[AArch64][SVE] Add patterns for some integer vector instructions

Add pattern matching for SVE vector instructions:

-- add, sub, and, or, xor instructions
-- sqadd, uqadd, sqsub, uqsub target-independent intrinsics
-- bic intrinsics
-- predicated add, sub, subr intrinsics

Patch Review: https://reviews.llvm.org/D69128
Patch authored by: dancgr (Danilo Carvalho Grael)

llvm/include/llvm/IR/IntrinsicsAArch64.td

@@ -815,10 +815,23 @@ let TargetPrefix = "aarch64" in {  // All intrinsics start with "llvm.aarch64.".
 
 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]>;
+
+
 //
 // 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_abs : AdvSIMD_Merged1VectorArg_Intrinsic;
 def int_aarch64_sve_neg : AdvSIMD_Merged1VectorArg_Intrinsic;
 

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

@@ -183,6 +183,13 @@ AArch64TargetLowering::AArch64TargetLowering(const TargetMachine &TM,
     addRegisterClass(MVT::nxv4f32, &AArch64::ZPRRegClass);
     addRegisterClass(MVT::nxv1f64, &AArch64::ZPRRegClass);
     addRegisterClass(MVT::nxv2f64, &AArch64::ZPRRegClass);
+
+    for (auto VT : { MVT::nxv16i8, MVT::nxv8i16, MVT::nxv4i32, MVT::nxv2i64 }) {
+      setOperationAction(ISD::SADDSAT, VT, Legal);
+      setOperationAction(ISD::UADDSAT, VT, Legal);
+      setOperationAction(ISD::SSUBSAT, VT, Legal);
+      setOperationAction(ISD::USUBSAT, VT, Legal);
+    }
   }
 
   // Compute derived properties from the register classes

llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td

@@ -18,26 +18,26 @@ let Predicates = [HasSVE] in {
   def SETFFR     : sve_int_setffr<"setffr">;
   def WRFFR      : sve_int_wrffr<"wrffr">;
 
-  defm ADD_ZZZ   : sve_int_bin_cons_arit_0<0b000, "add">;
+  defm ADD_ZZZ   : sve_int_bin_cons_arit_0<0b000, "add", add>;
-  defm SUB_ZZZ   : sve_int_bin_cons_arit_0<0b001, "sub">;
+  defm SUB_ZZZ   : sve_int_bin_cons_arit_0<0b001, "sub", sub>;
-  defm SQADD_ZZZ : sve_int_bin_cons_arit_0<0b100, "sqadd">;
+  defm SQADD_ZZZ : sve_int_bin_cons_arit_0<0b100, "sqadd", saddsat>;
-  defm UQADD_ZZZ : sve_int_bin_cons_arit_0<0b101, "uqadd">;
+  defm UQADD_ZZZ : sve_int_bin_cons_arit_0<0b101, "uqadd", uaddsat>;
-  defm SQSUB_ZZZ : sve_int_bin_cons_arit_0<0b110, "sqsub">;
+  defm SQSUB_ZZZ : sve_int_bin_cons_arit_0<0b110, "sqsub", ssubsat>;
-  defm UQSUB_ZZZ : sve_int_bin_cons_arit_0<0b111, "uqsub">;
+  defm UQSUB_ZZZ : sve_int_bin_cons_arit_0<0b111, "uqsub", usubsat>;
 
-  defm AND_ZZZ : sve_int_bin_cons_log<0b00, "and">;
+  defm AND_ZZZ : sve_int_bin_cons_log<0b00, "and", and>;
-  defm ORR_ZZZ : sve_int_bin_cons_log<0b01, "orr">;
+  defm ORR_ZZZ : sve_int_bin_cons_log<0b01, "orr", or>;
-  defm EOR_ZZZ : sve_int_bin_cons_log<0b10, "eor">;
+  defm EOR_ZZZ : sve_int_bin_cons_log<0b10, "eor", xor>;
-  defm BIC_ZZZ : sve_int_bin_cons_log<0b11, "bic">;
+  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">;
+  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">;
+  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">;
+  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">;
+  defm ORR_ZPmZ : sve_int_bin_pred_log<0b000, "orr", null_frag>;
-  defm EOR_ZPmZ : sve_int_bin_pred_log<0b001, "eor">;
+  defm EOR_ZPmZ : sve_int_bin_pred_log<0b001, "eor", null_frag>;
-  defm AND_ZPmZ : sve_int_bin_pred_log<0b010, "and">;
+  defm AND_ZPmZ : sve_int_bin_pred_log<0b010, "and", null_frag>;
-  defm BIC_ZPmZ : sve_int_bin_pred_log<0b011, "bic">;
+  defm BIC_ZPmZ : sve_int_bin_pred_log<0b011, "bic", null_frag>;
 
   defm ADD_ZI   : sve_int_arith_imm0<0b000, "add">;
   defm SUB_ZI   : sve_int_arith_imm0<0b001, "sub">;
@@ -73,14 +73,14 @@ let Predicates = [HasSVE] in {
   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">;
+  defm MUL_ZPmZ   : sve_int_bin_pred_arit_2<0b000, "mul", null_frag>;
-  defm SMULH_ZPmZ : sve_int_bin_pred_arit_2<0b010, "smulh">;
+  defm SMULH_ZPmZ : sve_int_bin_pred_arit_2<0b010, "smulh", null_frag>;
-  defm UMULH_ZPmZ : sve_int_bin_pred_arit_2<0b011, "umulh">;
+  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">;
+  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">;
+  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">;
+  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">;
+  defm UDIVR_ZPmZ : sve_int_bin_pred_arit_2_div<0b111, "udivr", null_frag>;
 
   defm SDOT_ZZZ : sve_intx_dot<0b0, "sdot", int_aarch64_sve_sdot>;
   defm UDOT_ZZZ : sve_intx_dot<0b1, "udot", int_aarch64_sve_udot>;
@@ -105,12 +105,12 @@ let Predicates = [HasSVE] in {
   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">;
+  defm SMAX_ZPmZ : sve_int_bin_pred_arit_1<0b000, "smax", null_frag>;
-  defm UMAX_ZPmZ : sve_int_bin_pred_arit_1<0b001, "umax">;
+  defm UMAX_ZPmZ : sve_int_bin_pred_arit_1<0b001, "umax", null_frag>;
-  defm SMIN_ZPmZ : sve_int_bin_pred_arit_1<0b010, "smin">;
+  defm SMIN_ZPmZ : sve_int_bin_pred_arit_1<0b010, "smin", null_frag>;
-  defm UMIN_ZPmZ : sve_int_bin_pred_arit_1<0b011, "umin">;
+  defm UMIN_ZPmZ : sve_int_bin_pred_arit_1<0b011, "umin", null_frag>;
-  defm SABD_ZPmZ : sve_int_bin_pred_arit_1<0b100, "sabd">;
+  defm SABD_ZPmZ : sve_int_bin_pred_arit_1<0b100, "sabd", null_frag>;
-  defm UABD_ZPmZ : sve_int_bin_pred_arit_1<0b101, "uabd">;
+  defm UABD_ZPmZ : sve_int_bin_pred_arit_1<0b101, "uabd", null_frag>;
 
   defm FRECPE_ZZ  : sve_fp_2op_u_zd<0b110, "frecpe">;
   defm FRSQRTE_ZZ : sve_fp_2op_u_zd<0b111, "frsqrte">;

llvm/lib/Target/AArch64/SVEInstrFormats.td

@@ -288,6 +288,11 @@ class SVE_1_Op_Pat<ValueType vtd, SDPatternOperator op, ValueType vt1,
 : Pat<(vtd (op vt1:$Op1)),
       (inst $Op1)>;
 
+class SVE_2_Op_Pat<ValueType vtd, SDPatternOperator op, ValueType vt1,
+                   ValueType vt2, Instruction inst>
+: 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)),
@@ -1122,11 +1127,16 @@ class sve_int_bin_cons_arit_0<bits<2> sz8_64, bits<3> opc, string asm,
   let Inst{4-0}   = Zd;
 }
 
-multiclass sve_int_bin_cons_arit_0<bits<3> opc, string asm> {
+multiclass sve_int_bin_cons_arit_0<bits<3> opc, string asm, SDPatternOperator op> {
   def _B : sve_int_bin_cons_arit_0<0b00, opc, asm, ZPR8>;
   def _H : sve_int_bin_cons_arit_0<0b01, opc, asm, ZPR16>;
   def _S : sve_int_bin_cons_arit_0<0b10, opc, asm, ZPR32>;
   def _D : sve_int_bin_cons_arit_0<0b11, opc, asm, ZPR64>;
+
+  def : SVE_2_Op_Pat<nxv16i8, op, nxv16i8, nxv16i8, !cast<Instruction>(NAME # _B)>;
+  def : SVE_2_Op_Pat<nxv8i16, op, nxv8i16, nxv8i16, !cast<Instruction>(NAME # _H)>;
+  def : SVE_2_Op_Pat<nxv4i32, op, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
+  def : SVE_2_Op_Pat<nxv2i64, op, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
 }
 
 //===----------------------------------------------------------------------===//
@@ -1801,38 +1811,61 @@ class sve_int_bin_pred_arit_log<bits<2> sz8_64, bits<2> fmt, bits<3> opc,
   let ElementSize = zprty.ElementSize;
 }
 
-multiclass sve_int_bin_pred_log<bits<3> opc, string asm> {
+multiclass sve_int_bin_pred_log<bits<3> opc, string asm, SDPatternOperator op> {
   def _B : sve_int_bin_pred_arit_log<0b00, 0b11, opc, asm, ZPR8>;
   def _H : sve_int_bin_pred_arit_log<0b01, 0b11, opc, asm, ZPR16>;
   def _S : sve_int_bin_pred_arit_log<0b10, 0b11, opc, asm, ZPR32>;
   def _D : sve_int_bin_pred_arit_log<0b11, 0b11, opc, asm, ZPR64>;
+
+  def : SVE_3_Op_Pat<nxv16i8, op, nxv16i1, nxv16i8, nxv16i8, !cast<Instruction>(NAME # _B)>;
+  def : SVE_3_Op_Pat<nxv8i16, op, nxv8i1, nxv8i16, nxv8i16, !cast<Instruction>(NAME # _H)>;
+  def : SVE_3_Op_Pat<nxv4i32, op, nxv4i1, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
+  def : SVE_3_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
 }
 
-multiclass sve_int_bin_pred_arit_0<bits<3> opc, string asm> {
+multiclass sve_int_bin_pred_arit_0<bits<3> opc, string asm, SDPatternOperator op> {
   def _B : sve_int_bin_pred_arit_log<0b00, 0b00, opc, asm, ZPR8>;
   def _H : sve_int_bin_pred_arit_log<0b01, 0b00, opc, asm, ZPR16>;
   def _S : sve_int_bin_pred_arit_log<0b10, 0b00, opc, asm, ZPR32>;
   def _D : sve_int_bin_pred_arit_log<0b11, 0b00, opc, asm, ZPR64>;
+
+  def : SVE_3_Op_Pat<nxv16i8, op, nxv16i1, nxv16i8, nxv16i8, !cast<Instruction>(NAME # _B)>;
+  def : SVE_3_Op_Pat<nxv8i16, op, nxv8i1, nxv8i16, nxv8i16, !cast<Instruction>(NAME # _H)>;
+  def : SVE_3_Op_Pat<nxv4i32, op, nxv4i1, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
+  def : SVE_3_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
 }
 
-multiclass sve_int_bin_pred_arit_1<bits<3> opc, string asm> {
+multiclass sve_int_bin_pred_arit_1<bits<3> opc, string asm, SDPatternOperator op> {
   def _B : sve_int_bin_pred_arit_log<0b00, 0b01, opc, asm, ZPR8>;
   def _H : sve_int_bin_pred_arit_log<0b01, 0b01, opc, asm, ZPR16>;
   def _S : sve_int_bin_pred_arit_log<0b10, 0b01, opc, asm, ZPR32>;
   def _D : sve_int_bin_pred_arit_log<0b11, 0b01, opc, asm, ZPR64>;
+
+  def : SVE_3_Op_Pat<nxv16i8, op, nxv16i1, nxv16i8, nxv16i8, !cast<Instruction>(NAME # _B)>;
+  def : SVE_3_Op_Pat<nxv8i16, op, nxv8i1, nxv8i16, nxv8i16, !cast<Instruction>(NAME # _H)>;
+  def : SVE_3_Op_Pat<nxv4i32, op, nxv4i1, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
+  def : SVE_3_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
 }
 
-multiclass sve_int_bin_pred_arit_2<bits<3> opc, string asm> {
+multiclass sve_int_bin_pred_arit_2<bits<3> opc, string asm, SDPatternOperator op> {
   def _B : sve_int_bin_pred_arit_log<0b00, 0b10, opc, asm, ZPR8>;
   def _H : sve_int_bin_pred_arit_log<0b01, 0b10, opc, asm, ZPR16>;
   def _S : sve_int_bin_pred_arit_log<0b10, 0b10, opc, asm, ZPR32>;
   def _D : sve_int_bin_pred_arit_log<0b11, 0b10, opc, asm, ZPR64>;
+
+  def : SVE_3_Op_Pat<nxv16i8, op, nxv16i1, nxv16i8, nxv16i8, !cast<Instruction>(NAME # _B)>;
+  def : SVE_3_Op_Pat<nxv8i16, op, nxv8i1, nxv8i16, nxv8i16, !cast<Instruction>(NAME # _H)>;
+  def : SVE_3_Op_Pat<nxv4i32, op, nxv4i1, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
+  def : SVE_3_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
 }
 
 // Special case for divides which are not defined for 8b/16b elements.
-multiclass sve_int_bin_pred_arit_2_div<bits<3> opc, string asm> {
+multiclass sve_int_bin_pred_arit_2_div<bits<3> opc, string asm, SDPatternOperator op> {
   def _S : sve_int_bin_pred_arit_log<0b10, 0b10, opc, asm, ZPR32>;
   def _D : sve_int_bin_pred_arit_log<0b11, 0b10, opc, asm, ZPR64>;
+
+  def : SVE_3_Op_Pat<nxv4i32, op, nxv4i1, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
+  def : SVE_3_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
 }
 
 //===----------------------------------------------------------------------===//
@@ -3086,9 +3119,14 @@ class sve_int_bin_cons_log<bits<2> opc, string asm>
   let Inst{4-0}   = Zd;
 }
 
-multiclass sve_int_bin_cons_log<bits<2> opc, string asm> {
+multiclass sve_int_bin_cons_log<bits<2> opc, string asm, SDPatternOperator op> {
   def NAME : sve_int_bin_cons_log<opc, asm>;
 
+  def : SVE_2_Op_Pat<nxv16i8, op, nxv16i8, nxv16i8, !cast<Instruction>(NAME)>;
+  def : SVE_2_Op_Pat<nxv8i16, op, nxv8i16, nxv8i16, !cast<Instruction>(NAME)>;
+  def : SVE_2_Op_Pat<nxv4i32, op, nxv4i32, nxv4i32, !cast<Instruction>(NAME)>;
+  def : SVE_2_Op_Pat<nxv2i64, op, nxv2i64, nxv2i64, !cast<Instruction>(NAME)>;
+
   def : InstAlias<asm # "\t$Zd, $Zn, $Zm",
                   (!cast<Instruction>(NAME) ZPR8:$Zd,  ZPR8:$Zn,  ZPR8:$Zm),  1>;
   def : InstAlias<asm # "\t$Zd, $Zn, $Zm",

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

@@ -0,0 +1,143 @@
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+
+define <vscale x 16 x i8> @add_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: add_i8:
+; CHECK: add z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.add.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> @add_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: add_i16:
+; CHECK: add z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.add.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> @add_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: add_i32:
+; CHECK: add z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.add.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> @add_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: add_i64:
+; 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
+}
+
+define <vscale x 8 x i16> @sub_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: sub_i16:
+; CHECK: sub z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.sub.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> @sub_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: sub_i32:
+; CHECK: sub z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.sub.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> @sub_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: sub_i64:
+; 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
+}
+
+define <vscale x 8 x i16> @subr_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: subr_i16:
+; CHECK: subr z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.subr.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> @subr_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: subr_i32:
+; CHECK: subr z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.subr.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> @subr_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: subr_i64:
+; 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
+}
+
+
+
+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>)

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

@@ -0,0 +1,216 @@
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+
+define <vscale x 2 x i64> @add_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: add_i64
+; CHECK: add z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = add <vscale x 2 x i64> %a, %b
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @add_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: add_i32
+; CHECK: add z0.s, z0.s, z1.s
+; CHECK-NEXT: ret
+  %res = add <vscale x 4 x i32> %a, %b
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @add_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: add_i16
+; CHECK: add z0.h, z0.h, z1.h
+; CHECK-NEXT: ret
+  %res = add <vscale x 8 x i16> %a, %b
+  ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @add_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: add_i8
+; CHECK: add z0.b, z0.b, z1.b
+; CHECK-NEXT: ret
+  %res = add <vscale x 16 x i8> %a, %b
+  ret <vscale x 16 x i8> %res
+}
+
+define <vscale x 2 x i64> @sub_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: sub_i64
+; CHECK: sub z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = sub <vscale x 2 x i64> %a, %b
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @sub_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: sub_i32
+; CHECK: sub z0.s, z0.s, z1.s
+; CHECK-NEXT: ret
+  %res = sub <vscale x 4 x i32> %a, %b
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @sub_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: sub_i16
+; CHECK: sub z0.h, z0.h, z1.h
+; CHECK-NEXT: ret
+  %res = sub <vscale x 8 x i16> %a, %b
+  ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @sub_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: sub_i8
+; CHECK: sub z0.b, z0.b, z1.b
+; CHECK-NEXT: ret
+  %res = sub <vscale x 16 x i8> %a, %b
+  ret <vscale x 16 x i8> %res
+}
+
+define <vscale x 2 x i64> @sqadd_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: sqadd_i64
+; CHECK: sqadd  z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.sadd.sat.nxv2i64(<vscale x 2 x i64>  %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @sqadd_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: sqadd_i32
+; CHECK: sqadd  z0.s, z0.s, z1.s
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.sadd.sat.nxv4i32(<vscale x 4 x i32>  %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @sqadd_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: sqadd_i16
+; CHECK: sqadd  z0.h, z0.h, z1.h
+; CHECK-NEXT: ret
+  %res = call <vscale x 8 x i16> @llvm.sadd.sat.nxv8i16(<vscale x 8 x i16>  %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @sqadd_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: sqadd_i8
+; CHECK: sqadd  z0.b, z0.b, z1.b
+; CHECK-NEXT: ret
+  %res = call <vscale x 16 x i8> @llvm.sadd.sat.nxv16i8(<vscale x 16 x i8>  %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %res
+}
+
+
+define <vscale x 2 x i64> @sqsub_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: sqsub_i64
+; CHECK: sqsub  z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.ssub.sat.nxv2i64(<vscale x 2 x i64>  %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @sqsub_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: sqsub_i32
+; CHECK: sqsub  z0.s, z0.s, z1.s
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.ssub.sat.nxv4i32(<vscale x 4 x i32>  %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @sqsub_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: sqsub_i16
+; CHECK: sqsub  z0.h, z0.h, z1.h
+; CHECK-NEXT: ret
+  %res = call <vscale x 8 x i16> @llvm.ssub.sat.nxv8i16(<vscale x 8 x i16>  %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @sqsub_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: sqsub_i8
+; CHECK: sqsub  z0.b, z0.b, z1.b
+; CHECK-NEXT: ret
+  %res = call <vscale x 16 x i8> @llvm.ssub.sat.nxv16i8(<vscale x 16 x i8>  %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %res
+}
+
+
+define <vscale x 2 x i64> @uqadd_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: uqadd_i64
+; CHECK: uqadd  z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.uadd.sat.nxv2i64(<vscale x 2 x i64>  %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @uqadd_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: uqadd_i32
+; CHECK: uqadd  z0.s, z0.s, z1.s
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.uadd.sat.nxv4i32(<vscale x 4 x i32>  %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @uqadd_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: uqadd_i16
+; CHECK: uqadd  z0.h, z0.h, z1.h
+; CHECK-NEXT: ret
+  %res = call <vscale x 8 x i16> @llvm.uadd.sat.nxv8i16(<vscale x 8 x i16>  %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @uqadd_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: uqadd_i8
+; CHECK: uqadd  z0.b, z0.b, z1.b
+; CHECK-NEXT: ret
+  %res = call <vscale x 16 x i8> @llvm.uadd.sat.nxv16i8(<vscale x 16 x i8>  %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %res
+}
+
+
+define <vscale x 2 x i64> @uqsub_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: uqsub_i64
+; CHECK: uqsub  z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.usub.sat.nxv2i64(<vscale x 2 x i64>  %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @uqsub_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: uqsub_i32
+; CHECK: uqsub  z0.s, z0.s, z1.s
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.usub.sat.nxv4i32(<vscale x 4 x i32>  %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @uqsub_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: uqsub_i16
+; CHECK: uqsub  z0.h, z0.h, z1.h
+; CHECK-NEXT: ret
+  %res = call <vscale x 8 x i16> @llvm.usub.sat.nxv8i16(<vscale x 8 x i16>  %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @uqsub_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: uqsub_i8
+; CHECK: uqsub  z0.b, z0.b, z1.b
+; CHECK-NEXT: ret
+  %res = call <vscale x 16 x i8> @llvm.usub.sat.nxv16i8(<vscale x 16 x i8>  %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %res
+}
+
+declare <vscale x 16 x i8> @llvm.sadd.sat.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.sadd.sat.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.sadd.sat.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.sadd.sat.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
+
+declare <vscale x 16 x i8> @llvm.ssub.sat.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.ssub.sat.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.ssub.sat.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.ssub.sat.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
+
+declare <vscale x 16 x i8> @llvm.uadd.sat.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.uadd.sat.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.uadd.sat.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.uadd.sat.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
+
+declare <vscale x 16 x i8> @llvm.usub.sat.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.usub.sat.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.usub.sat.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.usub.sat.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)

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

@@ -0,0 +1,138 @@
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+
+define <vscale x 2 x i64> @and_d(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: and_d
+; CHECK: and z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = and <vscale x 2 x i64> %a, %b
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @and_s(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: and_s
+; CHECK: and z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = and <vscale x 4 x i32> %a, %b
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @and_h(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: and_h
+; CHECK: and z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = and <vscale x 8 x i16> %a, %b
+  ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @and_b(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: and_b
+; CHECK: and z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = and <vscale x 16 x i8> %a, %b
+  ret <vscale x 16 x i8> %res
+}                                                                                          
+define <vscale x 2 x i64> @or_d(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: or_d
+; CHECK: orr z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = or <vscale x 2 x i64> %a, %b
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @or_s(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: or_s
+; CHECK: orr z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = or <vscale x 4 x i32> %a, %b
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @or_h(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: or_h
+; CHECK: orr z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = or <vscale x 8 x i16> %a, %b
+  ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @or_b(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: or_b
+; CHECK: orr z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = or <vscale x 16 x i8> %a, %b
+  ret <vscale x 16 x i8> %res
+}                                                                                          
+
+define <vscale x 2 x i64> @xor_d(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: xor_d
+; CHECK: eor z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = xor <vscale x 2 x i64> %a, %b
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @xor_s(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: xor_s
+; CHECK: eor z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = xor <vscale x 4 x i32> %a, %b
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @xor_h(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: xor_h
+; CHECK: eor z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = xor <vscale x 8 x i16> %a, %b
+  ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @xor_b(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: xor_b
+; CHECK: eor z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res = xor <vscale x 16 x i8> %a, %b
+  ret <vscale x 16 x i8> %res
+}
+
+define <vscale x 2 x i64> @bic_d(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: bic_d
+; CHECK: bic z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res =  call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i64> %a,
+                                                                <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @bic_s(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: bic_s
+; CHECK: bic z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res =  call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i32> %a,
+                                                                <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @bic_h(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: bic_h
+; CHECK: bic z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res =  call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i16> %a,
+                                                                <vscale x 8 x i16> %b)
+
+  ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @bic_b(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: bic_b
+; CHECK: bic z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+  %res =  call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i8> %a,
+                                                                <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %res
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)