diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -1327,6 +1327,202 @@
   return instCombineSVEVectorBinOp(IC, II);
 }
 
+static std::optional<Instruction *>
+instCombineSVEAllActive2VA(InstCombiner &IC, IntrinsicInst &II) {
+  auto *OpPredicate = II.getOperand(0);
+  auto *OpA = II.getOperand(1);
+  auto *OpB = II.getOperand(2);
+  if (!match(OpPredicate, m_Intrinsic<Intrinsic::aarch64_sve_ptrue>(
+                              m_ConstantInt<AArch64SVEPredPattern::all>())))
+    return std::nullopt;
+  IRBuilder<> Builder(II.getContext());
+  Builder.SetInsertPoint(&II);
+  switch (II.getIntrinsicID()) {
+  default:
+    return std::nullopt;
+  case Intrinsic::aarch64_sve_fabd: {
+    auto FABD_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_fabd_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, FABD_U);
+  }
+  case Intrinsic::aarch64_sve_fdiv: {
+    auto FDIV_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_fdiv_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, FDIV_U);
+  }
+  case Intrinsic::aarch64_sve_fmax: {
+    auto FMAX_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_fmax_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, FMAX_U);
+  }
+  case Intrinsic::aarch64_sve_fmaxnm: {
+    auto FMAXNM_U =
+        Builder.CreateIntrinsic(Intrinsic::aarch64_sve_fmaxnm_u, {II.getType()},
+                                {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, FMAXNM_U);
+  }
+  case Intrinsic::aarch64_sve_fmin: {
+    auto FMIN_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_fmin_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, FMIN_U);
+  }
+  case Intrinsic::aarch64_sve_fminnm: {
+    auto FMINNM_U =
+        Builder.CreateIntrinsic(Intrinsic::aarch64_sve_fminnm_u, {II.getType()},
+                                {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, FMINNM_U);
+  }
+  case Intrinsic::aarch64_sve_fmulx: {
+    auto FMULX_U =
+        Builder.CreateIntrinsic(Intrinsic::aarch64_sve_fmulx_u, {II.getType()},
+                                {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, FMULX_U);
+  }
+  case Intrinsic::aarch64_sve_smulh: {
+    auto SMULH_U =
+        Builder.CreateIntrinsic(Intrinsic::aarch64_sve_smulh_u, {II.getType()},
+                                {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, SMULH_U);
+  }
+  case Intrinsic::aarch64_sve_umulh: {
+    auto UMULH_U =
+        Builder.CreateIntrinsic(Intrinsic::aarch64_sve_umulh_u, {II.getType()},
+                                {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, UMULH_U);
+  }
+  case Intrinsic::aarch64_sve_smin: {
+    auto SMIN_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_smin_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, SMIN_U);
+  }
+  case Intrinsic::aarch64_sve_umin: {
+    auto UMIN_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_umin_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, UMIN_U);
+  }
+  case Intrinsic::aarch64_sve_smax: {
+    auto SMAX_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_smax_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, SMAX_U);
+  }
+  case Intrinsic::aarch64_sve_umax: {
+    auto UMAX_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_umax_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, UMAX_U);
+  }
+  case Intrinsic::aarch64_sve_sabd: {
+    auto SABD_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_sabd_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, SABD_U);
+  }
+  case Intrinsic::aarch64_sve_uabd: {
+    auto UABD_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_uabd_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, UABD_U);
+  }
+  case Intrinsic::aarch64_sve_asr: {
+    auto ASR_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_asr_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, ASR_U);
+  }
+  case Intrinsic::aarch64_sve_lsl: {
+    auto LSL_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_lsl_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, LSL_U);
+  }
+  case Intrinsic::aarch64_sve_lsr: {
+    auto LSR_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_lsr_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, LSR_U);
+  }
+  case Intrinsic::aarch64_sve_and: {
+    auto AND_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_and_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, AND_U);
+  }
+  case Intrinsic::aarch64_sve_bic: {
+    auto BIC_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_bic_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, BIC_U);
+  }
+  case Intrinsic::aarch64_sve_eor: {
+    auto EOR_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_eor_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, EOR_U);
+  }
+  case Intrinsic::aarch64_sve_orr: {
+    auto ORR_U = Builder.CreateIntrinsic(
+        Intrinsic::aarch64_sve_orr_u, {II.getType()}, {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, ORR_U);
+  }
+  case Intrinsic::aarch64_sve_sqsub: {
+    auto SQSUB_U =
+        Builder.CreateIntrinsic(Intrinsic::aarch64_sve_sqsub_u, {II.getType()},
+                                {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, SQSUB_U);
+  }
+  case Intrinsic::aarch64_sve_uqsub: {
+    auto UQSUB_U =
+        Builder.CreateIntrinsic(Intrinsic::aarch64_sve_uqsub_u, {II.getType()},
+                                {OpPredicate, OpA, OpB});
+    return IC.replaceInstUsesWith(II, UQSUB_U);
+  }
+  }
+}
+
+static std::optional<Instruction *>
+instCombineSVEAllActive3VA(InstCombiner &IC, IntrinsicInst &II) {
+  auto *OpPredicate = II.getOperand(0);
+  auto *OpA = II.getOperand(1);
+  auto *OpB = II.getOperand(2);
+  auto *OpC = II.getOperand(3);
+  if (!match(OpPredicate, m_Intrinsic<Intrinsic::aarch64_sve_ptrue>(
+                              m_ConstantInt<AArch64SVEPredPattern::all>())))
+    return std::nullopt;
+  IRBuilder<> Builder(II.getContext());
+  Builder.SetInsertPoint(&II);
+  switch (II.getIntrinsicID()) {
+  default:
+    return std::nullopt;
+  case Intrinsic::aarch64_sve_fmla: {
+    auto FMLA_U =
+        Builder.CreateIntrinsic(Intrinsic::aarch64_sve_fmla_u, {II.getType()},
+                                {OpPredicate, OpB, OpC, OpA});
+    return IC.replaceInstUsesWith(II, FMLA_U);
+  }
+  case Intrinsic::aarch64_sve_fmls: {
+    auto FMLS_U =
+        Builder.CreateIntrinsic(Intrinsic::aarch64_sve_fmls_u, {II.getType()},
+                                {OpPredicate, OpB, OpC, OpA});
+    return IC.replaceInstUsesWith(II, FMLS_U);
+  }
+  case Intrinsic::aarch64_sve_fnmla: {
+    auto FNMLA_U =
+        Builder.CreateIntrinsic(Intrinsic::aarch64_sve_fnmla_u, {II.getType()},
+                                {OpPredicate, OpB, OpC, OpA});
+    return IC.replaceInstUsesWith(II, FNMLA_U);
+  }
+  case Intrinsic::aarch64_sve_fnmls: {
+    auto FNMLS_U =
+        Builder.CreateIntrinsic(Intrinsic::aarch64_sve_fnmls_u, {II.getType()},
+                                {OpPredicate, OpB, OpC, OpA});
+    return IC.replaceInstUsesWith(II, FNMLS_U);
+  }
+  case Intrinsic::aarch64_sve_mla: {
+    auto MLA_U =
+        Builder.CreateIntrinsic(Intrinsic::aarch64_sve_mla_u, {II.getType()},
+                                {OpPredicate, OpB, OpC, OpA});
+    return IC.replaceInstUsesWith(II, MLA_U);
+  }
+  case Intrinsic::aarch64_sve_mls: {
+    auto MLS_U =
+        Builder.CreateIntrinsic(Intrinsic::aarch64_sve_mls_u, {II.getType()},
+                                {OpPredicate, OpB, OpC, OpA});
+    return IC.replaceInstUsesWith(II, MLS_U);
+  }
+  }
+}
+
 static std::optional<Instruction *> instCombineSVEVectorMul(InstCombiner &IC,
                                                             IntrinsicInst &II) {
   auto *OpPredicate = II.getOperand(0);
@@ -1695,6 +1891,38 @@
   case Intrinsic::aarch64_sve_ptest_first:
   case Intrinsic::aarch64_sve_ptest_last:
     return instCombineSVEPTest(IC, II);
+  case Intrinsic::aarch64_sve_fabd:
+  case Intrinsic::aarch64_sve_fdiv:
+  case Intrinsic::aarch64_sve_fmax:
+  case Intrinsic::aarch64_sve_fmaxnm:
+  case Intrinsic::aarch64_sve_fmin:
+  case Intrinsic::aarch64_sve_fminnm:
+  case Intrinsic::aarch64_sve_fmulx:
+  case Intrinsic::aarch64_sve_smulh:
+  case Intrinsic::aarch64_sve_umulh:
+  case Intrinsic::aarch64_sve_smin:
+  case Intrinsic::aarch64_sve_umin:
+  case Intrinsic::aarch64_sve_smax:
+  case Intrinsic::aarch64_sve_umax:
+  case Intrinsic::aarch64_sve_sabd:
+  case Intrinsic::aarch64_sve_uabd:
+  case Intrinsic::aarch64_sve_asr:
+  case Intrinsic::aarch64_sve_lsl:
+  case Intrinsic::aarch64_sve_lsr:
+  case Intrinsic::aarch64_sve_and:
+  case Intrinsic::aarch64_sve_bic:
+  case Intrinsic::aarch64_sve_eor:
+  case Intrinsic::aarch64_sve_orr:
+  case Intrinsic::aarch64_sve_sqsub:
+  case Intrinsic::aarch64_sve_uqsub:
+    return instCombineSVEAllActive2VA(IC, II);
+  case Intrinsic::aarch64_sve_fmla:
+  case Intrinsic::aarch64_sve_fmls:
+  case Intrinsic::aarch64_sve_fnmla:
+  case Intrinsic::aarch64_sve_fnmls:
+  case Intrinsic::aarch64_sve_mla:
+  case Intrinsic::aarch64_sve_mls:
+    return instCombineSVEAllActive3VA(IC, II);
   case Intrinsic::aarch64_sve_mul:
   case Intrinsic::aarch64_sve_fmul:
   case Intrinsic::aarch64_sve_fmul_u:
diff --git a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-m-to-x.ll b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-m-to-x.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-m-to-x.ll
@@ -0,0 +1,1749 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
+; RUN: opt -S -passes=instcombine < %s | FileCheck %s
+
+target triple = "aarch64-unknown-linux-gnu"
+
+declare <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32)
+declare <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32)
+declare <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32)
+declare <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32)
+
+; Replace SVE merging intrinsics to their equivalent undef (_u) variants when they take an all active predicate.
+
+; Float arithmetics
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fabd.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fabd_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fabd_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1:[0-9]+]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fabd.u.nxv8f16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fabd.nxv8f16(<vscale x 8 x i1> %1, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %2
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fabd.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fabd_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fabd_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fabd.u.nxv4f32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fabd.nxv4f32(<vscale x 4 x i1> %1, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %2
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fabd_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fabd_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fabd.u.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %2
+}
+
+define <vscale x 2 x double> @no_replace_fabd_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @no_replace_fabd_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %2
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fdiv.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fdiv_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fdiv_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fdiv.u.nxv8f16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fdiv.nxv8f16(<vscale x 8 x i1> %1, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %2
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fdiv_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fdiv_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fdiv.u.nxv4f32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1> %1, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %2
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fdiv_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fdiv_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fdiv.u.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %2
+}
+
+define <vscale x 2 x double> @no_replace_fdiv_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @no_replace_fdiv_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %2
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fmax_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fmax_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmax.u.nxv8f16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1> %1, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %2
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fmax_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fmax_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmax.u.nxv4f32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1> %1, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %2
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fmax_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fmax_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmax.u.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %2
+}
+
+define <vscale x 2 x double> @no_replace_fmax_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @no_replace_fmax_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %2
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fmaxnm_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fmaxnm_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.u.nxv8f16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1> %1, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %2
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fmaxnm_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fmaxnm_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.u.nxv4f32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1> %1, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %2
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fmaxnm_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fmaxnm_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmax.u.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %2
+}
+
+define <vscale x 2 x double> @no_replace_fmaxnm_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @no_replace_fmaxnm_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %2
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fmin_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fmin_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmin.u.nxv8f16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1> %1, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %2
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fmin_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fmin_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmin.u.nxv4f32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1> %1, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %2
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fmin_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fmin_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmin.u.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %2
+}
+
+define <vscale x 2 x double> @no_replace_fmin_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @no_replace_fmin_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %2
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fminnm_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fminnm_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fminnm.u.nxv8f16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1> %1, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %2
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fminnm_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fminnm_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fminnm.u.nxv4f32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1> %1, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %2
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fminnm_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fminnm_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fminnm.u.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %2
+}
+
+define <vscale x 2 x double> @no_replace_fminnm_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @no_replace_fminnm_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %2
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fmla_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fmla_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]], <vscale x 8 x half> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmla.u.nxv8f16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]], <vscale x 8 x half> [[A]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1> %1, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %2
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fmla_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fmla_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]], <vscale x 4 x float> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmla.u.nxv4f32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]], <vscale x 4 x float> [[A]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1> %1, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %2
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fmla_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fmla_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]], <vscale x 2 x double> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmla.u.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[B]], <vscale x 2 x double> [[C]], <vscale x 2 x double> [[A]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %2
+}
+
+define <vscale x 2 x double> @no_replace_fmla_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @no_replace_fmla_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]], <vscale x 2 x double> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]], <vscale x 2 x double> [[C]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %2
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fmls_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fmls_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]], <vscale x 8 x half> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmls.u.nxv8f16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]], <vscale x 8 x half> [[A]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1> %1, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %2
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fmls_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fmls_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]], <vscale x 4 x float> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmls.u.nxv4f32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]], <vscale x 4 x float> [[A]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1> %1, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %2
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fmls_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fmls_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]], <vscale x 2 x double> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmls.u.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[B]], <vscale x 2 x double> [[C]], <vscale x 2 x double> [[A]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %2
+}
+
+define <vscale x 2 x double> @no_replace_fmls_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @no_replace_fmls_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]], <vscale x 2 x double> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]], <vscale x 2 x double> [[C]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %2
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fnmla_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fnmla_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]], <vscale x 8 x half> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.u.nxv8f16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]], <vscale x 8 x half> [[A]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> %1, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %2
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fnmla_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fnmla_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]], <vscale x 4 x float> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.u.nxv4f32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]], <vscale x 4 x float> [[A]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> %1, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %2
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fnmla_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fnmla_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]], <vscale x 2 x double> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.u.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[B]], <vscale x 2 x double> [[C]], <vscale x 2 x double> [[A]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %2
+}
+
+define <vscale x 2 x double> @no_replace_fnmla_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @no_replace_fnmla_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]], <vscale x 2 x double> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]], <vscale x 2 x double> [[C]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %2
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fnmls_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fnmls_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]], <vscale x 8 x half> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmls.u.nxv8f16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]], <vscale x 8 x half> [[A]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1> %1, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %2
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fnmls_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fnmls_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]], <vscale x 4 x float> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmls.u.nxv4f32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]], <vscale x 4 x float> [[A]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1> %1, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %2
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fnmls_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fnmls_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]], <vscale x 2 x double> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmls.u.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[B]], <vscale x 2 x double> [[C]], <vscale x 2 x double> [[A]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %2
+}
+
+define <vscale x 2 x double> @no_replace_fnmls_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @no_replace_fnmls_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]], <vscale x 2 x double> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]], <vscale x 2 x double> [[C]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1> %1, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %2
+}
+
+; Integer arithmetics
+
+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>)
+define <vscale x 16 x i8> @replace_mla_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_mla_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]], <vscale x 16 x i8> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mla.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[B]], <vscale x 16 x i8> [[C]], <vscale x 16 x i8> [[A]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
+  ret <vscale x 16 x i8> %2
+}
+
+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>)
+define <vscale x 8 x i16> @replace_mla_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_mla_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]], <vscale x 8 x i16> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mla.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[B]], <vscale x 8 x i16> [[C]], <vscale x 8 x i16> [[A]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
+  ret <vscale x 8 x i16> %2
+}
+
+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>)
+define <vscale x 4 x i32> @replace_mla_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_mla_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]], <vscale x 4 x i32> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mla.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[B]], <vscale x 4 x i32> [[C]], <vscale x 4 x i32> [[A]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
+  ret <vscale x 4 x i32> %2
+}
+
+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>)
+define <vscale x 2 x i64> @replace_mla_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_mla_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]], <vscale x 2 x i64> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mla.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[B]], <vscale x 2 x i64> [[C]], <vscale x 2 x i64> [[A]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_mla_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_mla_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]], <vscale x 2 x i64> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]], <vscale x 2 x i64> [[C]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
+  ret <vscale x 2 x i64> %2
+}
+
+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>)
+define <vscale x 16 x i8> @replace_mls_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_mls_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]], <vscale x 16 x i8> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mls.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[B]], <vscale x 16 x i8> [[C]], <vscale x 16 x i8> [[A]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
+  ret <vscale x 16 x i8> %2
+}
+
+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>)
+define <vscale x 8 x i16> @replace_mls_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_mls_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]], <vscale x 8 x i16> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mls.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[B]], <vscale x 8 x i16> [[C]], <vscale x 8 x i16> [[A]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
+  ret <vscale x 8 x i16> %2
+}
+
+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>)
+define <vscale x 4 x i32> @replace_mls_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_mls_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]], <vscale x 4 x i32> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mls.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[B]], <vscale x 4 x i32> [[C]], <vscale x 4 x i32> [[A]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
+  ret <vscale x 4 x i32> %2
+}
+
+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>)
+define <vscale x 2 x i64> @replace_mls_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_mls_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]], <vscale x 2 x i64> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mls.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[B]], <vscale x 2 x i64> [[C]], <vscale x 2 x i64> [[A]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_mls_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_mls_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]], <vscale x 2 x i64> [[C:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]], <vscale x 2 x i64> [[C]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
+  ret <vscale x 2 x i64> %2
+}
+
+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>)
+define <vscale x 16 x i8> @replace_smulh_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_smulh_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smulh.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.smulh.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+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>)
+define <vscale x 8 x i16> @replace_smulh_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_smulh_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smulh.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.smulh.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+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>)
+define <vscale x 4 x i32> @replace_smulh_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_smulh_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smulh.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smulh.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+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>)
+define <vscale x 2 x i64> @replace_smulh_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_smulh_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smulh.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smulh.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_smulh_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_smulh_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smulh.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smulh.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+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>)
+define <vscale x 16 x i8> @replace_umulh_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_umulh_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umulh.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.umulh.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+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>)
+define <vscale x 8 x i16> @replace_umulh_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_umulh_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umulh.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.umulh.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+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>)
+define <vscale x 4 x i32> @replace_umulh_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_umulh_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umulh.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.umulh.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+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>)
+define <vscale x 2 x i64> @replace_umulh_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_umulh_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umulh.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umulh.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_umulh_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_umulh_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umulh.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umulh.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+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>)
+define <vscale x 16 x i8> @replace_smin_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_smin_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smin.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.smin.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+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>)
+define <vscale x 8 x i16> @replace_smin_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_smin_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smin.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.smin.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+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>)
+define <vscale x 4 x i32> @replace_smin_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_smin_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smin.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smin.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+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>)
+define <vscale x 2 x i64> @replace_smin_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_smin_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smin.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smin.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_smin_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_smin_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smin.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smin.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+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>)
+define <vscale x 16 x i8> @replace_umin_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_umin_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umin.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.umin.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+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>)
+define <vscale x 8 x i16> @replace_umin_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_umin_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umin.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.umin.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+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>)
+define <vscale x 4 x i32> @replace_umin_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_umin_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umin.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.umin.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+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>)
+define <vscale x 2 x i64> @replace_umin_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_umin_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umin.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_umin_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_umin_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+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>)
+define <vscale x 16 x i8> @replace_smax_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_smax_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smax.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.smax.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+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>)
+define <vscale x 8 x i16> @replace_smax_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_smax_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smax.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.smax.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+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>)
+define <vscale x 4 x i32> @replace_smax_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_smax_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smax.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smax.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+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>)
+define <vscale x 2 x i64> @replace_smax_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_smax_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smax.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smax.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_smax_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_smax_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smax.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smax.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+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>)
+define <vscale x 16 x i8> @replace_umax_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_umax_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umax.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.umax.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+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>)
+define <vscale x 8 x i16> @replace_umax_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_umax_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umax.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.umax.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+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>)
+define <vscale x 4 x i32> @replace_umax_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_umax_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umax.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.umax.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+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>)
+define <vscale x 2 x i64> @replace_umax_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_umax_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umax.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umax.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_umax_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_umax_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umax.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umax.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+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>)
+define <vscale x 16 x i8> @replace_sabd_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_sabd_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sabd.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.sabd.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+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>)
+define <vscale x 8 x i16> @replace_sabd_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_sabd_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sabd.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sabd.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+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>)
+define <vscale x 4 x i32> @replace_sabd_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_sabd_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sabd.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.sabd.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+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>)
+define <vscale x 2 x i64> @replace_sabd_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_sabd_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_sabd_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_sabd_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+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>)
+define <vscale x 16 x i8> @replace_uabd_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_uabd_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uabd.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.uabd.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+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>)
+define <vscale x 8 x i16> @replace_uabd_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_uabd_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uabd.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.uabd.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+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>)
+define <vscale x 4 x i32> @replace_uabd_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_uabd_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uabd.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.uabd.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+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>)
+define <vscale x 2 x i64> @replace_uabd_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_uabd_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_uabd_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_uabd_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+; Shifts
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.asr.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+define <vscale x 16 x i8> @replace_asr_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_asr_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.asr.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.asr.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+define <vscale x 8 x i16> @replace_asr_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_asr_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.asr.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.asr.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+define <vscale x 4 x i32> @replace_asr_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_asr_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.asr.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.asr.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+define <vscale x 2 x i64> @replace_asr_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_asr_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.asr.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.asr.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_asr_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_asr_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.asr.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.asr.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.lsl.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+define <vscale x 16 x i8> @replace_lsl_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_lsl_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.lsl.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.lsl.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.lsl.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+define <vscale x 8 x i16> @replace_lsl_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_lsl_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.lsl.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+define <vscale x 4 x i32> @replace_lsl_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_lsl_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.lsl.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+define <vscale x 2 x i64> @replace_lsl_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_lsl_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.lsl.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.lsl.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_lsl_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_lsl_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.lsl.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.lsl.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.lsr.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+define <vscale x 16 x i8> @replace_lsr_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_lsr_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.lsr.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.lsr.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.lsr.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+define <vscale x 8 x i16> @replace_lsr_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_lsr_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.lsr.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+define <vscale x 4 x i32> @replace_lsr_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_lsr_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.lsr.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+define <vscale x 2 x i64> @replace_lsr_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_lsr_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.lsr.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.lsr.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_lsr_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_lsr_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.lsr.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.lsr.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+; Logical operations
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+define <vscale x 16 x i8> @replace_and_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_and_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.and.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+define <vscale x 8 x i16> @replace_and_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_and_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.and.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+define <vscale x 4 x i32> @replace_and_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_and_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.and.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+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>)
+define <vscale x 2 x i64> @replace_and_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_and_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.and.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_and_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_and_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+define <vscale x 16 x i8> @replace_bic_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_bic_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bic.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+define <vscale x 8 x i16> @replace_bic_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_bic_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bic.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+define <vscale x 4 x i32> @replace_bic_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_bic_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bic.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+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>)
+define <vscale x 2 x i64> @replace_bic_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_bic_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_bic_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_bic_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+define <vscale x 16 x i8> @replace_eor_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_eor_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+define <vscale x 8 x i16> @replace_eor_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_eor_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+define <vscale x 4 x i32> @replace_eor_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_eor_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+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>)
+define <vscale x 2 x i64> @replace_eor_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_eor_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_eor_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_eor_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+define <vscale x 16 x i8> @replace_orr_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_orr_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.orr.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+define <vscale x 8 x i16> @replace_orr_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_orr_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.orr.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+define <vscale x 4 x i32> @replace_orr_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_orr_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.orr.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+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>)
+define <vscale x 2 x i64> @replace_orr_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_orr_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.orr.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_orr_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_orr_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+; SVE2 - Uniform DSP operations
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+define <vscale x 16 x i8> @replace_sqsub_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_sqsub_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+define <vscale x 8 x i16> @replace_sqsub_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_sqsub_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+define <vscale x 4 x i32> @replace_sqsub_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_sqsub_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+define <vscale x 2 x i64> @replace_sqsub_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_sqsub_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_sqsub_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_sqsub_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+define <vscale x 16 x i8> @replace_uqsub_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_uqsub_intrinsic_i8
+; CHECK-SAME: (<vscale x 16 x i8> [[A:%.*]], <vscale x 16 x i8> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.u.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+  %2 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %2
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+define <vscale x 8 x i16> @replace_uqsub_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_uqsub_intrinsic_i16
+; CHECK-SAME: (<vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.u.nxv8i16(<vscale x 8 x i1> [[TMP1]], <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
+;
+  %1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
+  %2 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %2
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+define <vscale x 4 x i32> @replace_uqsub_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_uqsub_intrinsic_i32
+; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.u.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
+;
+  %1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
+  %2 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %2
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+define <vscale x 2 x i64> @replace_uqsub_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_uqsub_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.u.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+define <vscale x 2 x i64> @no_replace_uqsub_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @no_replace_uqsub_intrinsic_i64
+; CHECK-SAME: (<vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.nxv2i64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
+;
+  %1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 5)
+  %2 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %2
+}
+
+attributes #0 = { "target-features"="+sve" }