[AArch64][SVE] Add remaining patterns and intrinsics for add/sub/mad patterns

[dancgr]

Summary

Add pattern matching and intrinsics for the following instructions:

• predicated orr, eor, and, bic
• predicated mul, smulh, umulh, sdiv, udiv, sdivr, udivr
• predicated smax, umax, smin, umin, sabd, uabd
• mad, msb, mla, mls

[sdesmalen]

Thanks @dancgr , LGTM

[amehsan]

committed
https://reviews.llvm.org/rGe55b536d7d81

llvm/include/llvm/IR/IntrinsicsAArch64.td

 let TargetPrefix = "aarch64" in {  // All intrinsics start with "llvm.aarch64.".
 
 
 class AdvSIMD_Pred2VectorArg_Intrinsic
     : Intrinsic<[llvm_anyvector_ty],
              [LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>, LLVMMatchType<0>, LLVMMatchType<0>],
              [IntrNoMem]>;
 
+class AdvSIMD_Pred3VectorArg_Intrinsic
+    : Intrinsic<[llvm_anyvector_ty],
+             [LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>, LLVMMatchType<0>, LLVMMatchType<0>, LLVMMatchType<0>],
+             [IntrNoMem]>;
+
 
 //
 // Integer arithmetic
 //
 
 def int_aarch64_sve_add   : AdvSIMD_Pred2VectorArg_Intrinsic;
 def int_aarch64_sve_sub   : AdvSIMD_Pred2VectorArg_Intrinsic;
 def int_aarch64_sve_subr  : AdvSIMD_Pred2VectorArg_Intrinsic;
 
-def int_aarch64_sve_bic  : AdvSIMD_2VectorArg_Intrinsic;
+def int_aarch64_sve_and        : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_or         : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_xor        : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_bic        : AdvSIMD_2VectorArg_Intrinsic;
+def int_aarch64_sve_bic_pred   : AdvSIMD_Pred2VectorArg_Intrinsic;
+
+def int_aarch64_sve_mul        : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_smulh      : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_umulh      : AdvSIMD_Pred2VectorArg_Intrinsic;
+
+def int_aarch64_sve_sdiv       : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_udiv       : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_sdivr      : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_udivr      : AdvSIMD_Pred2VectorArg_Intrinsic;
+
+def int_aarch64_sve_smax       : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_umax       : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_smin       : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_umin       : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_sabd       : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_uabd       : AdvSIMD_Pred2VectorArg_Intrinsic;
+
+def int_aarch64_sve_mad        : AdvSIMD_Pred3VectorArg_Intrinsic;
+def int_aarch64_sve_msb        : AdvSIMD_Pred3VectorArg_Intrinsic;
+def int_aarch64_sve_mla        : AdvSIMD_Pred3VectorArg_Intrinsic;
+def int_aarch64_sve_mls        : AdvSIMD_Pred3VectorArg_Intrinsic;
 
 def int_aarch64_sve_abs : AdvSIMD_Merged1VectorArg_Intrinsic;
 def int_aarch64_sve_neg : AdvSIMD_Merged1VectorArg_Intrinsic;
 
 def int_aarch64_sve_sdot      : AdvSIMD_SVE_DOT_Intrinsic;
 def int_aarch64_sve_sdot_lane : AdvSIMD_SVE_DOT_Indexed_Intrinsic;
 
 def int_aarch64_sve_udot      : AdvSIMD_SVE_DOT_Intrinsic;

llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td

let Predicates = [HasSVE] in {
   defm ORR_ZZZ : sve_int_bin_cons_log<0b01, "orr", or>;
   defm EOR_ZZZ : sve_int_bin_cons_log<0b10, "eor", xor>;
   defm BIC_ZZZ : sve_int_bin_cons_log<0b11, "bic", int_aarch64_sve_bic>;
 
   defm ADD_ZPmZ   : sve_int_bin_pred_arit_0<0b000, "add", int_aarch64_sve_add>;
   defm SUB_ZPmZ   : sve_int_bin_pred_arit_0<0b001, "sub", int_aarch64_sve_sub>;
   defm SUBR_ZPmZ  : sve_int_bin_pred_arit_0<0b011, "subr", int_aarch64_sve_subr>;
 
-  defm ORR_ZPmZ : sve_int_bin_pred_log<0b000, "orr", null_frag>;
-  defm EOR_ZPmZ : sve_int_bin_pred_log<0b001, "eor", null_frag>;
-  defm AND_ZPmZ : sve_int_bin_pred_log<0b010, "and", null_frag>;
-  defm BIC_ZPmZ : sve_int_bin_pred_log<0b011, "bic", null_frag>;
+  defm ORR_ZPmZ : sve_int_bin_pred_log<0b000, "orr", int_aarch64_sve_or>;
+  defm EOR_ZPmZ : sve_int_bin_pred_log<0b001, "eor", int_aarch64_sve_xor>;
+  defm AND_ZPmZ : sve_int_bin_pred_log<0b010, "and", int_aarch64_sve_and>;
+  defm BIC_ZPmZ : sve_int_bin_pred_log<0b011, "bic", int_aarch64_sve_bic_pred>;
 
   defm ADD_ZI   : sve_int_arith_imm0<0b000, "add">;
   defm SUB_ZI   : sve_int_arith_imm0<0b001, "sub">;
   defm SUBR_ZI  : sve_int_arith_imm0<0b011, "subr">;
   defm SQADD_ZI : sve_int_arith_imm0<0b100, "sqadd">;
   defm UQADD_ZI : sve_int_arith_imm0<0b101, "uqadd">;
   defm SQSUB_ZI : sve_int_arith_imm0<0b110, "sqsub">;
   defm UQSUB_ZI : sve_int_arith_imm0<0b111, "uqsub">;
 
-  defm MAD_ZPmZZ : sve_int_mladdsub_vvv_pred<0b0, "mad">;
-  defm MSB_ZPmZZ : sve_int_mladdsub_vvv_pred<0b1, "msb">;
-  defm MLA_ZPmZZ : sve_int_mlas_vvv_pred<0b0, "mla">;
-  defm MLS_ZPmZZ : sve_int_mlas_vvv_pred<0b1, "mls">;
+  defm MAD_ZPmZZ : sve_int_mladdsub_vvv_pred<0b0, "mad", int_aarch64_sve_mad>;
+  defm MSB_ZPmZZ : sve_int_mladdsub_vvv_pred<0b1, "msb", int_aarch64_sve_msb>;
+  defm MLA_ZPmZZ : sve_int_mlas_vvv_pred<0b0, "mla", int_aarch64_sve_mla>;
+  defm MLS_ZPmZZ : sve_int_mlas_vvv_pred<0b1, "mls", int_aarch64_sve_mls>;
 
   // SVE predicated integer reductions.
   defm SADDV_VPZ : sve_int_reduce_0_saddv<0b000, "saddv">;
   defm UADDV_VPZ : sve_int_reduce_0_uaddv<0b001, "uaddv">;
   defm SMAXV_VPZ : sve_int_reduce_1<0b000, "smaxv">;
   defm UMAXV_VPZ : sve_int_reduce_1<0b001, "umaxv">;
   defm SMINV_VPZ : sve_int_reduce_1<0b010, "sminv">;
   defm UMINV_VPZ : sve_int_reduce_1<0b011, "uminv">;
   defm ORV_VPZ   : sve_int_reduce_2<0b000, "orv">;
   defm EORV_VPZ  : sve_int_reduce_2<0b001, "eorv">;
   defm ANDV_VPZ  : sve_int_reduce_2<0b010, "andv">;
 
   defm ORR_ZI : sve_int_log_imm<0b00, "orr", "orn">;
   defm EOR_ZI : sve_int_log_imm<0b01, "eor", "eon">;
   defm AND_ZI : sve_int_log_imm<0b10, "and", "bic">;
 
   defm SMAX_ZI   : sve_int_arith_imm1<0b00, "smax", simm8>;
   defm SMIN_ZI   : sve_int_arith_imm1<0b10, "smin", simm8>;
   defm UMAX_ZI   : sve_int_arith_imm1<0b01, "umax", imm0_255>;
   defm UMIN_ZI   : sve_int_arith_imm1<0b11, "umin", imm0_255>;
 
   defm MUL_ZI    : sve_int_arith_imm2<"mul">;
-  defm MUL_ZPmZ   : sve_int_bin_pred_arit_2<0b000, "mul", null_frag>;
-  defm SMULH_ZPmZ : sve_int_bin_pred_arit_2<0b010, "smulh", null_frag>;
-  defm UMULH_ZPmZ : sve_int_bin_pred_arit_2<0b011, "umulh", null_frag>;
-
-  defm SDIV_ZPmZ  : sve_int_bin_pred_arit_2_div<0b100, "sdiv", null_frag>;
-  defm UDIV_ZPmZ  : sve_int_bin_pred_arit_2_div<0b101, "udiv", null_frag>;
-  defm SDIVR_ZPmZ : sve_int_bin_pred_arit_2_div<0b110, "sdivr", null_frag>;
-  defm UDIVR_ZPmZ : sve_int_bin_pred_arit_2_div<0b111, "udivr", null_frag>;
+  defm MUL_ZPmZ   : sve_int_bin_pred_arit_2<0b000, "mul", int_aarch64_sve_mul>;
+  defm SMULH_ZPmZ : sve_int_bin_pred_arit_2<0b010, "smulh", int_aarch64_sve_smulh>;
+  defm UMULH_ZPmZ : sve_int_bin_pred_arit_2<0b011, "umulh", int_aarch64_sve_umulh>;
+
+  defm SDIV_ZPmZ  : sve_int_bin_pred_arit_2_div<0b100, "sdiv", int_aarch64_sve_sdiv>;
+  defm UDIV_ZPmZ  : sve_int_bin_pred_arit_2_div<0b101, "udiv", int_aarch64_sve_udiv>;
+  defm SDIVR_ZPmZ : sve_int_bin_pred_arit_2_div<0b110, "sdivr", int_aarch64_sve_sdivr>;
+  defm UDIVR_ZPmZ : sve_int_bin_pred_arit_2_div<0b111, "udivr", int_aarch64_sve_udivr>;
 
   defm SDOT_ZZZ : sve_intx_dot<0b0, "sdot", int_aarch64_sve_sdot>;
   defm UDOT_ZZZ : sve_intx_dot<0b1, "udot", int_aarch64_sve_udot>;
 
   defm SDOT_ZZZI : sve_intx_dot_by_indexed_elem<0b0, "sdot", int_aarch64_sve_sdot_lane>;
   defm UDOT_ZZZI : sve_intx_dot_by_indexed_elem<0b1, "udot", int_aarch64_sve_udot_lane>;
 
   defm SXTB_ZPmZ : sve_int_un_pred_arit_0_h<0b000, "sxtb">;
   defm UXTB_ZPmZ : sve_int_un_pred_arit_0_h<0b001, "uxtb">;
   defm SXTH_ZPmZ : sve_int_un_pred_arit_0_w<0b010, "sxth">;
   defm UXTH_ZPmZ : sve_int_un_pred_arit_0_w<0b011, "uxth">;
   defm SXTW_ZPmZ : sve_int_un_pred_arit_0_d<0b100, "sxtw">;
   defm UXTW_ZPmZ : sve_int_un_pred_arit_0_d<0b101, "uxtw">;
   defm ABS_ZPmZ  : sve_int_un_pred_arit_0<  0b110, "abs", int_aarch64_sve_abs>;
   defm NEG_ZPmZ  : sve_int_un_pred_arit_0<  0b111, "neg", int_aarch64_sve_neg>;
 
   defm CLS_ZPmZ  : sve_int_un_pred_arit_1<   0b000, "cls",  null_frag>;
   defm CLZ_ZPmZ  : sve_int_un_pred_arit_1<   0b001, "clz",  null_frag>;
   defm CNT_ZPmZ  : sve_int_un_pred_arit_1<   0b010, "cnt",  int_aarch64_sve_cnt>;
   defm CNOT_ZPmZ : sve_int_un_pred_arit_1<   0b011, "cnot", null_frag>;
   defm NOT_ZPmZ  : sve_int_un_pred_arit_1<   0b110, "not",  null_frag>;
   defm FABS_ZPmZ : sve_int_un_pred_arit_1_fp<0b100, "fabs">;
   defm FNEG_ZPmZ : sve_int_un_pred_arit_1_fp<0b101, "fneg">;
 
-  defm SMAX_ZPmZ : sve_int_bin_pred_arit_1<0b000, "smax", null_frag>;
-  defm UMAX_ZPmZ : sve_int_bin_pred_arit_1<0b001, "umax", null_frag>;
-  defm SMIN_ZPmZ : sve_int_bin_pred_arit_1<0b010, "smin", null_frag>;
-  defm UMIN_ZPmZ : sve_int_bin_pred_arit_1<0b011, "umin", null_frag>;
-  defm SABD_ZPmZ : sve_int_bin_pred_arit_1<0b100, "sabd", null_frag>;
-  defm UABD_ZPmZ : sve_int_bin_pred_arit_1<0b101, "uabd", null_frag>;
+  defm SMAX_ZPmZ : sve_int_bin_pred_arit_1<0b000, "smax", int_aarch64_sve_smax>;
+  defm UMAX_ZPmZ : sve_int_bin_pred_arit_1<0b001, "umax", int_aarch64_sve_umax>;
+  defm SMIN_ZPmZ : sve_int_bin_pred_arit_1<0b010, "smin", int_aarch64_sve_smin>;
+  defm UMIN_ZPmZ : sve_int_bin_pred_arit_1<0b011, "umin", int_aarch64_sve_umin>;
+  defm SABD_ZPmZ : sve_int_bin_pred_arit_1<0b100, "sabd", int_aarch64_sve_sabd>;
+  defm UABD_ZPmZ : sve_int_bin_pred_arit_1<0b101, "uabd", int_aarch64_sve_uabd>;
 
   defm FRECPE_ZZ  : sve_fp_2op_u_zd<0b110, "frecpe">;
   defm FRSQRTE_ZZ : sve_fp_2op_u_zd<0b111, "frsqrte">;
 
   defm FADD_ZPmI    : sve_fp_2op_i_p_zds<0b000, "fadd", sve_fpimm_half_one>;
   defm FSUB_ZPmI    : sve_fp_2op_i_p_zds<0b001, "fsub", sve_fpimm_half_one>;
   defm FMUL_ZPmI    : sve_fp_2op_i_p_zds<0b010, "fmul", sve_fpimm_half_two>;
   defm FSUBR_ZPmI   : sve_fp_2op_i_p_zds<0b011, "fsubr", sve_fpimm_half_one>;

llvm/lib/Target/AArch64/SVEInstrFormats.td

 : Pat<(vtd (op vt1:$Op1, vt2:$Op2)),
       (inst $Op1, $Op2)>;
 
 class SVE_3_Op_Pat<ValueType vtd, SDPatternOperator op, ValueType vt1,
                    ValueType vt2, ValueType vt3, Instruction inst>
 : Pat<(vtd (op vt1:$Op1, vt2:$Op2, vt3:$Op3)),
       (inst $Op1, $Op2, $Op3)>;
 
+class SVE_4_Op_Pat<ValueType vtd, SDPatternOperator op, ValueType vt1,
+                   ValueType vt2, ValueType vt3, ValueType vt4, Instruction inst>
+: Pat<(vtd (op vt1:$Op1, vt2:$Op2, vt3:$Op3, vt4:$Op4)),
+      (inst $Op1, $Op2, $Op3, $Op4)>;
+
 def SVEDup0Undef : ComplexPattern<i64, 0, "SelectDupZeroOrUndef", []>;
 
 //===----------------------------------------------------------------------===//
 // SVE Predicate Misc Group
 //===----------------------------------------------------------------------===//
 
 class sve_int_pfalse<bits<6> opc, string asm>
 : I<(outs PPR8:$Pd), (ins),
: I<(outs zprty:$Zdn), (ins PPR3bAny:$Pg, zprty:$_Zdn, zprty:$Zm, zprty:$Za),
   let Inst{9-5}   = Za;
   let Inst{4-0}   = Zdn;
 
   let Constraints = "$Zdn = $_Zdn";
   let DestructiveInstType = Destructive;
   let ElementSize = zprty.ElementSize;
 }
 
-multiclass sve_int_mladdsub_vvv_pred<bits<1> opc, string asm> {
+multiclass sve_int_mladdsub_vvv_pred<bits<1> opc, string asm, SDPatternOperator op> {
   def _B : sve_int_mladdsub_vvv_pred<0b00, opc, asm, ZPR8>;
   def _H : sve_int_mladdsub_vvv_pred<0b01, opc, asm, ZPR16>;
   def _S : sve_int_mladdsub_vvv_pred<0b10, opc, asm, ZPR32>;
   def _D : sve_int_mladdsub_vvv_pred<0b11, opc, asm, ZPR64>;
+
+  def : SVE_4_Op_Pat<nxv16i8, op, nxv16i1, nxv16i8, nxv16i8, nxv16i8, !cast<Instruction>(NAME # _B)>;
+  def : SVE_4_Op_Pat<nxv8i16, op, nxv8i1, nxv8i16, nxv8i16, nxv8i16, !cast<Instruction>(NAME # _H)>;
+  def : SVE_4_Op_Pat<nxv4i32, op, nxv4i1, nxv4i32, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
+  def : SVE_4_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
 }
 
 class sve_int_mlas_vvv_pred<bits<2> sz8_64, bits<1> opc, string asm,
                             ZPRRegOp zprty>
 : I<(outs zprty:$Zda), (ins PPR3bAny:$Pg, zprty:$_Zda, zprty:$Zn, zprty:$Zm),
   asm, "\t$Zda, $Pg/m, $Zn, $Zm",
   "",
   []>, Sched<[]> {
: I<(outs zprty:$Zda), (ins PPR3bAny:$Pg, zprty:$_Zda, zprty:$Zn, zprty:$Zm),
   let Inst{9-5}   = Zn;
   let Inst{4-0}   = Zda;
 
   let Constraints = "$Zda = $_Zda";
   let DestructiveInstType = Destructive;
   let ElementSize = zprty.ElementSize;
 }
 
-multiclass sve_int_mlas_vvv_pred<bits<1> opc, string asm> {
+multiclass sve_int_mlas_vvv_pred<bits<1> opc, string asm, SDPatternOperator op> {
   def _B : sve_int_mlas_vvv_pred<0b00, opc, asm, ZPR8>;
   def _H : sve_int_mlas_vvv_pred<0b01, opc, asm, ZPR16>;
   def _S : sve_int_mlas_vvv_pred<0b10, opc, asm, ZPR32>;
   def _D : sve_int_mlas_vvv_pred<0b11, opc, asm, ZPR64>;
+
+  def : SVE_4_Op_Pat<nxv16i8, op, nxv16i1, nxv16i8, nxv16i8, nxv16i8, !cast<Instruction>(NAME # _B)>;
+  def : SVE_4_Op_Pat<nxv8i16, op, nxv8i1, nxv8i16, nxv8i16, nxv8i16, !cast<Instruction>(NAME # _H)>;
+  def : SVE_4_Op_Pat<nxv4i32, op, nxv4i1, nxv4i32, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
+  def : SVE_4_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
 }
 
 //===----------------------------------------------------------------------===//
 // SVE2 Integer Multiply-Add - Unpredicated Group
 //===----------------------------------------------------------------------===//
 
 class sve2_int_mla<bits<2> sz, bits<5> opc, string asm,
                    ZPRRegOp zprty1, ZPRRegOp zprty2>

llvm/test/CodeGen/AArch64/sve-int-arith-pred.ll

 ; CHECK: add z0.d, p0/m, z0.d, z1.d
 ; CHECK-NEXT: ret
   %out = call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> %pg,
                                                                <vscale x 2 x i64> %a,
                                                                <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %out
 }
 
-
-
-
 define <vscale x 16 x i8> @sub_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
 ; CHECK-LABEL: sub_i8:
 ; CHECK: sub z0.b, p0/m, z0.b, z1.b
 ; CHECK-NEXT: ret
   %out = call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> %pg,
                                                                <vscale x 16 x i8> %a,
                                                                <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %out

 ; CHECK: sub z0.d, p0/m, z0.d, z1.d
 ; CHECK-NEXT: ret
   %out = call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> %pg,
                                                                <vscale x 2 x i64> %a,
                                                                <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %out
 }
 
-
-
 define <vscale x 16 x i8> @subr_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
 ; CHECK-LABEL: subr_i8:
 ; CHECK: subr z0.b, p0/m, z0.b, z1.b
 ; CHECK-NEXT: ret
   %out = call <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1> %pg,
                                                                <vscale x 16 x i8> %a,
                                                                <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %out

 ; CHECK: subr z0.d, p0/m, z0.d, z1.d
 ; CHECK-NEXT: ret
   %out = call <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1> %pg,
                                                                <vscale x 2 x i64> %a,
                                                                <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %out
 }
 
+define <vscale x 16 x i8> @smax_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: smax_i8:
+; CHECK: smax z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.smax.nxv16i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a,
+                                                               <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @smax_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: smax_i16:
+; CHECK: smax z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.smax.nxv8i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a,
+                                                               <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @smax_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: smax_i32:
+; CHECK: smax z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.smax.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @smax_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: smax_i64:
+; CHECK: smax z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.smax.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+define <vscale x 16 x i8> @umax_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: umax_i8:
+; CHECK: umax z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.umax.nxv16i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a,
+                                                               <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @umax_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: umax_i16:
+; CHECK: umax z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.umax.nxv8i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a,
+                                                               <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @umax_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: umax_i32:
+; CHECK: umax z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.umax.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @umax_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: umax_i64:
+; CHECK: umax z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.umax.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+define <vscale x 16 x i8> @smin_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: smin_i8:
+; CHECK: smin z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.smin.nxv16i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a,
+                                                               <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @smin_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: smin_i16:
+; CHECK: smin z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.smin.nxv8i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a,
+                                                               <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @smin_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: smin_i32:
+; CHECK: smin z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.smin.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @smin_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: smin_i64:
+; CHECK: smin z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.smin.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+define <vscale x 16 x i8> @umin_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: umin_i8:
+; CHECK: umin z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.umin.nxv16i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a,
+                                                               <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @umin_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: umin_i16:
+; CHECK: umin z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.umin.nxv8i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a,
+                                                               <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @umin_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: umin_i32:
+; CHECK: umin z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.umin.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @umin_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: umin_i64:
+; CHECK: umin z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+define <vscale x 16 x i8> @sabd_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: sabd_i8:
+; CHECK: sabd z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.sabd.nxv16i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a,
+                                                               <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @sabd_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: sabd_i16:
+; CHECK: sabd z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.sabd.nxv8i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a,
+                                                               <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @sabd_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: sabd_i32:
+; CHECK: sabd z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.sabd.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @sabd_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: sabd_i64:
+; CHECK: sabd z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+define <vscale x 16 x i8> @uabd_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: uabd_i8:
+; CHECK: uabd z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.uabd.nxv16i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a,
+                                                               <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %out
+}
 
+define <vscale x 8 x i16> @uabd_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: uabd_i16:
+; CHECK: uabd z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.uabd.nxv8i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a,
+                                                               <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @uabd_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: uabd_i32:
+; CHECK: uabd z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.uabd.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @uabd_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: uabd_i64:
+; CHECK: uabd z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
 
 declare <vscale x 16 x  i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x  i8>, <vscale x 16 x  i8>)
 declare <vscale x  8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x  8 x i1>, <vscale x  8 x i16>, <vscale x  8 x i16>)
 declare <vscale x  4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x  4 x i1>, <vscale x  4 x i32>, <vscale x  4 x i32>)
 declare <vscale x  2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x  2 x i1>, <vscale x  2 x i64>, <vscale x  2 x i64>)
 
 declare <vscale x 16 x  i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x  i8>, <vscale x 16 x  i8>)
 declare <vscale x  8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x  8 x i1>, <vscale x  8 x i16>, <vscale x  8 x i16>)
 declare <vscale x  4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x  4 x i1>, <vscale x  4 x i32>, <vscale x  4 x i32>)
 declare <vscale x  2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x  2 x i1>, <vscale x  2 x i64>, <vscale x  2 x i64>)
 
 declare <vscale x 16 x  i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x  i8>, <vscale x 16 x  i8>)
 declare <vscale x  8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x  8 x i1>, <vscale x  8 x i16>, <vscale x  8 x i16>)
 declare <vscale x  4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x  4 x i1>, <vscale x  4 x i32>, <vscale x  4 x i32>)
 declare <vscale x  2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x  2 x i1>, <vscale x  2 x i64>, <vscale x  2 x i64>)
+
+declare <vscale x 16 x  i8> @llvm.aarch64.sve.smax.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x  i8>, <vscale x 16 x  i8>)
+declare <vscale x  8 x i16> @llvm.aarch64.sve.smax.nxv8i16(<vscale x  8 x i1>, <vscale x  8 x i16>, <vscale x  8 x i16>)
+declare <vscale x  4 x i32> @llvm.aarch64.sve.smax.nxv4i32(<vscale x  4 x i1>, <vscale x  4 x i32>, <vscale x  4 x i32>)
+declare <vscale x  2 x i64> @llvm.aarch64.sve.smax.nxv2i64(<vscale x  2 x i1>, <vscale x  2 x i64>, <vscale x  2 x i64>)
+
+declare <vscale x 16 x  i8> @llvm.aarch64.sve.umax.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x  i8>, <vscale x 16 x  i8>)
+declare <vscale x  8 x i16> @llvm.aarch64.sve.umax.nxv8i16(<vscale x  8 x i1>, <vscale x  8 x i16>, <vscale x  8 x i16>)
+declare <vscale x  4 x i32> @llvm.aarch64.sve.umax.nxv4i32(<vscale x  4 x i1>, <vscale x  4 x i32>, <vscale x  4 x i32>)
+declare <vscale x  2 x i64> @llvm.aarch64.sve.umax.nxv2i64(<vscale x  2 x i1>, <vscale x  2 x i64>, <vscale x  2 x i64>)
+
+declare <vscale x 16 x  i8> @llvm.aarch64.sve.smin.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x  i8>, <vscale x 16 x  i8>)
+declare <vscale x  8 x i16> @llvm.aarch64.sve.smin.nxv8i16(<vscale x  8 x i1>, <vscale x  8 x i16>, <vscale x  8 x i16>)
+declare <vscale x  4 x i32> @llvm.aarch64.sve.smin.nxv4i32(<vscale x  4 x i1>, <vscale x  4 x i32>, <vscale x  4 x i32>)
+declare <vscale x  2 x i64> @llvm.aarch64.sve.smin.nxv2i64(<vscale x  2 x i1>, <vscale x  2 x i64>, <vscale x  2 x i64>)
+
+declare <vscale x 16 x  i8> @llvm.aarch64.sve.umin.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x  i8>, <vscale x 16 x  i8>)
+declare <vscale x  8 x i16> @llvm.aarch64.sve.umin.nxv8i16(<vscale x  8 x i1>, <vscale x  8 x i16>, <vscale x  8 x i16>)
+declare <vscale x  4 x i32> @llvm.aarch64.sve.umin.nxv4i32(<vscale x  4 x i1>, <vscale x  4 x i32>, <vscale x  4 x i32>)
+declare <vscale x  2 x i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x  2 x i1>, <vscale x  2 x i64>, <vscale x  2 x i64>)
+
+declare <vscale x 16 x  i8> @llvm.aarch64.sve.sabd.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x  i8>, <vscale x 16 x  i8>)
+declare <vscale x  8 x i16> @llvm.aarch64.sve.sabd.nxv8i16(<vscale x  8 x i1>, <vscale x  8 x i16>, <vscale x  8 x i16>)
+declare <vscale x  4 x i32> @llvm.aarch64.sve.sabd.nxv4i32(<vscale x  4 x i1>, <vscale x  4 x i32>, <vscale x  4 x i32>)
+declare <vscale x  2 x i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x  2 x i1>, <vscale x  2 x i64>, <vscale x  2 x i64>)
+
+declare <vscale x 16 x  i8> @llvm.aarch64.sve.uabd.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x  i8>, <vscale x 16 x  i8>)
+declare <vscale x  8 x i16> @llvm.aarch64.sve.uabd.nxv8i16(<vscale x  8 x i1>, <vscale x  8 x i16>, <vscale x  8 x i16>)
+declare <vscale x  4 x i32> @llvm.aarch64.sve.uabd.nxv4i32(<vscale x  4 x i1>, <vscale x  4 x i32>, <vscale x  4 x i32>)
+declare <vscale x  2 x i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x  2 x i1>, <vscale x  2 x i64>, <vscale x  2 x i64>)

llvm/test/CodeGen/AArch64/sve-int-div-pred.ll

+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+
+define <vscale x 4 x i32> @sdiv_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: sdiv_i32:
+; CHECK: sdiv z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.sdiv.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @sdiv_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: sdiv_i64:
+; CHECK: sdiv z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.sdiv.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+define <vscale x 4 x i32> @udiv_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: udiv_i32:
+; CHECK: udiv z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.udiv.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @udiv_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: udiv_i64:
+; CHECK: udiv z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.udiv.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+define <vscale x 4 x i32> @sdivr_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: sdivr_i32:
+; CHECK: sdivr z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.sdivr.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @sdivr_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: sdivr_i64:
+; CHECK: sdivr z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.sdivr.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+define <vscale x 4 x i32> @udivr_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: udivr_i32:
+; CHECK: udivr z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.udivr.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @udivr_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: udivr_i64:
+; CHECK: udivr z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.udivr.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+declare <vscale x  4 x i32> @llvm.aarch64.sve.sdiv.nxv4i32(<vscale x  4 x i1>, <vscale x  4 x i32>, <vscale x  4 x i32>)
+declare <vscale x  2 x i64> @llvm.aarch64.sve.sdiv.nxv2i64(<vscale x  2 x i1>, <vscale x  2 x i64>, <vscale x  2 x i64>)
+declare <vscale x  4 x i32> @llvm.aarch64.sve.udiv.nxv4i32(<vscale x  4 x i1>, <vscale x  4 x i32>, <vscale x  4 x i32>)
+declare <vscale x  2 x i64> @llvm.aarch64.sve.udiv.nxv2i64(<vscale x  2 x i1>, <vscale x  2 x i64>, <vscale x  2 x i64>)
+declare <vscale x  4 x i32> @llvm.aarch64.sve.sdivr.nxv4i32(<vscale x  4 x i1>, <vscale x  4 x i32>, <vscale x  4 x i32>)
+declare <vscale x  2 x i64> @llvm.aarch64.sve.sdivr.nxv2i64(<vscale x  2 x i1>, <vscale x  2 x i64>, <vscale x  2 x i64>)
+declare <vscale x  4 x i32> @llvm.aarch64.sve.udivr.nxv4i32(<vscale x  4 x i1>, <vscale x  4 x i32>, <vscale x  4 x i32>)
+declare <vscale x  2 x i64> @llvm.aarch64.sve.udivr.nxv2i64(<vscale x  2 x i1>, <vscale x  2 x i64>, <vscale x  2 x i64>)
+

llvm/test/CodeGen/AArch64/sve-int-log-pred.ll

+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+
+define <vscale x 16 x i8> @and_pred_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: and_pred_i8:
+; CHECK: and z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv2i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a,
+                                                               <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @and_pred_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: and_pred_i16:
+; CHECK: and z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv2i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a,
+                                                               <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %out
+}
+
+
+define <vscale x 4 x i32> @and_pred_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: and_pred_i32:
+; CHECK: and z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv2i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @and_pred_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: and_pred_i64:
+; CHECK: and z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+
+define <vscale x 16 x i8> @or_pred_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: or_pred_i8:
+; CHECK: orr z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.or.nxv2i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a,
+                                                               <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @or_pred_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: or_pred_i16:
+; CHECK: orr z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.or.nxv2i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a,
+                                                               <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %out
+}
+
+
+define <vscale x 4 x i32> @or_pred_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: or_pred_i32:
+; CHECK: orr z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.or.nxv2i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @or_pred_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: or_pred_i64:
+; CHECK: orr z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.or.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+
+define <vscale x 16 x i8> @xor_pred_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: xor_pred_i8:
+; CHECK: eor z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.xor.nxv2i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a,
+                                                               <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @xor_pred_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: xor_pred_i16:
+; CHECK: eor z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.xor.nxv2i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a,
+                                                               <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %out
+}
+
+
+define <vscale x 4 x i32> @xor_pred_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: xor_pred_i32:
+; CHECK: eor z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.xor.nxv2i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @xor_pred_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: xor_pred_i64:
+; CHECK: eor z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.xor.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv2i8(<vscale x 16 x i1>,<vscale x 16 x i8>,<vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv2i16(<vscale x 8 x i1>,<vscale x 8 x i16>,<vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv2i32(<vscale x 4 x i1>,<vscale x 4 x i32>,<vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1>,<vscale x 2 x i64>,<vscale x 2 x i64>)
+declare <vscale x 16 x i8> @llvm.aarch64.sve.or.nxv2i8(<vscale x 16 x i1>,<vscale x 16 x i8>,<vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.or.nxv2i16(<vscale x 8 x i1>,<vscale x 8 x i16>,<vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.or.nxv2i32(<vscale x 4 x i1>,<vscale x 4 x i32>,<vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.or.nxv2i64(<vscale x 2 x i1>,<vscale x 2 x i64>,<vscale x 2 x i64>)
+declare <vscale x 16 x i8> @llvm.aarch64.sve.xor.nxv2i8(<vscale x 16 x i1>,<vscale x 16 x i8>,<vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.xor.nxv2i16(<vscale x 8 x i1>,<vscale x 8 x i16>,<vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.xor.nxv2i32(<vscale x 4 x i1>,<vscale x 4 x i32>,<vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.xor.nxv2i64(<vscale x 2 x i1>,<vscale x 2 x i64>,<vscale x 2 x i64>)

llvm/test/CodeGen/AArch64/sve-int-mad-pred.ll

+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+
+define <vscale x 16 x i8> @mad_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
+; CHECK-LABEL: mad_i8:
+; CHECK: mad z0.b, p0/m, z1.b, z2.b 
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.mad.nxv16i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a,
+                                                               <vscale x 16 x i8> %b,
+                                                               <vscale x 16 x i8> %c)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @mad_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) {
+; CHECK-LABEL: mad_i16:
+; CHECK: mad z0.h, p0/m, z1.h, z2.h 
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.mad.nxv8i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a,
+                                                               <vscale x 8 x i16> %b,
+                                                               <vscale x 8 x i16> %c)
+  ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @mad_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) {
+; CHECK-LABEL: mad_i32:
+; CHECK: mad z0.s, p0/m, z1.s, z2.s 
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.mad.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b,
+                                                               <vscale x 4 x i32> %c)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @mad_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) {
+; CHECK-LABEL: mad_i64:
+; CHECK: mad z0.d, p0/m, z1.d, z2.d 
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.mad.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b,
+                                                               <vscale x 2 x i64> %c)
+  ret <vscale x 2 x i64> %out
+}
+
+define <vscale x 16 x i8> @msb_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
+; CHECK-LABEL: msb_i8:
+; CHECK: msb z0.b, p0/m, z1.b, z2.b 
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.msb.nxv16i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a,
+                                                               <vscale x 16 x i8> %b,
+                                                               <vscale x 16 x i8> %c)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @msb_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) {
+; CHECK-LABEL: msb_i16:
+; CHECK: msb z0.h, p0/m, z1.h, z2.h 
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.msb.nxv8i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a,
+                                                               <vscale x 8 x i16> %b,
+                                                               <vscale x 8 x i16> %c)
+  ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @msb_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) {
+; CHECK-LABEL: msb_i32:
+; CHECK: msb z0.s, p0/m, z1.s, z2.s 
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.msb.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b,
+                                                               <vscale x 4 x i32> %c)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @msb_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) {
+; CHECK-LABEL: msb_i64:
+; CHECK: msb z0.d, p0/m, z1.d, z2.d 
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.msb.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b,
+                                                               <vscale x 2 x i64> %c)
+  ret <vscale x 2 x i64> %out
+}
+
+
+define <vscale x 16 x i8> @mla_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
+; CHECK-LABEL: mla_i8:
+; CHECK: mla z0.b, p0/m, z1.b, z2.b 
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a,
+                                                               <vscale x 16 x i8> %b,
+                                                               <vscale x 16 x i8> %c)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @mla_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) {
+; CHECK-LABEL: mla_i16:
+; CHECK: mla z0.h, p0/m, z1.h, z2.h 
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a,
+                                                               <vscale x 8 x i16> %b,
+                                                               <vscale x 8 x i16> %c)
+  ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @mla_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) {
+; CHECK-LABEL: mla_i32:
+; CHECK: mla z0.s, p0/m, z1.s, z2.s 
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b,
+                                                               <vscale x 4 x i32> %c)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @mla_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) {
+; CHECK-LABEL: mla_i64:
+; CHECK: mla z0.d, p0/m, z1.d, z2.d 
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b,
+                                                               <vscale x 2 x i64> %c)
+  ret <vscale x 2 x i64> %out
+}
+
+
+define <vscale x 16 x i8> @mls_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
+; CHECK-LABEL: mls_i8:
+; CHECK: mls z0.b, p0/m, z1.b, z2.b 
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a,
+                                                               <vscale x 16 x i8> %b,
+                                                               <vscale x 16 x i8> %c)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @mls_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) {
+; CHECK-LABEL: mls_i16:
+; CHECK: mls z0.h, p0/m, z1.h, z2.h 
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a,
+                                                               <vscale x 8 x i16> %b,
+                                                               <vscale x 8 x i16> %c)
+  ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @mls_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) {
+; CHECK-LABEL: mls_i32:
+; CHECK: mls z0.s, p0/m, z1.s, z2.s 
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b,
+                                                               <vscale x 4 x i32> %c)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @mls_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) {
+; CHECK-LABEL: mls_i64:
+; CHECK: mls z0.d, p0/m, z1.d, z2.d 
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b,
+                                                               <vscale x 2 x i64> %c)
+  ret <vscale x 2 x i64> %out
+}
+
+declare <vscale x 16 x  i8> @llvm.aarch64.sve.mad.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x  i8>,<vscale x 16 x  i8>,<vscale x 16 x  i8>)
+declare <vscale x 8 x  i16> @llvm.aarch64.sve.mad.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x  i16>,<vscale x 8 x  i16>,<vscale x 8 x  i16>)
+declare <vscale x 4 x  i32> @llvm.aarch64.sve.mad.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x  i32>,<vscale x 4 x  i32>,<vscale x 4 x  i32>)
+declare <vscale x 2 x  i64> @llvm.aarch64.sve.mad.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x  i64>,<vscale x 2 x  i64>,<vscale x 2 x  i64>)
+
+declare <vscale x 16 x  i8> @llvm.aarch64.sve.msb.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x  i8>,<vscale x 16 x  i8>,<vscale x 16 x  i8>)
+declare <vscale x 8 x  i16> @llvm.aarch64.sve.msb.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x  i16>,<vscale x 8 x  i16>,<vscale x 8 x  i16>)
+declare <vscale x 4 x  i32> @llvm.aarch64.sve.msb.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x  i32>,<vscale x 4 x  i32>,<vscale x 4 x  i32>)
+declare <vscale x 2 x  i64> @llvm.aarch64.sve.msb.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x  i64>,<vscale x 2 x  i64>,<vscale x 2 x  i64>)
+
+declare <vscale x 16 x  i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x  i8>,<vscale x 16 x  i8>,<vscale x 16 x  i8>)
+declare <vscale x 8 x  i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x  i16>,<vscale x 8 x  i16>,<vscale x 8 x  i16>)
+declare <vscale x 4 x  i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x  i32>,<vscale x 4 x  i32>,<vscale x 4 x  i32>)
+declare <vscale x 2 x  i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x  i64>,<vscale x 2 x  i64>,<vscale x 2 x  i64>)
+
+declare <vscale x 16 x  i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x  i8>,<vscale x 16 x  i8>,<vscale x 16 x  i8>)
+declare <vscale x 8 x  i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x  i16>,<vscale x 8 x  i16>,<vscale x 8 x  i16>)
+declare <vscale x 4 x  i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x  i32>,<vscale x 4 x  i32>,<vscale x 4 x  i32>)
+declare <vscale x 2 x  i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x  i64>,<vscale x 2 x  i64>,<vscale x 2 x  i64>)

llvm/test/CodeGen/AArch64/sve-int-mul-pred.ll

+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+
+define <vscale x 16 x i8> @mul_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: mul_i8:
+; CHECK: mul z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a,
+                                                               <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @mul_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: mul_i16:
+; CHECK: mul z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a,
+                                                               <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @mul_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: mul_i32:
+; CHECK: mul z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @mul_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: mul_i64:
+; CHECK: mul z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+define <vscale x 16 x i8> @smulh_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: smulh_i8:
+; CHECK: smulh z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.smulh.nxv16i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a,
+                                                               <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @smulh_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: smulh_i16:
+; CHECK: smulh z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.smulh.nxv8i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a,
+                                                               <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @smulh_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: smulh_i32:
+; CHECK: smulh z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.smulh.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @smulh_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: smulh_i64:
+; CHECK: smulh z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.smulh.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+define <vscale x 16 x i8> @umulh_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: umulh_i8:
+; CHECK: umulh z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.umulh.nxv16i8(<vscale x 16 x i1> %pg,
+                                                               <vscale x 16 x i8> %a,
+                                                               <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @umulh_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: umulh_i16:
+; CHECK: umulh z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.umulh.nxv8i16(<vscale x 8 x i1> %pg,
+                                                               <vscale x 8 x i16> %a,
+                                                               <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @umulh_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: umulh_i32:
+; CHECK: umulh z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.umulh.nxv4i32(<vscale x 4 x i1> %pg,
+                                                               <vscale x 4 x i32> %a,
+                                                               <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @umulh_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: umulh_i64:
+; CHECK: umulh z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.umulh.nxv2i64(<vscale x 2 x i1> %pg,
+                                                               <vscale x 2 x i64> %a,
+                                                               <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %out
+}
+
+declare <vscale x 16 x  i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x  i8>, <vscale x 16 x  i8>)
+declare <vscale x  8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x  8 x i1>, <vscale x  8 x i16>, <vscale x  8 x i16>)
+declare <vscale x  4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x  4 x i1>, <vscale x  4 x i32>, <vscale x  4 x i32>)
+declare <vscale x  2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x  2 x i1>, <vscale x  2 x i64>, <vscale x  2 x i64>)
+declare <vscale x 16 x  i8> @llvm.aarch64.sve.smulh.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x  i8>, <vscale x 16 x  i8>)
+declare <vscale x  8 x i16> @llvm.aarch64.sve.smulh.nxv8i16(<vscale x  8 x i1>, <vscale x  8 x i16>, <vscale x  8 x i16>)
+declare <vscale x  4 x i32> @llvm.aarch64.sve.smulh.nxv4i32(<vscale x  4 x i1>, <vscale x  4 x i32>, <vscale x  4 x i32>)
+declare <vscale x  2 x i64> @llvm.aarch64.sve.smulh.nxv2i64(<vscale x  2 x i1>, <vscale x  2 x i64>, <vscale x  2 x i64>)
+declare <vscale x 16 x  i8> @llvm.aarch64.sve.umulh.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x  i8>, <vscale x 16 x  i8>)
+declare <vscale x  8 x i16> @llvm.aarch64.sve.umulh.nxv8i16(<vscale x  8 x i1>, <vscale x  8 x i16>, <vscale x  8 x i16>)
+declare <vscale x  4 x i32> @llvm.aarch64.sve.umulh.nxv4i32(<vscale x  4 x i1>, <vscale x  4 x i32>, <vscale x  4 x i32>)
+declare <vscale x  2 x i64> @llvm.aarch64.sve.umulh.nxv2i64(<vscale x  2 x i1>, <vscale x  2 x i64>, <vscale x  2 x i64>)