diff --git a/llvm/lib/Target/AArch64/AArch64InstrAtomics.td b/llvm/lib/Target/AArch64/AArch64InstrAtomics.td
index 2d7a9d6f00bd0..aaf8e1bfc8f0f 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrAtomics.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrAtomics.td
@@ -548,13 +548,13 @@ defm atomic_load_fmin  : binary_atomic_op_fp<atomic_load_fmin>;
 defm atomic_load_fmax  : binary_atomic_op_fp<atomic_load_fmax>;
 
 let Predicates = [HasLSFE] in {
-  defm : LDFPOPregister_patterns<"LDFADD",   "atomic_load_fadd">;
-  defm : LDFPOPregister_patterns<"LDFMAXNM", "atomic_load_fmax">;
-  defm : LDFPOPregister_patterns<"LDFMINNM", "atomic_load_fmin">;
+  defm : LDFPOPregister_patterns<"FADD",   "atomic_load_fadd">;
+  defm : LDFPOPregister_patterns<"FMAXNM", "atomic_load_fmax">;
+  defm : LDFPOPregister_patterns<"FMINNM", "atomic_load_fmin">;
 
-  defm : LDBFPOPregister_patterns<"LDBFADD",   "atomic_load_fadd">;
-  defm : LDBFPOPregister_patterns<"LDBFMAXNM", "atomic_load_fmax">;
-  defm : LDBFPOPregister_patterns<"LDBFMINNM", "atomic_load_fmin">;
+  defm : LDBFPOPregister_patterns<"BFADD",   "atomic_load_fadd">;
+  defm : LDBFPOPregister_patterns<"BFMAXNM", "atomic_load_fmax">;
+  defm : LDBFPOPregister_patterns<"BFMINNM", "atomic_load_fmin">;
 }
 
 // v8.9a/v9.4a FEAT_LRCPC patterns
diff --git a/llvm/lib/Target/AArch64/AArch64InstrFormats.td b/llvm/lib/Target/AArch64/AArch64InstrFormats.td
index 255cd0ec5840c..99bd85a448d83 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrFormats.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrFormats.td
@@ -12493,19 +12493,39 @@ multiclass LDOPregister_patterns_mod<string inst, string op, string mod> {
                         (i32 (!cast<Instruction>(mod#Wrr) WZR, GPR32:$Rm))>;
 }
 
+class AtomicStoreMonotonicFrag<SDNode atomic_op> : PatFrag<
+  (ops node:$ptr, node:$value),
+  (atomic_op node:$ptr, node:$value),
+  [{ return SDValue(N, 0).use_empty() &&
+     cast<AtomicSDNode>(N)->getMergedOrdering() == AtomicOrdering::Monotonic; }]>;
+
+class AtomicStoreReleaseFrag<SDNode atomic_op> : PatFrag<
+  (ops node:$ptr, node:$value),
+  (atomic_op node:$ptr, node:$value),
+  [{ return SDValue(N, 0).use_empty() &&
+     cast<AtomicSDNode>(N)->getMergedOrdering() == AtomicOrdering::Release; }]>;
+
 let Predicates = [HasLSFE] in
 multiclass LDFPOPregister_patterns_ord_dag<string inst, string suffix, string op,
-                                         ValueType vt, dag data> {
+                                           ValueType vt, dag data> {
   def : Pat<(!cast<PatFrag>(op#"_"#vt#"_monotonic") FPR64:$Rn, data),
-            (!cast<Instruction>(inst # suffix) data, FPR64:$Rn)>;
+            (!cast<Instruction>("LD" # inst # suffix) data, FPR64:$Rn)>;
   def : Pat<(!cast<PatFrag>(op#"_"#vt#"_acquire") FPR64:$Rn, data),
-            (!cast<Instruction>(inst # "A" # suffix) data, FPR64:$Rn)>;
+            (!cast<Instruction>("LD" # inst # "A" # suffix) data, FPR64:$Rn)>;
   def : Pat<(!cast<PatFrag>(op#"_"#vt#"_release") FPR64:$Rn, data),
-            (!cast<Instruction>(inst # "L" # suffix) data, FPR64:$Rn)>;
+            (!cast<Instruction>("LD" # inst # "L" # suffix) data, FPR64:$Rn)>;
   def : Pat<(!cast<PatFrag>(op#"_"#vt#"_acq_rel") FPR64:$Rn, data),
-            (!cast<Instruction>(inst # "AL" # suffix) data, FPR64:$Rn)>;
+            (!cast<Instruction>("LD" # inst # "AL" # suffix) data, FPR64:$Rn)>;
   def : Pat<(!cast<PatFrag>(op#"_"#vt#"_seq_cst") FPR64:$Rn, data),
-            (!cast<Instruction>(inst # "AL" # suffix) data, FPR64:$Rn)>;
+            (!cast<Instruction>("LD" # inst # "AL" # suffix) data, FPR64:$Rn)>;
+
+  let AddedComplexity = 5 in {
+    def : Pat<(AtomicStoreMonotonicFrag<!cast<SDNode>(op)> FPR64:$Rn, data),
+              (!cast<Instruction>("ST" # inst # suffix) data, FPR64:$Rn)>;
+
+    def : Pat<(AtomicStoreReleaseFrag<!cast<SDNode>(op)> FPR64:$Rn, data),
+              (!cast<Instruction>("ST" # inst # "L" # suffix) data, FPR64:$Rn)>;
+  }
 }
 
 multiclass LDFPOPregister_patterns_ord<string inst, string suffix, string op,
diff --git a/llvm/test/CodeGen/AArch64/Atomics/aarch64-atomicrmw-lsfe.ll b/llvm/test/CodeGen/AArch64/Atomics/aarch64-atomicrmw-lsfe.ll
index fc9a126f79a83..bd9b814ac533e 100644
--- a/llvm/test/CodeGen/AArch64/Atomics/aarch64-atomicrmw-lsfe.ll
+++ b/llvm/test/CodeGen/AArch64/Atomics/aarch64-atomicrmw-lsfe.ll
@@ -10,6 +10,13 @@ define dso_local half @atomicrmw_fadd_half_aligned_monotonic(ptr %ptr, half %val
     ret half %r
 }
 
+define dso_local void @atomicrmw_fadd_half_aligned_monotonic_to_store(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fadd_half_aligned_monotonic_to_store:
+; CHECK:    stfadd h0, [x0]
+    %r = atomicrmw fadd ptr %ptr, half %value monotonic, align 2
+    ret void
+}
+
 define dso_local half @atomicrmw_fadd_half_aligned_acquire(ptr %ptr, half %value) {
 ; CHECK-LABEL: atomicrmw_fadd_half_aligned_acquire:
 ; CHECK:    ldfadda h0, h0, [x0]
@@ -24,6 +31,13 @@ define dso_local half @atomicrmw_fadd_half_aligned_release(ptr %ptr, half %value
     ret half %r
 }
 
+define dso_local void @atomicrmw_fadd_half_aligned_release_to_store(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fadd_half_aligned_release_to_store:
+; CHECK:    stfaddl h0, [x0]
+    %r = atomicrmw fadd ptr %ptr, half %value release, align 2
+    ret void
+}
+
 define dso_local half @atomicrmw_fadd_half_aligned_acq_rel(ptr %ptr, half %value) {
 ; CHECK-LABEL: atomicrmw_fadd_half_aligned_acq_rel:
 ; CHECK:    ldfaddal h0, h0, [x0]
@@ -45,6 +59,13 @@ define dso_local bfloat @atomicrmw_fadd_bfloat_aligned_monotonic(ptr %ptr, bfloa
     ret bfloat %r
 }
 
+define dso_local void @atomicrmw_fadd_bfloat_aligned_monotonic_to_store(ptr %ptr, bfloat %value) {
+; CHECK-LABEL: atomicrmw_fadd_bfloat_aligned_monotonic_to_store:
+; CHECK:    stbfadd h0, [x0]
+    %r = atomicrmw fadd ptr %ptr, bfloat %value monotonic, align 2
+    ret void
+}
+
 define dso_local bfloat @atomicrmw_fadd_bfloat_aligned_acquire(ptr %ptr, bfloat %value) {
 ; CHECK-LABEL: atomicrmw_fadd_bfloat_aligned_acquire:
 ; CHECK:    ldbfadda h0, h0, [x0]
@@ -59,6 +80,13 @@ define dso_local bfloat @atomicrmw_fadd_bfloat_aligned_release(ptr %ptr, bfloat
     ret bfloat %r
 }
 
+define dso_local void @atomicrmw_fadd_bfloat_aligned_release_to_store(ptr %ptr, bfloat %value) {
+; CHECK-LABEL: atomicrmw_fadd_bfloat_aligned_release_to_store:
+; CHECK:    stbfaddl h0, [x0]
+    %r = atomicrmw fadd ptr %ptr, bfloat %value release, align 2
+    ret void
+}
+
 define dso_local bfloat @atomicrmw_fadd_bfloat_aligned_acq_rel(ptr %ptr, bfloat %value) {
 ; CHECK-LABEL: atomicrmw_fadd_bfloat_aligned_acq_rel:
 ; CHECK:    ldbfaddal h0, h0, [x0]
@@ -80,6 +108,13 @@ define dso_local float @atomicrmw_fadd_float_aligned_monotonic(ptr %ptr, float %
     ret float %r
 }
 
+define dso_local void @atomicrmw_fadd_float_aligned_monotonic_to_store(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fadd_float_aligned_monotonic_to_store:
+; CHECK:    stfadd s0, [x0]
+    %r = atomicrmw fadd ptr %ptr, float %value monotonic, align 4
+    ret void
+}
+
 define dso_local float @atomicrmw_fadd_float_aligned_acquire(ptr %ptr, float %value) {
 ; CHECK-LABEL: atomicrmw_fadd_float_aligned_acquire:
 ; CHECK:    ldfadda s0, s0, [x0]
@@ -94,6 +129,13 @@ define dso_local float @atomicrmw_fadd_float_aligned_release(ptr %ptr, float %va
     ret float %r
 }
 
+define dso_local void @atomicrmw_fadd_float_aligned_release_to_store(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fadd_float_aligned_release_to_store:
+; CHECK:    stfaddl s0, [x0]
+    %r = atomicrmw fadd ptr %ptr, float %value release, align 4
+    ret void
+}
+
 define dso_local float @atomicrmw_fadd_float_aligned_acq_rel(ptr %ptr, float %value) {
 ; CHECK-LABEL: atomicrmw_fadd_float_aligned_acq_rel:
 ; CHECK:    ldfaddal s0, s0, [x0]
@@ -115,6 +157,13 @@ define dso_local double @atomicrmw_fadd_double_aligned_monotonic(ptr %ptr, doubl
     ret double %r
 }
 
+define dso_local void @atomicrmw_fadd_double_aligned_monotonic_to_store(ptr %ptr, double %value) {
+; CHECK-LABEL: atomicrmw_fadd_double_aligned_monotonic_to_store:
+; CHECK:    stfadd d0, [x0]
+    %r = atomicrmw fadd ptr %ptr, double %value monotonic, align 8
+    ret void
+}
+
 define dso_local double @atomicrmw_fadd_double_aligned_acquire(ptr %ptr, double %value) {
 ; CHECK-LABEL: atomicrmw_fadd_double_aligned_acquire:
 ; CHECK:    ldfadda d0, d0, [x0]
@@ -129,6 +178,13 @@ define dso_local double @atomicrmw_fadd_double_aligned_release(ptr %ptr, double
     ret double %r
 }
 
+define dso_local void @atomicrmw_fadd_double_aligned_release_to_store(ptr %ptr, double %value) {
+; CHECK-LABEL: atomicrmw_fadd_double_aligned_release_to_store:
+; CHECK:    stfaddl d0, [x0]
+    %r = atomicrmw fadd ptr %ptr, double %value release, align 8
+    ret void
+}
+
 define dso_local double @atomicrmw_fadd_double_aligned_acq_rel(ptr %ptr, double %value) {
 ; CHECK-LABEL: atomicrmw_fadd_double_aligned_acq_rel:
 ; CHECK:    ldfaddal d0, d0, [x0]
@@ -805,6 +861,13 @@ define dso_local half @atomicrmw_fmax_half_aligned_monotonic(ptr %ptr, half %val
     ret half %r
 }
 
+define dso_local void @atomicrmw_fmax_half_aligned_monotonic_to_store(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fmax_half_aligned_monotonic_to_store:
+; CHECK:    stfmaxnm h0, [x0]
+    %r = atomicrmw fmax ptr %ptr, half %value monotonic, align 2
+    ret void
+}
+
 define dso_local half @atomicrmw_fmax_half_aligned_acquire(ptr %ptr, half %value) {
 ; CHECK-LABEL: atomicrmw_fmax_half_aligned_acquire:
 ; CHECK:    ldfmaxnma h0, h0, [x0]
@@ -819,6 +882,13 @@ define dso_local half @atomicrmw_fmax_half_aligned_release(ptr %ptr, half %value
     ret half %r
 }
 
+define dso_local void @atomicrmw_fmax_half_aligned_release_to_store(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fmax_half_aligned_release_to_store:
+; CHECK:    stfmaxnml h0, [x0]
+    %r = atomicrmw fmax ptr %ptr, half %value release, align 2
+    ret void
+}
+
 define dso_local half @atomicrmw_fmax_half_aligned_acq_rel(ptr %ptr, half %value) {
 ; CHECK-LABEL: atomicrmw_fmax_half_aligned_acq_rel:
 ; CHECK:    ldfmaxnmal h0, h0, [x0]
@@ -840,6 +910,13 @@ define dso_local bfloat @atomicrmw_fmax_bfloat_aligned_monotonic(ptr %ptr, bfloa
     ret bfloat %r
 }
 
+define dso_local void @atomicrmw_fmax_bfloat_aligned_monotonic_to_store(ptr %ptr, bfloat %value) {
+; CHECK-LABEL: atomicrmw_fmax_bfloat_aligned_monotonic_to_store:
+; CHECK:    stbfmaxnm h0, [x0]
+    %r = atomicrmw fmax ptr %ptr, bfloat %value monotonic, align 2
+    ret void
+}
+
 define dso_local bfloat @atomicrmw_fmax_bfloat_aligned_acquire(ptr %ptr, bfloat %value) {
 ; CHECK-LABEL: atomicrmw_fmax_bfloat_aligned_acquire:
 ; CHECK:    ldbfmaxnma h0, h0, [x0]
@@ -854,6 +931,13 @@ define dso_local bfloat @atomicrmw_fmax_bfloat_aligned_release(ptr %ptr, bfloat
     ret bfloat %r
 }
 
+define dso_local void @atomicrmw_fmax_bfloat_aligned_release_to_store(ptr %ptr, bfloat %value) {
+; CHECK-LABEL: atomicrmw_fmax_bfloat_aligned_release_to_store:
+; CHECK:    stbfmaxnml h0, [x0]
+    %r = atomicrmw fmax ptr %ptr, bfloat %value release, align 2
+    ret void
+}
+
 define dso_local bfloat @atomicrmw_fmax_bfloat_aligned_acq_rel(ptr %ptr, bfloat %value) {
 ; CHECK-LABEL: atomicrmw_fmax_bfloat_aligned_acq_rel:
 ; CHECK:    ldbfmaxnmal h0, h0, [x0]
@@ -875,6 +959,13 @@ define dso_local float @atomicrmw_fmax_float_aligned_monotonic(ptr %ptr, float %
     ret float %r
 }
 
+define dso_local void @atomicrmw_fmax_float_aligned_monotonic_to_store(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fmax_float_aligned_monotonic_to_store:
+; CHECK:    stfmaxnm s0, [x0]
+    %r = atomicrmw fmax ptr %ptr, float %value monotonic, align 4
+    ret void
+}
+
 define dso_local float @atomicrmw_fmax_float_aligned_acquire(ptr %ptr, float %value) {
 ; CHECK-LABEL: atomicrmw_fmax_float_aligned_acquire:
 ; CHECK:    ldfmaxnma s0, s0, [x0]
@@ -889,6 +980,13 @@ define dso_local float @atomicrmw_fmax_float_aligned_release(ptr %ptr, float %va
     ret float %r
 }
 
+define dso_local void @atomicrmw_fmax_float_aligned_release_to_store(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fmax_float_aligned_release_to_store:
+; CHECK:    stfmaxnml s0, [x0]
+    %r = atomicrmw fmax ptr %ptr, float %value release, align 4
+    ret void
+}
+
 define dso_local float @atomicrmw_fmax_float_aligned_acq_rel(ptr %ptr, float %value) {
 ; CHECK-LABEL: atomicrmw_fmax_float_aligned_acq_rel:
 ; CHECK:    ldfmaxnmal s0, s0, [x0]
@@ -910,6 +1008,13 @@ define dso_local double @atomicrmw_fmax_double_aligned_monotonic(ptr %ptr, doubl
     ret double %r
 }
 
+define dso_local void @atomicrmw_fmax_double_aligned_monotonic_to_store(ptr %ptr, double %value) {
+; CHECK-LABEL: atomicrmw_fmax_double_aligned_monotonic_to_store:
+; CHECK:    stfmaxnm d0, [x0]
+    %r = atomicrmw fmax ptr %ptr, double %value monotonic, align 8
+    ret void
+}
+
 define dso_local double @atomicrmw_fmax_double_aligned_acquire(ptr %ptr, double %value) {
 ; CHECK-LABEL: atomicrmw_fmax_double_aligned_acquire:
 ; CHECK:    ldfmaxnma d0, d0, [x0]
@@ -924,6 +1029,13 @@ define dso_local double @atomicrmw_fmax_double_aligned_release(ptr %ptr, double
     ret double %r
 }
 
+define dso_local void @atomicrmw_fmax_double_aligned_release_to_store(ptr %ptr, double %value) {
+; CHECK-LABEL: atomicrmw_fmax_double_aligned_release_to_store:
+; CHECK:    stfmaxnml d0, [x0]
+    %r = atomicrmw fmax ptr %ptr, double %value release, align 8
+    ret void
+}
+
 define dso_local double @atomicrmw_fmax_double_aligned_acq_rel(ptr %ptr, double %value) {
 ; CHECK-LABEL: atomicrmw_fmax_double_aligned_acq_rel:
 ; CHECK:    ldfmaxnmal d0, d0, [x0]
@@ -1120,6 +1232,13 @@ define dso_local half @atomicrmw_fmin_half_aligned_monotonic(ptr %ptr, half %val
     ret half %r
 }
 
+define dso_local void @atomicrmw_fmin_half_aligned_monotonic_to_store(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fmin_half_aligned_monotonic_to_store:
+; CHECK:    stfminnm h0, [x0]
+    %r = atomicrmw fmin ptr %ptr, half %value monotonic, align 2
+    ret void
+}
+
 define dso_local half @atomicrmw_fmin_half_aligned_acquire(ptr %ptr, half %value) {
 ; CHECK-LABEL: atomicrmw_fmin_half_aligned_acquire:
 ; CHECK:    ldfminnma h0, h0, [x0]
@@ -1134,6 +1253,13 @@ define dso_local half @atomicrmw_fmin_half_aligned_release(ptr %ptr, half %value
     ret half %r
 }
 
+define dso_local void @atomicrmw_fmin_half_aligned_release_to_store(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fmin_half_aligned_release_to_store:
+; CHECK:    stfminnml h0, [x0]
+    %r = atomicrmw fmin ptr %ptr, half %value release, align 2
+    ret void
+}
+
 define dso_local half @atomicrmw_fmin_half_aligned_acq_rel(ptr %ptr, half %value) {
 ; CHECK-LABEL: atomicrmw_fmin_half_aligned_acq_rel:
 ; CHECK:    ldfminnmal h0, h0, [x0]
@@ -1155,6 +1281,13 @@ define dso_local bfloat @atomicrmw_fmin_bfloat_aligned_monotonic(ptr %ptr, bfloa
     ret bfloat %r
 }
 
+define dso_local void @atomicrmw_fmin_bfloat_aligned_monotonic_to_store(ptr %ptr, bfloat %value) {
+; CHECK-LABEL: atomicrmw_fmin_bfloat_aligned_monotonic_to_store:
+; CHECK:    stbfminnm h0, [x0]
+    %r = atomicrmw fmin ptr %ptr, bfloat %value monotonic, align 2
+    ret void
+}
+
 define dso_local bfloat @atomicrmw_fmin_bfloat_aligned_acquire(ptr %ptr, bfloat %value) {
 ; CHECK-LABEL: atomicrmw_fmin_bfloat_aligned_acquire:
 ; CHECK:    ldbfminnma h0, h0, [x0]
@@ -1169,6 +1302,13 @@ define dso_local bfloat @atomicrmw_fmin_bfloat_aligned_release(ptr %ptr, bfloat
     ret bfloat %r
 }
 
+define dso_local void @atomicrmw_fmin_bfloat_aligned_release_to_store(ptr %ptr, bfloat %value) {
+; CHECK-LABEL: atomicrmw_fmin_bfloat_aligned_release_to_store:
+; CHECK:    stbfminnml h0, [x0]
+    %r = atomicrmw fmin ptr %ptr, bfloat %value release, align 2
+    ret void
+}
+
 define dso_local bfloat @atomicrmw_fmin_bfloat_aligned_acq_rel(ptr %ptr, bfloat %value) {
 ; CHECK-LABEL: atomicrmw_fmin_bfloat_aligned_acq_rel:
 ; CHECK:    ldbfminnmal h0, h0, [x0]
@@ -1190,6 +1330,13 @@ define dso_local float @atomicrmw_fmin_float_aligned_monotonic(ptr %ptr, float %
     ret float %r
 }
 
+define dso_local void @atomicrmw_fmin_float_aligned_monotonic_to_store(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fmin_float_aligned_monotonic_to_store:
+; CHECK:    stfminnm s0, [x0]
+    %r = atomicrmw fmin ptr %ptr, float %value monotonic, align 4
+    ret void
+}
+
 define dso_local float @atomicrmw_fmin_float_aligned_acquire(ptr %ptr, float %value) {
 ; CHECK-LABEL: atomicrmw_fmin_float_aligned_acquire:
 ; CHECK:    ldfminnma s0, s0, [x0]
@@ -1204,6 +1351,13 @@ define dso_local float @atomicrmw_fmin_float_aligned_release(ptr %ptr, float %va
     ret float %r
 }
 
+define dso_local void @atomicrmw_fmin_float_aligned_release_to_store(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fmin_float_aligned_release_to_store:
+; CHECK:    stfminnml s0, [x0]
+    %r = atomicrmw fmin ptr %ptr, float %value release, align 4
+    ret void
+}
+
 define dso_local float @atomicrmw_fmin_float_aligned_acq_rel(ptr %ptr, float %value) {
 ; CHECK-LABEL: atomicrmw_fmin_float_aligned_acq_rel:
 ; CHECK:    ldfminnmal s0, s0, [x0]
@@ -1225,6 +1379,13 @@ define dso_local double @atomicrmw_fmin_double_aligned_monotonic(ptr %ptr, doubl
     ret double %r
 }
 
+define dso_local void @atomicrmw_fmin_double_aligned_monotonic_to_store(ptr %ptr, double %value) {
+; CHECK-LABEL: atomicrmw_fmin_double_aligned_monotonic_to_store:
+; CHECK:    stfminnm d0, [x0]
+    %r = atomicrmw fmin ptr %ptr, double %value monotonic, align 8
+    ret void
+}
+
 define dso_local double @atomicrmw_fmin_double_aligned_acquire(ptr %ptr, double %value) {
 ; CHECK-LABEL: atomicrmw_fmin_double_aligned_acquire:
 ; CHECK:    ldfminnma d0, d0, [x0]
@@ -1239,6 +1400,13 @@ define dso_local double @atomicrmw_fmin_double_aligned_release(ptr %ptr, double
     ret double %r
 }
 
+define dso_local void @atomicrmw_fmin_double_aligned_release_to_store(ptr %ptr, double %value) {
+; CHECK-LABEL: atomicrmw_fmin_double_aligned_release_to_store:
+; CHECK:    stfminnml d0, [x0]
+    %r = atomicrmw fmin ptr %ptr, double %value release, align 8
+    ret void
+}
+
 define dso_local double @atomicrmw_fmin_double_aligned_acq_rel(ptr %ptr, double %value) {
 ; CHECK-LABEL: atomicrmw_fmin_double_aligned_acq_rel:
 ; CHECK:    ldfminnmal d0, d0, [x0]
diff --git a/llvm/test/CodeGen/AArch64/Atomics/aarch64_be-atomicrmw-lsfe.ll b/llvm/test/CodeGen/AArch64/Atomics/aarch64_be-atomicrmw-lsfe.ll
index a22cc5806d86d..67a5565f31d94 100644
--- a/llvm/test/CodeGen/AArch64/Atomics/aarch64_be-atomicrmw-lsfe.ll
+++ b/llvm/test/CodeGen/AArch64/Atomics/aarch64_be-atomicrmw-lsfe.ll
@@ -10,6 +10,13 @@ define dso_local half @atomicrmw_fadd_half_aligned_monotonic(ptr %ptr, half %val
     ret half %r
 }
 
+define dso_local void @atomicrmw_fadd_half_aligned_monotonic_to_store(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fadd_half_aligned_monotonic_to_store:
+; CHECK:    stfadd h0, [x0]
+    %r = atomicrmw fadd ptr %ptr, half %value monotonic, align 2
+    ret void
+}
+
 define dso_local half @atomicrmw_fadd_half_aligned_acquire(ptr %ptr, half %value) {
 ; CHECK-LABEL: atomicrmw_fadd_half_aligned_acquire:
 ; CHECK:    ldfadda h0, h0, [x0]
@@ -24,6 +31,13 @@ define dso_local half @atomicrmw_fadd_half_aligned_release(ptr %ptr, half %value
     ret half %r
 }
 
+define dso_local void @atomicrmw_fadd_half_aligned_release_to_store(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fadd_half_aligned_release_to_store:
+; CHECK:    stfaddl h0, [x0]
+    %r = atomicrmw fadd ptr %ptr, half %value release, align 2
+    ret void
+}
+
 define dso_local half @atomicrmw_fadd_half_aligned_acq_rel(ptr %ptr, half %value) {
 ; CHECK-LABEL: atomicrmw_fadd_half_aligned_acq_rel:
 ; CHECK:    ldfaddal h0, h0, [x0]
@@ -45,6 +59,13 @@ define dso_local bfloat @atomicrmw_fadd_bfloat_aligned_monotonic(ptr %ptr, bfloa
     ret bfloat %r
 }
 
+define dso_local void @atomicrmw_fadd_bfloat_aligned_monotonic_to_store(ptr %ptr, bfloat %value) {
+; CHECK-LABEL: atomicrmw_fadd_bfloat_aligned_monotonic_to_store:
+; CHECK:    stbfadd h0, [x0]
+    %r = atomicrmw fadd ptr %ptr, bfloat %value monotonic, align 2
+    ret void
+}
+
 define dso_local bfloat @atomicrmw_fadd_bfloat_aligned_acquire(ptr %ptr, bfloat %value) {
 ; CHECK-LABEL: atomicrmw_fadd_bfloat_aligned_acquire:
 ; CHECK:    ldbfadda h0, h0, [x0]
@@ -59,6 +80,13 @@ define dso_local bfloat @atomicrmw_fadd_bfloat_aligned_release(ptr %ptr, bfloat
     ret bfloat %r
 }
 
+define dso_local void @atomicrmw_fadd_bfloat_aligned_release_to_store(ptr %ptr, bfloat %value) {
+; CHECK-LABEL: atomicrmw_fadd_bfloat_aligned_release_to_store:
+; CHECK:    stbfaddl h0, [x0]
+    %r = atomicrmw fadd ptr %ptr, bfloat %value release, align 2
+    ret void
+}
+
 define dso_local bfloat @atomicrmw_fadd_bfloat_aligned_acq_rel(ptr %ptr, bfloat %value) {
 ; CHECK-LABEL: atomicrmw_fadd_bfloat_aligned_acq_rel:
 ; CHECK:    ldbfaddal h0, h0, [x0]
@@ -80,6 +108,13 @@ define dso_local float @atomicrmw_fadd_float_aligned_monotonic(ptr %ptr, float %
     ret float %r
 }
 
+define dso_local void @atomicrmw_fadd_float_aligned_monotonic_to_store(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fadd_float_aligned_monotonic_to_store:
+; CHECK:    stfadd s0, [x0]
+    %r = atomicrmw fadd ptr %ptr, float %value monotonic, align 4
+    ret void
+}
+
 define dso_local float @atomicrmw_fadd_float_aligned_acquire(ptr %ptr, float %value) {
 ; CHECK-LABEL: atomicrmw_fadd_float_aligned_acquire:
 ; CHECK:    ldfadda s0, s0, [x0]
@@ -94,6 +129,13 @@ define dso_local float @atomicrmw_fadd_float_aligned_release(ptr %ptr, float %va
     ret float %r
 }
 
+define dso_local void @atomicrmw_fadd_float_aligned_release_to_store(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fadd_float_aligned_release_to_store:
+; CHECK:    stfaddl s0, [x0]
+    %r = atomicrmw fadd ptr %ptr, float %value release, align 4
+    ret void
+}
+
 define dso_local float @atomicrmw_fadd_float_aligned_acq_rel(ptr %ptr, float %value) {
 ; CHECK-LABEL: atomicrmw_fadd_float_aligned_acq_rel:
 ; CHECK:    ldfaddal s0, s0, [x0]
@@ -115,6 +157,13 @@ define dso_local double @atomicrmw_fadd_double_aligned_monotonic(ptr %ptr, doubl
     ret double %r
 }
 
+define dso_local void @atomicrmw_fadd_double_aligned_monotonic_to_store(ptr %ptr, double %value) {
+; CHECK-LABEL: atomicrmw_fadd_double_aligned_monotonic_to_store:
+; CHECK:    stfadd d0, [x0]
+    %r = atomicrmw fadd ptr %ptr, double %value monotonic, align 8
+    ret void
+}
+
 define dso_local double @atomicrmw_fadd_double_aligned_acquire(ptr %ptr, double %value) {
 ; CHECK-LABEL: atomicrmw_fadd_double_aligned_acquire:
 ; CHECK:    ldfadda d0, d0, [x0]
@@ -129,6 +178,13 @@ define dso_local double @atomicrmw_fadd_double_aligned_release(ptr %ptr, double
     ret double %r
 }
 
+define dso_local void @atomicrmw_fadd_double_aligned_release_to_store(ptr %ptr, double %value) {
+; CHECK-LABEL: atomicrmw_fadd_double_aligned_release_to_store:
+; CHECK:    stfaddl d0, [x0]
+    %r = atomicrmw fadd ptr %ptr, double %value release, align 8
+    ret void
+}
+
 define dso_local double @atomicrmw_fadd_double_aligned_acq_rel(ptr %ptr, double %value) {
 ; CHECK-LABEL: atomicrmw_fadd_double_aligned_acq_rel:
 ; CHECK:    ldfaddal d0, d0, [x0]
@@ -820,6 +876,13 @@ define dso_local half @atomicrmw_fmax_half_aligned_monotonic(ptr %ptr, half %val
     ret half %r
 }
 
+define dso_local void @atomicrmw_fmax_half_aligned_monotonic_to_store(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fmax_half_aligned_monotonic_to_store:
+; CHECK:    stfmaxnm h0, [x0]
+    %r = atomicrmw fmax ptr %ptr, half %value monotonic, align 2
+    ret void
+}
+
 define dso_local half @atomicrmw_fmax_half_aligned_acquire(ptr %ptr, half %value) {
 ; CHECK-LABEL: atomicrmw_fmax_half_aligned_acquire:
 ; CHECK:    ldfmaxnma h0, h0, [x0]
@@ -834,6 +897,13 @@ define dso_local half @atomicrmw_fmax_half_aligned_release(ptr %ptr, half %value
     ret half %r
 }
 
+define dso_local void @atomicrmw_fmax_half_aligned_release_to_store(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fmax_half_aligned_release_to_store:
+; CHECK:    stfmaxnml h0, [x0]
+    %r = atomicrmw fmax ptr %ptr, half %value release, align 2
+    ret void
+}
+
 define dso_local half @atomicrmw_fmax_half_aligned_acq_rel(ptr %ptr, half %value) {
 ; CHECK-LABEL: atomicrmw_fmax_half_aligned_acq_rel:
 ; CHECK:    ldfmaxnmal h0, h0, [x0]
@@ -855,6 +925,13 @@ define dso_local bfloat @atomicrmw_fmax_bfloat_aligned_monotonic(ptr %ptr, bfloa
     ret bfloat %r
 }
 
+define dso_local void @atomicrmw_fmax_bfloat_aligned_monotonic_to_store(ptr %ptr, bfloat %value) {
+; CHECK-LABEL: atomicrmw_fmax_bfloat_aligned_monotonic_to_store:
+; CHECK:    stbfmaxnm h0, [x0]
+    %r = atomicrmw fmax ptr %ptr, bfloat %value monotonic, align 2
+    ret void
+}
+
 define dso_local bfloat @atomicrmw_fmax_bfloat_aligned_acquire(ptr %ptr, bfloat %value) {
 ; CHECK-LABEL: atomicrmw_fmax_bfloat_aligned_acquire:
 ; CHECK:    ldbfmaxnma h0, h0, [x0]
@@ -869,6 +946,13 @@ define dso_local bfloat @atomicrmw_fmax_bfloat_aligned_release(ptr %ptr, bfloat
     ret bfloat %r
 }
 
+define dso_local void @atomicrmw_fmax_bfloat_aligned_release_to_store(ptr %ptr, bfloat %value) {
+; CHECK-LABEL: atomicrmw_fmax_bfloat_aligned_release_to_store:
+; CHECK:    stbfmaxnml h0, [x0]
+    %r = atomicrmw fmax ptr %ptr, bfloat %value release, align 2
+    ret void
+}
+
 define dso_local bfloat @atomicrmw_fmax_bfloat_aligned_acq_rel(ptr %ptr, bfloat %value) {
 ; CHECK-LABEL: atomicrmw_fmax_bfloat_aligned_acq_rel:
 ; CHECK:    ldbfmaxnmal h0, h0, [x0]
@@ -890,6 +974,13 @@ define dso_local float @atomicrmw_fmax_float_aligned_monotonic(ptr %ptr, float %
     ret float %r
 }
 
+define dso_local void @atomicrmw_fmax_float_aligned_monotonic_to_store(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fmax_float_aligned_monotonic_to_store:
+; CHECK:    stfmaxnm s0, [x0]
+    %r = atomicrmw fmax ptr %ptr, float %value monotonic, align 4
+    ret void
+}
+
 define dso_local float @atomicrmw_fmax_float_aligned_acquire(ptr %ptr, float %value) {
 ; CHECK-LABEL: atomicrmw_fmax_float_aligned_acquire:
 ; CHECK:    ldfmaxnma s0, s0, [x0]
@@ -904,6 +995,13 @@ define dso_local float @atomicrmw_fmax_float_aligned_release(ptr %ptr, float %va
     ret float %r
 }
 
+define dso_local void @atomicrmw_fmax_float_aligned_release_to_store(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fmax_float_aligned_release_to_store:
+; CHECK:    stfmaxnml s0, [x0]
+    %r = atomicrmw fmax ptr %ptr, float %value release, align 4
+    ret void
+}
+
 define dso_local float @atomicrmw_fmax_float_aligned_acq_rel(ptr %ptr, float %value) {
 ; CHECK-LABEL: atomicrmw_fmax_float_aligned_acq_rel:
 ; CHECK:    ldfmaxnmal s0, s0, [x0]
@@ -925,6 +1023,13 @@ define dso_local double @atomicrmw_fmax_double_aligned_monotonic(ptr %ptr, doubl
     ret double %r
 }
 
+define dso_local void @atomicrmw_fmax_double_aligned_monotonic_to_store(ptr %ptr, double %value) {
+; CHECK-LABEL: atomicrmw_fmax_double_aligned_monotonic_to_store:
+; CHECK:    stfmaxnm d0, [x0]
+    %r = atomicrmw fmax ptr %ptr, double %value monotonic, align 8
+    ret void
+}
+
 define dso_local double @atomicrmw_fmax_double_aligned_acquire(ptr %ptr, double %value) {
 ; CHECK-LABEL: atomicrmw_fmax_double_aligned_acquire:
 ; CHECK:    ldfmaxnma d0, d0, [x0]
@@ -939,6 +1044,13 @@ define dso_local double @atomicrmw_fmax_double_aligned_release(ptr %ptr, double
     ret double %r
 }
 
+define dso_local void @atomicrmw_fmax_double_aligned_release_to_store(ptr %ptr, double %value) {
+; CHECK-LABEL: atomicrmw_fmax_double_aligned_release_to_store:
+; CHECK:    stfmaxnml d0, [x0]
+    %r = atomicrmw fmax ptr %ptr, double %value release, align 8
+    ret void
+}
+
 define dso_local double @atomicrmw_fmax_double_aligned_acq_rel(ptr %ptr, double %value) {
 ; CHECK-LABEL: atomicrmw_fmax_double_aligned_acq_rel:
 ; CHECK:    ldfmaxnmal d0, d0, [x0]
@@ -1135,6 +1247,13 @@ define dso_local half @atomicrmw_fmin_half_aligned_monotonic(ptr %ptr, half %val
     ret half %r
 }
 
+define dso_local void @atomicrmw_fmin_half_aligned_monotonic_to_store(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fmin_half_aligned_monotonic_to_store:
+; CHECK:    stfminnm h0, [x0]
+    %r = atomicrmw fmin ptr %ptr, half %value monotonic, align 2
+    ret void
+}
+
 define dso_local half @atomicrmw_fmin_half_aligned_acquire(ptr %ptr, half %value) {
 ; CHECK-LABEL: atomicrmw_fmin_half_aligned_acquire:
 ; CHECK:    ldfminnma h0, h0, [x0]
@@ -1149,6 +1268,13 @@ define dso_local half @atomicrmw_fmin_half_aligned_release(ptr %ptr, half %value
     ret half %r
 }
 
+define dso_local void @atomicrmw_fmin_half_aligned_release_to_store(ptr %ptr, half %value) {
+; CHECK-LABEL: atomicrmw_fmin_half_aligned_release_to_store:
+; CHECK:    stfminnml h0, [x0]
+    %r = atomicrmw fmin ptr %ptr, half %value release, align 2
+    ret void
+}
+
 define dso_local half @atomicrmw_fmin_half_aligned_acq_rel(ptr %ptr, half %value) {
 ; CHECK-LABEL: atomicrmw_fmin_half_aligned_acq_rel:
 ; CHECK:    ldfminnmal h0, h0, [x0]
@@ -1170,6 +1296,13 @@ define dso_local bfloat @atomicrmw_fmin_bfloat_aligned_monotonic(ptr %ptr, bfloa
     ret bfloat %r
 }
 
+define dso_local void @atomicrmw_fmin_bfloat_aligned_monotonic_to_store(ptr %ptr, bfloat %value) {
+; CHECK-LABEL: atomicrmw_fmin_bfloat_aligned_monotonic_to_store:
+; CHECK:    stbfminnm h0, [x0]
+    %r = atomicrmw fmin ptr %ptr, bfloat %value monotonic, align 2
+    ret void
+}
+
 define dso_local bfloat @atomicrmw_fmin_bfloat_aligned_acquire(ptr %ptr, bfloat %value) {
 ; CHECK-LABEL: atomicrmw_fmin_bfloat_aligned_acquire:
 ; CHECK:    ldbfminnma h0, h0, [x0]
@@ -1184,6 +1317,13 @@ define dso_local bfloat @atomicrmw_fmin_bfloat_aligned_release(ptr %ptr, bfloat
     ret bfloat %r
 }
 
+define dso_local void @atomicrmw_fmin_bfloat_aligned_release_to_store(ptr %ptr, bfloat %value) {
+; CHECK-LABEL: atomicrmw_fmin_bfloat_aligned_release_to_store:
+; CHECK:    stbfminnml h0, [x0]
+    %r = atomicrmw fmin ptr %ptr, bfloat %value release, align 2
+    ret void
+}
+
 define dso_local bfloat @atomicrmw_fmin_bfloat_aligned_acq_rel(ptr %ptr, bfloat %value) {
 ; CHECK-LABEL: atomicrmw_fmin_bfloat_aligned_acq_rel:
 ; CHECK:    ldbfminnmal h0, h0, [x0]
@@ -1205,6 +1345,13 @@ define dso_local float @atomicrmw_fmin_float_aligned_monotonic(ptr %ptr, float %
     ret float %r
 }
 
+define dso_local void @atomicrmw_fmin_float_aligned_monotonic_to_store(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fmin_float_aligned_monotonic_to_store:
+; CHECK:    stfminnm s0, [x0]
+    %r = atomicrmw fmin ptr %ptr, float %value monotonic, align 4
+    ret void
+}
+
 define dso_local float @atomicrmw_fmin_float_aligned_acquire(ptr %ptr, float %value) {
 ; CHECK-LABEL: atomicrmw_fmin_float_aligned_acquire:
 ; CHECK:    ldfminnma s0, s0, [x0]
@@ -1219,6 +1366,13 @@ define dso_local float @atomicrmw_fmin_float_aligned_release(ptr %ptr, float %va
     ret float %r
 }
 
+define dso_local void @atomicrmw_fmin_float_aligned_release_to_store(ptr %ptr, float %value) {
+; CHECK-LABEL: atomicrmw_fmin_float_aligned_release_to_store:
+; CHECK:    stfminnml s0, [x0]
+    %r = atomicrmw fmin ptr %ptr, float %value release, align 4
+    ret void
+}
+
 define dso_local float @atomicrmw_fmin_float_aligned_acq_rel(ptr %ptr, float %value) {
 ; CHECK-LABEL: atomicrmw_fmin_float_aligned_acq_rel:
 ; CHECK:    ldfminnmal s0, s0, [x0]
@@ -1240,6 +1394,13 @@ define dso_local double @atomicrmw_fmin_double_aligned_monotonic(ptr %ptr, doubl
     ret double %r
 }
 
+define dso_local void @atomicrmw_fmin_double_aligned_monotonic_to_store(ptr %ptr, double %value) {
+; CHECK-LABEL: atomicrmw_fmin_double_aligned_monotonic_to_store:
+; CHECK:    stfminnm d0, [x0]
+    %r = atomicrmw fmin ptr %ptr, double %value monotonic, align 8
+    ret void
+}
+
 define dso_local double @atomicrmw_fmin_double_aligned_acquire(ptr %ptr, double %value) {
 ; CHECK-LABEL: atomicrmw_fmin_double_aligned_acquire:
 ; CHECK:    ldfminnma d0, d0, [x0]
@@ -1254,6 +1415,13 @@ define dso_local double @atomicrmw_fmin_double_aligned_release(ptr %ptr, double
     ret double %r
 }
 
+define dso_local void @atomicrmw_fmin_double_aligned_release_to_store(ptr %ptr, double %value) {
+; CHECK-LABEL: atomicrmw_fmin_double_aligned_release_to_store:
+; CHECK:    stfminnml d0, [x0]
+    %r = atomicrmw fmin ptr %ptr, double %value release, align 8
+    ret void
+}
+
 define dso_local double @atomicrmw_fmin_double_aligned_acq_rel(ptr %ptr, double %value) {
 ; CHECK-LABEL: atomicrmw_fmin_double_aligned_acq_rel:
 ; CHECK:    ldfminnmal d0, d0, [x0]
diff --git a/llvm/test/CodeGen/AArch64/Atomics/generate-tests.py b/llvm/test/CodeGen/AArch64/Atomics/generate-tests.py
index f40bbaeb930c0..b4aebea8ff547 100755
--- a/llvm/test/CodeGen/AArch64/Atomics/generate-tests.py
+++ b/llvm/test/CodeGen/AArch64/Atomics/generate-tests.py
@@ -189,18 +189,26 @@ def relpath():
     return fp
 
 
+def generate_store_opt_test(featname, ordering, op, alignval):
+    if featname != "lsfe" or op == "fsub" or alignval == 1:
+        return False
+    if ordering not in [AtomicOrder.monotonic, AtomicOrder.release]:
+        return False
+    return True
+
+
 def align(val, aligned: bool) -> int:
     return val if aligned else 1
 
 
-def all_atomicrmw(f, datatype, atomicrmw_ops):
+def all_atomicrmw(f, datatype, atomicrmw_ops, featname):
+    instr = "atomicrmw"
     for op in atomicrmw_ops:
         for aligned in Aligned:
             for ty, val in datatype:
                 alignval = align(val, aligned)
                 for ordering in ATOMICRMW_ORDERS:
                     name = f"atomicrmw_{op}_{ty}_{aligned}_{ordering}"
-                    instr = "atomicrmw"
                     f.write(
                         textwrap.dedent(
                             f"""
@@ -211,6 +219,18 @@ def all_atomicrmw(f, datatype, atomicrmw_ops):
                     """
                         )
                     )
+                    if generate_store_opt_test(featname, ordering, op, alignval):
+                        name = f"atomicrmw_{op}_{ty}_{aligned}_{ordering}_to_store"
+                        f.write(
+                            textwrap.dedent(
+                                f"""
+                           define dso_local void @{name}(ptr %ptr, {ty} %value) {{
+                               %r = {instr} {op} ptr %ptr, {ty} %value {ordering}, align {alignval}
+                               ret void
+                           }}
+                        """
+                            )
+                        )
 
 
 def all_load(f):
@@ -340,7 +360,7 @@ def write_lit_tests(feature, datatypes, ops):
             with open(f"{triple}-atomicrmw-{feat.name}.ll", "w") as f:
                 filter_args = r'--filter-out "\b(sp)\b" --filter "^\s*(ld[^r]|st[^r]|swp|cas|bl|add|and|eor|orn|orr|sub|mvn|sxt|cmp|ccmp|csel|dmb)"'
                 header(f, triple, [feat], filter_args)
-                all_atomicrmw(f, datatypes, ops)
+                all_atomicrmw(f, datatypes, ops, feat.name)
 
             # Floating point atomics only supported for atomicrmw currently
             if feature.test_scope() == "atomicrmw":