[llvm] [AArch64][GlobalISel] Fold buildvector of bitcast (PR #141553)

David Green via llvm-commits llvm-commits at lists.llvm.org
Sat May 16 05:08:29 PDT 2026


https://github.com/davemgreen updated https://github.com/llvm/llvm-project/pull/141553

>From 0555e4f1d0bdc1adb2d711188d0c6fca2f4f5ee0 Mon Sep 17 00:00:00 2001
From: David Green <david.green at arm.com>
Date: Sat, 16 May 2026 13:08:15 +0100
Subject: [PATCH] [AArch64][GlobalISel] Fold buildvector of bitcast

This adds a combine for buildvectors from bitcast values, sinking the bitcast
and generating a buildvector from the original scalar type.
  %5:_(<4 x s8>) = G_BITCAST %16:_(s32)
  %18:_(s8), %19:_(s8), %20:_(s8), %21:_(s8) = G_UNMERGE_VALUES %5:_(<4 x s8>)
  %22:_(s8) = G_IMPLICIT_DEF
  %23:_(<8 x s8>) = G_BUILD_VECTOR %18:_(s8), %19:_(s8), %20:_(s8), %21:_(s8), %22:_(s8), %22:_(s8), %22:_(s8), %22:_(s8)
=>
  <2 x s32> G_BUILD_VECTOR %16, %undef
  <8 x s8> G_BITCAST

It helps clean up some of the inefficiencies from widening scalar types.
---
 .../llvm/CodeGen/GlobalISel/CombinerHelper.h  |   7 +
 .../include/llvm/Target/GlobalISel/Combine.td |   7 +
 .../lib/CodeGen/GlobalISel/CombinerHelper.cpp |  64 ++++++++
 llvm/lib/Target/AArch64/AArch64Combine.td     |   1 +
 llvm/test/CodeGen/AArch64/add.ll              |  45 +-----
 llvm/test/CodeGen/AArch64/andorxor.ll         | 147 ++++--------------
 llvm/test/CodeGen/AArch64/bitcast-extend.ll   |  18 +--
 llvm/test/CodeGen/AArch64/bitcast.ll          |  50 ++----
 llvm/test/CodeGen/AArch64/ctlz.ll             |  24 +--
 llvm/test/CodeGen/AArch64/ctpop.ll            |  24 +--
 llvm/test/CodeGen/AArch64/cttz.ll             |  25 +--
 llvm/test/CodeGen/AArch64/mul.ll              |  26 +---
 llvm/test/CodeGen/AArch64/neon-dotreduce.ll   |  60 ++-----
 llvm/test/CodeGen/AArch64/sadd_sat_vec.ll     |  22 +--
 llvm/test/CodeGen/AArch64/ssub_sat_vec.ll     |  22 +--
 llvm/test/CodeGen/AArch64/sub.ll              |  45 +-----
 llvm/test/CodeGen/AArch64/uadd_sat_vec.ll     |  22 +--
 llvm/test/CodeGen/AArch64/usub_sat_vec.ll     |  22 +--
 18 files changed, 183 insertions(+), 448 deletions(-)

diff --git a/llvm/include/llvm/CodeGen/GlobalISel/CombinerHelper.h b/llvm/include/llvm/CodeGen/GlobalISel/CombinerHelper.h
index 0f6d6423e727d..082bb7ac39c38 100644
--- a/llvm/include/llvm/CodeGen/GlobalISel/CombinerHelper.h
+++ b/llvm/include/llvm/CodeGen/GlobalISel/CombinerHelper.h
@@ -290,6 +290,13 @@ class CombinerHelper {
   /// Replace \p MI with a build_vector.
   void applyCombineShuffleToBuildVector(MachineInstr &MI) const;
 
+  /// Combine G_BUILD_VECTOR(G_UNMERGE(G_BITCAST), Undef) to
+  /// G_BITCAST(G_BUILD_VECTOR(..))
+  bool matchCombineBuildVectorOfBitcast(MachineInstr &MI,
+                                        SmallVector<Register> &Ops) const;
+  void applyCombineBuildVectorOfBitcast(MachineInstr &MI,
+                                        SmallVector<Register> &Ops) const;
+
   /// Try to combine G_SHUFFLE_VECTOR into G_CONCAT_VECTORS.
   /// Returns true if MI changed.
   ///
diff --git a/llvm/include/llvm/Target/GlobalISel/Combine.td b/llvm/include/llvm/Target/GlobalISel/Combine.td
index aac51097a5756..6133c0bf77e6d 100644
--- a/llvm/include/llvm/Target/GlobalISel/Combine.td
+++ b/llvm/include/llvm/Target/GlobalISel/Combine.td
@@ -1836,6 +1836,13 @@ def combine_shuffle_vector_to_build_vector : GICombineRule<
   (match (G_SHUFFLE_VECTOR $dst, $src1, $src2, $mask):$root),
   (apply [{ Helper.applyCombineShuffleToBuildVector(*${root}); }])>;
 
+// Combines buildvector operations
+def combine_build_vector_of_bitcast : GICombineRule<
+  (defs root:$root, register_vector_matchinfo:$matchinfo),
+  (match (G_BUILD_VECTOR $dst, GIVariadic<>:$unused):$root,
+         [{ return Helper.matchCombineBuildVectorOfBitcast(*${root}, ${matchinfo}); }]),
+  (apply [{ Helper.applyCombineBuildVectorOfBitcast(*${root}, ${matchinfo}); }])>;
+
 def insert_vector_element_idx_undef : GICombineRule<
    (defs root:$root),
    (match (G_IMPLICIT_DEF $idx),
diff --git a/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
index 262e9b579a483..14b7be13401e4 100644
--- a/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
@@ -400,6 +400,70 @@ void CombinerHelper::applyCombineConcatVectors(
   MI.eraseFromParent();
 }
 
+bool CombinerHelper::matchCombineBuildVectorOfBitcast(
+    MachineInstr &MI, SmallVector<Register> &Ops) const {
+  auto &BV = cast<GBuildVector>(MI);
+
+  // Look at the first operand for a unmerge(bitcast) from a scalar type.
+  GUnmerge *Unmerge = getOpcodeDef<GUnmerge>(BV.getSourceReg(0), MRI);
+  if (!Unmerge || Unmerge->getReg(0) != BV.getSourceReg(0))
+    return false;
+  MachineInstr *BC = MRI.getVRegDef(Unmerge->getSourceReg());
+  if (BC->getOpcode() != TargetOpcode::G_BITCAST)
+    return false;
+  LLT InputTy = MRI.getType(BC->getOperand(1).getReg());
+  unsigned Factor = Unmerge->getNumDefs();
+  if (!InputTy.isScalar() || BV.getNumSources() % Factor != 0)
+    return false;
+
+  // Check if the build_vector is legal
+  LLT BVDstTy = LLT::fixed_vector(BV.getNumSources() / Factor, InputTy);
+  if (!isLegal({TargetOpcode::G_BUILD_VECTOR, {BVDstTy, InputTy}}))
+    return false;
+
+  // Check all other operands are bitcasts or undef.
+  for (unsigned Idx = 0; Idx < BV.getNumSources(); Idx += Factor) {
+    GUnmerge *Unmerge = getOpcodeDef<GUnmerge>(BV.getSourceReg(Idx), MRI);
+    if (!all_of(iota_range<unsigned>(0, Factor, false), [&](unsigned J) {
+          MachineInstr *Src = MRI.getVRegDef(BV.getSourceReg(Idx + J));
+          if (Src->getOpcode() == TargetOpcode::G_IMPLICIT_DEF)
+            return true;
+          return Unmerge && BV.getSourceReg(Idx + J) == Unmerge->getReg(J);
+        }))
+      return false;
+    if (!Unmerge)
+      Ops.push_back(0);
+    else {
+      MachineInstr *BC = MRI.getVRegDef(Unmerge->getSourceReg());
+      if (BC->getOpcode() != TargetOpcode::G_BITCAST ||
+          MRI.getType(BC->getOperand(1).getReg()) != InputTy)
+        return false;
+      Ops.push_back(BC->getOperand(1).getReg());
+    }
+  }
+
+  return true;
+}
+
+void CombinerHelper::applyCombineBuildVectorOfBitcast(
+    MachineInstr &MI, SmallVector<Register> &Ops) const {
+  LLT SrcTy = MRI.getType(Ops[0]);
+  // Build undef if any operations require it.
+  Register Undef = 0;
+  for (Register &Op : Ops) {
+    if (!Op) {
+      if (!Undef)
+        Undef = Builder.buildUndef(SrcTy).getReg(0);
+      Op = Undef;
+    }
+  }
+
+  LLT BVDstTy = LLT::fixed_vector(Ops.size(), SrcTy);
+  auto BV = Builder.buildBuildVector(BVDstTy, Ops);
+  Builder.buildBitcast(MI.getOperand(0).getReg(), BV);
+  MI.eraseFromParent();
+}
+
 void CombinerHelper::applyCombineShuffleToBuildVector(MachineInstr &MI) const {
   auto &Shuffle = cast<GShuffleVector>(MI);
 
diff --git a/llvm/lib/Target/AArch64/AArch64Combine.td b/llvm/lib/Target/AArch64/AArch64Combine.td
index 85dc140136b2a..3b68f44b2d391 100644
--- a/llvm/lib/Target/AArch64/AArch64Combine.td
+++ b/llvm/lib/Target/AArch64/AArch64Combine.td
@@ -378,6 +378,7 @@ def AArch64PostLegalizerCombiner
                         ptr_add_immed_chain, overlapping_and,
                         split_store_zero_128, undef_combines,
                         select_to_minmax, or_to_bsp, combine_concat_vector,
+                        combine_build_vector_of_bitcast,
                         commute_constant_to_rhs, extract_vec_elt_combines,
                         push_freeze_to_prevent_poison_from_propagating,
                         combine_mul_cmlt, combine_use_vector_truncate,
diff --git a/llvm/test/CodeGen/AArch64/add.ll b/llvm/test/CodeGen/AArch64/add.ll
index f2c7ca7bac03d..f71c58f16bf36 100644
--- a/llvm/test/CodeGen/AArch64/add.ll
+++ b/llvm/test/CodeGen/AArch64/add.ll
@@ -139,43 +139,14 @@ entry:
 }
 
 define void @v4i8(ptr %p1, ptr %p2) {
-; CHECK-SD-LABEL: v4i8:
-; CHECK-SD:       // %bb.0: // %entry
-; CHECK-SD-NEXT:    ldr s0, [x0]
-; CHECK-SD-NEXT:    ldr s1, [x1]
-; CHECK-SD-NEXT:    uaddl v0.8h, v0.8b, v1.8b
-; CHECK-SD-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
-; CHECK-SD-NEXT:    str s0, [x0]
-; CHECK-SD-NEXT:    ret
-;
-; CHECK-GI-LABEL: v4i8:
-; CHECK-GI:       // %bb.0: // %entry
-; CHECK-GI-NEXT:    ldr w8, [x0]
-; CHECK-GI-NEXT:    ldr w9, [x1]
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    fmov s1, w9
-; CHECK-GI-NEXT:    mov b2, v0.b[1]
-; CHECK-GI-NEXT:    mov b3, v1.b[1]
-; CHECK-GI-NEXT:    mov b4, v0.b[2]
-; CHECK-GI-NEXT:    mov b5, v0.b[3]
-; CHECK-GI-NEXT:    fmov w8, s2
-; CHECK-GI-NEXT:    mov b2, v1.b[2]
-; CHECK-GI-NEXT:    fmov w9, s3
-; CHECK-GI-NEXT:    mov b3, v1.b[3]
-; CHECK-GI-NEXT:    mov v0.h[1], w8
-; CHECK-GI-NEXT:    mov v1.h[1], w9
-; CHECK-GI-NEXT:    fmov w8, s4
-; CHECK-GI-NEXT:    fmov w9, s2
-; CHECK-GI-NEXT:    mov v0.h[2], w8
-; CHECK-GI-NEXT:    mov v1.h[2], w9
-; CHECK-GI-NEXT:    fmov w8, s5
-; CHECK-GI-NEXT:    fmov w9, s3
-; CHECK-GI-NEXT:    mov v0.h[3], w8
-; CHECK-GI-NEXT:    mov v1.h[3], w9
-; CHECK-GI-NEXT:    add v0.4h, v0.4h, v1.4h
-; CHECK-GI-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
-; CHECK-GI-NEXT:    str s0, [x0]
-; CHECK-GI-NEXT:    ret
+; CHECK-LABEL: v4i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ldr s0, [x0]
+; CHECK-NEXT:    ldr s1, [x1]
+; CHECK-NEXT:    uaddl v0.8h, v0.8b, v1.8b
+; CHECK-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
+; CHECK-NEXT:    str s0, [x0]
+; CHECK-NEXT:    ret
 entry:
   %d = load <4 x i8>, ptr %p1
   %e = load <4 x i8>, ptr %p2
diff --git a/llvm/test/CodeGen/AArch64/andorxor.ll b/llvm/test/CodeGen/AArch64/andorxor.ll
index f967bf2fbaefc..6e1f7710b4cd8 100644
--- a/llvm/test/CodeGen/AArch64/andorxor.ll
+++ b/llvm/test/CodeGen/AArch64/andorxor.ll
@@ -435,45 +435,16 @@ entry:
 }
 
 define void @and_v4i8(ptr %p1, ptr %p2) {
-; CHECK-SD-LABEL: and_v4i8:
-; CHECK-SD:       // %bb.0: // %entry
-; CHECK-SD-NEXT:    ldr s0, [x0]
-; CHECK-SD-NEXT:    ldr s1, [x1]
-; CHECK-SD-NEXT:    zip1 v0.8b, v0.8b, v0.8b
-; CHECK-SD-NEXT:    zip1 v1.8b, v1.8b, v1.8b
-; CHECK-SD-NEXT:    and v0.8b, v0.8b, v1.8b
-; CHECK-SD-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
-; CHECK-SD-NEXT:    str s0, [x0]
-; CHECK-SD-NEXT:    ret
-;
-; CHECK-GI-LABEL: and_v4i8:
-; CHECK-GI:       // %bb.0: // %entry
-; CHECK-GI-NEXT:    ldr w8, [x0]
-; CHECK-GI-NEXT:    ldr w9, [x1]
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    fmov s1, w9
-; CHECK-GI-NEXT:    mov b2, v0.b[1]
-; CHECK-GI-NEXT:    mov b3, v1.b[1]
-; CHECK-GI-NEXT:    mov b4, v0.b[2]
-; CHECK-GI-NEXT:    mov b5, v0.b[3]
-; CHECK-GI-NEXT:    fmov w8, s2
-; CHECK-GI-NEXT:    mov b2, v1.b[2]
-; CHECK-GI-NEXT:    fmov w9, s3
-; CHECK-GI-NEXT:    mov b3, v1.b[3]
-; CHECK-GI-NEXT:    mov v0.h[1], w8
-; CHECK-GI-NEXT:    mov v1.h[1], w9
-; CHECK-GI-NEXT:    fmov w8, s4
-; CHECK-GI-NEXT:    fmov w9, s2
-; CHECK-GI-NEXT:    mov v0.h[2], w8
-; CHECK-GI-NEXT:    mov v1.h[2], w9
-; CHECK-GI-NEXT:    fmov w8, s5
-; CHECK-GI-NEXT:    fmov w9, s3
-; CHECK-GI-NEXT:    mov v0.h[3], w8
-; CHECK-GI-NEXT:    mov v1.h[3], w9
-; CHECK-GI-NEXT:    and v0.8b, v0.8b, v1.8b
-; CHECK-GI-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
-; CHECK-GI-NEXT:    str s0, [x0]
-; CHECK-GI-NEXT:    ret
+; CHECK-LABEL: and_v4i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ldr s0, [x0]
+; CHECK-NEXT:    ldr s1, [x1]
+; CHECK-NEXT:    zip1 v0.8b, v0.8b, v0.8b
+; CHECK-NEXT:    zip1 v1.8b, v1.8b, v1.8b
+; CHECK-NEXT:    and v0.8b, v0.8b, v1.8b
+; CHECK-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
+; CHECK-NEXT:    str s0, [x0]
+; CHECK-NEXT:    ret
 entry:
   %d = load <4 x i8>, ptr %p1
   %e = load <4 x i8>, ptr %p2
@@ -483,45 +454,16 @@ entry:
 }
 
 define void @or_v4i8(ptr %p1, ptr %p2) {
-; CHECK-SD-LABEL: or_v4i8:
-; CHECK-SD:       // %bb.0: // %entry
-; CHECK-SD-NEXT:    ldr s0, [x0]
-; CHECK-SD-NEXT:    ldr s1, [x1]
-; CHECK-SD-NEXT:    zip1 v0.8b, v0.8b, v0.8b
-; CHECK-SD-NEXT:    zip1 v1.8b, v1.8b, v1.8b
-; CHECK-SD-NEXT:    orr v0.8b, v0.8b, v1.8b
-; CHECK-SD-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
-; CHECK-SD-NEXT:    str s0, [x0]
-; CHECK-SD-NEXT:    ret
-;
-; CHECK-GI-LABEL: or_v4i8:
-; CHECK-GI:       // %bb.0: // %entry
-; CHECK-GI-NEXT:    ldr w8, [x0]
-; CHECK-GI-NEXT:    ldr w9, [x1]
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    fmov s1, w9
-; CHECK-GI-NEXT:    mov b2, v0.b[1]
-; CHECK-GI-NEXT:    mov b3, v1.b[1]
-; CHECK-GI-NEXT:    mov b4, v0.b[2]
-; CHECK-GI-NEXT:    mov b5, v0.b[3]
-; CHECK-GI-NEXT:    fmov w8, s2
-; CHECK-GI-NEXT:    mov b2, v1.b[2]
-; CHECK-GI-NEXT:    fmov w9, s3
-; CHECK-GI-NEXT:    mov b3, v1.b[3]
-; CHECK-GI-NEXT:    mov v0.h[1], w8
-; CHECK-GI-NEXT:    mov v1.h[1], w9
-; CHECK-GI-NEXT:    fmov w8, s4
-; CHECK-GI-NEXT:    fmov w9, s2
-; CHECK-GI-NEXT:    mov v0.h[2], w8
-; CHECK-GI-NEXT:    mov v1.h[2], w9
-; CHECK-GI-NEXT:    fmov w8, s5
-; CHECK-GI-NEXT:    fmov w9, s3
-; CHECK-GI-NEXT:    mov v0.h[3], w8
-; CHECK-GI-NEXT:    mov v1.h[3], w9
-; CHECK-GI-NEXT:    orr v0.8b, v0.8b, v1.8b
-; CHECK-GI-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
-; CHECK-GI-NEXT:    str s0, [x0]
-; CHECK-GI-NEXT:    ret
+; CHECK-LABEL: or_v4i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ldr s0, [x0]
+; CHECK-NEXT:    ldr s1, [x1]
+; CHECK-NEXT:    zip1 v0.8b, v0.8b, v0.8b
+; CHECK-NEXT:    zip1 v1.8b, v1.8b, v1.8b
+; CHECK-NEXT:    orr v0.8b, v0.8b, v1.8b
+; CHECK-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
+; CHECK-NEXT:    str s0, [x0]
+; CHECK-NEXT:    ret
 entry:
   %d = load <4 x i8>, ptr %p1
   %e = load <4 x i8>, ptr %p2
@@ -531,45 +473,16 @@ entry:
 }
 
 define void @xor_v4i8(ptr %p1, ptr %p2) {
-; CHECK-SD-LABEL: xor_v4i8:
-; CHECK-SD:       // %bb.0: // %entry
-; CHECK-SD-NEXT:    ldr s0, [x0]
-; CHECK-SD-NEXT:    ldr s1, [x1]
-; CHECK-SD-NEXT:    zip1 v0.8b, v0.8b, v0.8b
-; CHECK-SD-NEXT:    zip1 v1.8b, v1.8b, v1.8b
-; CHECK-SD-NEXT:    eor v0.8b, v0.8b, v1.8b
-; CHECK-SD-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
-; CHECK-SD-NEXT:    str s0, [x0]
-; CHECK-SD-NEXT:    ret
-;
-; CHECK-GI-LABEL: xor_v4i8:
-; CHECK-GI:       // %bb.0: // %entry
-; CHECK-GI-NEXT:    ldr w8, [x0]
-; CHECK-GI-NEXT:    ldr w9, [x1]
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    fmov s1, w9
-; CHECK-GI-NEXT:    mov b2, v0.b[1]
-; CHECK-GI-NEXT:    mov b3, v1.b[1]
-; CHECK-GI-NEXT:    mov b4, v0.b[2]
-; CHECK-GI-NEXT:    mov b5, v0.b[3]
-; CHECK-GI-NEXT:    fmov w8, s2
-; CHECK-GI-NEXT:    mov b2, v1.b[2]
-; CHECK-GI-NEXT:    fmov w9, s3
-; CHECK-GI-NEXT:    mov b3, v1.b[3]
-; CHECK-GI-NEXT:    mov v0.h[1], w8
-; CHECK-GI-NEXT:    mov v1.h[1], w9
-; CHECK-GI-NEXT:    fmov w8, s4
-; CHECK-GI-NEXT:    fmov w9, s2
-; CHECK-GI-NEXT:    mov v0.h[2], w8
-; CHECK-GI-NEXT:    mov v1.h[2], w9
-; CHECK-GI-NEXT:    fmov w8, s5
-; CHECK-GI-NEXT:    fmov w9, s3
-; CHECK-GI-NEXT:    mov v0.h[3], w8
-; CHECK-GI-NEXT:    mov v1.h[3], w9
-; CHECK-GI-NEXT:    eor v0.8b, v0.8b, v1.8b
-; CHECK-GI-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
-; CHECK-GI-NEXT:    str s0, [x0]
-; CHECK-GI-NEXT:    ret
+; CHECK-LABEL: xor_v4i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ldr s0, [x0]
+; CHECK-NEXT:    ldr s1, [x1]
+; CHECK-NEXT:    zip1 v0.8b, v0.8b, v0.8b
+; CHECK-NEXT:    zip1 v1.8b, v1.8b, v1.8b
+; CHECK-NEXT:    eor v0.8b, v0.8b, v1.8b
+; CHECK-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
+; CHECK-NEXT:    str s0, [x0]
+; CHECK-NEXT:    ret
 entry:
   %d = load <4 x i8>, ptr %p1
   %e = load <4 x i8>, ptr %p2
diff --git a/llvm/test/CodeGen/AArch64/bitcast-extend.ll b/llvm/test/CodeGen/AArch64/bitcast-extend.ll
index e110a6e283989..23cfe5a2f399f 100644
--- a/llvm/test/CodeGen/AArch64/bitcast-extend.ll
+++ b/llvm/test/CodeGen/AArch64/bitcast-extend.ll
@@ -13,14 +13,7 @@ define <4 x i16> @z_i32_v4i16(i32 %x) {
 ; CHECK-GI-LABEL: z_i32_v4i16:
 ; CHECK-GI:       // %bb.0:
 ; CHECK-GI-NEXT:    fmov s0, w0
-; CHECK-GI-NEXT:    mov b1, v0.b[1]
-; CHECK-GI-NEXT:    mov v2.b[0], v0.b[0]
-; CHECK-GI-NEXT:    mov b3, v0.b[2]
-; CHECK-GI-NEXT:    mov b0, v0.b[3]
-; CHECK-GI-NEXT:    mov v2.b[1], v1.b[0]
-; CHECK-GI-NEXT:    mov v2.b[2], v3.b[0]
-; CHECK-GI-NEXT:    mov v2.b[3], v0.b[0]
-; CHECK-GI-NEXT:    ushll v0.8h, v2.8b, #0
+; CHECK-GI-NEXT:    ushll v0.8h, v0.8b, #0
 ; CHECK-GI-NEXT:    // kill: def $d0 killed $d0 killed $q0
 ; CHECK-GI-NEXT:    ret
   %b = bitcast i32 %x to <4 x i8>
@@ -116,14 +109,7 @@ define <4 x i16> @s_i32_v4i16(i32 %x) {
 ; CHECK-GI-LABEL: s_i32_v4i16:
 ; CHECK-GI:       // %bb.0:
 ; CHECK-GI-NEXT:    fmov s0, w0
-; CHECK-GI-NEXT:    mov b1, v0.b[1]
-; CHECK-GI-NEXT:    mov v2.b[0], v0.b[0]
-; CHECK-GI-NEXT:    mov b3, v0.b[2]
-; CHECK-GI-NEXT:    mov b0, v0.b[3]
-; CHECK-GI-NEXT:    mov v2.b[1], v1.b[0]
-; CHECK-GI-NEXT:    mov v2.b[2], v3.b[0]
-; CHECK-GI-NEXT:    mov v2.b[3], v0.b[0]
-; CHECK-GI-NEXT:    sshll v0.8h, v2.8b, #0
+; CHECK-GI-NEXT:    sshll v0.8h, v0.8b, #0
 ; CHECK-GI-NEXT:    // kill: def $d0 killed $d0 killed $q0
 ; CHECK-GI-NEXT:    ret
   %b = bitcast i32 %x to <4 x i8>
diff --git a/llvm/test/CodeGen/AArch64/bitcast.ll b/llvm/test/CodeGen/AArch64/bitcast.ll
index 0f02e1c1f067b..f293934572b16 100644
--- a/llvm/test/CodeGen/AArch64/bitcast.ll
+++ b/llvm/test/CodeGen/AArch64/bitcast.ll
@@ -69,28 +69,12 @@ define i32 @bitcast_v4i8_i32(<4 x i8> %a, <4 x i8> %b){
 }
 
 define <4 x i8> @bitcast_i32_v4i8(i32 %a, i32 %b){
-; CHECK-SD-LABEL: bitcast_i32_v4i8:
-; CHECK-SD:       // %bb.0:
-; CHECK-SD-NEXT:    add w8, w0, w1
-; CHECK-SD-NEXT:    fmov s0, w8
-; CHECK-SD-NEXT:    zip1 v0.8b, v0.8b, v0.8b
-; CHECK-SD-NEXT:    ret
-;
-; CHECK-GI-LABEL: bitcast_i32_v4i8:
-; CHECK-GI:       // %bb.0:
-; CHECK-GI-NEXT:    add w8, w0, w1
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    mov b1, v0.b[1]
-; CHECK-GI-NEXT:    mov b2, v0.b[2]
-; CHECK-GI-NEXT:    fmov w8, s1
-; CHECK-GI-NEXT:    mov b1, v0.b[3]
-; CHECK-GI-NEXT:    mov v0.h[1], w8
-; CHECK-GI-NEXT:    fmov w8, s2
-; CHECK-GI-NEXT:    mov v0.h[2], w8
-; CHECK-GI-NEXT:    fmov w8, s1
-; CHECK-GI-NEXT:    mov v0.h[3], w8
-; CHECK-GI-NEXT:    // kill: def $d0 killed $d0 killed $q0
-; CHECK-GI-NEXT:    ret
+; CHECK-LABEL: bitcast_i32_v4i8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    add w8, w0, w1
+; CHECK-NEXT:    fmov s0, w8
+; CHECK-NEXT:    zip1 v0.8b, v0.8b, v0.8b
+; CHECK-NEXT:    ret
   %c = add i32 %a, %b
   %d = bitcast i32 %c to <4 x i8>
   ret <4 x i8> %d
@@ -121,22 +105,12 @@ define i32 @bitcast_v2i16_i32(<2 x i16> %a, <2 x i16> %b){
 }
 
 define <2 x i16> @bitcast_i32_v2i16(i32 %a, i32 %b){
-; CHECK-SD-LABEL: bitcast_i32_v2i16:
-; CHECK-SD:       // %bb.0:
-; CHECK-SD-NEXT:    add w8, w0, w1
-; CHECK-SD-NEXT:    fmov s0, w8
-; CHECK-SD-NEXT:    zip1 v0.4h, v0.4h, v0.4h
-; CHECK-SD-NEXT:    ret
-;
-; CHECK-GI-LABEL: bitcast_i32_v2i16:
-; CHECK-GI:       // %bb.0:
-; CHECK-GI-NEXT:    add w8, w0, w1
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    mov h1, v0.h[1]
-; CHECK-GI-NEXT:    fmov w8, s1
-; CHECK-GI-NEXT:    mov v0.s[1], w8
-; CHECK-GI-NEXT:    // kill: def $d0 killed $d0 killed $q0
-; CHECK-GI-NEXT:    ret
+; CHECK-LABEL: bitcast_i32_v2i16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    add w8, w0, w1
+; CHECK-NEXT:    fmov s0, w8
+; CHECK-NEXT:    zip1 v0.4h, v0.4h, v0.4h
+; CHECK-NEXT:    ret
   %c = add i32 %a, %b
   %d = bitcast i32 %c to <2 x i16>
   ret <2 x i16> %d
diff --git a/llvm/test/CodeGen/AArch64/ctlz.ll b/llvm/test/CodeGen/AArch64/ctlz.ll
index a1b6f1b931808..968fd6d7c9813 100644
--- a/llvm/test/CodeGen/AArch64/ctlz.ll
+++ b/llvm/test/CodeGen/AArch64/ctlz.ll
@@ -54,16 +54,10 @@ define void @v3i8(ptr %p1) {
 ;
 ; CHECK-GI-LABEL: v3i8:
 ; CHECK-GI:       // %bb.0: // %entry
-; CHECK-GI-NEXT:    ldr w8, [x0]
-; CHECK-GI-NEXT:    add x9, x0, #2
-; CHECK-GI-NEXT:    fmov s0, w8
+; CHECK-GI-NEXT:    ldr s0, [x0]
 ; CHECK-GI-NEXT:    add x8, x0, #1
-; CHECK-GI-NEXT:    mov b1, v0.b[1]
-; CHECK-GI-NEXT:    mov v2.b[0], v0.b[0]
-; CHECK-GI-NEXT:    mov b0, v0.b[2]
-; CHECK-GI-NEXT:    mov v2.b[1], v1.b[0]
-; CHECK-GI-NEXT:    mov v2.b[2], v0.b[0]
-; CHECK-GI-NEXT:    clz v0.8b, v2.8b
+; CHECK-GI-NEXT:    add x9, x0, #2
+; CHECK-GI-NEXT:    clz v0.8b, v0.8b
 ; CHECK-GI-NEXT:    st1 { v0.b }[0], [x0]
 ; CHECK-GI-NEXT:    st1 { v0.b }[1], [x8]
 ; CHECK-GI-NEXT:    st1 { v0.b }[2], [x9]
@@ -89,16 +83,8 @@ define void @v4i8(ptr %p1) {
 ;
 ; CHECK-GI-LABEL: v4i8:
 ; CHECK-GI:       // %bb.0: // %entry
-; CHECK-GI-NEXT:    ldr w8, [x0]
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    mov b1, v0.b[1]
-; CHECK-GI-NEXT:    mov v2.b[0], v0.b[0]
-; CHECK-GI-NEXT:    mov b3, v0.b[2]
-; CHECK-GI-NEXT:    mov b0, v0.b[3]
-; CHECK-GI-NEXT:    mov v2.b[1], v1.b[0]
-; CHECK-GI-NEXT:    mov v2.b[2], v3.b[0]
-; CHECK-GI-NEXT:    mov v2.b[3], v0.b[0]
-; CHECK-GI-NEXT:    clz v0.8b, v2.8b
+; CHECK-GI-NEXT:    ldr s0, [x0]
+; CHECK-GI-NEXT:    clz v0.8b, v0.8b
 ; CHECK-GI-NEXT:    str s0, [x0]
 ; CHECK-GI-NEXT:    ret
 entry:
diff --git a/llvm/test/CodeGen/AArch64/ctpop.ll b/llvm/test/CodeGen/AArch64/ctpop.ll
index 61a9d84ad2622..00d3542988272 100644
--- a/llvm/test/CodeGen/AArch64/ctpop.ll
+++ b/llvm/test/CodeGen/AArch64/ctpop.ll
@@ -53,16 +53,10 @@ define void @v3i8(ptr %p1) {
 ;
 ; CHECK-GI-LABEL: v3i8:
 ; CHECK-GI:       // %bb.0: // %entry
-; CHECK-GI-NEXT:    ldr w8, [x0]
-; CHECK-GI-NEXT:    add x9, x0, #2
-; CHECK-GI-NEXT:    fmov s0, w8
+; CHECK-GI-NEXT:    ldr s0, [x0]
 ; CHECK-GI-NEXT:    add x8, x0, #1
-; CHECK-GI-NEXT:    mov b1, v0.b[1]
-; CHECK-GI-NEXT:    mov v2.b[0], v0.b[0]
-; CHECK-GI-NEXT:    mov b0, v0.b[2]
-; CHECK-GI-NEXT:    mov v2.b[1], v1.b[0]
-; CHECK-GI-NEXT:    mov v2.b[2], v0.b[0]
-; CHECK-GI-NEXT:    cnt v0.8b, v2.8b
+; CHECK-GI-NEXT:    add x9, x0, #2
+; CHECK-GI-NEXT:    cnt v0.8b, v0.8b
 ; CHECK-GI-NEXT:    st1 { v0.b }[0], [x0]
 ; CHECK-GI-NEXT:    st1 { v0.b }[1], [x8]
 ; CHECK-GI-NEXT:    st1 { v0.b }[2], [x9]
@@ -87,16 +81,8 @@ define void @v4i8(ptr %p1) {
 ;
 ; CHECK-GI-LABEL: v4i8:
 ; CHECK-GI:       // %bb.0: // %entry
-; CHECK-GI-NEXT:    ldr w8, [x0]
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    mov b1, v0.b[1]
-; CHECK-GI-NEXT:    mov v2.b[0], v0.b[0]
-; CHECK-GI-NEXT:    mov b3, v0.b[2]
-; CHECK-GI-NEXT:    mov b0, v0.b[3]
-; CHECK-GI-NEXT:    mov v2.b[1], v1.b[0]
-; CHECK-GI-NEXT:    mov v2.b[2], v3.b[0]
-; CHECK-GI-NEXT:    mov v2.b[3], v0.b[0]
-; CHECK-GI-NEXT:    cnt v0.8b, v2.8b
+; CHECK-GI-NEXT:    ldr s0, [x0]
+; CHECK-GI-NEXT:    cnt v0.8b, v0.8b
 ; CHECK-GI-NEXT:    str s0, [x0]
 ; CHECK-GI-NEXT:    ret
 entry:
diff --git a/llvm/test/CodeGen/AArch64/cttz.ll b/llvm/test/CodeGen/AArch64/cttz.ll
index 3199796ecd341..1f4ac01c485e5 100644
--- a/llvm/test/CodeGen/AArch64/cttz.ll
+++ b/llvm/test/CodeGen/AArch64/cttz.ll
@@ -103,24 +103,15 @@ define void @v4i8(ptr %p1) {
 ;
 ; CHECK-GI-LABEL: v4i8:
 ; CHECK-GI:       // %bb.0: // %entry
-; CHECK-GI-NEXT:    ldr w9, [x0]
 ; CHECK-GI-NEXT:    mov w8, #255 // =0xff
-; CHECK-GI-NEXT:    fmov s0, w9
-; CHECK-GI-NEXT:    mov b1, v0.b[1]
-; CHECK-GI-NEXT:    mov b2, v0.b[2]
-; CHECK-GI-NEXT:    mov b3, v0.b[3]
-; CHECK-GI-NEXT:    fmov w9, s1
-; CHECK-GI-NEXT:    fmov s1, w8
-; CHECK-GI-NEXT:    mov v0.h[1], w9
-; CHECK-GI-NEXT:    mov v1.h[1], w8
-; CHECK-GI-NEXT:    fmov w9, s2
-; CHECK-GI-NEXT:    mov v0.h[2], w9
-; CHECK-GI-NEXT:    mov v1.h[2], w8
-; CHECK-GI-NEXT:    fmov w9, s3
-; CHECK-GI-NEXT:    mov v0.h[3], w9
-; CHECK-GI-NEXT:    mov v1.h[3], w8
-; CHECK-GI-NEXT:    eor v2.8b, v0.8b, v1.8b
-; CHECK-GI-NEXT:    add v0.4h, v0.4h, v1.4h
+; CHECK-GI-NEXT:    ldr s1, [x0]
+; CHECK-GI-NEXT:    fmov s0, w8
+; CHECK-GI-NEXT:    zip1 v2.8b, v1.8b, v1.8b
+; CHECK-GI-NEXT:    mov v0.h[1], w8
+; CHECK-GI-NEXT:    mov v0.h[2], w8
+; CHECK-GI-NEXT:    mov v0.h[3], w8
+; CHECK-GI-NEXT:    eor v2.8b, v2.8b, v0.8b
+; CHECK-GI-NEXT:    uaddw v0.8h, v0.8h, v1.8b
 ; CHECK-GI-NEXT:    and v0.8b, v2.8b, v0.8b
 ; CHECK-GI-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
 ; CHECK-GI-NEXT:    cnt v0.8b, v0.8b
diff --git a/llvm/test/CodeGen/AArch64/mul.ll b/llvm/test/CodeGen/AArch64/mul.ll
index 10400fd442cb1..59438f62a12bb 100644
--- a/llvm/test/CodeGen/AArch64/mul.ll
+++ b/llvm/test/CodeGen/AArch64/mul.ll
@@ -162,28 +162,10 @@ define void @v4i8(ptr %p1, ptr %p2) {
 ;
 ; CHECK-GI-LABEL: v4i8:
 ; CHECK-GI:       // %bb.0: // %entry
-; CHECK-GI-NEXT:    ldr w8, [x0]
-; CHECK-GI-NEXT:    ldr w9, [x1]
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    fmov s1, w9
-; CHECK-GI-NEXT:    mov b2, v0.b[1]
-; CHECK-GI-NEXT:    mov b3, v1.b[1]
-; CHECK-GI-NEXT:    mov b4, v0.b[2]
-; CHECK-GI-NEXT:    mov b5, v0.b[3]
-; CHECK-GI-NEXT:    fmov w8, s2
-; CHECK-GI-NEXT:    mov b2, v1.b[2]
-; CHECK-GI-NEXT:    fmov w9, s3
-; CHECK-GI-NEXT:    mov b3, v1.b[3]
-; CHECK-GI-NEXT:    mov v0.h[1], w8
-; CHECK-GI-NEXT:    mov v1.h[1], w9
-; CHECK-GI-NEXT:    fmov w8, s4
-; CHECK-GI-NEXT:    fmov w9, s2
-; CHECK-GI-NEXT:    mov v0.h[2], w8
-; CHECK-GI-NEXT:    mov v1.h[2], w9
-; CHECK-GI-NEXT:    fmov w8, s5
-; CHECK-GI-NEXT:    fmov w9, s3
-; CHECK-GI-NEXT:    mov v0.h[3], w8
-; CHECK-GI-NEXT:    mov v1.h[3], w9
+; CHECK-GI-NEXT:    ldr s0, [x0]
+; CHECK-GI-NEXT:    ldr s1, [x1]
+; CHECK-GI-NEXT:    zip1 v0.8b, v0.8b, v0.8b
+; CHECK-GI-NEXT:    zip1 v1.8b, v1.8b, v1.8b
 ; CHECK-GI-NEXT:    mul v0.4h, v0.4h, v1.4h
 ; CHECK-GI-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
 ; CHECK-GI-NEXT:    str s0, [x0]
diff --git a/llvm/test/CodeGen/AArch64/neon-dotreduce.ll b/llvm/test/CodeGen/AArch64/neon-dotreduce.ll
index e176cd3233d69..e3e314eb9e977 100644
--- a/llvm/test/CodeGen/AArch64/neon-dotreduce.ll
+++ b/llvm/test/CodeGen/AArch64/neon-dotreduce.ll
@@ -28,26 +28,10 @@ define i32 @test_udot_v4i8(ptr nocapture readonly %a, ptr nocapture readonly %b,
 ;
 ; CHECK-GI-LABEL: test_udot_v4i8:
 ; CHECK-GI:       // %bb.0: // %entry
-; CHECK-GI-NEXT:    ldr w8, [x1]
-; CHECK-GI-NEXT:    ldr w9, [x0]
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    fmov s1, w9
-; CHECK-GI-NEXT:    mov b2, v0.b[1]
-; CHECK-GI-NEXT:    mov v3.b[0], v0.b[0]
-; CHECK-GI-NEXT:    mov b4, v1.b[1]
-; CHECK-GI-NEXT:    mov v5.b[0], v1.b[0]
-; CHECK-GI-NEXT:    mov v3.b[1], v2.b[0]
-; CHECK-GI-NEXT:    mov b2, v0.b[2]
-; CHECK-GI-NEXT:    mov b0, v0.b[3]
-; CHECK-GI-NEXT:    mov v5.b[1], v4.b[0]
-; CHECK-GI-NEXT:    mov b4, v1.b[2]
-; CHECK-GI-NEXT:    mov b1, v1.b[3]
-; CHECK-GI-NEXT:    mov v3.b[2], v2.b[0]
-; CHECK-GI-NEXT:    mov v5.b[2], v4.b[0]
-; CHECK-GI-NEXT:    mov v3.b[3], v0.b[0]
-; CHECK-GI-NEXT:    mov v5.b[3], v1.b[0]
-; CHECK-GI-NEXT:    ushll v0.8h, v3.8b, #0
-; CHECK-GI-NEXT:    ushll v1.8h, v5.8b, #0
+; CHECK-GI-NEXT:    ldr s0, [x1]
+; CHECK-GI-NEXT:    ldr s1, [x0]
+; CHECK-GI-NEXT:    ushll v0.8h, v0.8b, #0
+; CHECK-GI-NEXT:    ushll v1.8h, v1.8b, #0
 ; CHECK-GI-NEXT:    mul v0.4h, v0.4h, v1.4h
 ; CHECK-GI-NEXT:    uaddlv s0, v0.4h
 ; CHECK-GI-NEXT:    fmov w8, s0
@@ -75,16 +59,8 @@ define i32 @test_udot_v4i8_nomla(ptr nocapture readonly %a1) {
 ;
 ; CHECK-GI-LABEL: test_udot_v4i8_nomla:
 ; CHECK-GI:       // %bb.0: // %entry
-; CHECK-GI-NEXT:    ldr w8, [x0]
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    mov b1, v0.b[1]
-; CHECK-GI-NEXT:    mov v2.b[0], v0.b[0]
-; CHECK-GI-NEXT:    mov b3, v0.b[2]
-; CHECK-GI-NEXT:    mov b0, v0.b[3]
-; CHECK-GI-NEXT:    mov v2.b[1], v1.b[0]
-; CHECK-GI-NEXT:    mov v2.b[2], v3.b[0]
-; CHECK-GI-NEXT:    mov v2.b[3], v0.b[0]
-; CHECK-GI-NEXT:    ushll v0.8h, v2.8b, #0
+; CHECK-GI-NEXT:    ldr s0, [x0]
+; CHECK-GI-NEXT:    ushll v0.8h, v0.8b, #0
 ; CHECK-GI-NEXT:    uaddlv s0, v0.4h
 ; CHECK-GI-NEXT:    fmov w8, s0
 ; CHECK-GI-NEXT:    and w0, w8, #0xffff
@@ -110,26 +86,10 @@ define i32 @test_sdot_v4i8(ptr nocapture readonly %a, ptr nocapture readonly %b,
 ;
 ; CHECK-GI-LABEL: test_sdot_v4i8:
 ; CHECK-GI:       // %bb.0: // %entry
-; CHECK-GI-NEXT:    ldr w8, [x1]
-; CHECK-GI-NEXT:    ldr w9, [x0]
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    fmov s1, w9
-; CHECK-GI-NEXT:    mov b2, v0.b[1]
-; CHECK-GI-NEXT:    mov v3.b[0], v0.b[0]
-; CHECK-GI-NEXT:    mov b4, v1.b[1]
-; CHECK-GI-NEXT:    mov v5.b[0], v1.b[0]
-; CHECK-GI-NEXT:    mov v3.b[1], v2.b[0]
-; CHECK-GI-NEXT:    mov b2, v0.b[2]
-; CHECK-GI-NEXT:    mov b0, v0.b[3]
-; CHECK-GI-NEXT:    mov v5.b[1], v4.b[0]
-; CHECK-GI-NEXT:    mov b4, v1.b[2]
-; CHECK-GI-NEXT:    mov b1, v1.b[3]
-; CHECK-GI-NEXT:    mov v3.b[2], v2.b[0]
-; CHECK-GI-NEXT:    mov v5.b[2], v4.b[0]
-; CHECK-GI-NEXT:    mov v3.b[3], v0.b[0]
-; CHECK-GI-NEXT:    mov v5.b[3], v1.b[0]
-; CHECK-GI-NEXT:    sshll v0.8h, v3.8b, #0
-; CHECK-GI-NEXT:    sshll v1.8h, v5.8b, #0
+; CHECK-GI-NEXT:    ldr s0, [x1]
+; CHECK-GI-NEXT:    ldr s1, [x0]
+; CHECK-GI-NEXT:    sshll v0.8h, v0.8b, #0
+; CHECK-GI-NEXT:    sshll v1.8h, v1.8b, #0
 ; CHECK-GI-NEXT:    mul v0.4h, v0.4h, v1.4h
 ; CHECK-GI-NEXT:    saddlv s0, v0.4h
 ; CHECK-GI-NEXT:    fmov w8, s0
diff --git a/llvm/test/CodeGen/AArch64/sadd_sat_vec.ll b/llvm/test/CodeGen/AArch64/sadd_sat_vec.ll
index 88f1324762f8f..8d3a9ee8beba4 100644
--- a/llvm/test/CodeGen/AArch64/sadd_sat_vec.ll
+++ b/llvm/test/CodeGen/AArch64/sadd_sat_vec.ll
@@ -127,25 +127,9 @@ define void @v4i8(ptr %px, ptr %py, ptr %pz) nounwind {
 ;
 ; CHECK-GI-LABEL: v4i8:
 ; CHECK-GI:       // %bb.0:
-; CHECK-GI-NEXT:    ldr w8, [x0]
-; CHECK-GI-NEXT:    ldr w9, [x1]
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    fmov s1, w9
-; CHECK-GI-NEXT:    mov b2, v0.b[1]
-; CHECK-GI-NEXT:    mov v3.b[0], v0.b[0]
-; CHECK-GI-NEXT:    mov b4, v1.b[1]
-; CHECK-GI-NEXT:    mov v5.b[0], v1.b[0]
-; CHECK-GI-NEXT:    mov v3.b[1], v2.b[0]
-; CHECK-GI-NEXT:    mov b2, v0.b[2]
-; CHECK-GI-NEXT:    mov b0, v0.b[3]
-; CHECK-GI-NEXT:    mov v5.b[1], v4.b[0]
-; CHECK-GI-NEXT:    mov b4, v1.b[2]
-; CHECK-GI-NEXT:    mov b1, v1.b[3]
-; CHECK-GI-NEXT:    mov v3.b[2], v2.b[0]
-; CHECK-GI-NEXT:    mov v5.b[2], v4.b[0]
-; CHECK-GI-NEXT:    mov v3.b[3], v0.b[0]
-; CHECK-GI-NEXT:    mov v5.b[3], v1.b[0]
-; CHECK-GI-NEXT:    sqadd v0.8b, v3.8b, v5.8b
+; CHECK-GI-NEXT:    ldr s0, [x0]
+; CHECK-GI-NEXT:    ldr s1, [x1]
+; CHECK-GI-NEXT:    sqadd v0.8b, v0.8b, v1.8b
 ; CHECK-GI-NEXT:    str s0, [x2]
 ; CHECK-GI-NEXT:    ret
   %x = load <4 x i8>, ptr %px
diff --git a/llvm/test/CodeGen/AArch64/ssub_sat_vec.ll b/llvm/test/CodeGen/AArch64/ssub_sat_vec.ll
index 55608f6ef21b8..f4359edcc1bbd 100644
--- a/llvm/test/CodeGen/AArch64/ssub_sat_vec.ll
+++ b/llvm/test/CodeGen/AArch64/ssub_sat_vec.ll
@@ -127,25 +127,9 @@ define void @v4i8(ptr %px, ptr %py, ptr %pz) nounwind {
 ;
 ; CHECK-GI-LABEL: v4i8:
 ; CHECK-GI:       // %bb.0:
-; CHECK-GI-NEXT:    ldr w8, [x0]
-; CHECK-GI-NEXT:    ldr w9, [x1]
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    fmov s1, w9
-; CHECK-GI-NEXT:    mov b2, v0.b[1]
-; CHECK-GI-NEXT:    mov v3.b[0], v0.b[0]
-; CHECK-GI-NEXT:    mov b4, v1.b[1]
-; CHECK-GI-NEXT:    mov v5.b[0], v1.b[0]
-; CHECK-GI-NEXT:    mov v3.b[1], v2.b[0]
-; CHECK-GI-NEXT:    mov b2, v0.b[2]
-; CHECK-GI-NEXT:    mov b0, v0.b[3]
-; CHECK-GI-NEXT:    mov v5.b[1], v4.b[0]
-; CHECK-GI-NEXT:    mov b4, v1.b[2]
-; CHECK-GI-NEXT:    mov b1, v1.b[3]
-; CHECK-GI-NEXT:    mov v3.b[2], v2.b[0]
-; CHECK-GI-NEXT:    mov v5.b[2], v4.b[0]
-; CHECK-GI-NEXT:    mov v3.b[3], v0.b[0]
-; CHECK-GI-NEXT:    mov v5.b[3], v1.b[0]
-; CHECK-GI-NEXT:    sqsub v0.8b, v3.8b, v5.8b
+; CHECK-GI-NEXT:    ldr s0, [x0]
+; CHECK-GI-NEXT:    ldr s1, [x1]
+; CHECK-GI-NEXT:    sqsub v0.8b, v0.8b, v1.8b
 ; CHECK-GI-NEXT:    str s0, [x2]
 ; CHECK-GI-NEXT:    ret
   %x = load <4 x i8>, ptr %px
diff --git a/llvm/test/CodeGen/AArch64/sub.ll b/llvm/test/CodeGen/AArch64/sub.ll
index 402f35e134dbe..4516cf821af20 100644
--- a/llvm/test/CodeGen/AArch64/sub.ll
+++ b/llvm/test/CodeGen/AArch64/sub.ll
@@ -139,43 +139,14 @@ entry:
 }
 
 define void @v4i8(ptr %p1, ptr %p2) {
-; CHECK-SD-LABEL: v4i8:
-; CHECK-SD:       // %bb.0: // %entry
-; CHECK-SD-NEXT:    ldr s0, [x0]
-; CHECK-SD-NEXT:    ldr s1, [x1]
-; CHECK-SD-NEXT:    usubl v0.8h, v0.8b, v1.8b
-; CHECK-SD-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
-; CHECK-SD-NEXT:    str s0, [x0]
-; CHECK-SD-NEXT:    ret
-;
-; CHECK-GI-LABEL: v4i8:
-; CHECK-GI:       // %bb.0: // %entry
-; CHECK-GI-NEXT:    ldr w8, [x0]
-; CHECK-GI-NEXT:    ldr w9, [x1]
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    fmov s1, w9
-; CHECK-GI-NEXT:    mov b2, v0.b[1]
-; CHECK-GI-NEXT:    mov b3, v1.b[1]
-; CHECK-GI-NEXT:    mov b4, v0.b[2]
-; CHECK-GI-NEXT:    mov b5, v0.b[3]
-; CHECK-GI-NEXT:    fmov w8, s2
-; CHECK-GI-NEXT:    mov b2, v1.b[2]
-; CHECK-GI-NEXT:    fmov w9, s3
-; CHECK-GI-NEXT:    mov b3, v1.b[3]
-; CHECK-GI-NEXT:    mov v0.h[1], w8
-; CHECK-GI-NEXT:    mov v1.h[1], w9
-; CHECK-GI-NEXT:    fmov w8, s4
-; CHECK-GI-NEXT:    fmov w9, s2
-; CHECK-GI-NEXT:    mov v0.h[2], w8
-; CHECK-GI-NEXT:    mov v1.h[2], w9
-; CHECK-GI-NEXT:    fmov w8, s5
-; CHECK-GI-NEXT:    fmov w9, s3
-; CHECK-GI-NEXT:    mov v0.h[3], w8
-; CHECK-GI-NEXT:    mov v1.h[3], w9
-; CHECK-GI-NEXT:    sub v0.4h, v0.4h, v1.4h
-; CHECK-GI-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
-; CHECK-GI-NEXT:    str s0, [x0]
-; CHECK-GI-NEXT:    ret
+; CHECK-LABEL: v4i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ldr s0, [x0]
+; CHECK-NEXT:    ldr s1, [x1]
+; CHECK-NEXT:    usubl v0.8h, v0.8b, v1.8b
+; CHECK-NEXT:    uzp1 v0.8b, v0.8b, v0.8b
+; CHECK-NEXT:    str s0, [x0]
+; CHECK-NEXT:    ret
 entry:
   %d = load <4 x i8>, ptr %p1
   %e = load <4 x i8>, ptr %p2
diff --git a/llvm/test/CodeGen/AArch64/uadd_sat_vec.ll b/llvm/test/CodeGen/AArch64/uadd_sat_vec.ll
index 644313c953607..afcebf34bcd0d 100644
--- a/llvm/test/CodeGen/AArch64/uadd_sat_vec.ll
+++ b/llvm/test/CodeGen/AArch64/uadd_sat_vec.ll
@@ -124,25 +124,9 @@ define void @v4i8(ptr %px, ptr %py, ptr %pz) nounwind {
 ;
 ; CHECK-GI-LABEL: v4i8:
 ; CHECK-GI:       // %bb.0:
-; CHECK-GI-NEXT:    ldr w8, [x0]
-; CHECK-GI-NEXT:    ldr w9, [x1]
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    fmov s1, w9
-; CHECK-GI-NEXT:    mov b2, v0.b[1]
-; CHECK-GI-NEXT:    mov v3.b[0], v0.b[0]
-; CHECK-GI-NEXT:    mov b4, v1.b[1]
-; CHECK-GI-NEXT:    mov v5.b[0], v1.b[0]
-; CHECK-GI-NEXT:    mov v3.b[1], v2.b[0]
-; CHECK-GI-NEXT:    mov b2, v0.b[2]
-; CHECK-GI-NEXT:    mov b0, v0.b[3]
-; CHECK-GI-NEXT:    mov v5.b[1], v4.b[0]
-; CHECK-GI-NEXT:    mov b4, v1.b[2]
-; CHECK-GI-NEXT:    mov b1, v1.b[3]
-; CHECK-GI-NEXT:    mov v3.b[2], v2.b[0]
-; CHECK-GI-NEXT:    mov v5.b[2], v4.b[0]
-; CHECK-GI-NEXT:    mov v3.b[3], v0.b[0]
-; CHECK-GI-NEXT:    mov v5.b[3], v1.b[0]
-; CHECK-GI-NEXT:    uqadd v0.8b, v3.8b, v5.8b
+; CHECK-GI-NEXT:    ldr s0, [x0]
+; CHECK-GI-NEXT:    ldr s1, [x1]
+; CHECK-GI-NEXT:    uqadd v0.8b, v0.8b, v1.8b
 ; CHECK-GI-NEXT:    str s0, [x2]
 ; CHECK-GI-NEXT:    ret
   %x = load <4 x i8>, ptr %px
diff --git a/llvm/test/CodeGen/AArch64/usub_sat_vec.ll b/llvm/test/CodeGen/AArch64/usub_sat_vec.ll
index 9a982f0196755..8ffafb247c568 100644
--- a/llvm/test/CodeGen/AArch64/usub_sat_vec.ll
+++ b/llvm/test/CodeGen/AArch64/usub_sat_vec.ll
@@ -124,25 +124,9 @@ define void @v4i8(ptr %px, ptr %py, ptr %pz) nounwind {
 ;
 ; CHECK-GI-LABEL: v4i8:
 ; CHECK-GI:       // %bb.0:
-; CHECK-GI-NEXT:    ldr w8, [x0]
-; CHECK-GI-NEXT:    ldr w9, [x1]
-; CHECK-GI-NEXT:    fmov s0, w8
-; CHECK-GI-NEXT:    fmov s1, w9
-; CHECK-GI-NEXT:    mov b2, v0.b[1]
-; CHECK-GI-NEXT:    mov v3.b[0], v0.b[0]
-; CHECK-GI-NEXT:    mov b4, v1.b[1]
-; CHECK-GI-NEXT:    mov v5.b[0], v1.b[0]
-; CHECK-GI-NEXT:    mov v3.b[1], v2.b[0]
-; CHECK-GI-NEXT:    mov b2, v0.b[2]
-; CHECK-GI-NEXT:    mov b0, v0.b[3]
-; CHECK-GI-NEXT:    mov v5.b[1], v4.b[0]
-; CHECK-GI-NEXT:    mov b4, v1.b[2]
-; CHECK-GI-NEXT:    mov b1, v1.b[3]
-; CHECK-GI-NEXT:    mov v3.b[2], v2.b[0]
-; CHECK-GI-NEXT:    mov v5.b[2], v4.b[0]
-; CHECK-GI-NEXT:    mov v3.b[3], v0.b[0]
-; CHECK-GI-NEXT:    mov v5.b[3], v1.b[0]
-; CHECK-GI-NEXT:    uqsub v0.8b, v3.8b, v5.8b
+; CHECK-GI-NEXT:    ldr s0, [x0]
+; CHECK-GI-NEXT:    ldr s1, [x1]
+; CHECK-GI-NEXT:    uqsub v0.8b, v0.8b, v1.8b
 ; CHECK-GI-NEXT:    str s0, [x2]
 ; CHECK-GI-NEXT:    ret
   %x = load <4 x i8>, ptr %px



More information about the llvm-commits mailing list