[AArch64][SVE] Correct intrinsics and patterns for logical predicate instructions

[paulwalker-arm]

Summary

In general SVE intrinsics are considered predicated and merging
with everything else having suitable decoration.  For predicated
zeroing operations (like the predicate logical instructions) we
use the "_z" suffix.  After this change all intrinsics use their
expected names (i.e. orr instead of or and eor instead of xor).

I've removed intrinsics and patterns for condition code setting
instructions as that data is not returned as part of the intrinsic.
The expectation is to ask for a cc flag explicitly.

For example:
  a = and_z(pg, p1, p2)
  cc = ptest_<flag>(pg, a)

With the code generator expected to use "s" variants of instructions
when available.

[efriedma]

LGTM

I probably should have spotted the issue with the "s" intrinsics earlier; I wasn't really thinking about it.

llvm/include/llvm/IR/IntrinsicsAArch64.td

 
 def int_aarch64_sve_uunpkhi   : AdvSIMD_SVE_Unpack_Intrinsic;
 def int_aarch64_sve_uunpklo   : AdvSIMD_SVE_Unpack_Intrinsic;
 
 //
 // Logical operations
 //
 
-def int_aarch64_sve_cnot : AdvSIMD_Merged1VectorArg_Intrinsic;
-def int_aarch64_sve_not  : AdvSIMD_Merged1VectorArg_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_base    : AdvSIMD_2VectorArg_Intrinsic;
-def int_aarch64_sve_bic         : AdvSIMD_Pred2VectorArg_Intrinsic;
-
-def int_aarch64_sve_eor         : AdvSIMD_Pred2VectorArg_Intrinsic;
-def int_aarch64_sve_ands        : AdvSIMD_Pred2VectorArg_Intrinsic;
-def int_aarch64_sve_bics        : AdvSIMD_Pred2VectorArg_Intrinsic;
-def int_aarch64_sve_eors        : AdvSIMD_Pred2VectorArg_Intrinsic;
-def int_aarch64_sve_orr         : AdvSIMD_Pred2VectorArg_Intrinsic;
-def int_aarch64_sve_orn         : AdvSIMD_Pred2VectorArg_Intrinsic;
-def int_aarch64_sve_nor         : AdvSIMD_Pred2VectorArg_Intrinsic;
-def int_aarch64_sve_nand        : AdvSIMD_Pred2VectorArg_Intrinsic;
-def int_aarch64_sve_orrs        : AdvSIMD_Pred2VectorArg_Intrinsic;
-def int_aarch64_sve_orns        : AdvSIMD_Pred2VectorArg_Intrinsic;
-def int_aarch64_sve_nors        : AdvSIMD_Pred2VectorArg_Intrinsic;
-def int_aarch64_sve_nands       : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_and  : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_bic  : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_cnot : AdvSIMD_Merged1VectorArg_Intrinsic;
+def int_aarch64_sve_eor  : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_not  : AdvSIMD_Merged1VectorArg_Intrinsic;
+def int_aarch64_sve_orr  : AdvSIMD_Pred2VectorArg_Intrinsic;
 
+// TODO: Deprecated and will be replaced by isel patterns.
 def int_aarch64_sve_orr_imm  : AdvSIMD_1VectorArg_Imm64_Intrinsic;
 def int_aarch64_sve_eor_imm  : AdvSIMD_1VectorArg_Imm64_Intrinsic;
 def int_aarch64_sve_and_imm  : AdvSIMD_1VectorArg_Imm64_Intrinsic;
 
 //
 // Conversion
 //
 

 //
 
 def int_aarch64_sve_ptrue : AdvSIMD_SVE_PTRUE_Intrinsic;
 
 //
 // Predicate operations
 //
 
+def int_aarch64_sve_and_z   : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_bic_z   : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_eor_z   : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_nand_z  : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_nor_z   : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_orn_z   : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_orr_z   : AdvSIMD_Pred2VectorArg_Intrinsic;
 def int_aarch64_sve_pfirst  : AdvSIMD_Pred1VectorArg_Intrinsic;
 def int_aarch64_sve_pnext   : AdvSIMD_Pred1VectorArg_Intrinsic;
 def int_aarch64_sve_punpkhi : AdvSIMD_SVE_PUNPKHI_Intrinsic;
 def int_aarch64_sve_punpklo : AdvSIMD_SVE_PUNPKHI_Intrinsic;
 
 //
 // Gather loads:
 //

llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td

let Predicates = [HasSVE] in {
   defm SQADD_ZZZ : sve_int_bin_cons_arit_0<0b100, "sqadd", saddsat>;
   defm UQADD_ZZZ : sve_int_bin_cons_arit_0<0b101, "uqadd", uaddsat>;
   defm SQSUB_ZZZ : sve_int_bin_cons_arit_0<0b110, "sqsub", ssubsat>;
   defm UQSUB_ZZZ : sve_int_bin_cons_arit_0<0b111, "uqsub", usubsat>;
 
   defm AND_ZZZ : sve_int_bin_cons_log<0b00, "and", and>;
   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_base>;
+  defm BIC_ZZZ : sve_int_bin_cons_log<0b11, "bic", null_frag>;
 
   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", int_aarch64_sve_or>;
-  defm EOR_ZPmZ : sve_int_bin_pred_log<0b001, "eor", int_aarch64_sve_xor>;
+  defm ORR_ZPmZ : sve_int_bin_pred_log<0b000, "orr", int_aarch64_sve_orr>;
+  defm EOR_ZPmZ : sve_int_bin_pred_log<0b001, "eor", int_aarch64_sve_eor>;
   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>;
 
   defm ADD_ZI   : sve_int_arith_imm0<0b000, "add", int_aarch64_sve_add_imm>;
   defm SUB_ZI   : sve_int_arith_imm0<0b001, "sub", int_aarch64_sve_sub_imm>;
   defm SUBR_ZI  : sve_int_arith_imm0<0b011, "subr", int_aarch64_sve_subr_imm>;
   defm SQADD_ZI : sve_int_arith_imm0<0b100, "sqadd", int_aarch64_sve_sqadd_imm>;
   defm UQADD_ZI : sve_int_arith_imm0<0b101, "uqadd", int_aarch64_sve_uqadd_imm>;
let Predicates = [HasSVE] in {
   defm BRKB_PPmP  : sve_int_break_m<0b101, "brkb">;
   defm BRKBS_PPzP : sve_int_break_z<0b110, "brkbs">;
 
   def PTEST_PP : sve_int_ptest<0b010000, "ptest">;
   def PFALSE   : sve_int_pfalse<0b000000, "pfalse">;
   defm PFIRST  : sve_int_pfirst<0b00000, "pfirst", int_aarch64_sve_pfirst>;
   defm PNEXT   : sve_int_pnext<0b00110, "pnext", int_aarch64_sve_pnext>;
 
-  defm AND_PPzPP   : sve_int_pred_log<0b0000, "and", int_aarch64_sve_and>;
-  defm BIC_PPzPP   : sve_int_pred_log<0b0001, "bic", int_aarch64_sve_bic>;
-  defm EOR_PPzPP   : sve_int_pred_log<0b0010, "eor", int_aarch64_sve_eor>;
+  defm AND_PPzPP   : sve_int_pred_log<0b0000, "and", int_aarch64_sve_and_z>;
+  defm BIC_PPzPP   : sve_int_pred_log<0b0001, "bic", int_aarch64_sve_bic_z>;
+  defm EOR_PPzPP   : sve_int_pred_log<0b0010, "eor", int_aarch64_sve_eor_z>;
   defm SEL_PPPP    : sve_int_pred_log<0b0011, "sel", vselect>;
-  defm ANDS_PPzPP  : sve_int_pred_log<0b0100, "ands", int_aarch64_sve_ands>;
-  defm BICS_PPzPP  : sve_int_pred_log<0b0101, "bics", int_aarch64_sve_bics>;
-  defm EORS_PPzPP  : sve_int_pred_log<0b0110, "eors", int_aarch64_sve_eors>;
-  defm ORR_PPzPP   : sve_int_pred_log<0b1000, "orr", int_aarch64_sve_orr>;
-  defm ORN_PPzPP   : sve_int_pred_log<0b1001, "orn", int_aarch64_sve_orn>;
-  defm NOR_PPzPP   : sve_int_pred_log<0b1010, "nor", int_aarch64_sve_nor>;
-  defm NAND_PPzPP  : sve_int_pred_log<0b1011, "nand", int_aarch64_sve_nand>;
-  defm ORRS_PPzPP  : sve_int_pred_log<0b1100, "orrs", int_aarch64_sve_orrs>;
-  defm ORNS_PPzPP  : sve_int_pred_log<0b1101, "orns", int_aarch64_sve_orns>;
-  defm NORS_PPzPP  : sve_int_pred_log<0b1110, "nors", int_aarch64_sve_nors>;
-  defm NANDS_PPzPP : sve_int_pred_log<0b1111, "nands", int_aarch64_sve_nands>;
+  defm ANDS_PPzPP  : sve_int_pred_log<0b0100, "ands", null_frag>;
+  defm BICS_PPzPP  : sve_int_pred_log<0b0101, "bics", null_frag>;
+  defm EORS_PPzPP  : sve_int_pred_log<0b0110, "eors", null_frag>;
+  defm ORR_PPzPP   : sve_int_pred_log<0b1000, "orr", int_aarch64_sve_orr_z>;
+  defm ORN_PPzPP   : sve_int_pred_log<0b1001, "orn", int_aarch64_sve_orn_z>;
+  defm NOR_PPzPP   : sve_int_pred_log<0b1010, "nor", int_aarch64_sve_nor_z>;
+  defm NAND_PPzPP  : sve_int_pred_log<0b1011, "nand", int_aarch64_sve_nand_z>;
+  defm ORRS_PPzPP  : sve_int_pred_log<0b1100, "orrs", null_frag>;
+  defm ORNS_PPzPP  : sve_int_pred_log<0b1101, "orns", null_frag>;
+  defm NORS_PPzPP  : sve_int_pred_log<0b1110, "nors", null_frag>;
+  defm NANDS_PPzPP : sve_int_pred_log<0b1111, "nands", null_frag>;
 
   defm CLASTA_RPZ : sve_int_perm_clast_rz<0, "clasta">;
   defm CLASTB_RPZ : sve_int_perm_clast_rz<1, "clastb">;
   defm CLASTA_VPZ : sve_int_perm_clast_vz<0, "clasta">;
   defm CLASTB_VPZ : sve_int_perm_clast_vz<1, "clastb">;
   defm CLASTA_ZPZ : sve_int_perm_clast_zz<0, "clasta">;
   defm CLASTB_ZPZ : sve_int_perm_clast_zz<1, "clastb">;
 

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)
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv2i8(<vscale x 16 x i1> %pg,
   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,
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.orr.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,
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.orr.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,
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.orr.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)
+  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv2i8(<vscale x 16 x i1> %pg,
   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,
+  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.eor.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,
+  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.eor.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,
+  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.eor.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> @bic_pred_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
 ; CHECK-LABEL: bic_pred_i8:
 ; CHECK: bic z0.b, p0/m, z0.b, z1.b
 ; CHECK-NEXT: ret
   %out = call <vscale x 16 x i8> @llvm.aarch64.sve.bic.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> @bic_pred_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
 ; CHECK-LABEL: bic_pred_i16:
 ; CHECK: bic z0.h, p0/m, z0.h, z1.h
 ; CHECK-NEXT: ret
   %out = call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv2i16(<vscale x 8 x i1> %pg,
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> %pg,
                                                                <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>)
+declare <vscale x 16 x i8> @llvm.aarch64.sve.orr.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.orr.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.orr.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.orr.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.eor.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.eor.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.eor.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.eor.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.bic.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.bic.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.bic.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.bic.nxv2i64(<vscale x 2 x i1>,<vscale x 2 x i64>,<vscale x 2 x i64>)

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

 
 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.base.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.base.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.base.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.base.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.base.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
-declare <vscale x 4 x i32> @llvm.aarch64.sve.bic.base.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
-declare <vscale x 8 x i16> @llvm.aarch64.sve.bic.base.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
-declare <vscale x 16 x i8> @llvm.aarch64.sve.bic.base.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)

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

; CHECK-NEXT: ret
   %res = select <vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd
   ret <vscale x 2 x i1> %res;
 }
 
 define <vscale x 16 x i1> @and_16(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd) {
 ; CHECK-LABEL: and_16:
 ; CHECK: and p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.and.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
+  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.and.z.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
   ret <vscale x 16 x i1> %res;
 }
 
 define <vscale x 8 x i1> @and_8(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd) {
 ; CHECK-LABEL: and_8:
 ; CHECK: and p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.and.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
+  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.and.z.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
   ret <vscale x 8 x i1> %res;
 }
 
 define <vscale x 4 x i1> @and_4(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd) {
 ; CHECK-LABEL: and_4:
 ; CHECK: and p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.and.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
+  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.and.z.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
   ret <vscale x 4 x i1> %res;
 }
 
 define <vscale x 2 x i1> @and_2(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd) {
 ; CHECK-LABEL: and_2:
 ; CHECK: and p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.and.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
+  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.and.z.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
   ret <vscale x 2 x i1> %res;
 }
 
-
 define <vscale x 16 x i1> @bic_16(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd) {
 ; CHECK-LABEL: bic_16:
 ; CHECK: bic p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.bic.pred.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
+  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.bic.z.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
   ret <vscale x 16 x i1> %res;
 }
 
 define <vscale x 8 x i1> @bic_8(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd) {
 ; CHECK-LABEL: bic_8:
 ; CHECK: bic p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.bic.pred.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
+  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.bic.z.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
   ret <vscale x 8 x i1> %res;
 }
 
 define <vscale x 4 x i1> @bic_4(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd) {
 ; CHECK-LABEL: bic_4:
 ; CHECK: bic p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.bic.pred.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
+  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.bic.z.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
   ret <vscale x 4 x i1> %res;
 }
 
 define <vscale x 2 x i1> @bic_2(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd) {
 ; CHECK-LABEL: bic_2:
 ; CHECK: bic p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.bic.pred.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
+  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.bic.z.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
   ret <vscale x 2 x i1> %res;
 }
 
 define <vscale x 16 x i1> @eor_16(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd) {
 ; CHECK-LABEL: eor_16:
 ; CHECK: eor p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.eor.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
+  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.eor.z.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
   ret <vscale x 16 x i1> %res;
 }
 
 define <vscale x 8 x i1> @eor_8(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd) {
 ; CHECK-LABEL: eor_8:
 ; CHECK: eor p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.eor.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
+  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.eor.z.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
   ret <vscale x 8 x i1> %res;
 }
 
 define <vscale x 4 x i1> @eor_4(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd) {
 ; CHECK-LABEL: eor_4:
 ; CHECK: eor p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.eor.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
+  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.eor.z.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
   ret <vscale x 4 x i1> %res;
 }
 
 define <vscale x 2 x i1> @eor_2(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd) {
 ; CHECK-LABEL: eor_2:
 ; CHECK: eor p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.eor.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
-  ret <vscale x 2 x i1> %res;
-}
-
-define <vscale x 16 x i1> @ands_16(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd) {
-; CHECK-LABEL: ands_16:
-; CHECK: ands p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.ands.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
-  ret <vscale x 16 x i1> %res;
-}
-
-define <vscale x 8 x i1> @ands_8(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd) {
-; CHECK-LABEL: ands_8:
-; CHECK: ands p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.ands.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
-  ret <vscale x 8 x i1> %res;
-}
-
-define <vscale x 4 x i1> @ands_4(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd) {
-; CHECK-LABEL: ands_4:
-; CHECK: ands p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.ands.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
-  ret <vscale x 4 x i1> %res;
-}
-
-define <vscale x 2 x i1> @ands_2(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd) {
-; CHECK-LABEL: ands_2:
-; CHECK: ands p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.ands.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
-  ret <vscale x 2 x i1> %res;
-}
-
-
-define <vscale x 16 x i1> @bics_16(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd) {
-; CHECK-LABEL: bics_16:
-; CHECK: bics p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.bics.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
-  ret <vscale x 16 x i1> %res;
-}
-
-define <vscale x 8 x i1> @bics_8(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd) {
-; CHECK-LABEL: bics_8:
-; CHECK: bics p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.bics.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
-  ret <vscale x 8 x i1> %res;
-}
-
-define <vscale x 4 x i1> @bics_4(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd) {
-; CHECK-LABEL: bics_4:
-; CHECK: bics p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.bics.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
-  ret <vscale x 4 x i1> %res;
-}
-
-define <vscale x 2 x i1> @bics_2(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd) {
-; CHECK-LABEL: bics_2:
-; CHECK: bics p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.bics.nxv2i1(<vscale x 2 x i1> %Pg,
-    <vscale x 2 x i1> %Pn,
-    <vscale x 2 x i1> %Pd)
+  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.eor.z.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
   ret <vscale x 2 x i1> %res;
 }
 
-
-define <vscale x 16 x i1> @eors_16(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd) {
-; CHECK-LABEL: eors_16:
-; CHECK: eors p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.eors.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
-  ret <vscale x 16 x i1> %res;
-}
-
-define <vscale x 8 x i1> @eors_8(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd) {
-; CHECK-LABEL: eors_8:
-; CHECK: eors p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.eors.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
-  ret <vscale x 8 x i1> %res;
-}
-
-define <vscale x 4 x i1> @eors_4(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd) {
-; CHECK-LABEL: eors_4:
-; CHECK: eors p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.eors.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
-  ret <vscale x 4 x i1> %res;
-}
-
-define <vscale x 2 x i1> @eors_2(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd) {
-; CHECK-LABEL: eors_2:
-; CHECK: eors p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.eors.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
-  ret <vscale x 2 x i1> %res;
-}
-
-
 define <vscale x 16 x i1> @orr_16(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd) {
 ; CHECK-LABEL: orr_16:
 ; CHECK: orr p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.orr.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
+  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.orr.z.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
   ret <vscale x 16 x i1> %res;
 }
 
 define <vscale x 8 x i1> @orr_8(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd) {
 ; CHECK-LABEL: orr_8:
 ; CHECK: orr p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.orr.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
+  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.orr.z.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
   ret <vscale x 8 x i1> %res;
 }
 
 define <vscale x 4 x i1> @orr_4(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd) {
 ; CHECK-LABEL: orr_4:
 ; CHECK: orr p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.orr.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
+  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.orr.z.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
   ret <vscale x 4 x i1> %res;
 }
 
 define <vscale x 2 x i1> @orr_2(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd) {
 ; CHECK-LABEL: orr_2:
 ; CHECK: orr p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.orr.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
+  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.orr.z.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
   ret <vscale x 2 x i1> %res;
 }
 
-
 define <vscale x 16 x i1> @orn_16(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd) {
 ; CHECK-LABEL: orn_16:
 ; CHECK: orn p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.orn.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
+  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.orn.z.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
   ret <vscale x 16 x i1> %res;
 }
 
 define <vscale x 8 x i1> @orn_8(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd) {
 ; CHECK-LABEL: orn_8:
 ; CHECK: orn p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.orn.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
+  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.orn.z.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
   ret <vscale x 8 x i1> %res;
 }
 
 define <vscale x 4 x i1> @orn_4(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd) {
 ; CHECK-LABEL: orn_4:
 ; CHECK: orn p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.orn.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
+  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.orn.z.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
   ret <vscale x 4 x i1> %res;
 }
 
 define <vscale x 2 x i1> @orn_2(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd) {
 ; CHECK-LABEL: orn_2:
 ; CHECK: orn p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.orn.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
+  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.orn.z.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
   ret <vscale x 2 x i1> %res;
 }
 
 define <vscale x 16 x i1> @nor_16(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd) {
 ; CHECK-LABEL: nor_16:
 ; CHECK: nor p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.nor.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
+  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.nor.z.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
   ret <vscale x 16 x i1> %res;
 }
 
 define <vscale x 8 x i1> @nor_8(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd) {
 ; CHECK-LABEL: nor_8:
 ; CHECK: nor p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.nor.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
+  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.nor.z.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
   ret <vscale x 8 x i1> %res;
 }
 
 define <vscale x 4 x i1> @nor_4(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd) {
 ; CHECK-LABEL: nor_4:
 ; CHECK: nor p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.nor.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
+  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.nor.z.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
   ret <vscale x 4 x i1> %res;
 }
 
 define <vscale x 2 x i1> @nor_2(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd) {
 ; CHECK-LABEL: nor_2:
 ; CHECK: nor p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.nor.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
+  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.nor.z.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
   ret <vscale x 2 x i1> %res;
 }
 
 define <vscale x 16 x i1> @nand_16(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd) {
 ; CHECK-LABEL: nand_16:
 ; CHECK: nand p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.nand.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn,  <vscale x 16 x i1> %Pd)
+  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.nand.z.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn,  <vscale x 16 x i1> %Pd)
   ret <vscale x 16 x i1> %res;
 }
 
 define <vscale x 8 x i1> @nand_8(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd) {
 ; CHECK-LABEL: nand_8:
 ; CHECK: nand p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.nand.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
+  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.nand.z.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
   ret <vscale x 8 x i1> %res;
 }
 
 define <vscale x 4 x i1> @nand_4(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd) {
 ; CHECK-LABEL: nand_4:
 ; CHECK: nand p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.nand.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
+  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.nand.z.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
   ret <vscale x 4 x i1> %res;
 }
 
 define <vscale x 2 x i1> @nand_2(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd) {
 ; CHECK-LABEL: nand_2:
 ; CHECK: nand p0.b, p0/z, p1.b, p2.b
 ; CHECK-NEXT: ret
-  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.nand.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
-  ret <vscale x 2 x i1> %res;
-}
-
-define <vscale x 16 x i1> @orrs_16(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd) {
-; CHECK-LABEL: orrs_16:
-; CHECK: orrs p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.orrs.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
-  ret <vscale x 16 x i1> %res;
-}
-
-define <vscale x 8 x i1> @orrs_8(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd) {
-; CHECK-LABEL: orrs_8:
-; CHECK: orrs p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.orrs.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
-  ret <vscale x 8 x i1> %res;
-}
-
-define <vscale x 4 x i1> @orrs_4(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd) {
-; CHECK-LABEL: orrs_4:
-; CHECK: orrs p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.orrs.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
-  ret <vscale x 4 x i1> %res;
-}
-
-define <vscale x 2 x i1> @orrs_2(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd) {
-; CHECK-LABEL: orrs_2:
-; CHECK: orrs p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.orrs.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
-  ret <vscale x 2 x i1> %res;
-}
-
-define <vscale x 16 x i1> @orns_16(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd) {
-; CHECK-LABEL: orns_16:
-; CHECK: orns p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.orns.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
-  ret <vscale x 16 x i1> %res;
-}
-
-define <vscale x 8 x i1> @orns_8(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd) {
-; CHECK-LABEL: orns_8:
-; CHECK: orns p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.orns.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
-  ret <vscale x 8 x i1> %res;
-}
-
-define <vscale x 4 x i1> @orns_4(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd) {
-; CHECK-LABEL: orns_4:
-; CHECK: orns p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.orns.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn,  <vscale x 4 x i1> %Pd)
-  ret <vscale x 4 x i1> %res;
-}
-
-define <vscale x 2 x i1> @orns_2(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd) {
-; CHECK-LABEL: orns_2:
-; CHECK: orns p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.orns.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
-  ret <vscale x 2 x i1> %res;
-}
-
-define <vscale x 16 x i1> @nors_16(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd) {
-; CHECK-LABEL: nors_16:
-; CHECK: nors p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.nors.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
-  ret <vscale x 16 x i1> %res;
-}
-
-define <vscale x 8 x i1> @nors_8(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd) {
-; CHECK-LABEL: nors_8:
-; CHECK: nors p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.nors.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
-  ret <vscale x 8 x i1> %res;
-}
-
-define <vscale x 4 x i1> @nors_4(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd) {
-; CHECK-LABEL: nors_4:
-; CHECK: nors p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.nors.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
-  ret <vscale x 4 x i1> %res;
-}
-
-define <vscale x 2 x i1> @nors_2(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd) {
-; CHECK-LABEL: nors_2:
-; CHECK: nors p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.nors.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
-  ret <vscale x 2 x i1> %res;
-}
-
-define <vscale x 16 x i1> @nands_16(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd) {
-; CHECK-LABEL: nands_16:
-; CHECK: nands p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 16 x i1> @llvm.aarch64.sve.nands.nxv16i1(<vscale x 16 x i1> %Pg, <vscale x 16 x i1> %Pn, <vscale x 16 x i1> %Pd)
-  ret <vscale x 16 x i1> %res;
-}
-
-define <vscale x 8 x i1> @nands_8(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd) {
-; CHECK-LABEL: nands_8:
-; CHECK: nands p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 8 x i1> @llvm.aarch64.sve.nands.nxv8i1(<vscale x 8 x i1> %Pg, <vscale x 8 x i1> %Pn, <vscale x 8 x i1> %Pd)
-  ret <vscale x 8 x i1> %res;
-}
-
-define <vscale x 4 x i1> @nands_4(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd) {
-; CHECK-LABEL: nands_4:
-; CHECK: nands p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 4 x i1> @llvm.aarch64.sve.nands.nxv4i1(<vscale x 4 x i1> %Pg, <vscale x 4 x i1> %Pn, <vscale x 4 x i1> %Pd)
-  ret <vscale x 4 x i1> %res;
-}
-
-define <vscale x 2 x i1> @nands_2(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd) {
-; CHECK-LABEL: nands_2:
-; CHECK: nands p0.b, p0/z, p1.b, p2.b
-; CHECK-NEXT: ret
-  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.nands.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
+  %res = call <vscale x 2 x i1> @llvm.aarch64.sve.nand.z.nxv2i1(<vscale x 2 x i1> %Pg, <vscale x 2 x i1> %Pn, <vscale x 2 x i1> %Pd)
   ret <vscale x 2 x i1> %res;
 }
 
-declare <vscale x 16 x i1> @llvm.aarch64.sve.and.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
-declare <vscale x 8 x i1> @llvm.aarch64.sve.and.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
-declare <vscale x 4 x i1> @llvm.aarch64.sve.and.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
-declare <vscale x 2 x i1> @llvm.aarch64.sve.and.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
-declare <vscale x 16 x i1> @llvm.aarch64.sve.bic.pred.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
-declare <vscale x 8 x i1> @llvm.aarch64.sve.bic.pred.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
-declare <vscale x 4 x i1> @llvm.aarch64.sve.bic.pred.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
-declare <vscale x 2 x i1> @llvm.aarch64.sve.bic.pred.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
-declare <vscale x 16 x i1> @llvm.aarch64.sve.eor.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
-declare <vscale x 8 x i1> @llvm.aarch64.sve.eor.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
-declare <vscale x 4 x i1> @llvm.aarch64.sve.eor.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
-declare <vscale x 2 x i1> @llvm.aarch64.sve.eor.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
-declare <vscale x 16 x i1> @llvm.aarch64.sve.ands.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
-declare <vscale x 8 x i1> @llvm.aarch64.sve.ands.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
-declare <vscale x 4 x i1> @llvm.aarch64.sve.ands.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
-declare <vscale x 2 x i1> @llvm.aarch64.sve.ands.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
-declare <vscale x 16 x i1> @llvm.aarch64.sve.bics.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
-declare <vscale x 8 x i1> @llvm.aarch64.sve.bics.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
-declare <vscale x 4 x i1> @llvm.aarch64.sve.bics.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
-declare <vscale x 2 x i1> @llvm.aarch64.sve.bics.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
-declare <vscale x 16 x i1> @llvm.aarch64.sve.eors.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
-declare <vscale x 8 x i1> @llvm.aarch64.sve.eors.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
-declare <vscale x 4 x i1> @llvm.aarch64.sve.eors.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
-declare <vscale x 2 x i1> @llvm.aarch64.sve.eors.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
-declare <vscale x 16 x i1> @llvm.aarch64.sve.orr.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
-declare <vscale x 8 x i1> @llvm.aarch64.sve.orr.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
-declare <vscale x 4 x i1> @llvm.aarch64.sve.orr.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
-declare <vscale x 2 x i1> @llvm.aarch64.sve.orr.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
-declare <vscale x 16 x i1> @llvm.aarch64.sve.orn.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
-declare <vscale x 8 x i1> @llvm.aarch64.sve.orn.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
-declare <vscale x 4 x i1> @llvm.aarch64.sve.orn.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
-declare <vscale x 2 x i1> @llvm.aarch64.sve.orn.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
-declare <vscale x 16 x i1> @llvm.aarch64.sve.nor.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
-declare <vscale x 8 x i1> @llvm.aarch64.sve.nor.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
-declare <vscale x 4 x i1> @llvm.aarch64.sve.nor.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
-declare <vscale x 2 x i1> @llvm.aarch64.sve.nor.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
-declare <vscale x 16 x i1> @llvm.aarch64.sve.nand.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
-declare <vscale x 8 x i1> @llvm.aarch64.sve.nand.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
-declare <vscale x 4 x i1> @llvm.aarch64.sve.nand.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
-declare <vscale x 2 x i1> @llvm.aarch64.sve.nand.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
-declare <vscale x 16 x i1> @llvm.aarch64.sve.orrs.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
-declare <vscale x 8 x i1> @llvm.aarch64.sve.orrs.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
-declare <vscale x 4 x i1> @llvm.aarch64.sve.orrs.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
-declare <vscale x 2 x i1> @llvm.aarch64.sve.orrs.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
-declare <vscale x 16 x i1> @llvm.aarch64.sve.orns.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
-declare <vscale x 8 x i1> @llvm.aarch64.sve.orns.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
-declare <vscale x 4 x i1> @llvm.aarch64.sve.orns.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
-declare <vscale x 2 x i1> @llvm.aarch64.sve.orns.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
-declare <vscale x 16 x i1> @llvm.aarch64.sve.nors.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
-declare <vscale x 8 x i1> @llvm.aarch64.sve.nors.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
-declare <vscale x 4 x i1> @llvm.aarch64.sve.nors.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
-declare <vscale x 2 x i1> @llvm.aarch64.sve.nors.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
-declare <vscale x 16 x i1> @llvm.aarch64.sve.nands.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
-declare <vscale x 8 x i1> @llvm.aarch64.sve.nands.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
-declare <vscale x 4 x i1> @llvm.aarch64.sve.nands.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
-declare <vscale x 2 x i1> @llvm.aarch64.sve.nands.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
+declare <vscale x 16 x i1> @llvm.aarch64.sve.and.z.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
+declare <vscale x 8 x i1> @llvm.aarch64.sve.and.z.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
+declare <vscale x 4 x i1> @llvm.aarch64.sve.and.z.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
+declare <vscale x 2 x i1> @llvm.aarch64.sve.and.z.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
+declare <vscale x 16 x i1> @llvm.aarch64.sve.bic.z.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
+declare <vscale x 8 x i1> @llvm.aarch64.sve.bic.z.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
+declare <vscale x 4 x i1> @llvm.aarch64.sve.bic.z.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
+declare <vscale x 2 x i1> @llvm.aarch64.sve.bic.z.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
+declare <vscale x 16 x i1> @llvm.aarch64.sve.eor.z.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
+declare <vscale x 8 x i1> @llvm.aarch64.sve.eor.z.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
+declare <vscale x 4 x i1> @llvm.aarch64.sve.eor.z.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
+declare <vscale x 2 x i1> @llvm.aarch64.sve.eor.z.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
+declare <vscale x 16 x i1> @llvm.aarch64.sve.orr.z.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
+declare <vscale x 8 x i1> @llvm.aarch64.sve.orr.z.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
+declare <vscale x 4 x i1> @llvm.aarch64.sve.orr.z.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
+declare <vscale x 2 x i1> @llvm.aarch64.sve.orr.z.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
+declare <vscale x 16 x i1> @llvm.aarch64.sve.orn.z.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
+declare <vscale x 8 x i1> @llvm.aarch64.sve.orn.z.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
+declare <vscale x 4 x i1> @llvm.aarch64.sve.orn.z.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
+declare <vscale x 2 x i1> @llvm.aarch64.sve.orn.z.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
+declare <vscale x 16 x i1> @llvm.aarch64.sve.nor.z.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
+declare <vscale x 8 x i1> @llvm.aarch64.sve.nor.z.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
+declare <vscale x 4 x i1> @llvm.aarch64.sve.nor.z.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
+declare <vscale x 2 x i1> @llvm.aarch64.sve.nor.z.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)
+declare <vscale x 16 x i1> @llvm.aarch64.sve.nand.z.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
+declare <vscale x 8 x i1> @llvm.aarch64.sve.nand.z.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i1>)
+declare <vscale x 4 x i1> @llvm.aarch64.sve.nand.z.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x i1>)
+declare <vscale x 2 x i1> @llvm.aarch64.sve.nand.z.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x i1>)