[llvm] [AArch64][SVE] Added optimisation for SVE intrinsics for no active lanes (PR #73943)

[Mark Harley via llvm-commits]

https://github.com/MarkAHarley updated https://github.com/llvm/llvm-project/pull/73943

>From 77ab0d72d1cf556cf21d2838f7d97644974e580a Mon Sep 17 00:00:00 2001
From: Mark Harley <mark.harley at arm.com>
Date: Thu, 30 Nov 2023 16:17:54 +0000
Subject: [PATCH 1/2] [AArch64][SVE][NFC] Added tests for SVE intrinsic calls
 with all false predicates

---
 ...-intrinsic-comb-m-forms-no-active-lanes.ll | 1454 +++++++++++++++++
 ...-intrinsic-comb-u-forms-no-active-lanes.ll | 1448 ++++++++++++++++
 2 files changed, 2902 insertions(+)
 create mode 100644 llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-m-forms-no-active-lanes.ll
 create mode 100644 llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-u-forms-no-active-lanes.ll

diff --git a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-m-forms-no-active-lanes.ll b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-m-forms-no-active-lanes.ll
new file mode 100644
index 000000000000000..5ea6fff12134c19
--- /dev/null
+++ b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-m-forms-no-active-lanes.ll
@@ -0,0 +1,1454 @@
+; 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"
+
+; Replace SVE _m intrinsics with their first operand when the predicate is all false.
+
+; Float arithmetic
+
+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 fast <vscale x 8 x half> @llvm.aarch64.sve.fabd.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fabd.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+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 fast <vscale x 4 x float> @llvm.aarch64.sve.fabd.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fabd.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+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 fast <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+; aarch64_sve_fadd intrinsic combines to a LLVM instruction fadd.
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fadd_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fadd_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fadd.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fadd_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fadd_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fadd.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fadd.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fadd_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fadd_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+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 fast <vscale x 8 x half> @llvm.aarch64.sve.fdiv.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fdiv.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+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 fast <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+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 fast <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+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 fast <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+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 fast <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+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 fast <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %1
+}
+
+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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %1
+}
+
+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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %1
+}
+
+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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %1
+}
+
+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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %1
+}
+
+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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %1
+}
+
+; aarch64_sve_fmul intrinsic combines to a LLVM instruction fmul.
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fmul_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fmul_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fmul_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fmul_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fmul_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fmul_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmulx.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fmulx_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fmulx_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmulx.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmulx.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmulx.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fmulx_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fmulx_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmulx.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmulx.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmulx.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fmulx_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fmulx_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmulx.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmulx.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+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 fast <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %1
+}
+
+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 fast <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %1
+}
+
+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 fast <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %1
+}
+
+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 fast <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %1
+}
+
+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 fast <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %1
+}
+
+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 fast <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %1
+}
+
+; aarch64_sve_fsub intrinsic combines to a LLVM instruction fsub.
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fsub.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fsub_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fsub_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fsub.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fsub.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fsub_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fsub_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fsub_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fsub_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+; Integer arithmetic
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+define <vscale x 16 x i8> @replace_add_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_add_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 i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+define <vscale x 8 x i16> @replace_add_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_add_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 i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+define <vscale x 4 x i32> @replace_add_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_add_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 i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+define <vscale x 2 x i64> @replace_add_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_add_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 i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+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 i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]], <vscale x 16 x i8> [[C]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]], <vscale x 8 x i16> [[C]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]], <vscale x 4 x i32> [[C]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
+  ret <vscale x 2 x i64> %1
+}
+
+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 i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]], <vscale x 16 x i8> [[C]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]], <vscale x 8 x i16> [[C]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]], <vscale x 4 x i32> [[C]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+define <vscale x 16 x i8> @replace_mul_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_mul_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 i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+define <vscale x 8 x i16> @replace_mul_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_mul_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 i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+define <vscale x 4 x i32> @replace_mul_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_mul_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 i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+define <vscale x 2 x i64> @replace_mul_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_mul_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 i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+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 i8> @llvm.aarch64.sve.sabd.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.sabd.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.sabd.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sabd.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.sabd.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.sabd.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+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 i8> @llvm.aarch64.sve.smax.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.smax.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.smax.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.smax.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.smax.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smax.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.smax.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smax.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+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 i8> @llvm.aarch64.sve.smin.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.smin.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.smin.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.smin.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.smin.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smin.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.smin.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smin.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+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 i8> @llvm.aarch64.sve.smulh.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.smulh.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.smulh.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.smulh.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.smulh.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smulh.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.smulh.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smulh.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+define <vscale x 16 x i8> @replace_sub_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_sub_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 i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+define <vscale x 8 x i16> @replace_sub_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_sub_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 i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+define <vscale x 4 x i32> @replace_sub_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_sub_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 i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+define <vscale x 2 x i64> @replace_sub_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_sub_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 i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+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 i8> @llvm.aarch64.sve.uabd.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.uabd.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.uabd.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.uabd.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.uabd.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.uabd.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+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 i8> @llvm.aarch64.sve.umax.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.umax.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.umax.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.umax.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.umax.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.umax.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.umax.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umax.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+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 i8> @llvm.aarch64.sve.umin.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.umin.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.umin.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.umin.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.umin.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.umin.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+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 i8> @llvm.aarch64.sve.umulh.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.umulh.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.umulh.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.umulh.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.umulh.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.umulh.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.umulh.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umulh.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+; 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 i8> @llvm.aarch64.sve.asr.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.asr.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.asr.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.asr.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.asr.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.asr.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.asr.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.asr.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+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 i8> @llvm.aarch64.sve.lsl.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.lsl.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.lsl.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.lsl.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.lsl.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.lsl.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+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 i8> @llvm.aarch64.sve.lsr.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.lsr.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.lsr.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.lsr.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.lsr.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.lsr.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+; 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 i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+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 i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+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 i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+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 i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+; 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 i8> @llvm.aarch64.sve.sqsub.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.sqsub.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.sqsub.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.sqsub.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+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 i8> @llvm.aarch64.sve.uqsub.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+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 i16> @llvm.aarch64.sve.uqsub.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+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 i32> @llvm.aarch64.sve.uqsub.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+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 i64> @llvm.aarch64.sve.uqsub.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+attributes #0 = { "target-features"="+sve,+sve2" }
diff --git a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-u-forms-no-active-lanes.ll b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-u-forms-no-active-lanes.ll
new file mode 100644
index 000000000000000..d3e51231fb52c04
--- /dev/null
+++ b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-u-forms-no-active-lanes.ll
@@ -0,0 +1,1448 @@
+; 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"
+
+; Replace SVE _u intrinsics with undef if the predicate is all false.
+
+; Float arithmetic
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fabd.u.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 fast <vscale x 8 x half> @llvm.aarch64.sve.fabd.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fabd.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fabd.u.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 fast <vscale x 4 x float> @llvm.aarch64.sve.fabd.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fabd.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fabd.u.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 fast <vscale x 2 x double> @llvm.aarch64.sve.fabd.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fabd.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fadd.u.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fadd_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fadd_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fadd.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fadd.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fadd.u.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fadd_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fadd_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fadd.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fadd.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fadd.u.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fadd_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fadd_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fadd.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fadd.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fdiv.u.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 fast <vscale x 8 x half> @llvm.aarch64.sve.fdiv.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fdiv.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fdiv.u.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 fast <vscale x 4 x float> @llvm.aarch64.sve.fdiv.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fdiv.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fdiv.u.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 fast <vscale x 2 x double> @llvm.aarch64.sve.fdiv.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fdiv.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmax.u.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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmax.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmax.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmax.u.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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmax.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmax.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmax.u.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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmax.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmax.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.u.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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.u.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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.u.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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmin.u.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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmin.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmin.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmin.u.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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmin.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmin.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmin.u.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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmin.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmin.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fminnm.u.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 fast <vscale x 8 x half> @llvm.aarch64.sve.fminnm.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fminnm.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fminnm.u.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 fast <vscale x 4 x float> @llvm.aarch64.sve.fminnm.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fminnm.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fminnm.u.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 fast <vscale x 2 x double> @llvm.aarch64.sve.fminnm.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fminnm.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmla.u.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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmla.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmla.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmla.u.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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmla.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmla.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmla.u.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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmla.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmla.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %1
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmls.u.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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmls.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmls.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmls.u.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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmls.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmls.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmls.u.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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmls.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmls.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %1
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmul.u.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fmul_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fmul_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmul.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmul.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmul.u.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fmul_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fmul_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmul.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmul.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmul.u.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fmul_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fmul_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmul.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmul.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fmulx.u.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fmulx_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fmulx_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmulx.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmulx.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fmulx.u.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fmulx_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fmulx_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmulx.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmulx.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fmulx.u.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fmulx_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fmulx_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmulx.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmulx.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fnmla.u.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 fast <vscale x 8 x half> @llvm.aarch64.sve.fnmla.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fnmla.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fnmla.u.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 fast <vscale x 4 x float> @llvm.aarch64.sve.fnmla.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fnmla.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fnmla.u.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 fast <vscale x 2 x double> @llvm.aarch64.sve.fnmla.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fnmla.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %1
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fnmls.u.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 fast <vscale x 8 x half> @llvm.aarch64.sve.fnmls.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fnmls.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fnmls.u.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 fast <vscale x 4 x float> @llvm.aarch64.sve.fnmls.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fnmls.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fnmls.u.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 fast <vscale x 2 x double> @llvm.aarch64.sve.fnmls.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fnmls.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %1
+}
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.fsub.u.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
+define <vscale x 8 x half> @replace_fsub_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x half> @replace_fsub_intrinsic_half
+; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fsub.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fsub.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
+  ret <vscale x 8 x half> %1
+}
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.fsub.u.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
+define <vscale x 4 x float> @replace_fsub_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x float> @replace_fsub_intrinsic_float
+; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fsub.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fsub.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.fsub.u.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
+define <vscale x 2 x double> @replace_fsub_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x double> @replace_fsub_intrinsic_double
+; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fsub.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fsub.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
+  ret <vscale x 2 x double> %1
+}
+
+; Integer arithmetic
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.add.u.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+define <vscale x 16 x i8> @replace_add_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_add_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 i8> @llvm.aarch64.sve.add.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.add.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.add.u.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+define <vscale x 8 x i16> @replace_add_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_add_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 i16> @llvm.aarch64.sve.add.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.add.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.add.u.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+define <vscale x 4 x i32> @replace_add_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_add_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 i32> @llvm.aarch64.sve.add.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.add.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.add.u.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+define <vscale x 2 x i64> @replace_add_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_add_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 i64> @llvm.aarch64.sve.add.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.add.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.mla.u.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 i8> @llvm.aarch64.sve.mla.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]], <vscale x 16 x i8> [[C]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.mla.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.mla.u.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 i16> @llvm.aarch64.sve.mla.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]], <vscale x 8 x i16> [[C]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.mla.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.mla.u.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 i32> @llvm.aarch64.sve.mla.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]], <vscale x 4 x i32> [[C]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.mla.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.mla.u.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 i64> @llvm.aarch64.sve.mla.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mla.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.mls.u.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 i8> @llvm.aarch64.sve.mls.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]], <vscale x 16 x i8> [[C]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.mls.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.mls.u.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 i16> @llvm.aarch64.sve.mls.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]], <vscale x 8 x i16> [[C]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.mls.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.mls.u.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 i32> @llvm.aarch64.sve.mls.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]], <vscale x 4 x i32> [[C]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.mls.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.mls.u.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 i64> @llvm.aarch64.sve.mls.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mls.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.mul.u.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+define <vscale x 16 x i8> @replace_mul_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_mul_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 i8> @llvm.aarch64.sve.mul.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.mul.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.mul.u.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+define <vscale x 8 x i16> @replace_mul_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_mul_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 i16> @llvm.aarch64.sve.mul.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.mul.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.mul.u.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+define <vscale x 4 x i32> @replace_mul_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_mul_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 i32> @llvm.aarch64.sve.mul.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.mul.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.mul.u.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+define <vscale x 2 x i64> @replace_mul_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_mul_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 i64> @llvm.aarch64.sve.mul.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mul.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.sabd.u.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 i8> @llvm.aarch64.sve.sabd.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.sabd.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.sabd.u.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 i16> @llvm.aarch64.sve.sabd.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sabd.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.sabd.u.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 i32> @llvm.aarch64.sve.sabd.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.sabd.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.sabd.u.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 i64> @llvm.aarch64.sve.sabd.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.smax.u.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 i8> @llvm.aarch64.sve.smax.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.smax.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.smax.u.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 i16> @llvm.aarch64.sve.smax.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.smax.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.smax.u.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 i32> @llvm.aarch64.sve.smax.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smax.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.smax.u.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 i64> @llvm.aarch64.sve.smax.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smax.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.smin.u.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 i8> @llvm.aarch64.sve.smin.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.smin.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.smin.u.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 i16> @llvm.aarch64.sve.smin.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.smin.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.smin.u.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 i32> @llvm.aarch64.sve.smin.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smin.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.smin.u.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 i64> @llvm.aarch64.sve.smin.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smin.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.smulh.u.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 i8> @llvm.aarch64.sve.smulh.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.smulh.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.smulh.u.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 i16> @llvm.aarch64.sve.smulh.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.smulh.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.smulh.u.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 i32> @llvm.aarch64.sve.smulh.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smulh.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.smulh.u.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 i64> @llvm.aarch64.sve.smulh.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smulh.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.sub.u.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+define <vscale x 16 x i8> @replace_sub_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
+; CHECK-LABEL: define <vscale x 16 x i8> @replace_sub_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 i8> @llvm.aarch64.sve.sub.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.sub.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.sub.u.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+define <vscale x 8 x i16> @replace_sub_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
+; CHECK-LABEL: define <vscale x 8 x i16> @replace_sub_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 i16> @llvm.aarch64.sve.sub.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sub.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.sub.u.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+define <vscale x 4 x i32> @replace_sub_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
+; CHECK-LABEL: define <vscale x 4 x i32> @replace_sub_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 i32> @llvm.aarch64.sve.sub.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.sub.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.sub.u.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+define <vscale x 2 x i64> @replace_sub_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
+; CHECK-LABEL: define <vscale x 2 x i64> @replace_sub_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 i64> @llvm.aarch64.sve.sub.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sub.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.uabd.u.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 i8> @llvm.aarch64.sve.uabd.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.uabd.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.uabd.u.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 i16> @llvm.aarch64.sve.uabd.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.uabd.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.uabd.u.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 i32> @llvm.aarch64.sve.uabd.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.uabd.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.uabd.u.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 i64> @llvm.aarch64.sve.uabd.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.umax.u.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 i8> @llvm.aarch64.sve.umax.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.umax.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.umax.u.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 i16> @llvm.aarch64.sve.umax.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.umax.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.umax.u.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 i32> @llvm.aarch64.sve.umax.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.umax.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.umax.u.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 i64> @llvm.aarch64.sve.umax.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umax.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.umin.u.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 i8> @llvm.aarch64.sve.umin.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.umin.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.umin.u.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 i16> @llvm.aarch64.sve.umin.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.umin.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.umin.u.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 i32> @llvm.aarch64.sve.umin.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.umin.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.umin.u.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 i64> @llvm.aarch64.sve.umin.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umin.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.umulh.u.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 i8> @llvm.aarch64.sve.umulh.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.umulh.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.umulh.u.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 i16> @llvm.aarch64.sve.umulh.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.umulh.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.umulh.u.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 i32> @llvm.aarch64.sve.umulh.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.umulh.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.umulh.u.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 i64> @llvm.aarch64.sve.umulh.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umulh.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+; Shifts
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.asr.u.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 i8> @llvm.aarch64.sve.asr.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.asr.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.asr.u.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 i16> @llvm.aarch64.sve.asr.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.asr.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.asr.u.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 i32> @llvm.aarch64.sve.asr.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.asr.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.asr.u.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 i64> @llvm.aarch64.sve.asr.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.asr.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.lsl.u.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 i8> @llvm.aarch64.sve.lsl.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.lsl.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.lsl.u.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 i16> @llvm.aarch64.sve.lsl.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.lsl.u.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 i32> @llvm.aarch64.sve.lsl.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.lsl.u.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 i64> @llvm.aarch64.sve.lsl.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.lsl.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.lsr.u.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 i8> @llvm.aarch64.sve.lsr.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.lsr.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.lsr.u.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 i16> @llvm.aarch64.sve.lsr.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.lsr.u.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 i32> @llvm.aarch64.sve.lsr.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.lsr.u.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 i64> @llvm.aarch64.sve.lsr.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.lsr.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+; Logical operations
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.and.u.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 i8> @llvm.aarch64.sve.and.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.and.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.and.u.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 i16> @llvm.aarch64.sve.and.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.and.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.and.u.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 i32> @llvm.aarch64.sve.and.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.and.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.and.u.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 i64> @llvm.aarch64.sve.and.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.and.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.bic.u.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 i8> @llvm.aarch64.sve.bic.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.bic.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.bic.u.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 i16> @llvm.aarch64.sve.bic.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.bic.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.bic.u.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 i32> @llvm.aarch64.sve.bic.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.bic.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.bic.u.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 i64> @llvm.aarch64.sve.bic.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.bic.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.eor.u.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 i8> @llvm.aarch64.sve.eor.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.eor.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.eor.u.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 i16> @llvm.aarch64.sve.eor.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.eor.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.eor.u.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 i32> @llvm.aarch64.sve.eor.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.eor.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.eor.u.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 i64> @llvm.aarch64.sve.eor.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.eor.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.orr.u.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 i8> @llvm.aarch64.sve.orr.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.orr.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.orr.u.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 i16> @llvm.aarch64.sve.orr.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.orr.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.orr.u.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 i32> @llvm.aarch64.sve.orr.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.orr.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.orr.u.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 i64> @llvm.aarch64.sve.orr.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.orr.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+; SVE2 - Uniform DSP operations
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.u.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 i8> @llvm.aarch64.sve.sqsub.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.u.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 i16> @llvm.aarch64.sve.sqsub.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.u.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 i32> @llvm.aarch64.sve.sqsub.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.u.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 i64> @llvm.aarch64.sve.sqsub.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.u.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 i8> @llvm.aarch64.sve.uqsub.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+;
+  %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+  ret <vscale x 16 x i8> %1
+}
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.u.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 i16> @llvm.aarch64.sve.uqsub.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+;
+  %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+  ret <vscale x 8 x i16> %1
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.u.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 i32> @llvm.aarch64.sve.uqsub.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+;
+  %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+  ret <vscale x 4 x i32> %1
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.u.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 i64> @llvm.aarch64.sve.uqsub.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+;
+  %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+  ret <vscale x 2 x i64> %1
+}
+
+attributes #0 = { "target-features"="+sve,+sve2" }

>From 0fd70aa3aeebc192a6efa7a9f8d45d3ac3a69480 Mon Sep 17 00:00:00 2001
From: Mark Harley <mark.harley at arm.com>
Date: Thu, 30 Nov 2023 17:16:14 +0000
Subject: [PATCH 2/2] [AArch64][SVE] Added optimisation for SVE intrinsics with
 no active lanes

---
 .../AArch64/AArch64TargetTransformInfo.cpp    | 166 ++++++--
 ...-intrinsic-comb-m-forms-no-active-lanes.ll | 390 ++++++------------
 ...-intrinsic-comb-u-forms-no-active-lanes.ll | 390 ++++++------------
 3 files changed, 382 insertions(+), 564 deletions(-)

diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index b5b8b68291786dc..a0e42a183f1d90d 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -1406,9 +1406,30 @@ static std::optional<Instruction *> instCombineSVEAllActive(IntrinsicInst &II,
   return &II;
 }
 
+// Optimize operations that take an all false predicate or send them for
+// canonicalization.
+static std::optional<Instruction *>
+instCombineSVEAllOrNoActive(InstCombiner &IC, IntrinsicInst &II,
+                            Intrinsic::ID IID) {
+  if (match(II.getOperand(0), m_ZeroInt())) {
+    if (II.getIntrinsicID() != IID)
+      // llvm_ir, pred(0), op1, op2 - Spec says to return op1 when all lanes are
+      // inactive for sv[func]_m or sv[func]_z
+      return IC.replaceInstUsesWith(II, II.getOperand(1));
+    else
+      // llvm_ir_u, pred(0), op1, op2 - Spec says to return undef when all lanes
+      // are inactive for sv[func]_x
+      return IC.replaceInstUsesWith(II, UndefValue::get(II.getType()));
+  }
+  if (II.getIntrinsicID() != IID)
+    return instCombineSVEAllActive(II, IID);
+  return std::nullopt;
+}
+
 static std::optional<Instruction *> instCombineSVEVectorAdd(InstCombiner &IC,
                                                             IntrinsicInst &II) {
-  if (auto II_U = instCombineSVEAllActive(II, Intrinsic::aarch64_sve_add_u))
+  if (auto II_U =
+          instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_add_u))
     return II_U;
   if (auto MLA = instCombineSVEVectorFuseMulAddSub<Intrinsic::aarch64_sve_mul,
                                                    Intrinsic::aarch64_sve_mla>(
@@ -1421,9 +1442,22 @@ static std::optional<Instruction *> instCombineSVEVectorAdd(InstCombiner &IC,
   return std::nullopt;
 }
 
+static std::optional<Instruction *>
+instCombineSVEVectorAddU(InstCombiner &IC, IntrinsicInst &II) {
+  if (auto II_U =
+          instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_add_u))
+    return II_U;
+  else {
+    return instCombineSVEVectorFuseMulAddSub<Intrinsic::aarch64_sve_mul_u,
+                                             Intrinsic::aarch64_sve_mla_u>(
+        IC, II, true);
+  }
+}
+
 static std::optional<Instruction *>
 instCombineSVEVectorFAdd(InstCombiner &IC, IntrinsicInst &II) {
-  if (auto II_U = instCombineSVEAllActive(II, Intrinsic::aarch64_sve_fadd_u))
+  if (auto II_U =
+          instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_fadd_u))
     return II_U;
   if (auto FMLA =
           instCombineSVEVectorFuseMulAddSub<Intrinsic::aarch64_sve_fmul,
@@ -1445,6 +1479,9 @@ instCombineSVEVectorFAdd(InstCombiner &IC, IntrinsicInst &II) {
 
 static std::optional<Instruction *>
 instCombineSVEVectorFAddU(InstCombiner &IC, IntrinsicInst &II) {
+  if (auto II_U =
+          instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_fadd_u))
+    return II_U;
   if (auto FMLA =
           instCombineSVEVectorFuseMulAddSub<Intrinsic::aarch64_sve_fmul,
                                             Intrinsic::aarch64_sve_fmla>(IC, II,
@@ -1465,7 +1502,8 @@ instCombineSVEVectorFAddU(InstCombiner &IC, IntrinsicInst &II) {
 
 static std::optional<Instruction *>
 instCombineSVEVectorFSub(InstCombiner &IC, IntrinsicInst &II) {
-  if (auto II_U = instCombineSVEAllActive(II, Intrinsic::aarch64_sve_fsub_u))
+  if (auto II_U =
+          instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_fsub_u))
     return II_U;
   if (auto FMLS =
           instCombineSVEVectorFuseMulAddSub<Intrinsic::aarch64_sve_fmul,
@@ -1487,6 +1525,9 @@ instCombineSVEVectorFSub(InstCombiner &IC, IntrinsicInst &II) {
 
 static std::optional<Instruction *>
 instCombineSVEVectorFSubU(InstCombiner &IC, IntrinsicInst &II) {
+  if (auto II_U =
+          instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_fsub_u))
+    return II_U;
   if (auto FMLS =
           instCombineSVEVectorFuseMulAddSub<Intrinsic::aarch64_sve_fmul,
                                             Intrinsic::aarch64_sve_fmls>(IC, II,
@@ -1507,7 +1548,8 @@ instCombineSVEVectorFSubU(InstCombiner &IC, IntrinsicInst &II) {
 
 static std::optional<Instruction *> instCombineSVEVectorSub(InstCombiner &IC,
                                                             IntrinsicInst &II) {
-  if (auto II_U = instCombineSVEAllActive(II, Intrinsic::aarch64_sve_sub_u))
+  if (auto II_U =
+          instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_sub_u))
     return II_U;
   if (auto MLS = instCombineSVEVectorFuseMulAddSub<Intrinsic::aarch64_sve_mul,
                                                    Intrinsic::aarch64_sve_mls>(
@@ -1516,6 +1558,18 @@ static std::optional<Instruction *> instCombineSVEVectorSub(InstCombiner &IC,
   return std::nullopt;
 }
 
+static std::optional<Instruction *>
+instCombineSVEVectorSubU(InstCombiner &IC, IntrinsicInst &II) {
+  if (auto II_U =
+          instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_sub_u))
+    return II_U;
+  else {
+    return instCombineSVEVectorFuseMulAddSub<Intrinsic::aarch64_sve_mul_u,
+                                             Intrinsic::aarch64_sve_mls_u>(
+        IC, II, true);
+  }
+}
+
 static std::optional<Instruction *> instCombineSVEVectorMul(InstCombiner &IC,
                                                             IntrinsicInst &II,
                                                             Intrinsic::ID IID) {
@@ -1523,10 +1577,8 @@ static std::optional<Instruction *> instCombineSVEVectorMul(InstCombiner &IC,
   auto *OpMultiplicand = II.getOperand(1);
   auto *OpMultiplier = II.getOperand(2);
 
-  // Canonicalise a non _u intrinsic only.
-  if (II.getIntrinsicID() != IID)
-    if (auto II_U = instCombineSVEAllActive(II, IID))
-      return II_U;
+  if (auto II_U = instCombineSVEAllOrNoActive(IC, II, IID))
+    return II_U;
 
   // Return true if a given instruction is a unit splat value, false otherwise.
   auto IsUnitSplat = [](auto *I) {
@@ -1891,34 +1943,45 @@ AArch64TTIImpl::instCombineIntrinsic(InstCombiner &IC,
   case Intrinsic::aarch64_sve_ptest_last:
     return instCombineSVEPTest(IC, II);
   case Intrinsic::aarch64_sve_fabd:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_fabd_u);
+  case Intrinsic::aarch64_sve_fabd_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_fabd_u);
   case Intrinsic::aarch64_sve_fadd:
     return instCombineSVEVectorFAdd(IC, II);
   case Intrinsic::aarch64_sve_fadd_u:
     return instCombineSVEVectorFAddU(IC, II);
   case Intrinsic::aarch64_sve_fdiv:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_fdiv_u);
+  case Intrinsic::aarch64_sve_fdiv_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_fdiv_u);
   case Intrinsic::aarch64_sve_fmax:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_fmax_u);
+  case Intrinsic::aarch64_sve_fmax_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_fmax_u);
   case Intrinsic::aarch64_sve_fmaxnm:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_fmaxnm_u);
+  case Intrinsic::aarch64_sve_fmaxnm_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_fmaxnm_u);
   case Intrinsic::aarch64_sve_fmin:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_fmin_u);
+  case Intrinsic::aarch64_sve_fmin_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_fmin_u);
   case Intrinsic::aarch64_sve_fminnm:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_fminnm_u);
+  case Intrinsic::aarch64_sve_fminnm_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_fminnm_u);
   case Intrinsic::aarch64_sve_fmla:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_fmla_u);
+  case Intrinsic::aarch64_sve_fmla_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_fmla_u);
   case Intrinsic::aarch64_sve_fmls:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_fmls_u);
+  case Intrinsic::aarch64_sve_fmls_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_fmls_u);
   case Intrinsic::aarch64_sve_fmul:
   case Intrinsic::aarch64_sve_fmul_u:
     return instCombineSVEVectorMul(IC, II, Intrinsic::aarch64_sve_fmul_u);
   case Intrinsic::aarch64_sve_fmulx:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_fmulx_u);
+  case Intrinsic::aarch64_sve_fmulx_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_fmulx_u);
   case Intrinsic::aarch64_sve_fnmla:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_fnmla_u);
+  case Intrinsic::aarch64_sve_fnmla_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_fnmla_u);
   case Intrinsic::aarch64_sve_fnmls:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_fnmls_u);
+  case Intrinsic::aarch64_sve_fnmls_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_fnmls_u);
   case Intrinsic::aarch64_sve_fsub:
     return instCombineSVEVectorFSub(IC, II);
   case Intrinsic::aarch64_sve_fsub_u:
@@ -1926,56 +1989,71 @@ AArch64TTIImpl::instCombineIntrinsic(InstCombiner &IC,
   case Intrinsic::aarch64_sve_add:
     return instCombineSVEVectorAdd(IC, II);
   case Intrinsic::aarch64_sve_add_u:
-    return instCombineSVEVectorFuseMulAddSub<Intrinsic::aarch64_sve_mul_u,
-                                             Intrinsic::aarch64_sve_mla_u>(
-        IC, II, true);
+    return instCombineSVEVectorAddU(IC, II);
   case Intrinsic::aarch64_sve_mla:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_mla_u);
+  case Intrinsic::aarch64_sve_mla_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_mla_u);
   case Intrinsic::aarch64_sve_mls:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_mls_u);
+  case Intrinsic::aarch64_sve_mls_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_mls_u);
   case Intrinsic::aarch64_sve_mul:
   case Intrinsic::aarch64_sve_mul_u:
     return instCombineSVEVectorMul(IC, II, Intrinsic::aarch64_sve_mul_u);
   case Intrinsic::aarch64_sve_sabd:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_sabd_u);
+  case Intrinsic::aarch64_sve_sabd_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_sabd_u);
   case Intrinsic::aarch64_sve_smax:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_smax_u);
+  case Intrinsic::aarch64_sve_smax_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_smax_u);
   case Intrinsic::aarch64_sve_smin:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_smin_u);
+  case Intrinsic::aarch64_sve_smin_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_smin_u);
   case Intrinsic::aarch64_sve_smulh:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_smulh_u);
+  case Intrinsic::aarch64_sve_smulh_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_smulh_u);
   case Intrinsic::aarch64_sve_sub:
     return instCombineSVEVectorSub(IC, II);
   case Intrinsic::aarch64_sve_sub_u:
-    return instCombineSVEVectorFuseMulAddSub<Intrinsic::aarch64_sve_mul_u,
-                                             Intrinsic::aarch64_sve_mls_u>(
-        IC, II, true);
+    return instCombineSVEVectorSubU(IC, II);
   case Intrinsic::aarch64_sve_uabd:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_uabd_u);
+  case Intrinsic::aarch64_sve_uabd_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_uabd_u);
   case Intrinsic::aarch64_sve_umax:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_umax_u);
+  case Intrinsic::aarch64_sve_umax_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_umax_u);
   case Intrinsic::aarch64_sve_umin:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_umin_u);
+  case Intrinsic::aarch64_sve_umin_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_umin_u);
   case Intrinsic::aarch64_sve_umulh:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_umulh_u);
+  case Intrinsic::aarch64_sve_umulh_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_umulh_u);
   case Intrinsic::aarch64_sve_asr:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_asr_u);
+  case Intrinsic::aarch64_sve_asr_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_asr_u);
   case Intrinsic::aarch64_sve_lsl:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_lsl_u);
+  case Intrinsic::aarch64_sve_lsl_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_lsl_u);
   case Intrinsic::aarch64_sve_lsr:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_lsr_u);
+  case Intrinsic::aarch64_sve_lsr_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_lsr_u);
   case Intrinsic::aarch64_sve_and:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_and_u);
+  case Intrinsic::aarch64_sve_and_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_and_u);
   case Intrinsic::aarch64_sve_bic:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_bic_u);
+  case Intrinsic::aarch64_sve_bic_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_bic_u);
   case Intrinsic::aarch64_sve_eor:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_eor_u);
+  case Intrinsic::aarch64_sve_eor_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_eor_u);
   case Intrinsic::aarch64_sve_orr:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_orr_u);
+  case Intrinsic::aarch64_sve_orr_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_orr_u);
   case Intrinsic::aarch64_sve_sqsub:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_sqsub_u);
+  case Intrinsic::aarch64_sve_sqsub_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_sqsub_u);
   case Intrinsic::aarch64_sve_uqsub:
-    return instCombineSVEAllActive(II, Intrinsic::aarch64_sve_uqsub_u);
+  case Intrinsic::aarch64_sve_uqsub_u:
+    return instCombineSVEAllOrNoActive(IC, II, Intrinsic::aarch64_sve_uqsub_u);
   case Intrinsic::aarch64_sve_tbl:
     return instCombineSVETBL(IC, II);
   case Intrinsic::aarch64_sve_uunpkhi:
diff --git a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-m-forms-no-active-lanes.ll b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-m-forms-no-active-lanes.ll
index 5ea6fff12134c19..463a5f5d2cfb5c8 100644
--- a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-m-forms-no-active-lanes.ll
+++ b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-m-forms-no-active-lanes.ll
@@ -11,8 +11,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fabd.nxv8f16(<vscale x 8 x i1>, <v
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fabd.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> [[A]]
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fabd.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -22,8 +21,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fabd.nxv4f32(<vscale x 4 x i1>, <
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fabd.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> [[A]]
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fabd.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -33,8 +31,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1>,
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> [[A]]
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -46,8 +43,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1>, <v
 define <vscale x 8 x half> @replace_fadd_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
 ; CHECK-LABEL: define <vscale x 8 x half> @replace_fadd_intrinsic_half
 ; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> [[A]]
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -57,8 +53,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fadd.nxv4f32(<vscale x 4 x i1>, <
 define <vscale x 4 x float> @replace_fadd_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
 ; CHECK-LABEL: define <vscale x 4 x float> @replace_fadd_intrinsic_float
 ; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fadd.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> [[A]]
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fadd.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -68,8 +63,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1>,
 define <vscale x 2 x double> @replace_fadd_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
 ; CHECK-LABEL: define <vscale x 2 x double> @replace_fadd_intrinsic_double
 ; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> [[A]]
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -79,8 +73,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fdiv.nxv8f16(<vscale x 8 x i1>, <v
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fdiv.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> [[A]]
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fdiv.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -90,8 +83,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1>, <
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> [[A]]
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -101,8 +93,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1>,
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> [[A]]
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -112,8 +103,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1>, <v
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> [[A]]
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -123,8 +113,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1>, <
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> [[A]]
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -134,8 +123,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1>,
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> [[A]]
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -145,8 +133,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1>,
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> [[A]]
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -156,8 +143,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1>,
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> [[A]]
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -167,8 +153,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1>
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> [[A]]
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -178,8 +163,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1>, <v
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> [[A]]
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -189,8 +173,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1>, <
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> [[A]]
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -200,8 +183,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1>,
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> [[A]]
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -211,8 +193,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1>,
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> [[A]]
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -222,8 +203,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1>,
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> [[A]]
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -233,8 +213,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1>
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> [[A]]
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -244,8 +223,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1>, <v
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> [[A]]
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
   ret <vscale x 8 x half> %1
@@ -255,8 +233,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1>, <
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> [[A]]
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
   ret <vscale x 4 x float> %1
@@ -266,8 +243,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1>,
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> [[A]]
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
   ret <vscale x 2 x double> %1
@@ -277,8 +253,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1>, <v
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> [[A]]
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
   ret <vscale x 8 x half> %1
@@ -288,8 +263,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1>, <
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> [[A]]
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
   ret <vscale x 4 x float> %1
@@ -299,8 +273,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1>,
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> [[A]]
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
   ret <vscale x 2 x double> %1
@@ -312,8 +285,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1>, <v
 define <vscale x 8 x half> @replace_fmul_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
 ; CHECK-LABEL: define <vscale x 8 x half> @replace_fmul_intrinsic_half
 ; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> [[A]]
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -323,8 +295,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1>, <
 define <vscale x 4 x float> @replace_fmul_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
 ; CHECK-LABEL: define <vscale x 4 x float> @replace_fmul_intrinsic_float
 ; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> [[A]]
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -334,8 +305,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1>,
 define <vscale x 2 x double> @replace_fmul_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
 ; CHECK-LABEL: define <vscale x 2 x double> @replace_fmul_intrinsic_double
 ; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> [[A]]
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -345,8 +315,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fmulx.nxv8f16(<vscale x 8 x i1>, <
 define <vscale x 8 x half> @replace_fmulx_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
 ; CHECK-LABEL: define <vscale x 8 x half> @replace_fmulx_intrinsic_half
 ; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmulx.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> [[A]]
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmulx.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -356,8 +325,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fmulx.nxv4f32(<vscale x 4 x i1>,
 define <vscale x 4 x float> @replace_fmulx_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
 ; CHECK-LABEL: define <vscale x 4 x float> @replace_fmulx_intrinsic_float
 ; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmulx.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> [[A]]
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmulx.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -367,8 +335,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fmulx.nxv2f64(<vscale x 2 x i1>,
 define <vscale x 2 x double> @replace_fmulx_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
 ; CHECK-LABEL: define <vscale x 2 x double> @replace_fmulx_intrinsic_double
 ; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmulx.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> [[A]]
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmulx.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -378,8 +345,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1>, <
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> [[A]]
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
   ret <vscale x 8 x half> %1
@@ -389,8 +355,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1>,
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> [[A]]
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
   ret <vscale x 4 x float> %1
@@ -400,8 +365,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1>,
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> [[A]]
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
   ret <vscale x 2 x double> %1
@@ -411,8 +375,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1>, <
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> [[A]]
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
   ret <vscale x 8 x half> %1
@@ -422,8 +385,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1>,
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> [[A]]
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
   ret <vscale x 4 x float> %1
@@ -433,8 +395,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1>,
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> [[A]]
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
   ret <vscale x 2 x double> %1
@@ -446,8 +407,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fsub.nxv8f16(<vscale x 8 x i1>, <v
 define <vscale x 8 x half> @replace_fsub_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
 ; CHECK-LABEL: define <vscale x 8 x half> @replace_fsub_intrinsic_half
 ; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fsub.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> [[A]]
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fsub.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -457,8 +417,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1>, <
 define <vscale x 4 x float> @replace_fsub_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
 ; CHECK-LABEL: define <vscale x 4 x float> @replace_fsub_intrinsic_float
 ; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> [[A]]
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -468,8 +427,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1>,
 define <vscale x 2 x double> @replace_fsub_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
 ; CHECK-LABEL: define <vscale x 2 x double> @replace_fsub_intrinsic_double
 ; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> [[A]]
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -481,8 +439,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1>, <vs
 define <vscale x 16 x i8> @replace_add_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
 ; CHECK-LABEL: define <vscale x 16 x i8> @replace_add_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 i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -492,8 +449,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1>, <vsc
 define <vscale x 8 x i16> @replace_add_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
 ; CHECK-LABEL: define <vscale x 8 x i16> @replace_add_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 i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -503,8 +459,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1>, <vsc
 define <vscale x 4 x i32> @replace_add_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
 ; CHECK-LABEL: define <vscale x 4 x i32> @replace_add_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 i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -514,8 +469,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1>, <vsc
 define <vscale x 2 x i64> @replace_add_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
 ; CHECK-LABEL: define <vscale x 2 x i64> @replace_add_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 i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -525,8 +479,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1>, <vs
 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 i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]], <vscale x 16 x i8> [[C]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
   ret <vscale x 16 x i8> %1
@@ -536,8 +489,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1>, <vsc
 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 i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]], <vscale x 8 x i16> [[C]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
   ret <vscale x 8 x i16> %1
@@ -547,8 +499,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1>, <vsc
 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 i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]], <vscale x 4 x i32> [[C]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
   ret <vscale x 4 x i32> %1
@@ -558,8 +509,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1>, <vsc
 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 i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
   ret <vscale x 2 x i64> %1
@@ -569,8 +519,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1>, <vs
 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 i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]], <vscale x 16 x i8> [[C]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
   ret <vscale x 16 x i8> %1
@@ -580,8 +529,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1>, <vsc
 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 i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]], <vscale x 8 x i16> [[C]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
   ret <vscale x 8 x i16> %1
@@ -591,8 +539,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1>, <vsc
 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 i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]], <vscale x 4 x i32> [[C]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
   ret <vscale x 4 x i32> %1
@@ -602,8 +549,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1>, <vsc
 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 i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
   ret <vscale x 2 x i64> %1
@@ -613,8 +559,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1>, <vs
 define <vscale x 16 x i8> @replace_mul_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
 ; CHECK-LABEL: define <vscale x 16 x i8> @replace_mul_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 i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -624,8 +569,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1>, <vsc
 define <vscale x 8 x i16> @replace_mul_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
 ; CHECK-LABEL: define <vscale x 8 x i16> @replace_mul_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 i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -635,8 +579,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1>, <vsc
 define <vscale x 4 x i32> @replace_mul_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
 ; CHECK-LABEL: define <vscale x 4 x i32> @replace_mul_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 i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -646,8 +589,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1>, <vsc
 define <vscale x 2 x i64> @replace_mul_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
 ; CHECK-LABEL: define <vscale x 2 x i64> @replace_mul_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 i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -657,8 +599,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.sabd.nxv16i8(<vscale x 16 x i1>, <v
 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 i8> @llvm.aarch64.sve.sabd.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.sabd.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -668,8 +609,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.sabd.nxv8i16(<vscale x 8 x i1>, <vs
 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 i16> @llvm.aarch64.sve.sabd.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sabd.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -679,8 +619,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.sabd.nxv4i32(<vscale x 4 x i1>, <vs
 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 i32> @llvm.aarch64.sve.sabd.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.sabd.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -690,8 +629,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1>, <vs
 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 i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -701,8 +639,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.smax.nxv16i8(<vscale x 16 x i1>, <v
 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 i8> @llvm.aarch64.sve.smax.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.smax.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -712,8 +649,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.smax.nxv8i16(<vscale x 8 x i1>, <vs
 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 i16> @llvm.aarch64.sve.smax.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.smax.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -723,8 +659,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.smax.nxv4i32(<vscale x 4 x i1>, <vs
 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 i32> @llvm.aarch64.sve.smax.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smax.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -734,8 +669,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.smax.nxv2i64(<vscale x 2 x i1>, <vs
 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 i64> @llvm.aarch64.sve.smax.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smax.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -745,8 +679,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.smin.nxv16i8(<vscale x 16 x i1>, <v
 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 i8> @llvm.aarch64.sve.smin.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.smin.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -756,8 +689,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.smin.nxv8i16(<vscale x 8 x i1>, <vs
 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 i16> @llvm.aarch64.sve.smin.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.smin.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -767,8 +699,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.smin.nxv4i32(<vscale x 4 x i1>, <vs
 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 i32> @llvm.aarch64.sve.smin.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smin.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -778,8 +709,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.smin.nxv2i64(<vscale x 2 x i1>, <vs
 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 i64> @llvm.aarch64.sve.smin.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smin.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -789,8 +719,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.smulh.nxv16i8(<vscale x 16 x i1>, <
 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 i8> @llvm.aarch64.sve.smulh.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.smulh.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -800,8 +729,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.smulh.nxv8i16(<vscale x 8 x i1>, <v
 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 i16> @llvm.aarch64.sve.smulh.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.smulh.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -811,8 +739,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.smulh.nxv4i32(<vscale x 4 x i1>, <v
 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 i32> @llvm.aarch64.sve.smulh.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smulh.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -822,8 +749,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.smulh.nxv2i64(<vscale x 2 x i1>, <v
 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 i64> @llvm.aarch64.sve.smulh.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smulh.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -833,8 +759,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1>, <vs
 define <vscale x 16 x i8> @replace_sub_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
 ; CHECK-LABEL: define <vscale x 16 x i8> @replace_sub_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 i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -844,8 +769,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1>, <vsc
 define <vscale x 8 x i16> @replace_sub_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
 ; CHECK-LABEL: define <vscale x 8 x i16> @replace_sub_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 i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -855,8 +779,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1>, <vsc
 define <vscale x 4 x i32> @replace_sub_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
 ; CHECK-LABEL: define <vscale x 4 x i32> @replace_sub_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 i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -866,8 +789,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1>, <vsc
 define <vscale x 2 x i64> @replace_sub_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
 ; CHECK-LABEL: define <vscale x 2 x i64> @replace_sub_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 i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -877,8 +799,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.uabd.nxv16i8(<vscale x 16 x i1>, <v
 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 i8> @llvm.aarch64.sve.uabd.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.uabd.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -888,8 +809,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.uabd.nxv8i16(<vscale x 8 x i1>, <vs
 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 i16> @llvm.aarch64.sve.uabd.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.uabd.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -899,8 +819,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.uabd.nxv4i32(<vscale x 4 x i1>, <vs
 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 i32> @llvm.aarch64.sve.uabd.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.uabd.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -910,8 +829,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1>, <vs
 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 i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -921,8 +839,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.umax.nxv16i8(<vscale x 16 x i1>, <v
 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 i8> @llvm.aarch64.sve.umax.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.umax.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -932,8 +849,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.umax.nxv8i16(<vscale x 8 x i1>, <vs
 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 i16> @llvm.aarch64.sve.umax.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.umax.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -943,8 +859,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.umax.nxv4i32(<vscale x 4 x i1>, <vs
 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 i32> @llvm.aarch64.sve.umax.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.umax.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -954,8 +869,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.umax.nxv2i64(<vscale x 2 x i1>, <vs
 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 i64> @llvm.aarch64.sve.umax.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umax.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -965,8 +879,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.umin.nxv16i8(<vscale x 16 x i1>, <v
 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 i8> @llvm.aarch64.sve.umin.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.umin.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -976,8 +889,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.umin.nxv8i16(<vscale x 8 x i1>, <vs
 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 i16> @llvm.aarch64.sve.umin.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.umin.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -987,8 +899,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.umin.nxv4i32(<vscale x 4 x i1>, <vs
 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 i32> @llvm.aarch64.sve.umin.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.umin.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -998,8 +909,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1>, <vs
 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 i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1009,8 +919,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.umulh.nxv16i8(<vscale x 16 x i1>, <
 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 i8> @llvm.aarch64.sve.umulh.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.umulh.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1020,8 +929,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.umulh.nxv8i16(<vscale x 8 x i1>, <v
 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 i16> @llvm.aarch64.sve.umulh.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.umulh.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1031,8 +939,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.umulh.nxv4i32(<vscale x 4 x i1>, <v
 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 i32> @llvm.aarch64.sve.umulh.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.umulh.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1042,8 +949,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.umulh.nxv2i64(<vscale x 2 x i1>, <v
 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 i64> @llvm.aarch64.sve.umulh.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umulh.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1055,8 +961,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.asr.nxv16i8(<vscale x 16 x i1>, <vs
 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 i8> @llvm.aarch64.sve.asr.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.asr.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1066,8 +971,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.asr.nxv8i16(<vscale x 8 x i1>, <vsc
 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 i16> @llvm.aarch64.sve.asr.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.asr.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1077,8 +981,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.asr.nxv4i32(<vscale x 4 x i1>, <vsc
 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 i32> @llvm.aarch64.sve.asr.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.asr.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1088,8 +991,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.asr.nxv2i64(<vscale x 2 x i1>, <vsc
 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 i64> @llvm.aarch64.sve.asr.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.asr.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1099,8 +1001,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.lsl.nxv16i8(<vscale x 16 x i1>, <vs
 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 i8> @llvm.aarch64.sve.lsl.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.lsl.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1110,8 +1011,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.lsl.nxv8i16(<vscale x 8 x i1>, <vsc
 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 i16> @llvm.aarch64.sve.lsl.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1121,8 +1021,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.lsl.nxv4i32(<vscale x 4 x i1>, <vsc
 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 i32> @llvm.aarch64.sve.lsl.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1132,8 +1031,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.lsl.nxv2i64(<vscale x 2 x i1>, <vsc
 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 i64> @llvm.aarch64.sve.lsl.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.lsl.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1143,8 +1041,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.lsr.nxv16i8(<vscale x 16 x i1>, <vs
 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 i8> @llvm.aarch64.sve.lsr.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.lsr.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1154,8 +1051,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.lsr.nxv8i16(<vscale x 8 x i1>, <vsc
 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 i16> @llvm.aarch64.sve.lsr.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1165,8 +1061,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.lsr.nxv4i32(<vscale x 4 x i1>, <vsc
 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 i32> @llvm.aarch64.sve.lsr.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1176,8 +1071,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.lsr.nxv2i64(<vscale x 2 x i1>, <vsc
 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 i64> @llvm.aarch64.sve.lsr.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.lsr.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1189,8 +1083,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1>, <vs
 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 i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1200,8 +1093,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1>, <vsc
 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 i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1211,8 +1103,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1>, <vsc
 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 i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1222,8 +1113,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1>, <vsc
 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 i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1233,8 +1123,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1>, <vs
 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 i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1244,8 +1133,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1>, <vsc
 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 i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1255,8 +1143,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1>, <vsc
 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 i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1266,8 +1153,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1>, <vsc
 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 i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1277,8 +1163,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1>, <vs
 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 i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1288,8 +1173,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1>, <vsc
 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 i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1299,8 +1183,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1>, <vsc
 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 i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1310,8 +1193,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1>, <vsc
 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 i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1321,8 +1203,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1>, <vs
 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 i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1332,8 +1213,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1>, <vsc
 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 i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1343,8 +1223,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1>, <vsc
 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 i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1354,8 +1233,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1>, <vsc
 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 i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1367,8 +1245,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.nxv16i8(<vscale x 16 x i1>, <
 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 i8> @llvm.aarch64.sve.sqsub.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1378,8 +1255,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.nxv8i16(<vscale x 8 x i1>, <v
 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 i16> @llvm.aarch64.sve.sqsub.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1389,8 +1265,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.nxv4i32(<vscale x 4 x i1>, <v
 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 i32> @llvm.aarch64.sve.sqsub.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1400,8 +1275,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.nxv2i64(<vscale x 2 x i1>, <v
 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 i64> @llvm.aarch64.sve.sqsub.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1411,8 +1285,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.nxv16i8(<vscale x 16 x i1>, <
 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 i8> @llvm.aarch64.sve.uqsub.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> [[A]]
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1422,8 +1295,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.nxv8i16(<vscale x 8 x i1>, <v
 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 i16> @llvm.aarch64.sve.uqsub.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[A]]
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1433,8 +1305,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.nxv4i32(<vscale x 4 x i1>, <v
 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 i32> @llvm.aarch64.sve.uqsub.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[A]]
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1444,8 +1315,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.nxv2i64(<vscale x 2 x i1>, <v
 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 i64> @llvm.aarch64.sve.uqsub.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[A]]
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
diff --git a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-u-forms-no-active-lanes.ll b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-u-forms-no-active-lanes.ll
index d3e51231fb52c04..7a01dce5e212836 100644
--- a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-u-forms-no-active-lanes.ll
+++ b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-u-forms-no-active-lanes.ll
@@ -11,8 +11,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fabd.u.nxv8f16(<vscale x 8 x i1>,
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fabd.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> undef
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fabd.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -22,8 +21,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fabd.u.nxv4f32(<vscale x 4 x i1>,
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fabd.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> undef
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fabd.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -33,8 +31,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fabd.u.nxv2f64(<vscale x 2 x i1>
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fabd.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> undef
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fabd.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -44,8 +41,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fadd.u.nxv8f16(<vscale x 8 x i1>,
 define <vscale x 8 x half> @replace_fadd_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
 ; CHECK-LABEL: define <vscale x 8 x half> @replace_fadd_intrinsic_half
 ; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fadd.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> undef
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fadd.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -55,8 +51,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fadd.u.nxv4f32(<vscale x 4 x i1>,
 define <vscale x 4 x float> @replace_fadd_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
 ; CHECK-LABEL: define <vscale x 4 x float> @replace_fadd_intrinsic_float
 ; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fadd.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> undef
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fadd.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -66,8 +61,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fadd.u.nxv2f64(<vscale x 2 x i1>
 define <vscale x 2 x double> @replace_fadd_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
 ; CHECK-LABEL: define <vscale x 2 x double> @replace_fadd_intrinsic_double
 ; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fadd.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> undef
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fadd.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -77,8 +71,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fdiv.u.nxv8f16(<vscale x 8 x i1>,
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fdiv.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> undef
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fdiv.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -88,8 +81,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fdiv.u.nxv4f32(<vscale x 4 x i1>,
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fdiv.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> undef
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fdiv.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -99,8 +91,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fdiv.u.nxv2f64(<vscale x 2 x i1>
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fdiv.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> undef
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fdiv.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -110,8 +101,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fmax.u.nxv8f16(<vscale x 8 x i1>,
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmax.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> undef
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmax.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -121,8 +111,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fmax.u.nxv4f32(<vscale x 4 x i1>,
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmax.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> undef
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmax.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -132,8 +121,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fmax.u.nxv2f64(<vscale x 2 x i1>
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmax.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> undef
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmax.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -143,8 +131,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.u.nxv8f16(<vscale x 8 x i1>
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> undef
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -154,8 +141,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.u.nxv4f32(<vscale x 4 x i1
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> undef
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -165,8 +151,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.u.nxv2f64(<vscale x 2 x i
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> undef
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -176,8 +161,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fmin.u.nxv8f16(<vscale x 8 x i1>,
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmin.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> undef
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmin.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -187,8 +171,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fmin.u.nxv4f32(<vscale x 4 x i1>,
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmin.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> undef
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmin.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -198,8 +181,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fmin.u.nxv2f64(<vscale x 2 x i1>
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmin.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> undef
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmin.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -209,8 +191,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fminnm.u.nxv8f16(<vscale x 8 x i1>
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fminnm.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> undef
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fminnm.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -220,8 +201,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fminnm.u.nxv4f32(<vscale x 4 x i1
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fminnm.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> undef
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fminnm.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -231,8 +211,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fminnm.u.nxv2f64(<vscale x 2 x i
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fminnm.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> undef
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fminnm.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -242,8 +221,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fmla.u.nxv8f16(<vscale x 8 x i1>,
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmla.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> undef
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmla.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
   ret <vscale x 8 x half> %1
@@ -253,8 +231,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fmla.u.nxv4f32(<vscale x 4 x i1>,
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmla.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> undef
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmla.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
   ret <vscale x 4 x float> %1
@@ -264,8 +241,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fmla.u.nxv2f64(<vscale x 2 x i1>
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmla.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> undef
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmla.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
   ret <vscale x 2 x double> %1
@@ -275,8 +251,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fmls.u.nxv8f16(<vscale x 8 x i1>,
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fmls.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> undef
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmls.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
   ret <vscale x 8 x half> %1
@@ -286,8 +261,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fmls.u.nxv4f32(<vscale x 4 x i1>,
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fmls.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> undef
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmls.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
   ret <vscale x 4 x float> %1
@@ -297,8 +271,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fmls.u.nxv2f64(<vscale x 2 x i1>
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fmls.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> undef
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmls.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
   ret <vscale x 2 x double> %1
@@ -308,8 +281,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fmul.u.nxv8f16(<vscale x 8 x i1>,
 define <vscale x 8 x half> @replace_fmul_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
 ; CHECK-LABEL: define <vscale x 8 x half> @replace_fmul_intrinsic_half
 ; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmul.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> undef
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmul.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -319,8 +291,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fmul.u.nxv4f32(<vscale x 4 x i1>,
 define <vscale x 4 x float> @replace_fmul_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
 ; CHECK-LABEL: define <vscale x 4 x float> @replace_fmul_intrinsic_float
 ; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmul.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> undef
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmul.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -330,8 +301,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fmul.u.nxv2f64(<vscale x 2 x i1>
 define <vscale x 2 x double> @replace_fmul_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
 ; CHECK-LABEL: define <vscale x 2 x double> @replace_fmul_intrinsic_double
 ; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmul.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> undef
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmul.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -341,8 +311,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fmulx.u.nxv8f16(<vscale x 8 x i1>,
 define <vscale x 8 x half> @replace_fmulx_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
 ; CHECK-LABEL: define <vscale x 8 x half> @replace_fmulx_intrinsic_half
 ; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmulx.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> undef
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fmulx.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -352,8 +321,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fmulx.u.nxv4f32(<vscale x 4 x i1>
 define <vscale x 4 x float> @replace_fmulx_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
 ; CHECK-LABEL: define <vscale x 4 x float> @replace_fmulx_intrinsic_float
 ; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmulx.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> undef
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fmulx.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -363,8 +331,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fmulx.u.nxv2f64(<vscale x 2 x i1
 define <vscale x 2 x double> @replace_fmulx_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
 ; CHECK-LABEL: define <vscale x 2 x double> @replace_fmulx_intrinsic_double
 ; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmulx.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> undef
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fmulx.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -374,8 +341,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fnmla.u.nxv8f16(<vscale x 8 x i1>,
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fnmla.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> undef
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fnmla.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
   ret <vscale x 8 x half> %1
@@ -385,8 +351,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fnmla.u.nxv4f32(<vscale x 4 x i1>
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fnmla.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> undef
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fnmla.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
   ret <vscale x 4 x float> %1
@@ -396,8 +361,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fnmla.u.nxv2f64(<vscale x 2 x i1
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fnmla.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> undef
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fnmla.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
   ret <vscale x 2 x double> %1
@@ -407,8 +371,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fnmls.u.nxv8f16(<vscale x 8 x i1>,
 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 fast <vscale x 8 x half> @llvm.aarch64.sve.fnmls.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]], <vscale x 8 x half> [[C]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> undef
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fnmls.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c)
   ret <vscale x 8 x half> %1
@@ -418,8 +381,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fnmls.u.nxv4f32(<vscale x 4 x i1>
 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 fast <vscale x 4 x float> @llvm.aarch64.sve.fnmls.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]], <vscale x 4 x float> [[C]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> undef
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fnmls.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
   ret <vscale x 4 x float> %1
@@ -429,8 +391,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fnmls.u.nxv2f64(<vscale x 2 x i1
 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 fast <vscale x 2 x double> @llvm.aarch64.sve.fnmls.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> undef
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fnmls.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
   ret <vscale x 2 x double> %1
@@ -440,8 +401,7 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fsub.u.nxv8f16(<vscale x 8 x i1>,
 define <vscale x 8 x half> @replace_fsub_intrinsic_half(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
 ; CHECK-LABEL: define <vscale x 8 x half> @replace_fsub_intrinsic_half
 ; CHECK-SAME: (<vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fsub.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> [[A]], <vscale x 8 x half> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x half> undef
 ;
   %1 = tail call fast <vscale x 8 x half> @llvm.aarch64.sve.fsub.u.nxv8f16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
   ret <vscale x 8 x half> %1
@@ -451,8 +411,7 @@ declare <vscale x 4 x float> @llvm.aarch64.sve.fsub.u.nxv4f32(<vscale x 4 x i1>,
 define <vscale x 4 x float> @replace_fsub_intrinsic_float(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
 ; CHECK-LABEL: define <vscale x 4 x float> @replace_fsub_intrinsic_float
 ; CHECK-SAME: (<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fsub.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> [[A]], <vscale x 4 x float> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x float> undef
 ;
   %1 = tail call fast <vscale x 4 x float> @llvm.aarch64.sve.fsub.u.nxv4f32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
   ret <vscale x 4 x float> %1
@@ -462,8 +421,7 @@ declare <vscale x 2 x double> @llvm.aarch64.sve.fsub.u.nxv2f64(<vscale x 2 x i1>
 define <vscale x 2 x double> @replace_fsub_intrinsic_double(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
 ; CHECK-LABEL: define <vscale x 2 x double> @replace_fsub_intrinsic_double
 ; CHECK-SAME: (<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]]) #[[ATTR1]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fsub.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> [[A]], <vscale x 2 x double> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x double> undef
 ;
   %1 = tail call fast <vscale x 2 x double> @llvm.aarch64.sve.fsub.u.nxv2f64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 2 x double> %1
@@ -475,8 +433,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.add.u.nxv16i8(<vscale x 16 x i1>, <
 define <vscale x 16 x i8> @replace_add_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
 ; CHECK-LABEL: define <vscale x 16 x i8> @replace_add_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 i8> @llvm.aarch64.sve.add.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.add.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -486,8 +443,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.add.u.nxv8i16(<vscale x 8 x i1>, <v
 define <vscale x 8 x i16> @replace_add_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
 ; CHECK-LABEL: define <vscale x 8 x i16> @replace_add_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 i16> @llvm.aarch64.sve.add.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.add.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -497,8 +453,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.add.u.nxv4i32(<vscale x 4 x i1>, <v
 define <vscale x 4 x i32> @replace_add_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
 ; CHECK-LABEL: define <vscale x 4 x i32> @replace_add_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 i32> @llvm.aarch64.sve.add.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.add.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -508,8 +463,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.add.u.nxv2i64(<vscale x 2 x i1>, <v
 define <vscale x 2 x i64> @replace_add_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
 ; CHECK-LABEL: define <vscale x 2 x i64> @replace_add_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 i64> @llvm.aarch64.sve.add.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.add.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -519,8 +473,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.mla.u.nxv16i8(<vscale x 16 x i1>, <
 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 i8> @llvm.aarch64.sve.mla.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]], <vscale x 16 x i8> [[C]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.mla.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
   ret <vscale x 16 x i8> %1
@@ -530,8 +483,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.mla.u.nxv8i16(<vscale x 8 x i1>, <v
 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 i16> @llvm.aarch64.sve.mla.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]], <vscale x 8 x i16> [[C]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.mla.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
   ret <vscale x 8 x i16> %1
@@ -541,8 +493,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.mla.u.nxv4i32(<vscale x 4 x i1>, <v
 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 i32> @llvm.aarch64.sve.mla.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]], <vscale x 4 x i32> [[C]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.mla.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
   ret <vscale x 4 x i32> %1
@@ -552,8 +503,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.mla.u.nxv2i64(<vscale x 2 x i1>, <v
 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 i64> @llvm.aarch64.sve.mla.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mla.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
   ret <vscale x 2 x i64> %1
@@ -563,8 +513,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.mls.u.nxv16i8(<vscale x 16 x i1>, <
 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 i8> @llvm.aarch64.sve.mls.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]], <vscale x 16 x i8> [[C]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.mls.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
   ret <vscale x 16 x i8> %1
@@ -574,8 +523,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.mls.u.nxv8i16(<vscale x 8 x i1>, <v
 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 i16> @llvm.aarch64.sve.mls.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]], <vscale x 8 x i16> [[C]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.mls.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
   ret <vscale x 8 x i16> %1
@@ -585,8 +533,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.mls.u.nxv4i32(<vscale x 4 x i1>, <v
 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 i32> @llvm.aarch64.sve.mls.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]], <vscale x 4 x i32> [[C]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.mls.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
   ret <vscale x 4 x i32> %1
@@ -596,8 +543,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.mls.u.nxv2i64(<vscale x 2 x i1>, <v
 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 i64> @llvm.aarch64.sve.mls.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <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> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mls.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
   ret <vscale x 2 x i64> %1
@@ -607,8 +553,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.mul.u.nxv16i8(<vscale x 16 x i1>, <
 define <vscale x 16 x i8> @replace_mul_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
 ; CHECK-LABEL: define <vscale x 16 x i8> @replace_mul_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 i8> @llvm.aarch64.sve.mul.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.mul.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -618,8 +563,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.mul.u.nxv8i16(<vscale x 8 x i1>, <v
 define <vscale x 8 x i16> @replace_mul_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
 ; CHECK-LABEL: define <vscale x 8 x i16> @replace_mul_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 i16> @llvm.aarch64.sve.mul.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.mul.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -629,8 +573,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.mul.u.nxv4i32(<vscale x 4 x i1>, <v
 define <vscale x 4 x i32> @replace_mul_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
 ; CHECK-LABEL: define <vscale x 4 x i32> @replace_mul_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 i32> @llvm.aarch64.sve.mul.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.mul.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -640,8 +583,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.mul.u.nxv2i64(<vscale x 2 x i1>, <v
 define <vscale x 2 x i64> @replace_mul_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
 ; CHECK-LABEL: define <vscale x 2 x i64> @replace_mul_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 i64> @llvm.aarch64.sve.mul.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.mul.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -651,8 +593,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.sabd.u.nxv16i8(<vscale x 16 x i1>,
 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 i8> @llvm.aarch64.sve.sabd.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.sabd.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -662,8 +603,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.sabd.u.nxv8i16(<vscale x 8 x i1>, <
 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 i16> @llvm.aarch64.sve.sabd.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sabd.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -673,8 +613,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.sabd.u.nxv4i32(<vscale x 4 x i1>, <
 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 i32> @llvm.aarch64.sve.sabd.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.sabd.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -684,8 +623,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.sabd.u.nxv2i64(<vscale x 2 x i1>, <
 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 i64> @llvm.aarch64.sve.sabd.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -695,8 +633,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.smax.u.nxv16i8(<vscale x 16 x i1>,
 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 i8> @llvm.aarch64.sve.smax.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.smax.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -706,8 +643,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.smax.u.nxv8i16(<vscale x 8 x i1>, <
 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 i16> @llvm.aarch64.sve.smax.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.smax.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -717,8 +653,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.smax.u.nxv4i32(<vscale x 4 x i1>, <
 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 i32> @llvm.aarch64.sve.smax.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smax.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -728,8 +663,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.smax.u.nxv2i64(<vscale x 2 x i1>, <
 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 i64> @llvm.aarch64.sve.smax.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smax.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -739,8 +673,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.smin.u.nxv16i8(<vscale x 16 x i1>,
 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 i8> @llvm.aarch64.sve.smin.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.smin.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -750,8 +683,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.smin.u.nxv8i16(<vscale x 8 x i1>, <
 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 i16> @llvm.aarch64.sve.smin.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.smin.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -761,8 +693,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.smin.u.nxv4i32(<vscale x 4 x i1>, <
 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 i32> @llvm.aarch64.sve.smin.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smin.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -772,8 +703,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.smin.u.nxv2i64(<vscale x 2 x i1>, <
 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 i64> @llvm.aarch64.sve.smin.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smin.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -783,8 +713,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.smulh.u.nxv16i8(<vscale x 16 x i1>,
 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 i8> @llvm.aarch64.sve.smulh.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.smulh.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -794,8 +723,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.smulh.u.nxv8i16(<vscale x 8 x i1>,
 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 i16> @llvm.aarch64.sve.smulh.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.smulh.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -805,8 +733,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.smulh.u.nxv4i32(<vscale x 4 x i1>,
 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 i32> @llvm.aarch64.sve.smulh.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smulh.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -816,8 +743,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.smulh.u.nxv2i64(<vscale x 2 x i1>,
 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 i64> @llvm.aarch64.sve.smulh.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.smulh.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -827,8 +753,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.sub.u.nxv16i8(<vscale x 16 x i1>, <
 define <vscale x 16 x i8> @replace_sub_intrinsic_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
 ; CHECK-LABEL: define <vscale x 16 x i8> @replace_sub_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 i8> @llvm.aarch64.sve.sub.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.sub.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -838,8 +763,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.sub.u.nxv8i16(<vscale x 8 x i1>, <v
 define <vscale x 8 x i16> @replace_sub_intrinsic_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
 ; CHECK-LABEL: define <vscale x 8 x i16> @replace_sub_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 i16> @llvm.aarch64.sve.sub.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sub.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -849,8 +773,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.sub.u.nxv4i32(<vscale x 4 x i1>, <v
 define <vscale x 4 x i32> @replace_sub_intrinsic_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
 ; CHECK-LABEL: define <vscale x 4 x i32> @replace_sub_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 i32> @llvm.aarch64.sve.sub.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.sub.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -860,8 +783,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.sub.u.nxv2i64(<vscale x 2 x i1>, <v
 define <vscale x 2 x i64> @replace_sub_intrinsic_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
 ; CHECK-LABEL: define <vscale x 2 x i64> @replace_sub_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 i64> @llvm.aarch64.sve.sub.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sub.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -871,8 +793,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.uabd.u.nxv16i8(<vscale x 16 x i1>,
 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 i8> @llvm.aarch64.sve.uabd.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.uabd.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -882,8 +803,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.uabd.u.nxv8i16(<vscale x 8 x i1>, <
 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 i16> @llvm.aarch64.sve.uabd.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.uabd.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -893,8 +813,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.uabd.u.nxv4i32(<vscale x 4 x i1>, <
 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 i32> @llvm.aarch64.sve.uabd.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.uabd.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -904,8 +823,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.uabd.u.nxv2i64(<vscale x 2 x i1>, <
 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 i64> @llvm.aarch64.sve.uabd.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -915,8 +833,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.umax.u.nxv16i8(<vscale x 16 x i1>,
 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 i8> @llvm.aarch64.sve.umax.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.umax.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -926,8 +843,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.umax.u.nxv8i16(<vscale x 8 x i1>, <
 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 i16> @llvm.aarch64.sve.umax.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.umax.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -937,8 +853,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.umax.u.nxv4i32(<vscale x 4 x i1>, <
 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 i32> @llvm.aarch64.sve.umax.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.umax.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -948,8 +863,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.umax.u.nxv2i64(<vscale x 2 x i1>, <
 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 i64> @llvm.aarch64.sve.umax.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umax.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -959,8 +873,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.umin.u.nxv16i8(<vscale x 16 x i1>,
 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 i8> @llvm.aarch64.sve.umin.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.umin.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -970,8 +883,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.umin.u.nxv8i16(<vscale x 8 x i1>, <
 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 i16> @llvm.aarch64.sve.umin.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.umin.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -981,8 +893,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.umin.u.nxv4i32(<vscale x 4 x i1>, <
 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 i32> @llvm.aarch64.sve.umin.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.umin.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -992,8 +903,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.umin.u.nxv2i64(<vscale x 2 x i1>, <
 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 i64> @llvm.aarch64.sve.umin.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umin.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1003,8 +913,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.umulh.u.nxv16i8(<vscale x 16 x i1>,
 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 i8> @llvm.aarch64.sve.umulh.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.umulh.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1014,8 +923,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.umulh.u.nxv8i16(<vscale x 8 x i1>,
 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 i16> @llvm.aarch64.sve.umulh.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.umulh.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1025,8 +933,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.umulh.u.nxv4i32(<vscale x 4 x i1>,
 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 i32> @llvm.aarch64.sve.umulh.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.umulh.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1036,8 +943,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.umulh.u.nxv2i64(<vscale x 2 x i1>,
 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 i64> @llvm.aarch64.sve.umulh.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.umulh.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1049,8 +955,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.asr.u.nxv16i8(<vscale x 16 x i1>, <
 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 i8> @llvm.aarch64.sve.asr.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.asr.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1060,8 +965,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.asr.u.nxv8i16(<vscale x 8 x i1>, <v
 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 i16> @llvm.aarch64.sve.asr.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.asr.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1071,8 +975,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.asr.u.nxv4i32(<vscale x 4 x i1>, <v
 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 i32> @llvm.aarch64.sve.asr.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.asr.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1082,8 +985,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.asr.u.nxv2i64(<vscale x 2 x i1>, <v
 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 i64> @llvm.aarch64.sve.asr.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.asr.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1093,8 +995,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.lsl.u.nxv16i8(<vscale x 16 x i1>, <
 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 i8> @llvm.aarch64.sve.lsl.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.lsl.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1104,8 +1005,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.lsl.u.nxv8i16(<vscale x 8 x i1>, <v
 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 i16> @llvm.aarch64.sve.lsl.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1115,8 +1015,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.lsl.u.nxv4i32(<vscale x 4 x i1>, <v
 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 i32> @llvm.aarch64.sve.lsl.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1126,8 +1025,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.lsl.u.nxv2i64(<vscale x 2 x i1>, <v
 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 i64> @llvm.aarch64.sve.lsl.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.lsl.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1137,8 +1035,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.lsr.u.nxv16i8(<vscale x 16 x i1>, <
 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 i8> @llvm.aarch64.sve.lsr.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.lsr.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1148,8 +1045,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.lsr.u.nxv8i16(<vscale x 8 x i1>, <v
 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 i16> @llvm.aarch64.sve.lsr.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1159,8 +1055,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.lsr.u.nxv4i32(<vscale x 4 x i1>, <v
 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 i32> @llvm.aarch64.sve.lsr.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1170,8 +1065,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.lsr.u.nxv2i64(<vscale x 2 x i1>, <v
 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 i64> @llvm.aarch64.sve.lsr.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.lsr.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1183,8 +1077,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.and.u.nxv16i8(<vscale x 16 x i1>, <
 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 i8> @llvm.aarch64.sve.and.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.and.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1194,8 +1087,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.and.u.nxv8i16(<vscale x 8 x i1>, <v
 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 i16> @llvm.aarch64.sve.and.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.and.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1205,8 +1097,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.and.u.nxv4i32(<vscale x 4 x i1>, <v
 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 i32> @llvm.aarch64.sve.and.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.and.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1216,8 +1107,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.and.u.nxv2i64(<vscale x 2 x i1>, <v
 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 i64> @llvm.aarch64.sve.and.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.and.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1227,8 +1117,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.bic.u.nxv16i8(<vscale x 16 x i1>, <
 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 i8> @llvm.aarch64.sve.bic.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.bic.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1238,8 +1127,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.bic.u.nxv8i16(<vscale x 8 x i1>, <v
 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 i16> @llvm.aarch64.sve.bic.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.bic.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1249,8 +1137,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.bic.u.nxv4i32(<vscale x 4 x i1>, <v
 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 i32> @llvm.aarch64.sve.bic.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.bic.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1260,8 +1147,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.bic.u.nxv2i64(<vscale x 2 x i1>, <v
 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 i64> @llvm.aarch64.sve.bic.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.bic.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1271,8 +1157,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.eor.u.nxv16i8(<vscale x 16 x i1>, <
 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 i8> @llvm.aarch64.sve.eor.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.eor.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1282,8 +1167,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.eor.u.nxv8i16(<vscale x 8 x i1>, <v
 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 i16> @llvm.aarch64.sve.eor.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.eor.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1293,8 +1177,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.eor.u.nxv4i32(<vscale x 4 x i1>, <v
 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 i32> @llvm.aarch64.sve.eor.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.eor.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1304,8 +1187,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.eor.u.nxv2i64(<vscale x 2 x i1>, <v
 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 i64> @llvm.aarch64.sve.eor.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.eor.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1315,8 +1197,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.orr.u.nxv16i8(<vscale x 16 x i1>, <
 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 i8> @llvm.aarch64.sve.orr.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.orr.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1326,8 +1207,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.orr.u.nxv8i16(<vscale x 8 x i1>, <v
 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 i16> @llvm.aarch64.sve.orr.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.orr.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1337,8 +1217,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.orr.u.nxv4i32(<vscale x 4 x i1>, <v
 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 i32> @llvm.aarch64.sve.orr.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.orr.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1348,8 +1227,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.orr.u.nxv2i64(<vscale x 2 x i1>, <v
 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 i64> @llvm.aarch64.sve.orr.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.orr.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1361,8 +1239,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.u.nxv16i8(<vscale x 16 x i1>,
 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 i8> @llvm.aarch64.sve.sqsub.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1372,8 +1249,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.u.nxv8i16(<vscale x 8 x i1>,
 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 i16> @llvm.aarch64.sve.sqsub.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1383,8 +1259,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.u.nxv4i32(<vscale x 4 x i1>,
 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 i32> @llvm.aarch64.sve.sqsub.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1394,8 +1269,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.u.nxv2i64(<vscale x 2 x i1>,
 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 i64> @llvm.aarch64.sve.sqsub.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1
@@ -1405,8 +1279,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.u.nxv16i8(<vscale x 16 x i1>,
 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 i8> @llvm.aarch64.sve.uqsub.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> [[A]], <vscale x 16 x i8> [[B]])
-; CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 16 x i8> undef
 ;
   %1 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.u.nxv16i8(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
   ret <vscale x 16 x i8> %1
@@ -1416,8 +1289,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.u.nxv8i16(<vscale x 8 x i1>,
 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 i16> @llvm.aarch64.sve.uqsub.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> [[A]], <vscale x 8 x i16> [[B]])
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 8 x i16> undef
 ;
   %1 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.u.nxv8i16(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
   ret <vscale x 8 x i16> %1
@@ -1427,8 +1299,7 @@ declare <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.u.nxv4i32(<vscale x 4 x i1>,
 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 i32> @llvm.aarch64.sve.uqsub.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]])
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 4 x i32> undef
 ;
   %1 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.u.nxv4i32(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
   ret <vscale x 4 x i32> %1
@@ -1438,8 +1309,7 @@ declare <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.u.nxv2i64(<vscale x 2 x i1>,
 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 i64> @llvm.aarch64.sve.uqsub.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> [[A]], <vscale x 2 x i64> [[B]])
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    ret <vscale x 2 x i64> undef
 ;
   %1 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.u.nxv2i64(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 2 x i64> %1