[AArch64][SVE] Add support for DestructiveTernaryCommWithRev DestructiveInstType

[cameron.mcinally]

Summary

This is the fifth patch in a series to support prefixing destructive operations, with the MOVPRFX instruction, to build constructive operations. The previous patch is D75064.

Here we add support for the DestructiveTernaryCommWithRev DestructiveInstType.

[cameron.mcinally]

Correct formatting to appease Harbormaster.

[cameron.mcinally]

Ping.

llvm/lib/Target/AArch64/AArch64ExpandPseudoInsts.cpp

bool AArch64ExpandPseudo::expand_DestructiveOp(
 
   unsigned DstReg = MI.getOperand(0).getReg();
   bool DstIsDead = MI.getOperand(0).isDead();
 
   if (DType == AArch64::DestructiveBinary)
     assert(DstReg != MI.getOperand(3).getReg());
 
   bool UseRev = false;
-  unsigned PredIdx, DOPIdx, SrcIdx;
+  unsigned PredIdx, DOPIdx, SrcIdx, Src2Idx;
   switch (DType) {
   case AArch64::DestructiveBinaryComm:
   case AArch64::DestructiveBinaryCommWithRev:
     if (DstReg == MI.getOperand(3).getReg()) {
       // FSUB Zd, Pg, Zs1, Zd  ==> FSUBR   Zd, Pg/m, Zd, Zs1
       std::tie(PredIdx, DOPIdx, SrcIdx) = std::make_tuple(1, 3, 2);
       UseRev = true;
       break;
     }
     LLVM_FALLTHROUGH;
   case AArch64::DestructiveBinary:
     std::tie(PredIdx, DOPIdx, SrcIdx) = std::make_tuple(1, 2, 3);
    break;
+  case AArch64::DestructiveTernaryCommWithRev:
+    std::tie(PredIdx, DOPIdx, SrcIdx, Src2Idx) = std::make_tuple(1, 2, 3, 4);
+    if (DstReg == MI.getOperand(3).getReg()) {
+      // FMLA Zd, Pg, Za, Zd, Zm ==> FMAD Zdn, Pg, Zm, Za
+      std::tie(PredIdx, DOPIdx, SrcIdx, Src2Idx) = std::make_tuple(1, 3, 4, 2);
+      UseRev = true;
+    } else if (DstReg == MI.getOperand(4).getReg()) {
+      // FMLA Zd, Pg, Za, Zm, Zd ==> FMAD Zdn, Pg, Zm, Za
+      std::tie(PredIdx, DOPIdx, SrcIdx, Src2Idx) = std::make_tuple(1, 4, 3, 2);
+      UseRev = true;
+    }
+    break;
   default:
     llvm_unreachable("Unsupported Destructive Operand type");
   }
 
 #ifndef NDEBUG
   // MOVPRFX can only be used if the destination operand
   // is the destructive operand, not as any other operand,
   // so the Destructive Operand must be unique.
   bool DOPRegIsUnique = false;
   switch (DType) {
   case AArch64::DestructiveBinaryComm:
   case AArch64::DestructiveBinaryCommWithRev:
     DOPRegIsUnique =
       DstReg != MI.getOperand(DOPIdx).getReg() ||
       MI.getOperand(DOPIdx).getReg() != MI.getOperand(SrcIdx).getReg();
     break;
+  case AArch64::DestructiveTernaryCommWithRev:
+    DOPRegIsUnique =
+        DstReg != MI.getOperand(DOPIdx).getReg() ||
+        (MI.getOperand(DOPIdx).getReg() != MI.getOperand(SrcIdx).getReg() &&
+         MI.getOperand(DOPIdx).getReg() != MI.getOperand(Src2Idx).getReg());
+    break;
   }
 
   assert (DOPRegIsUnique && "The destructive operand should be unique");
 #endif
 
   // Resolve the reverse opcode
   if (UseRev) {
     if (AArch64::getSVERevInstr(Opcode) != -1)
#endif
 
   switch (DType) {
   case AArch64::DestructiveBinaryComm:
   case AArch64::DestructiveBinaryCommWithRev:
     DOP.add(MI.getOperand(PredIdx))
        .addReg(MI.getOperand(DOPIdx).getReg(), RegState::Kill)
        .add(MI.getOperand(SrcIdx));
     break;
+  case AArch64::DestructiveTernaryCommWithRev:
+    DOP.add(MI.getOperand(PredIdx))
+        .addReg(MI.getOperand(DOPIdx).getReg(), RegState::Kill)
+        .add(MI.getOperand(SrcIdx))
+        .add(MI.getOperand(Src2Idx));
+    break;
   }
 
   if (PRFX) {
     finalizeBundle(MBB, PRFX->getIterator(), MBBI->getIterator());
     transferImpOps(MI, PRFX, DOP);
   } else
     transferImpOps(MI, DOP, DOP);
 

llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td

let Predicates = [HasSVE] in {
   defm FRECPS_ZZZ  : sve_fp_3op_u_zd<0b110, "frecps",  int_aarch64_sve_frecps_x>;
   defm FRSQRTS_ZZZ : sve_fp_3op_u_zd<0b111, "frsqrts", int_aarch64_sve_frsqrts_x>;
 
   defm FTSSEL_ZZZ : sve_int_bin_cons_misc_0_b<"ftssel", int_aarch64_sve_ftssel_x>;
 
   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",  int_aarch64_sve_fmla>;
-  defm FMLS_ZPmZZ  : sve_fp_3op_p_zds_a<0b01, "fmls",  int_aarch64_sve_fmls>;
-  defm FNMLA_ZPmZZ : sve_fp_3op_p_zds_a<0b10, "fnmla", int_aarch64_sve_fnmla>;
-  defm FNMLS_ZPmZZ : sve_fp_3op_p_zds_a<0b11, "fnmls", int_aarch64_sve_fnmls>;
-
-  defm FMAD_ZPmZZ  : sve_fp_3op_p_zds_b<0b00, "fmad",  int_aarch64_sve_fmad>;
-  defm FMSB_ZPmZZ  : sve_fp_3op_p_zds_b<0b01, "fmsb",  int_aarch64_sve_fmsb>;
-  defm FNMAD_ZPmZZ : sve_fp_3op_p_zds_b<0b10, "fnmad", int_aarch64_sve_fnmad>;
-  defm FNMSB_ZPmZZ : sve_fp_3op_p_zds_b<0b11, "fnmsb", int_aarch64_sve_fnmsb>;
+  defm FMLA_ZPmZZ  : sve_fp_3op_p_zds_a<0b00, "fmla",  "FMLA_ZPZZZ", int_aarch64_sve_fmla, "FMAD_ZPmZZ", 1>;
+  defm FMLS_ZPmZZ  : sve_fp_3op_p_zds_a<0b01, "fmls",  "FMLS_ZPZZZ", int_aarch64_sve_fmls, "FMSB_ZPmZZ", 1>;
+  defm FNMLA_ZPmZZ : sve_fp_3op_p_zds_a<0b10, "fnmla", "FNMLA_ZPZZZ", int_aarch64_sve_fnmla, "FNMAD_ZPmZZ", 1>;
+  defm FNMLS_ZPmZZ : sve_fp_3op_p_zds_a<0b11, "fnmls", "FNMLS_ZPZZZ", int_aarch64_sve_fnmls, "FNMSB_ZPmZZ", 1>;
+
+  defm FMAD_ZPmZZ  : sve_fp_3op_p_zds_b<0b00, "fmad",  int_aarch64_sve_fmad, "FMLA_ZPmZZ", 0>;
+  defm FMSB_ZPmZZ  : sve_fp_3op_p_zds_b<0b01, "fmsb",  int_aarch64_sve_fmsb, "FMLS_ZPmZZ", 0>;
+  defm FNMAD_ZPmZZ : sve_fp_3op_p_zds_b<0b10, "fnmad", int_aarch64_sve_fnmad, "FNMLA_ZPmZZ", 0>;
+  defm FNMSB_ZPmZZ : sve_fp_3op_p_zds_b<0b11, "fnmsb", int_aarch64_sve_fnmsb, "FNMLS_ZPmZZ", 0>;
+
+  defm FMLA_ZPZZZ  : sve_fp_3op_p_zds_zx<int_aarch64_sve_fmla, int_aarch64_sve_fmad>;
+  defm FMLS_ZPZZZ  : sve_fp_3op_p_zds_zx<int_aarch64_sve_fmls, int_aarch64_sve_fmsb>;
+  defm FNMLA_ZPZZZ : sve_fp_3op_p_zds_zx<int_aarch64_sve_fnmla, int_aarch64_sve_fnmad>;
+  defm FNMLS_ZPZZZ : sve_fp_3op_p_zds_zx<int_aarch64_sve_fnmls, int_aarch64_sve_fnmsb>;
 
   defm FTMAD_ZZI : sve_fp_ftmad<"ftmad", int_aarch64_sve_ftmad_x>;
 
   defm FMLA_ZZZI : sve_fp_fma_by_indexed_elem<0b0, "fmla", int_aarch64_sve_fmla_lane>;
   defm FMLS_ZZZI : sve_fp_fma_by_indexed_elem<0b1, "fmls", int_aarch64_sve_fmls_lane>;
 
   defm FCMLA_ZZZI : sve_fp_fcmla_by_indexed_elem<"fcmla", int_aarch64_sve_fcmla_lane>;
   defm FMUL_ZZZI   : sve_fp_fmul_by_indexed_elem<"fmul", int_aarch64_sve_fmul_lane>;

llvm/lib/Target/AArch64/SVEInstrFormats.td

 def SVEDup0 : ComplexPattern<i64, 0, "SelectDupZero", []>;
 def SVEDup0Undef : ComplexPattern<i64, 0, "SelectDupZeroOrUndef", []>;
 
 let AddedComplexity = 1 in {
 class SVE_3_Op_Pat_SelZero<ValueType vtd, SDPatternOperator op, ValueType vt1,
                    ValueType vt2, ValueType vt3, Instruction inst>
 : Pat<(vtd (vtd (op vt1:$Op1, (vselect vt1:$Op1, vt2:$Op2, (SVEDup0)), vt3:$Op3))),
       (inst $Op1, $Op2, $Op3)>;
+
+class SVE_4_Op_Pat_SelZero<ValueType vtd, SDPatternOperator op, ValueType vt1,
+                   ValueType vt2, ValueType vt3, ValueType vt4,
+                   Instruction inst>
+: Pat<(vtd (op vt1:$Op1, (vselect vt1:$Op1, vt2:$Op2, (SVEDup0)), vt3:$Op3, vt4:$Op4)),
+      (inst $Op1, $Op2, $Op3, $Op4)>;
 }
 
 //
 // Common but less generic patterns.
 //
 
 class SVE_1_Op_AllActive_Pat<ValueType vtd, SDPatternOperator op, ValueType vt1,
                              Instruction inst, Instruction ptrue>

 //
 let hasNoSchedulingInfo = 1 in {
   class PredTwoOpPseudo<string name, ZPRRegOp zprty,
                         FalseLanesEnum flags = FalseLanesNone>
   : SVEPseudo2Instr<name, 0>,
     Pseudo<(outs zprty:$Zd), (ins PPR3bAny:$Pg, zprty:$Zs1, zprty:$Zs2), []> {
     let FalseLanes = flags;
   }
+
+  class PredThreeOpPseudo<string name, ZPRRegOp zprty,
+                          FalseLanesEnum flags = FalseLanesNone>
+  : SVEPseudo2Instr<name, 0>,
+    Pseudo<(outs zprty:$Zd), (ins PPR3bAny:$Pg, zprty:$Zs1, zprty:$Zs2, zprty:$Zs3), []> {
+    let FalseLanes = flags;
+  }
 }
 
 //===----------------------------------------------------------------------===//
 // SVE Predicate Misc Group
 //===----------------------------------------------------------------------===//
 
 class sve_int_pfalse<bits<6> opc, string asm>
 : I<(outs PPR8:$Pd), (ins),
: I<(outs zprty:$Zda), (ins PPR3bAny:$Pg, zprty:$_Zda, zprty:$Zn, zprty:$Zm),
   let Inst{20-16} = Zm;
   let Inst{15}    = 0b0;
   let Inst{14-13} = opc;
   let Inst{12-10} = Pg;
   let Inst{9-5}   = Zn;
   let Inst{4-0}   = Zda;
 
   let Constraints = "$Zda = $_Zda";
-  let DestructiveInstType = DestructiveOther;
   let ElementSize = zprty.ElementSize;
 }
 
-multiclass sve_fp_3op_p_zds_a<bits<2> opc, string asm, SDPatternOperator op> {
-  def _H : sve_fp_3op_p_zds_a<0b01, opc, asm, ZPR16>;
-  def _S : sve_fp_3op_p_zds_a<0b10, opc, asm, ZPR32>;
-  def _D : sve_fp_3op_p_zds_a<0b11, opc, asm, ZPR64>;
+multiclass sve_fp_3op_p_zds_a<bits<2> opc, string asm, string Ps,
+                              SDPatternOperator op, string revname="",
+                              bit isOrig=0> {
+  let DestructiveInstType = DestructiveTernaryCommWithRev in {
+  def _H : sve_fp_3op_p_zds_a<0b01, opc, asm, ZPR16>,
+           SVEPseudo2Instr<Ps # _H, 1>, SVEInstr2Rev<NAME # _H, revname # _H, isOrig>;
+  def _S : sve_fp_3op_p_zds_a<0b10, opc, asm, ZPR32>,
+           SVEPseudo2Instr<Ps # _S, 1>, SVEInstr2Rev<NAME # _S, revname # _S, isOrig>;
+  def _D : sve_fp_3op_p_zds_a<0b11, opc, asm, ZPR64>,
+           SVEPseudo2Instr<Ps # _D, 1>, SVEInstr2Rev<NAME # _D, revname # _D, isOrig>;
+  }
 
   def : SVE_4_Op_Pat<nxv8f16, op, nxv8i1, nxv8f16, nxv8f16, nxv8f16, !cast<Instruction>(NAME # _H)>;
   def : SVE_4_Op_Pat<nxv4f32, op, nxv4i1, nxv4f32, nxv4f32, nxv4f32, !cast<Instruction>(NAME # _S)>;
   def : SVE_4_Op_Pat<nxv2f64, op, nxv2i1, nxv2f64, nxv2f64, nxv2f64, !cast<Instruction>(NAME # _D)>;
 }
 
 class sve_fp_3op_p_zds_b<bits<2> sz, bits<2> opc, string asm,
                          ZPRRegOp zprty>
: I<(outs zprty:$Zdn), (ins PPR3bAny:$Pg, zprty:$_Zdn, zprty:$Zm, zprty:$Za),
   let Inst{9-5}   = Zm;
   let Inst{4-0}   = Zdn;
 
   let Constraints = "$Zdn = $_Zdn";
   let DestructiveInstType = DestructiveOther;
   let ElementSize = zprty.ElementSize;
 }
 
-multiclass sve_fp_3op_p_zds_b<bits<2> opc, string asm, SDPatternOperator op> {
-  def _H : sve_fp_3op_p_zds_b<0b01, opc, asm, ZPR16>;
-  def _S : sve_fp_3op_p_zds_b<0b10, opc, asm, ZPR32>;
-  def _D : sve_fp_3op_p_zds_b<0b11, opc, asm, ZPR64>;
+multiclass sve_fp_3op_p_zds_b<bits<2> opc, string asm, SDPatternOperator op,
+                              string revname, bit isOrig> {
+  def _H : sve_fp_3op_p_zds_b<0b01, opc, asm, ZPR16>,
+           SVEInstr2Rev<NAME # _H, revname # _H, isOrig>;
+  def _S : sve_fp_3op_p_zds_b<0b10, opc, asm, ZPR32>,
+           SVEInstr2Rev<NAME # _S, revname # _S, isOrig>;
+  def _D : sve_fp_3op_p_zds_b<0b11, opc, asm, ZPR64>,
+           SVEInstr2Rev<NAME # _D, revname # _D, isOrig>;
 
   def : SVE_4_Op_Pat<nxv8f16, op, nxv8i1, nxv8f16, nxv8f16, nxv8f16, !cast<Instruction>(NAME # _H)>;
   def : SVE_4_Op_Pat<nxv4f32, op, nxv4i1, nxv4f32, nxv4f32, nxv4f32, !cast<Instruction>(NAME # _S)>;
   def : SVE_4_Op_Pat<nxv2f64, op, nxv2i1, nxv2f64, nxv2f64, nxv2f64, !cast<Instruction>(NAME # _D)>;
 }
 
+multiclass sve_fp_3op_p_zds_zx<SDPatternOperator op, SDPatternOperator rev_op> {
+  def _ZERO_H : PredThreeOpPseudo<NAME # _H, ZPR16, FalseLanesZero>;
+  def _ZERO_S : PredThreeOpPseudo<NAME # _S, ZPR32, FalseLanesZero>;
+  def _ZERO_D : PredThreeOpPseudo<NAME # _D, ZPR64, FalseLanesZero>;
+
+  def : SVE_4_Op_Pat_SelZero<nxv8f16, op, nxv8i1, nxv8f16, nxv8f16, nxv8f16, !cast<Instruction>(NAME # _ZERO_H)>;
+  def : SVE_4_Op_Pat_SelZero<nxv4f32, op, nxv4i1, nxv4f32, nxv4f32, nxv4f32, !cast<Instruction>(NAME # _ZERO_S)>;
+  def : SVE_4_Op_Pat_SelZero<nxv2f64, op, nxv2i1, nxv2f64, nxv2f64, nxv2f64, !cast<Instruction>(NAME # _ZERO_D)>;
+
+  // As above but with the accumulator in it's alternative position.
+  def : Pat<(nxv8f16 (rev_op nxv8i1:$Op1, (vselect nxv8i1:$Op1, nxv8f16:$Op2, (SVEDup0)), nxv8f16:$Op3, nxv8f16:$Op4)),
+            (!cast<Instruction>(NAME # _ZERO_H) $Op1, $Op4, $Op2, $Op3)>;
+  def : Pat<(nxv4f32 (rev_op nxv4i1:$Op1, (vselect nxv4i1:$Op1, nxv4f32:$Op2, (SVEDup0)), nxv4f32:$Op3, nxv4f32:$Op4)),
+            (!cast<Instruction>(NAME # _ZERO_S) $Op1, $Op4, $Op2, $Op3)>;
+  def : Pat<(nxv2f64 (rev_op nxv2i1:$Op1, (vselect nxv2i1:$Op1, nxv2f64:$Op2, (SVEDup0)), nxv2f64:$Op3, nxv2f64:$Op4)),
+            (!cast<Instruction>(NAME # _ZERO_D) $Op1, $Op4, $Op2, $Op3)>;
+}
+
 //===----------------------------------------------------------------------===//
 // SVE Floating Point Multiply-Add - Indexed Group
 //===----------------------------------------------------------------------===//
 
 class sve_fp_fma_by_indexed_elem<bits<2> sz, bit opc, string asm,
                                  ZPRRegOp zprty1,
                                  ZPRRegOp zprty2, Operand itype>
 : I<(outs zprty1:$Zda), (ins zprty1:$_Zda, zprty1:$Zn, zprty2:$Zm, itype:$iop),

llvm/test/CodeGen/AArch64/sve-intrinsics-fp-arith-merging.ll

; CHECK-NEXT: ret
   %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
   %out = call <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1> %pg,
                                                               <vscale x 2 x double> %a_z,
                                                               <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %out
 }
 
 ;
+; FMAD
+;
+
+define <vscale x 8 x half> @fmad_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
+; CHECK-LABEL: fmad_h:
+; CHECK:      movprfx z0.h, p0/z, z0.h
+; CHECK-NEXT: fmad z0.h, p0/m, z1.h, z2.h
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> zeroinitializer
+  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fmad.nxv8f16(<vscale x 8 x i1> %pg,
+                                                            <vscale x 8 x half> %a_z,
+                                                            <vscale x 8 x half> %b,
+                                                            <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %out
+}
+
+define <vscale x 4 x float> @fmad_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
+; CHECK-LABEL: fmad_s:
+; CHECK:      movprfx z0.s, p0/z, z0.s
+; CHECK-NEXT: fmad z0.s, p0/m, z1.s, z2.s
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
+  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmad.nxv4f32(<vscale x 4 x i1> %pg,
+                                                             <vscale x 4 x float> %a_z,
+                                                             <vscale x 4 x float> %b,
+                                                             <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %out
+}
+
+define <vscale x 2 x double> @fmad_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
+; CHECK-LABEL: fmad_d:
+; CHECK:      movprfx z0.d, p0/z, z0.d
+; CHECK-NEXT: fmad z0.d, p0/m, z1.d, z2.d
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
+  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmad.nxv2f64(<vscale x 2 x i1> %pg,
+                                                              <vscale x 2 x double> %a_z,
+                                                              <vscale x 2 x double> %b,
+                                                              <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %out
+}
+
+;
 ; FMAX
 ;
 
 define <vscale x 4 x float> @fmax_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
 ; CHECK-LABEL: fmax_s:
 ; CHECK:      movprfx z0.s, p0/z, z0.s
 ; CHECK-NEXT: fmax z0.s, p0/m, z0.s, z1.s
 ; CHECK-NEXT: ret
; CHECK-NEXT: ret
   %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
   %out = call <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1> %pg,
                                                                 <vscale x 2 x double> %a_z,
                                                                 <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %out
 }
 
 ;
+; FMLA
+;
+
+define <vscale x 8 x half> @fmla_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
+; CHECK-LABEL: fmla_h:
+; CHECK:      movprfx z0.h, p0/z, z0.h
+; CHECK-NEXT: fmla z0.h, p0/m, z1.h, z2.h
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> zeroinitializer
+  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1> %pg,
+                                                            <vscale x 8 x half> %a_z,
+                                                            <vscale x 8 x half> %b,
+                                                            <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %out
+}
+
+define <vscale x 4 x float> @fmla_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
+; CHECK-LABEL: fmla_s:
+; CHECK:      movprfx z0.s, p0/z, z0.s
+; CHECK-NEXT: fmla z0.s, p0/m, z1.s, z2.s
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
+  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1> %pg,
+                                                             <vscale x 4 x float> %a_z,
+                                                             <vscale x 4 x float> %b,
+                                                             <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %out
+}
+
+define <vscale x 2 x double> @fmla_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
+; CHECK-LABEL: fmla_d:
+; CHECK:      movprfx z0.d, p0/z, z0.d
+; CHECK-NEXT: fmla z0.d, p0/m, z1.d, z2.d
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
+  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1> %pg,
+                                                              <vscale x 2 x double> %a_z,
+                                                              <vscale x 2 x double> %b,
+                                                              <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %out
+}
+
+;
+; FMLS
+;
+
+define <vscale x 8 x half> @fmls_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
+; CHECK-LABEL: fmls_h:
+; CHECK:      movprfx z0.h, p0/z, z0.h
+; CHECK-NEXT: fmls z0.h, p0/m, z1.h, z2.h
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> zeroinitializer
+  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1> %pg,
+                                                            <vscale x 8 x half> %a_z,
+                                                            <vscale x 8 x half> %b,
+                                                            <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %out
+}
+
+define <vscale x 4 x float> @fmls_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
+; CHECK-LABEL: fmls_s:
+; CHECK:      movprfx z0.s, p0/z, z0.s
+; CHECK-NEXT: fmls z0.s, p0/m, z1.s, z2.s
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
+  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1> %pg,
+                                                             <vscale x 4 x float> %a_z,
+                                                             <vscale x 4 x float> %b,
+                                                             <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %out
+}
+
+define <vscale x 2 x double> @fmls_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
+; CHECK-LABEL: fmls_d:
+; CHECK:      movprfx z0.d, p0/z, z0.d
+; CHECK-NEXT: fmls z0.d, p0/m, z1.d, z2.d
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
+  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1> %pg,
+                                                              <vscale x 2 x double> %a_z,
+                                                              <vscale x 2 x double> %b,
+                                                              <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %out
+}
+
+;
+; FMSB
+;
+
+define <vscale x 8 x half> @fmsb_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
+; CHECK-LABEL: fmsb_h:
+; CHECK:      movprfx z0.h, p0/z, z0.h
+; CHECK-NEXT: fmsb z0.h, p0/m, z1.h, z2.h
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> zeroinitializer
+  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fmsb.nxv8f16(<vscale x 8 x i1> %pg,
+                                                            <vscale x 8 x half> %a_z,
+                                                            <vscale x 8 x half> %b,
+                                                            <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %out
+}
+
+define <vscale x 4 x float> @fmsb_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
+; CHECK-LABEL: fmsb_s:
+; CHECK:      movprfx z0.s, p0/z, z0.s
+; CHECK-NEXT: fmsb z0.s, p0/m, z1.s, z2.s
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
+  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmsb.nxv4f32(<vscale x 4 x i1> %pg,
+                                                             <vscale x 4 x float> %a_z,
+                                                             <vscale x 4 x float> %b,
+                                                             <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %out
+}
+
+define <vscale x 2 x double> @fmsb_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
+; CHECK-LABEL: fmsb_d:
+; CHECK:      movprfx z0.d, p0/z, z0.d
+; CHECK-NEXT: fmsb z0.d, p0/m, z1.d, z2.d
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
+  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmsb.nxv2f64(<vscale x 2 x i1> %pg,
+                                                              <vscale x 2 x double> %a_z,
+                                                              <vscale x 2 x double> %b,
+                                                              <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %out
+}
+
+;
 ; FMUL
 ;
 
 define <vscale x 4 x float> @fmul_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
 ; CHECK-LABEL: fmul_s:
 ; CHECK:      movprfx z0.s, p0/z, z0.s
 ; CHECK-NEXT: fmul z0.s, p0/m, z0.s, z1.s
 ; CHECK-NEXT: ret
; CHECK-NEXT: ret
   %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
   %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> %pg,
                                                               <vscale x 2 x double> %a_z,
                                                               <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %out
 }
 
 ;
+; FNMAD
+;
+
+define <vscale x 8 x half> @fnmad_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
+; CHECK-LABEL: fnmad_h:
+; CHECK:      movprfx z0.h, p0/z, z0.h
+; CHECK-NEXT: fnmad z0.h, p0/m, z1.h, z2.h
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> zeroinitializer
+  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fnmad.nxv8f16(<vscale x 8 x i1> %pg,
+                                                             <vscale x 8 x half> %a_z,
+                                                             <vscale x 8 x half> %b,
+                                                             <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %out
+}
+
+define <vscale x 4 x float> @fnmad_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
+; CHECK-LABEL: fnmad_s:
+; CHECK:      movprfx z0.s, p0/z, z0.s
+; CHECK-NEXT: fnmad z0.s, p0/m, z1.s, z2.s
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
+  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fnmad.nxv4f32(<vscale x 4 x i1> %pg,
+                                                              <vscale x 4 x float> %a_z,
+                                                              <vscale x 4 x float> %b,
+                                                              <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %out
+}
+
+define <vscale x 2 x double> @fnmad_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
+; CHECK-LABEL: fnmad_d:
+; CHECK:      movprfx z0.d, p0/z, z0.d
+; CHECK-NEXT: fnmad z0.d, p0/m, z1.d, z2.d
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
+  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fnmad.nxv2f64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x double> %a_z,
+                                                               <vscale x 2 x double> %b,
+                                                               <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %out
+}
+
+;
+; FNMLA
+;
+
+define <vscale x 8 x half> @fnmla_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
+; CHECK-LABEL: fnmla_h:
+; CHECK:      movprfx z0.h, p0/z, z0.h
+; CHECK-NEXT: fnmla z0.h, p0/m, z1.h, z2.h
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> zeroinitializer
+  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> %pg,
+                                                             <vscale x 8 x half> %a_z,
+                                                             <vscale x 8 x half> %b,
+                                                             <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %out
+}
+
+define <vscale x 4 x float> @fnmla_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
+; CHECK-LABEL: fnmla_s:
+; CHECK:      movprfx z0.s, p0/z, z0.s
+; CHECK-NEXT: fnmla z0.s, p0/m, z1.s, z2.s
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
+  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> %pg,
+                                                              <vscale x 4 x float> %a_z,
+                                                              <vscale x 4 x float> %b,
+                                                              <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %out
+}
+
+define <vscale x 2 x double> @fnmla_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
+; CHECK-LABEL: fnmla_d:
+; CHECK:      movprfx z0.d, p0/z, z0.d
+; CHECK-NEXT: fnmla z0.d, p0/m, z1.d, z2.d
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
+  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x double> %a_z,
+                                                               <vscale x 2 x double> %b,
+                                                               <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %out
+}
+
+;
+; FNMLS
+;
+
+define <vscale x 8 x half> @fnmls_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
+; CHECK-LABEL: fnmls_h:
+; CHECK:      movprfx z0.h, p0/z, z0.h
+; CHECK-NEXT: fnmls z0.h, p0/m, z1.h, z2.h
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> zeroinitializer
+  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1> %pg,
+                                                             <vscale x 8 x half> %a_z,
+                                                             <vscale x 8 x half> %b,
+                                                             <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %out
+}
+
+define <vscale x 4 x float> @fnmls_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
+; CHECK-LABEL: fnmls_s:
+; CHECK:      movprfx z0.s, p0/z, z0.s
+; CHECK-NEXT: fnmls z0.s, p0/m, z1.s, z2.s
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
+  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1> %pg,
+                                                              <vscale x 4 x float> %a_z,
+                                                              <vscale x 4 x float> %b,
+                                                              <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %out
+}
+
+define <vscale x 2 x double> @fnmls_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
+; CHECK-LABEL: fnmls_d:
+; CHECK:      movprfx z0.d, p0/z, z0.d
+; CHECK-NEXT: fnmls z0.d, p0/m, z1.d, z2.d
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
+  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x double> %a_z,
+                                                               <vscale x 2 x double> %b,
+                                                               <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %out
+}
+
+;
+; FNMSB
+;
+
+define <vscale x 8 x half> @fnmsb_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
+; CHECK-LABEL: fnmsb_h:
+; CHECK:      movprfx z0.h, p0/z, z0.h
+; CHECK-NEXT: fnmsb z0.h, p0/m, z1.h, z2.h
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> zeroinitializer
+  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fnmsb.nxv8f16(<vscale x 8 x i1> %pg,
+                                                             <vscale x 8 x half> %a_z,
+                                                             <vscale x 8 x half> %b,
+                                                             <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %out
+}
+
+define <vscale x 4 x float> @fnmsb_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
+; CHECK-LABEL: fnmsb_s:
+; CHECK:      movprfx z0.s, p0/z, z0.s
+; CHECK-NEXT: fnmsb z0.s, p0/m, z1.s, z2.s
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
+  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fnmsb.nxv4f32(<vscale x 4 x i1> %pg,
+                                                              <vscale x 4 x float> %a_z,
+                                                              <vscale x 4 x float> %b,
+                                                              <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %out
+}
+
+define <vscale x 2 x double> @fnmsb_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
+; CHECK-LABEL: fnmsb_d:
+; CHECK:      movprfx z0.d, p0/z, z0.d
+; CHECK-NEXT: fnmsb z0.d, p0/m, z1.d, z2.d
+; CHECK-NEXT: ret
+  %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
+  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fnmsb.nxv2f64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x double> %a_z,
+                                                               <vscale x 2 x double> %b,
+                                                               <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %out
+}
+
+;
 ; FSUB
 ;
 
 define <vscale x 4 x float> @fsub_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
 ; CHECK-LABEL: fsub_s:
 ; CHECK:      movprfx z0.s, p0/z, z0.s
 ; CHECK-NEXT: fsub z0.s, p0/m, z0.s, z1.s
 ; CHECK-NEXT: ret

 declare <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
 
 declare <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
 
 declare <vscale x 4 x float> @llvm.aarch64.sve.fdivr.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 2 x double> @llvm.aarch64.sve.fdivr.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
 
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmad.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmad.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmad.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+
 declare <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
 
 declare <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
 
 declare <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
 
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmla.lane.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, i32)
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmla.lane.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, i32)
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmla.lane.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, i32)
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmls.lane.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, i32)
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmls.lane.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, i32)
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmls.lane.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, i32)
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmsb.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmsb.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmsb.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+
 declare <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
 
 declare <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
 
 declare <vscale x 4 x float> @llvm.aarch64.sve.fmulx.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 2 x double> @llvm.aarch64.sve.fmulx.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
 
+declare <vscale x 8 x half> @llvm.aarch64.sve.fnmad.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+declare <vscale x 4 x float> @llvm.aarch64.sve.fnmad.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.aarch64.sve.fnmad.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+declare <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+declare <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fnmsb.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+declare <vscale x 4 x float> @llvm.aarch64.sve.fnmsb.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.aarch64.sve.fnmsb.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+
 declare <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
 
 declare <vscale x 4 x float> @llvm.aarch64.sve.fsubr.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 2 x double> @llvm.aarch64.sve.fsubr.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)