret <vscale x 8 x i16> %zext
+}
+
+define <vscale x 4 x i32> @ld1_nxv4i32_zext8(i8* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv4i32_zext8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    ld1b { z0.s }, p0/z, [x0, x1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i8, i8* %addr, i64 %off
+  %ptrcast = bitcast i8* %ptr to <vscale x 4 x i8>*
+  %val = load volatile <vscale x 4 x i8>, <vscale x 4 x i8>* %ptrcast
+  %zext = zext <vscale x 4 x i8> %val to <vscale x 4 x i32>
+  ret <vscale x 4 x i32> %zext
+}
+
+define <vscale x 2 x i64> @ld1_nxv2i64_zext8(i8* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv2i64_zext8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    ld1b { z0.d }, p0/z, [x0, x1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i8, i8* %addr, i64 %off
+  %ptrcast = bitcast i8* %ptr to <vscale x 2 x i8>*
+  %val = load volatile <vscale x 2 x i8>, <vscale x 2 x i8>* %ptrcast
+  %zext = zext <vscale x 2 x i8> %val to <vscale x 2 x i64>
+  ret <vscale x 2 x i64> %zext
+}
+
+define <vscale x 8 x i16> @ld1_nxv8i16_sext8(i8* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv8i16_sext8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.h
+; CHECK-NEXT:    ld1sb { z0.h }, p0/z, [x0, x1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i8, i8* %addr, i64 %off
+  %ptrcast = bitcast i8* %ptr to <vscale x 8 x i8>*
+  %val = load volatile <vscale x 8 x i8>, <vscale x 8 x i8>* %ptrcast
+  %sext = sext <vscale x 8 x i8> %val to <vscale x 8 x i16>
+  ret <vscale x 8 x i16> %sext
+}
+
+define <vscale x 4 x i32> @ld1_nxv4i32_sext8(i8* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv4i32_sext8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    ld1sb { z0.s }, p0/z, [x0, x1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i8, i8* %addr, i64 %off
+  %ptrcast = bitcast i8* %ptr to <vscale x 4 x i8>*
+  %val = load volatile <vscale x 4 x i8>, <vscale x 4 x i8>* %ptrcast
+  %sext = sext <vscale x 4 x i8> %val to <vscale x 4 x i32>
+  ret <vscale x 4 x i32> %sext
+}
+
+define <vscale x 2 x i64> @ld1_nxv2i64_sext8(i8* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv2i64_sext8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    ld1sb { z0.d }, p0/z, [x0, x1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i8, i8* %addr, i64 %off
+  %ptrcast = bitcast i8* %ptr to <vscale x 2 x i8>*
+  %val = load volatile <vscale x 2 x i8>, <vscale x 2 x i8>* %ptrcast
+  %sext = sext <vscale x 2 x i8> %val to <vscale x 2 x i64>
+  ret <vscale x 2 x i64> %sext
+}
+
+; LD1H
+
+define <vscale x 8 x i16> @ld1_nxv8i16(i16* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv8i16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.h
+; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x0, x1, lsl #1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i16, i16* %addr, i64 %off
+  %ptrcast = bitcast i16* %ptr to <vscale x 8 x i16>*
+  %val = load volatile <vscale x 8 x i16>, <vscale x 8 x i16>* %ptrcast
+  ret <vscale x 8 x i16> %val
+}
+
+define <vscale x 4 x i32> @ld1_nxv4i32_zext16(i16* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv4i32_zext16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    ld1h { z0.s }, p0/z, [x0, x1, lsl #1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i16, i16* %addr, i64 %off
+  %ptrcast = bitcast i16* %ptr to <vscale x 4 x i16>*
+  %val = load volatile <vscale x 4 x i16>, <vscale x 4 x i16>* %ptrcast
+  %zext = zext <vscale x 4 x i16> %val to <vscale x 4 x i32>
+  ret <vscale x 4 x i32> %zext
+}
+
+define <vscale x 2 x i64> @ld1_nxv2i64_zext16(i16* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv2i64_zext16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, x1, lsl #1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i16, i16* %addr, i64 %off
+  %ptrcast = bitcast i16* %ptr to <vscale x 2 x i16>*
+  %val = load volatile <vscale x 2 x i16>, <vscale x 2 x i16>* %ptrcast
+  %zext = zext <vscale x 2 x i16> %val to <vscale x 2 x i64>
+  ret <vscale x 2 x i64> %zext
+}
+
+define <vscale x 4 x i32> @ld1_nxv4i32_sext16(i16* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv4i32_sext16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    ld1sh { z0.s }, p0/z, [x0, x1, lsl #1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i16, i16* %addr, i64 %off
+  %ptrcast = bitcast i16* %ptr to <vscale x 4 x i16>*
+  %val = load volatile <vscale x 4 x i16>, <vscale x 4 x i16>* %ptrcast
+  %sext = sext <vscale x 4 x i16> %val to <vscale x 4 x i32>
+  ret <vscale x 4 x i32> %sext
+}
+
+define <vscale x 2 x i64> @ld1_nxv2i64_sext16(i16* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv2i64_sext16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    ld1sh { z0.d }, p0/z, [x0, x1, lsl #1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i16, i16* %addr, i64 %off
+  %ptrcast = bitcast i16* %ptr to <vscale x 2 x i16>*
+  %val = load volatile <vscale x 2 x i16>, <vscale x 2 x i16>* %ptrcast
+  %sext = sext <vscale x 2 x i16> %val to <vscale x 2 x i64>
+  ret <vscale x 2 x i64> %sext
+}
+
+define <vscale x 8 x half> @ld1_nxv8f16(half* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv8f16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.h
+; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x0, x1, lsl #1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds half, half* %addr, i64 %off
+  %ptrcast = bitcast half* %ptr to <vscale x 8 x half>*
+  %val = load volatile <vscale x 8 x half>, <vscale x 8 x half>* %ptrcast
+  ret <vscale x 8 x half> %val
+}
+
+define <vscale x 8 x bfloat> @ld1_nxv8bf16(bfloat* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv8bf16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.h
+; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x0, x1, lsl #1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds bfloat, bfloat* %addr, i64 %off
+  %ptrcast = bitcast bfloat* %ptr to <vscale x 8 x bfloat>*
+  %val = load volatile <vscale x 8 x bfloat>, <vscale x 8 x bfloat>* %ptrcast
+  ret <vscale x 8 x bfloat> %val
+}
+
+define <vscale x 4 x half> @ld1_nxv4f16(half* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv4f16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    ld1h { z0.s }, p0/z, [x0, x1, lsl #1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds half, half* %addr, i64 %off
+  %ptrcast = bitcast half* %ptr to <vscale x 4 x half>*
+  %val = load volatile <vscale x 4 x half>, <vscale x 4 x half>* %ptrcast
+  ret <vscale x 4 x half> %val
+}
+
+define <vscale x 2 x half> @ld1_nxv2f16(half* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv2f16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, x1, lsl #1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds half, half* %addr, i64 %off
+  %ptrcast = bitcast half* %ptr to <vscale x 2 x half>*
+  %val = load volatile <vscale x 2 x half>, <vscale x 2 x half>* %ptrcast
+  ret <vscale x 2 x half> %val
+}
+
+; LD1W
+
+define <vscale x 4 x i32> @ld1_nxv4i32(i32* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv4i32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0, x1, lsl #2]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i32, i32* %addr, i64 %off
+  %ptrcast = bitcast i32* %ptr to <vscale x 4 x i32>*
+  %val = load volatile <vscale x 4 x i32>, <vscale x 4 x i32>* %ptrcast
+  ret <vscale x 4 x i32> %val
+}
+
+define <vscale x 2 x i64> @ld1_nxv2i64_zext32(i32* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv2i64_zext32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, x1, lsl #2]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i32, i32* %addr, i64 %off
+  %ptrcast = bitcast i32* %ptr to <vscale x 2 x i32>*
+  %val = load volatile <vscale x 2 x i32>, <vscale x 2 x i32>* %ptrcast
+  %zext = zext <vscale x 2 x i32> %val to <vscale x 2 x i64>
+  ret <vscale x 2 x i64> %zext
+}
+
+define <vscale x 2 x i64> @ld1_nxv2i64_sext32(i32* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv2i64_sext32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    ld1sw { z0.d }, p0/z, [x0, x1, lsl #2]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i32, i32* %addr, i64 %off
+  %ptrcast = bitcast i32* %ptr to <vscale x 2 x i32>*
+  %val = load volatile <vscale x 2 x i32>, <vscale x 2 x i32>* %ptrcast
+  %sext = sext <vscale x 2 x i32> %val to <vscale x 2 x i64>
+  ret <vscale x 2 x i64> %sext
+}
+
+define <vscale x 4 x float> @ld1_nxv4f32(float* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv4f32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0, x1, lsl #2]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds float, float* %addr, i64 %off
+  %ptrcast = bitcast float* %ptr to <vscale x 4 x float>*
+  %val = load volatile <vscale x 4 x float>, <vscale x 4 x float>* %ptrcast
+  ret <vscale x 4 x float> %val
+}
+
+define <vscale x 2 x float> @ld1_nxv2f32(float* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv2f32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, x1, lsl #2]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds float, float* %addr, i64 %off
+  %ptrcast = bitcast float* %ptr to <vscale x 2 x float>*
+  %val = load volatile <vscale x 2 x float>, <vscale x 2 x float>* %ptrcast
+  ret <vscale x 2 x float> %val
+}
+
+; LD1D
+
+define <vscale x 2 x i64> @ld1_nxv2i64(i64* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv2i64:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0, x1, lsl #3]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i64, i64* %addr, i64 %off
+  %ptrcast = bitcast i64* %ptr to <vscale x 2 x i64>*
+  %val = load volatile <vscale x 2 x i64>, <vscale x 2 x i64>* %ptrcast
+  ret <vscale x 2 x i64> %val
+}
+
+define <vscale x 2 x double> @ld1_nxv2f64(double* %addr, i64 %off) {
+; CHECK-LABEL: ld1_nxv2f64:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0, x1, lsl #3]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds double, double* %addr, i64 %off
+  %ptrcast = bitcast double* %ptr to <vscale x 2 x double>*
+  %val = load volatile <vscale x 2 x double>, <vscale x 2 x double>* %ptrcast
+  ret <vscale x 2 x double> %val
+}
diff --git a/llvm/test/CodeGen/AArch64/sve-st1-addressing-mode-reg-imm.ll b/llvm/test/CodeGen/AArch64/sve-st1-addressing-mode-reg-imm.ll
--- a/llvm/test/CodeGen/AArch64/sve-st1-addressing-mode-reg-imm.ll
+++ b/llvm/test/CodeGen/AArch64/sve-st1-addressing-mode-reg-imm.ll
@@ -43,9 +43,9 @@
 define void @st1b_out_of_upper_bound(<vscale x 16 x i8> %data, <vscale x 16 x i8>* %a) {
 ; CHECK-LABEL: st1b_out_of_upper_bound:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    addvl x8, x0, #8
+; CHECK-NEXT:    rdvl x8, #8
 ; CHECK-NEXT:    ptrue p0.b
-; CHECK-NEXT:    st1b { z0.b }, p0, [x8]
+; CHECK-NEXT:    st1b { z0.b }, p0, [x0, x8]
 ; CHECK-NEXT:    ret
   %base = getelementptr <vscale x 16 x i8>, <vscale x 16 x i8>* %a, i64 8
   store <vscale x 16 x i8> %data, <vscale x 16 x i8>* %base
@@ -55,9 +55,9 @@
 define void @st1b_out_of_lower_bound(<vscale x 16 x i8> %data, <vscale x 16 x i8>* %a) {
 ; CHECK-LABEL: st1b_out_of_lower_bound:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    addvl x8, x0, #-9
+; CHECK-NEXT:    rdvl x8, #-9
 ; CHECK-NEXT:    ptrue p0.b
-; CHECK-NEXT:    st1b { z0.b }, p0, [x8]
+; CHECK-NEXT:    st1b { z0.b }, p0, [x0, x8]
 ; CHECK-NEXT:    ret
   %base = getelementptr <vscale x 16 x i8>, <vscale x 16 x i8>* %a, i64 -9
   store <vscale x 16 x i8> %data, <vscale x 16 x i8>* %base
diff --git a/llvm/test/CodeGen/AArch64/sve-st1-addressing-mode-reg-reg.ll b/llvm/test/CodeGen/AArch64/sve-st1-addressing-mode-reg-reg.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/sve-st1-addressing-mode-reg-reg.ll
@@ -0,0 +1,224 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve,+bf16 < %s 2>%t | FileCheck %s
+; RUN: FileCheck --check-prefix=WARN --allow-empty %s <%t
+
+; If this check fails please read test/CodeGen/AArch64/README for instructions on how to resolve it.
+; WARN-NOT: warning
+
+; ST1B
+
+define void @st1_nxv16i8(i8* %addr, i64 %off, <vscale x 16 x i8> %val) {
+; CHECK-LABEL: st1_nxv16i8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.b
+; CHECK-NEXT:    st1b { z0.b }, p0, [x0, x1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i8, i8* %addr, i64 %off
+  %ptrcast = bitcast i8* %ptr to <vscale x 16 x i8>*
+  store <vscale x 16 x i8> %val, <vscale x 16 x i8>* %ptrcast
+  ret void
+}
+
+define void @st1_nxv8i16_trunc8(i8* %addr, i64 %off, <vscale x 8 x i16> %val) {
+; CHECK-LABEL: st1_nxv8i16_trunc8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.h
+; CHECK-NEXT:    st1b { z0.h }, p0, [x0, x1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i8, i8* %addr, i64 %off
+  %ptrcast = bitcast i8* %ptr to <vscale x 8 x i8>*
+  %trunc = trunc <vscale x 8 x i16> %val to <vscale x 8 x i8>
+  store <vscale x 8 x i8> %trunc, <vscale x 8 x i8>* %ptrcast
+  ret void
+}
+
+define void @st1_nxv4i32_trunc8(i8* %addr, i64 %off, <vscale x 4 x i32> %val) {
+; CHECK-LABEL: st1_nxv4i32_trunc8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    st1b { z0.s }, p0, [x0, x1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i8, i8* %addr, i64 %off
+  %ptrcast = bitcast i8* %ptr to <vscale x 4 x i8>*
+  %trunc = trunc <vscale x 4 x i32> %val to <vscale x 4 x i8>
+  store <vscale x 4 x i8> %trunc, <vscale x 4 x i8>* %ptrcast
+  ret void
+}
+
+define void @st1_nxv2i64_trunc8(i8* %addr, i64 %off, <vscale x 2 x i64> %val) {
+; CHECK-LABEL: st1_nxv2i64_trunc8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    st1b { z0.d }, p0, [x0, x1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i8, i8* %addr, i64 %off
+  %ptrcast = bitcast i8* %ptr to <vscale x 2 x i8>*
+  %trunc = trunc <vscale x 2 x i64> %val to <vscale x 2 x i8>
+  store <vscale x 2 x i8> %trunc, <vscale x 2 x i8>* %ptrcast
+  ret void
+}
+
+; ST1H
+
+define void @st1_nxv8i16(i16* %addr, i64 %off, <vscale x 8 x i16> %val) {
+; CHECK-LABEL: st1_nxv8i16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.h
+; CHECK-NEXT:    st1h { z0.h }, p0, [x0, x1, lsl #1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i16, i16* %addr, i64 %off
+  %ptrcast = bitcast i16* %ptr to <vscale x 8 x i16>*
+  store <vscale x 8 x i16> %val, <vscale x 8 x i16>* %ptrcast
+  ret void
+}
+
+define void @st1_nxv4i32_trunc16(i16* %addr, i64 %off, <vscale x 4 x i32> %val) {
+; CHECK-LABEL: st1_nxv4i32_trunc16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    st1h { z0.s }, p0, [x0, x1, lsl #1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i16, i16* %addr, i64 %off
+  %ptrcast = bitcast i16* %ptr to <vscale x 4 x i16>*
+  %trunc = trunc <vscale x 4 x i32> %val to <vscale x 4 x i16>
+  store <vscale x 4 x i16> %trunc, <vscale x 4 x i16>* %ptrcast
+  ret void
+}
+
+define void @st1_nxv2i64_trunc16(i16* %addr, i64 %off, <vscale x 2 x i64> %val) {
+; CHECK-LABEL: st1_nxv2i64_trunc16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    st1h { z0.d }, p0, [x0, x1, lsl #1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i16, i16* %addr, i64 %off
+  %ptrcast = bitcast i16* %ptr to <vscale x 2 x i16>*
+  %trunc = trunc <vscale x 2 x i64> %val to <vscale x 2 x i16>
+  store <vscale x 2 x i16> %trunc, <vscale x 2 x i16>* %ptrcast
+  ret void
+}
+
+define void @st1_nxv8f16(half* %addr, i64 %off, <vscale x 8 x half> %val) {
+; CHECK-LABEL: st1_nxv8f16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.h
+; CHECK-NEXT:    st1h { z0.h }, p0, [x0, x1, lsl #1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds half, half* %addr, i64 %off
+  %ptrcast = bitcast half* %ptr to <vscale x 8 x half>*
+  store <vscale x 8 x half> %val, <vscale x 8 x half>* %ptrcast
+  ret void
+}
+
+define void @st1_nxv8bf16(bfloat* %addr, i64 %off, <vscale x 8 x bfloat> %val) {
+; CHECK-LABEL: st1_nxv8bf16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.h
+; CHECK-NEXT:    st1h { z0.h }, p0, [x0, x1, lsl #1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds bfloat, bfloat* %addr, i64 %off
+  %ptrcast = bitcast bfloat* %ptr to <vscale x 8 x bfloat>*
+  store <vscale x 8 x bfloat> %val, <vscale x 8 x bfloat>* %ptrcast
+  ret void
+}
+
+define void @st1_nxv4f16(half* %addr, i64 %off, <vscale x 4 x half> %val) {
+; CHECK-LABEL: st1_nxv4f16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    st1h { z0.s }, p0, [x0, x1, lsl #1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds half, half* %addr, i64 %off
+  %ptrcast = bitcast half* %ptr to <vscale x 4 x half>*
+  store <vscale x 4 x half> %val, <vscale x 4 x half>* %ptrcast
+  ret void
+}
+
+define void @st1_nxv2f16(half* %addr, i64 %off, <vscale x 2 x half> %val) {
+; CHECK-LABEL: st1_nxv2f16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    st1h { z0.d }, p0, [x0, x1, lsl #1]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds half, half* %addr, i64 %off
+  %ptrcast = bitcast half* %ptr to <vscale x 2 x half>*
+  store <vscale x 2 x half> %val, <vscale x 2 x half>* %ptrcast
+  ret void
+}
+
+; ST1W
+
+define void @st1_nxv4i32(i32* %addr, i64 %off, <vscale x 4 x i32> %val) {
+; CHECK-LABEL: st1_nxv4i32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    st1w { z0.s }, p0, [x0, x1, lsl #2]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i32, i32* %addr, i64 %off
+  %ptrcast = bitcast i32* %ptr to <vscale x 4 x i32>*
+  store <vscale x 4 x i32> %val, <vscale x 4 x i32>* %ptrcast
+  ret void
+}
+
+define void @st1_nxv2i64_trunc32(i32* %addr, i64 %off, <vscale x 2 x i64> %val) {
+; CHECK-LABEL: st1_nxv2i64_trunc32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    st1w { z0.d }, p0, [x0, x1, lsl #2]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i32, i32* %addr, i64 %off
+  %ptrcast = bitcast i32* %ptr to <vscale x 2 x i32>*
+  %trunc = trunc <vscale x 2 x i64> %val to <vscale x 2 x i32>
+  store <vscale x 2 x i32> %trunc, <vscale x 2 x i32>* %ptrcast
+  ret void
+}
+
+define void @st1_nxv4f32(float* %addr, i64 %off, <vscale x 4 x float> %val) {
+; CHECK-LABEL: st1_nxv4f32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    st1w { z0.s }, p0, [x0, x1, lsl #2]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds float, float* %addr, i64 %off
+  %ptrcast = bitcast float* %ptr to <vscale x 4 x float>*
+  store <vscale x 4 x float> %val, <vscale x 4 x float>* %ptrcast
+  ret void
+}
+
+define void @st1_nxv2f32(float* %addr, i64 %off, <vscale x 2 x float> %val) {
+; CHECK-LABEL: st1_nxv2f32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    st1w { z0.d }, p0, [x0, x1, lsl #2]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds float, float* %addr, i64 %off
+  %ptrcast = bitcast float* %ptr to <vscale x 2 x float>*
+  store <vscale x 2 x float> %val, <vscale x 2 x float>* %ptrcast
+  ret void
+}
+
+; ST1D
+
+define void @st1_nxv2i64(i64* %addr, i64 %off, <vscale x 2 x i64> %val) {
+; CHECK-LABEL: st1_nxv2i64:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    st1d { z0.d }, p0, [x0, x1, lsl #3]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds i64, i64* %addr, i64 %off
+  %ptrcast = bitcast i64* %ptr to <vscale x 2 x i64>*
+  store <vscale x 2 x i64> %val, <vscale x 2 x i64>* %ptrcast
+  ret void
+}
+
+define void @st1_nxv2f64(double* %addr, i64 %off, <vscale x 2 x double> %val) {
+; CHECK-LABEL: st1_nxv2f64:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    st1d { z0.d }, p0, [x0, x1, lsl #3]
+; CHECK-NEXT:    ret
+  %ptr = getelementptr inbounds double, double* %addr, i64 %off
+  %ptrcast = bitcast double* %ptr to <vscale x 2 x double>*
+  store <vscale x 2 x double> %val, <vscale x 2 x double>* %ptrcast
+  ret void
+}