Index: llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
===================================================================
--- llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
+++ llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
@@ -308,6 +308,12 @@
   return N->hasOneUse();
 }]>;
 
+def AArch64fmul_p_oneuse : PatFrag<(ops node:$pred, node:$src1, node:$src2),
+                                   (AArch64fmul_p node:$pred, node:$src1, node:$src2), [{
+  return N->hasOneUse();
+}]>;
+
+
 def AArch64fabd_p : PatFrag<(ops node:$pg, node:$op1, node:$op2),
                             (AArch64fabs_mt node:$pg, (AArch64fsub_p node:$pg, node:$op1, node:$op2), undef)>;
 
@@ -356,6 +362,23 @@
                               // sub(a, select(mask, mul(b, c), splat(0))) -> mls(a, mask, b, c)
                               (sub node:$op1, (vselect node:$pred, (AArch64mul_p_oneuse (SVEAllActive), node:$op2, node:$op3), (SVEDup0)))]>;
 
+class fma_patfrags<SDPatternOperator intrinsic, SDPatternOperator sdnode>
+    : PatFrags<(ops node:$pred, node:$op1, node:$op2, node:$op3),
+               [(intrinsic node:$pred, node:$op1, node:$op2, node:$op3),
+                (sdnode (SVEAllActive), node:$op1, (vselect node:$pred, (AArch64fmul_p_oneuse (SVEAllActive), node:$op2, node:$op3), (SVEDup0)))],
+               [{
+  if ((N->getOpcode() != AArch64ISD::FADD_PRED) &&
+      (N->getOpcode() != AArch64ISD::FSUB_PRED))
+    return true;  // it's the intrinsic
+  SDValue Sel = N->getOperand(2);
+  SDValue FMul = Sel->getOperand(1);
+  return N->getFlags().hasAllowContract() &&
+         FMul->getFlags().hasAllowContract();
+}]>;
+
+def AArch64fmla_m1 : fma_patfrags<int_aarch64_sve_fmla, AArch64fadd_p>;
+def AArch64fmls_m1 : fma_patfrags<int_aarch64_sve_fmls, AArch64fsub_p>;
+
 let Predicates = [HasSVE] in {
   defm RDFFR_PPz  : sve_int_rdffr_pred<0b0, "rdffr", int_aarch64_sve_rdffr_z>;
   def  RDFFRS_PPz : sve_int_rdffr_pred<0b1, "rdffrs">;
@@ -592,8 +615,8 @@
   defm FCADD_ZPmZ : sve_fp_fcadd<"fcadd", int_aarch64_sve_fcadd>;
   defm FCMLA_ZPmZZ : sve_fp_fcmla<"fcmla", int_aarch64_sve_fcmla>;
 
-  defm FMLA_ZPmZZ  : sve_fp_3op_p_zds_a<0b00, "fmla",  "FMLA_ZPZZZ", int_aarch64_sve_fmla, "FMAD_ZPmZZ">;
-  defm FMLS_ZPmZZ  : sve_fp_3op_p_zds_a<0b01, "fmls",  "FMLS_ZPZZZ", int_aarch64_sve_fmls, "FMSB_ZPmZZ">;
+  defm FMLA_ZPmZZ  : sve_fp_3op_p_zds_a<0b00, "fmla",  "FMLA_ZPZZZ", AArch64fmla_m1, "FMAD_ZPmZZ">;
+  defm FMLS_ZPmZZ  : sve_fp_3op_p_zds_a<0b01, "fmls",  "FMLS_ZPZZZ", AArch64fmls_m1, "FMSB_ZPmZZ">;
   defm FNMLA_ZPmZZ : sve_fp_3op_p_zds_a<0b10, "fnmla", "FNMLA_ZPZZZ", int_aarch64_sve_fnmla, "FNMAD_ZPmZZ">;
   defm FNMLS_ZPmZZ : sve_fp_3op_p_zds_a<0b11, "fnmls", "FNMLS_ZPZZZ", int_aarch64_sve_fnmls, "FNMSB_ZPmZZ">;
 
Index: llvm/lib/Target/AArch64/SVEInstrFormats.td
===================================================================
--- llvm/lib/Target/AArch64/SVEInstrFormats.td
+++ llvm/lib/Target/AArch64/SVEInstrFormats.td
@@ -542,6 +542,7 @@
 : PatFrags<(ops node:$Pg, node:$Op1, node:$Op2), [
     (intrinsic node:$Pg, node:$Op1, node:$Op2),
     (vselect node:$Pg, (sdnode (SVEAllActive), node:$Op1, node:$Op2), node:$Op1),
+    (sdnode (SVEAllActive), node:$Op1, (vselect node:$Pg, node:$Op2, (SVEDup0)))
   ]>;
 
 //
Index: llvm/test/CodeGen/AArch64/sve-fp-combine.ll
===================================================================
--- llvm/test/CodeGen/AArch64/sve-fp-combine.ll
+++ llvm/test/CodeGen/AArch64/sve-fp-combine.ll
@@ -826,9 +826,7 @@
 define <vscale x 8 x half> @fadd_h_sel(<vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x i1> %mask) {
 ; CHECK-LABEL: fadd_h_sel:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z2.h, #0 // =0x0
-; CHECK-NEXT:    sel z1.h, p0, z1.h, z2.h
-; CHECK-NEXT:    fadd z0.h, z0.h, z1.h
+; CHECK-NEXT:    fadd z0.h, p0/m, z0.h, z1.h
 ; CHECK-NEXT:    ret
   %sel = select <vscale x 8 x i1> %mask, <vscale x 8 x half> %b, <vscale x 8 x half> zeroinitializer
   %fadd = fadd <vscale x 8 x half> %a, %sel
@@ -838,9 +836,7 @@
 define <vscale x 4 x float> @fadd_s_sel(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: fadd_s_sel:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z2.s, #0 // =0x0
-; CHECK-NEXT:    sel z1.s, p0, z1.s, z2.s
-; CHECK-NEXT:    fadd z0.s, z0.s, z1.s
+; CHECK-NEXT:    fadd z0.s, p0/m, z0.s, z1.s
 ; CHECK-NEXT:    ret
   %sel = select <vscale x 4 x i1> %mask, <vscale x 4 x float> %b, <vscale x 4 x float> zeroinitializer
   %fadd = fadd <vscale x 4 x float> %a, %sel
@@ -850,9 +846,7 @@
 define <vscale x 2 x double> @fadd_d_sel(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: fadd_d_sel:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z2.d, #0 // =0x0
-; CHECK-NEXT:    sel z1.d, p0, z1.d, z2.d
-; CHECK-NEXT:    fadd z0.d, z0.d, z1.d
+; CHECK-NEXT:    fadd z0.d, p0/m, z0.d, z1.d
 ; CHECK-NEXT:    ret
   %sel = select <vscale x 2 x i1> %mask, <vscale x 2 x double> %b, <vscale x 2 x double> zeroinitializer
   %fadd = fadd <vscale x 2 x double> %a, %sel
@@ -862,9 +856,7 @@
 define <vscale x 8 x half> @fsub_h_sel(<vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x i1> %mask) {
 ; CHECK-LABEL: fsub_h_sel:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z2.h, #0 // =0x0
-; CHECK-NEXT:    sel z1.h, p0, z1.h, z2.h
-; CHECK-NEXT:    fsub z0.h, z0.h, z1.h
+; CHECK-NEXT:    fsub z0.h, p0/m, z0.h, z1.h
 ; CHECK-NEXT:    ret
   %sel = select <vscale x 8 x i1> %mask, <vscale x 8 x half> %b, <vscale x 8 x half> zeroinitializer
   %fsub = fsub <vscale x 8 x half> %a, %sel
@@ -874,9 +866,7 @@
 define <vscale x 4 x float> @fsub_s_sel(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: fsub_s_sel:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z2.s, #0 // =0x0
-; CHECK-NEXT:    sel z1.s, p0, z1.s, z2.s
-; CHECK-NEXT:    fsub z0.s, z0.s, z1.s
+; CHECK-NEXT:    fsub z0.s, p0/m, z0.s, z1.s
 ; CHECK-NEXT:    ret
   %sel = select <vscale x 4 x i1> %mask, <vscale x 4 x float> %b, <vscale x 4 x float> zeroinitializer
   %fsub = fsub <vscale x 4 x float> %a, %sel
@@ -886,9 +876,7 @@
 define <vscale x 2 x double> @fsub_d_sel(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: fsub_d_sel:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z2.d, #0 // =0x0
-; CHECK-NEXT:    sel z1.d, p0, z1.d, z2.d
-; CHECK-NEXT:    fsub z0.d, z0.d, z1.d
+; CHECK-NEXT:    fsub z0.d, p0/m, z0.d, z1.d
 ; CHECK-NEXT:    ret
   %sel = select <vscale x 2 x i1> %mask, <vscale x 2 x double> %b, <vscale x 2 x double> zeroinitializer
   %fsub = fsub <vscale x 2 x double> %a, %sel
@@ -898,9 +886,7 @@
 define <vscale x 8 x half> @fmul_h_sel(<vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x i1> %mask) {
 ; CHECK-LABEL: fmul_h_sel:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z2.h, #0 // =0x0
-; CHECK-NEXT:    sel z1.h, p0, z1.h, z2.h
-; CHECK-NEXT:    fmul z0.h, z0.h, z1.h
+; CHECK-NEXT:    fmul z0.h, p0/m, z0.h, z1.h
 ; CHECK-NEXT:    ret
   %sel = select <vscale x 8 x i1> %mask, <vscale x 8 x half> %b, <vscale x 8 x half> zeroinitializer
   %fmul = fmul <vscale x 8 x half> %a, %sel
@@ -910,9 +896,7 @@
 define <vscale x 4 x float> @fmul_s_sel(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: fmul_s_sel:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z2.s, #0 // =0x0
-; CHECK-NEXT:    sel z1.s, p0, z1.s, z2.s
-; CHECK-NEXT:    fmul z0.s, z0.s, z1.s
+; CHECK-NEXT:    fmul z0.s, p0/m, z0.s, z1.s
 ; CHECK-NEXT:    ret
   %sel = select <vscale x 4 x i1> %mask, <vscale x 4 x float> %b, <vscale x 4 x float> zeroinitializer
   %fmul = fmul <vscale x 4 x float> %a, %sel
@@ -922,9 +906,7 @@
 define <vscale x 2 x double> @fmul_d_sel(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: fmul_d_sel:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z2.d, #0 // =0x0
-; CHECK-NEXT:    sel z1.d, p0, z1.d, z2.d
-; CHECK-NEXT:    fmul z0.d, z0.d, z1.d
+; CHECK-NEXT:    fmul z0.d, p0/m, z0.d, z1.d
 ; CHECK-NEXT:    ret
   %sel = select <vscale x 2 x i1> %mask, <vscale x 2 x double> %b, <vscale x 2 x double> zeroinitializer
   %fmul = fmul <vscale x 2 x double> %a, %sel
@@ -934,10 +916,7 @@
 define <vscale x 8 x half> @fadd_sel_fmul_h(<vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c, <vscale x 8 x i1> %mask) {
 ; CHECK-LABEL: fadd_sel_fmul_h:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z3.h, #0 // =0x0
-; CHECK-NEXT:    fmul z1.h, z1.h, z2.h
-; CHECK-NEXT:    sel z1.h, p0, z1.h, z3.h
-; CHECK-NEXT:    fadd z0.h, z0.h, z1.h
+; CHECK-NEXT:    fmla z0.h, p0/m, z1.h, z2.h
 ; CHECK-NEXT:    ret
   %fmul = fmul contract <vscale x 8 x half> %b, %c
   %sel = select <vscale x 8 x i1> %mask, <vscale x 8 x half> %fmul, <vscale x 8 x half> zeroinitializer
@@ -948,10 +927,7 @@
 define <vscale x 4 x float> @fadd_sel_fmul_s(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: fadd_sel_fmul_s:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z3.s, #0 // =0x0
-; CHECK-NEXT:    fmul z1.s, z1.s, z2.s
-; CHECK-NEXT:    sel z1.s, p0, z1.s, z3.s
-; CHECK-NEXT:    fadd z0.s, z0.s, z1.s
+; CHECK-NEXT:    fmla z0.s, p0/m, z1.s, z2.s
 ; CHECK-NEXT:    ret
   %fmul = fmul contract <vscale x 4 x float> %b, %c
   %sel = select <vscale x 4 x i1> %mask, <vscale x 4 x float> %fmul, <vscale x 4 x float> zeroinitializer
@@ -962,10 +938,7 @@
 define <vscale x 2 x double> @fadd_sel_fmul_d(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: fadd_sel_fmul_d:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z3.d, #0 // =0x0
-; CHECK-NEXT:    fmul z1.d, z1.d, z2.d
-; CHECK-NEXT:    sel z1.d, p0, z1.d, z3.d
-; CHECK-NEXT:    fadd z0.d, z0.d, z1.d
+; CHECK-NEXT:    fmla z0.d, p0/m, z1.d, z2.d
 ; CHECK-NEXT:    ret
   %fmul = fmul contract <vscale x 2 x double> %b, %c
   %sel = select <vscale x 2 x i1> %mask, <vscale x 2 x double> %fmul, <vscale x 2 x double> zeroinitializer
@@ -976,10 +949,7 @@
 define <vscale x 8 x half> @fsub_sel_fmul_h(<vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c, <vscale x 8 x i1> %mask) {
 ; CHECK-LABEL: fsub_sel_fmul_h:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z3.h, #0 // =0x0
-; CHECK-NEXT:    fmul z1.h, z1.h, z2.h
-; CHECK-NEXT:    sel z1.h, p0, z1.h, z3.h
-; CHECK-NEXT:    fsub z0.h, z0.h, z1.h
+; CHECK-NEXT:    fmls z0.h, p0/m, z1.h, z2.h
 ; CHECK-NEXT:    ret
   %fmul = fmul contract <vscale x 8 x half> %b, %c
   %sel = select <vscale x 8 x i1> %mask, <vscale x 8 x half> %fmul, <vscale x 8 x half> zeroinitializer
@@ -990,10 +960,7 @@
 define <vscale x 4 x float> @fsub_sel_fmul_s(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: fsub_sel_fmul_s:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z3.s, #0 // =0x0
-; CHECK-NEXT:    fmul z1.s, z1.s, z2.s
-; CHECK-NEXT:    sel z1.s, p0, z1.s, z3.s
-; CHECK-NEXT:    fsub z0.s, z0.s, z1.s
+; CHECK-NEXT:    fmls z0.s, p0/m, z1.s, z2.s
 ; CHECK-NEXT:    ret
   %fmul = fmul contract <vscale x 4 x float> %b, %c
   %sel = select <vscale x 4 x i1> %mask, <vscale x 4 x float> %fmul, <vscale x 4 x float> zeroinitializer
@@ -1004,13 +971,35 @@
 define <vscale x 2 x double> @fsub_sel_fmul_d(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: fsub_sel_fmul_d:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z3.d, #0 // =0x0
-; CHECK-NEXT:    fmul z1.d, z1.d, z2.d
-; CHECK-NEXT:    sel z1.d, p0, z1.d, z3.d
-; CHECK-NEXT:    fsub z0.d, z0.d, z1.d
+; CHECK-NEXT:    fmls z0.d, p0/m, z1.d, z2.d
 ; CHECK-NEXT:    ret
   %fmul = fmul contract <vscale x 2 x double> %b, %c
   %sel = select <vscale x 2 x i1> %mask, <vscale x 2 x double> %fmul, <vscale x 2 x double> zeroinitializer
   %fsub = fsub contract <vscale x 2 x double> %a, %sel
   ret <vscale x 2 x double> %fsub
 }
+
+; Verify combine requires contract fast-math flag.
+define <vscale x 4 x float> @fadd_sel_fmul_nocontract_s(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c, <vscale x 4 x i1> %mask) {
+; CHECK-LABEL: fadd_sel_fmul_nocontract_s:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fmul z1.s, z1.s, z2.s
+; CHECK-NEXT:    fadd z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT:    ret
+  %fmul = fmul <vscale x 4 x float> %b, %c
+  %sel = select <vscale x 4 x i1> %mask, <vscale x 4 x float> %fmul, <vscale x 4 x float> zeroinitializer
+  %fadd = fadd contract <vscale x 4 x float> %a, %sel
+  ret <vscale x 4 x float> %fadd
+}
+
+define <vscale x 4 x float> @fadd_nocontract_sel_fmul_s(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c, <vscale x 4 x i1> %mask) {
+; CHECK-LABEL: fadd_nocontract_sel_fmul_s:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fmul z1.s, z1.s, z2.s
+; CHECK-NEXT:    fadd z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT:    ret
+  %fmul = fmul contract <vscale x 4 x float> %b, %c
+  %sel = select <vscale x 4 x i1> %mask, <vscale x 4 x float> %fmul, <vscale x 4 x float> zeroinitializer
+  %fadd = fadd <vscale x 4 x float> %a, %sel
+  ret <vscale x 4 x float> %fadd
+}