[llvm] [CodeGen] Combine two loops in SloIndexes.cpp file (PR #127631)

via llvm-commits llvm-commits at lists.llvm.org
Thu Feb 27 08:03:27 PST 2025


https://github.com/Rifet-c updated https://github.com/llvm/llvm-project/pull/127631

>From 62eb585c589a8f870857eaea54cce4c967ed0655 Mon Sep 17 00:00:00 2001
From: Aleksandr Levin <aleksandr.levin at codasip.com>
Date: Tue, 18 Feb 2025 14:06:48 +0100
Subject: [PATCH] Merged two loops that were iterating over the same machine
 basic block, also did some minor readability improvements (like commenting
 and absorbing if condition into a variable), also adjusted tests to match the
 new behavior

---
 llvm/lib/CodeGen/SlotIndexes.cpp        |   32 +-
 llvm/test/CodeGen/Thumb2/mve-shuffle.ll |  200 ++--
 llvm/test/CodeGen/Thumb2/mve-vld3.ll    | 1219 +++++++++++++++--------
 3 files changed, 965 insertions(+), 486 deletions(-)

diff --git a/llvm/lib/CodeGen/SlotIndexes.cpp b/llvm/lib/CodeGen/SlotIndexes.cpp
index 1b92a5aa59d18..63e8627ad2a66 100644
--- a/llvm/lib/CodeGen/SlotIndexes.cpp
+++ b/llvm/lib/CodeGen/SlotIndexes.cpp
@@ -212,6 +212,7 @@ void SlotIndexes::repairIndexesInRange(MachineBasicBlock *MBB,
   IndexList::iterator ListI = endIdx.listEntry()->getIterator();
   MachineBasicBlock::iterator MBBI = End;
   bool pastStart = false;
+  bool oldIndexesRemoved = false;
   while (ListI != ListB || MBBI != Begin || (includeStart && !pastStart)) {
     assert(ListI->getIndex() >= startIdx.getIndex() &&
            (includeStart || !pastStart) &&
@@ -220,6 +221,8 @@ void SlotIndexes::repairIndexesInRange(MachineBasicBlock *MBB,
     MachineInstr *SlotMI = ListI->getInstr();
     MachineInstr *MI = (MBBI != MBB->end() && !pastStart) ? &*MBBI : nullptr;
     bool MBBIAtBegin = MBBI == Begin && (!includeStart || pastStart);
+    bool MIIndexNotFound = MI && mi2iMap.find(MI) == mi2iMap.end();
+    bool SlotMIRemoved = false;
 
     if (SlotMI == MI && !MBBIAtBegin) {
       --ListI;
@@ -227,25 +230,30 @@ void SlotIndexes::repairIndexesInRange(MachineBasicBlock *MBB,
         --MBBI;
       else
         pastStart = true;
-    } else if (MI && !mi2iMap.contains(MI)) {
+    } else if (MIIndexNotFound || oldIndexesRemoved) {
       if (MBBI != Begin)
         --MBBI;
       else
         pastStart = true;
     } else {
-      --ListI;
-      if (SlotMI)
+      // We ran through all the indexes on the interval
+      //   -> The only thing left is to go through all the
+      //   remaining MBB instructions and update their indexes
+      if (ListI == ListB)
+        oldIndexesRemoved = true;
+      else
+        --ListI;
+      if (SlotMI) {
         removeMachineInstrFromMaps(*SlotMI);
+        SlotMIRemoved = true;
+      }
     }
-  }
 
-  // In theory this could be combined with the previous loop, but it is tricky
-  // to update the IndexList while we are iterating it.
-  for (MachineBasicBlock::iterator I = End; I != Begin;) {
-    --I;
-    MachineInstr &MI = *I;
-    if (!MI.isDebugOrPseudoInstr() && !mi2iMap.contains(&MI))
-      insertMachineInstrInMaps(MI);
+    MachineInstr *instrToInsert = SlotMIRemoved ? SlotMI : MI;
+
+    // Insert isntruction back into the maps after passing it/removing the index
+    if ((MIIndexNotFound || SlotMIRemoved) && instrToInsert->getParent() != nullptr && !instrToInsert->isDebugOrPseudoInstr())
+      insertMachineInstrInMaps(*instrToInsert);
   }
 }
 
@@ -287,4 +295,4 @@ LLVM_DUMP_METHOD void SlotIndex::dump() const {
   print(dbgs());
   dbgs() << "\n";
 }
-#endif
+#endif
\ No newline at end of file
diff --git a/llvm/test/CodeGen/Thumb2/mve-shuffle.ll b/llvm/test/CodeGen/Thumb2/mve-shuffle.ll
index feda774ab0e65..1c3482111c273 100644
--- a/llvm/test/CodeGen/Thumb2/mve-shuffle.ll
+++ b/llvm/test/CodeGen/Thumb2/mve-shuffle.ll
@@ -223,18 +223,31 @@ entry:
 }
 
 define arm_aapcs_vfpcc <8 x i16> @shuffle3_i16(<8 x i16> %src) {
-; CHECK-LABEL: shuffle3_i16:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    vmovx.f16 s5, s3
-; CHECK-NEXT:    vmovx.f16 s6, s1
-; CHECK-NEXT:    vmovx.f16 s4, s0
-; CHECK-NEXT:    vins.f16 s1, s0
-; CHECK-NEXT:    vins.f16 s6, s4
-; CHECK-NEXT:    vins.f16 s5, s3
-; CHECK-NEXT:    vmov.f32 s4, s2
-; CHECK-NEXT:    vmov.f32 s7, s1
-; CHECK-NEXT:    vmov q0, q1
-; CHECK-NEXT:    bx lr
+; CHECK-LV-LABEL: shuffle3_i16:
+; CHECK-LV:       @ %bb.0: @ %entry
+; CHECK-LV-NEXT:    vmovx.f16 s5, s3
+; CHECK-LV-NEXT:    vmovx.f16 s6, s1
+; CHECK-LV-NEXT:    vmovx.f16 s4, s0
+; CHECK-LV-NEXT:    vins.f16 s1, s0
+; CHECK-LV-NEXT:    vins.f16 s6, s4
+; CHECK-LV-NEXT:    vins.f16 s5, s3
+; CHECK-LV-NEXT:    vmov.f32 s4, s2
+; CHECK-LV-NEXT:    vmov.f32 s7, s1
+; CHECK-LV-NEXT:    vmov q0, q1
+; CHECK-LV-NEXT:    bx lr
+
+; CHECK-LIS-LABEL: shuffle3_i16:
+; CHECK-LIS:       @ %bb.0: @ %entry
+; CHECK-LIS-NEXT:    vmov q1, q0
+; CHECK-LIS-NEXT:    vmovx.f16 s2, s5
+; CHECK-LIS-NEXT:    vmovx.f16 s0, s4
+; CHECK-LIS-NEXT:    vins.f16 s5, s4
+; CHECK-LIS-NEXT:    vins.f16 s2, s0
+; CHECK-LIS-NEXT:    vmov.f32 s0, s6
+; CHECK-LIS-NEXT:    vmovx.f16 s1, s7
+; CHECK-LIS-NEXT:    vmov.f32 s3, s5
+; CHECK-LIS-NEXT:    vins.f16 s1, s7
+; CHECK-LIS-NEXT:    bx lr
 entry:
   %out = shufflevector <8 x i16> %src, <8 x i16> undef, <8 x i32> <i32 4, i32 5, i32 7, i32 6, i32 3, i32 1, i32 2, i32 0>
   ret <8 x i16> %out
@@ -1145,18 +1158,31 @@ entry:
 }
 
 define arm_aapcs_vfpcc <8 x half> @shuffle3_f16(<8 x half> %src) {
-; CHECK-LABEL: shuffle3_f16:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    vmovx.f16 s5, s3
-; CHECK-NEXT:    vmovx.f16 s6, s1
-; CHECK-NEXT:    vmovx.f16 s4, s0
-; CHECK-NEXT:    vins.f16 s1, s0
-; CHECK-NEXT:    vins.f16 s6, s4
-; CHECK-NEXT:    vins.f16 s5, s3
-; CHECK-NEXT:    vmov.f32 s4, s2
-; CHECK-NEXT:    vmov.f32 s7, s1
-; CHECK-NEXT:    vmov q0, q1
-; CHECK-NEXT:    bx lr
+; CHECK-LV-LABEL: shuffle3_f16:
+; CHECK-LV:       @ %bb.0: @ %entry
+; CHECK-LV-NEXT:    vmovx.f16 s5, s3
+; CHECK-LV-NEXT:    vmovx.f16 s6, s1
+; CHECK-LV-NEXT:    vmovx.f16 s4, s0
+; CHECK-LV-NEXT:    vins.f16 s1, s0
+; CHECK-LV-NEXT:    vins.f16 s6, s4
+; CHECK-LV-NEXT:    vins.f16 s5, s3
+; CHECK-LV-NEXT:    vmov.f32 s4, s2
+; CHECK-LV-NEXT:    vmov.f32 s7, s1
+; CHECK-LV-NEXT:    vmov q0, q1
+; CHECK-LV-NEXT:    bx lr
+
+; CHECK-LIS-LABEL: shuffle3_f16:
+; CHECK-LIS:       @ %bb.0: @ %entry
+; CHECK-LIS-NEXT:    vmov q1, q0
+; CHECK-LIS-NEXT:    vmovx.f16 s2, s5
+; CHECK-LIS-NEXT:    vmovx.f16 s0, s4
+; CHECK-LIS-NEXT:    vins.f16 s5, s4
+; CHECK-LIS-NEXT:    vins.f16 s2, s0
+; CHECK-LIS-NEXT:    vmov.f32 s0, s6
+; CHECK-LIS-NEXT:    vmovx.f16 s1, s7
+; CHECK-LIS-NEXT:    vmov.f32 s3, s5
+; CHECK-LIS-NEXT:    vins.f16 s1, s7
+; CHECK-LIS-NEXT:    bx lr
 entry:
   %out = shufflevector <8 x half> %src, <8 x half> undef, <8 x i32> <i32 4, i32 5, i32 7, i32 6, i32 3, i32 1, i32 2, i32 0>
   ret <8 x half> %out
@@ -1467,27 +1493,47 @@ entry:
   ret <2 x double> %out
 }
 define arm_aapcs_vfpcc <8 x double> @shuffle9_f64(<4 x double> %src1, <4 x double> %src2) {
-; CHECK-LABEL: shuffle9_f64:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .vsave {d8, d9, d10, d11}
-; CHECK-NEXT:    vpush {d8, d9, d10, d11}
-; CHECK-NEXT:    vmov q5, q2
-; CHECK-NEXT:    vmov.f32 s16, s0
-; CHECK-NEXT:    vmov.f32 s18, s20
-; CHECK-NEXT:    vmov.f32 s20, s2
-; CHECK-NEXT:    vmov.f32 s10, s12
-; CHECK-NEXT:    vmov.f32 s19, s21
-; CHECK-NEXT:    vmov.f32 s8, s4
-; CHECK-NEXT:    vmov.f32 s17, s1
-; CHECK-NEXT:    vmov.f32 s21, s3
-; CHECK-NEXT:    vmov q0, q4
-; CHECK-NEXT:    vmov.f32 s12, s6
-; CHECK-NEXT:    vmov.f32 s11, s13
-; CHECK-NEXT:    vmov.f32 s9, s5
-; CHECK-NEXT:    vmov.f32 s13, s7
-; CHECK-NEXT:    vmov q1, q5
-; CHECK-NEXT:    vpop {d8, d9, d10, d11}
-; CHECK-NEXT:    bx lr
+; CHECK-LV-LABEL: shuffle9_f64:
+; CHECK-LV:       @ %bb.0: @ %entry
+; CHECK-LV-NEXT:    .vsave {d8, d9, d10, d11}
+; CHECK-LV-NEXT:    vpush {d8, d9, d10, d11}
+; CHECK-LV-NEXT:    vmov q5, q2
+; CHECK-LV-NEXT:    vmov.f32 s16, s0
+; CHECK-LV-NEXT:    vmov.f32 s18, s20
+; CHECK-LV-NEXT:    vmov.f32 s20, s2
+; CHECK-LV-NEXT:    vmov.f32 s10, s12
+; CHECK-LV-NEXT:    vmov.f32 s19, s21
+; CHECK-LV-NEXT:    vmov.f32 s8, s4
+; CHECK-LV-NEXT:    vmov.f32 s17, s1
+; CHECK-LV-NEXT:    vmov.f32 s21, s3
+; CHECK-LV-NEXT:    vmov q0, q4
+; CHECK-LV-NEXT:    vmov.f32 s12, s6
+; CHECK-LV-NEXT:    vmov.f32 s11, s13
+; CHECK-LV-NEXT:    vmov.f32 s9, s5
+; CHECK-LV-NEXT:    vmov.f32 s13, s7
+; CHECK-LV-NEXT:    vmov q1, q5
+; CHECK-LV-NEXT:    vpop {d8, d9, d10, d11}
+; CHECK-LV-NEXT:    bx lr
+
+; CHECK-LIS-LABEL: shuffle9_f64:
+; CHECK-LIS:       @ %bb.0: @ %entry
+; CHECK-LIS-NEXT:    .vsave {d8, d9, d10, d11}
+; CHECK-LIS-NEXT:    vpush {d8, d9, d10, d11}
+; CHECK-LIS-NEXT:    vmov q5, q2
+; CHECK-LIS-NEXT:    vmov q4, q0
+; CHECK-LIS-NEXT:    vmov.f32 s2, s20
+; CHECK-LIS-NEXT:    vmov.f32 s20, s18
+; CHECK-LIS-NEXT:    vmov.f32 s10, s12
+; CHECK-LIS-NEXT:    vmov.f32 s3, s21
+; CHECK-LIS-NEXT:    vmov.f32 s8, s4
+; CHECK-LIS-NEXT:    vmov.f32 s21, s19
+; CHECK-LIS-NEXT:    vmov.f32 s12, s6
+; CHECK-LIS-NEXT:    vmov.f32 s11, s13
+; CHECK-LIS-NEXT:    vmov.f32 s9, s5
+; CHECK-LIS-NEXT:    vmov.f32 s13, s7
+; CHECK-LIS-NEXT:    vmov q1, q5
+; CHECK-LIS-NEXT:    vpop {d8, d9, d10, d11}
+; CHECK-LIS-NEXT:    bx lr
 entry:
   %out = shufflevector <4 x double> %src1, <4 x double> %src2, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
   ret <8 x double> %out
@@ -1560,27 +1606,47 @@ entry:
   ret <2 x i64> %out
 }
 define arm_aapcs_vfpcc <8 x i64> @shuffle9_i64(<4 x i64> %src1, <4 x i64> %src2) {
-; CHECK-LABEL: shuffle9_i64:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .vsave {d8, d9, d10, d11}
-; CHECK-NEXT:    vpush {d8, d9, d10, d11}
-; CHECK-NEXT:    vmov q5, q2
-; CHECK-NEXT:    vmov.f32 s16, s0
-; CHECK-NEXT:    vmov.f32 s18, s20
-; CHECK-NEXT:    vmov.f32 s20, s2
-; CHECK-NEXT:    vmov.f32 s10, s12
-; CHECK-NEXT:    vmov.f32 s19, s21
-; CHECK-NEXT:    vmov.f32 s8, s4
-; CHECK-NEXT:    vmov.f32 s17, s1
-; CHECK-NEXT:    vmov.f32 s21, s3
-; CHECK-NEXT:    vmov q0, q4
-; CHECK-NEXT:    vmov.f32 s12, s6
-; CHECK-NEXT:    vmov.f32 s11, s13
-; CHECK-NEXT:    vmov.f32 s9, s5
-; CHECK-NEXT:    vmov.f32 s13, s7
-; CHECK-NEXT:    vmov q1, q5
-; CHECK-NEXT:    vpop {d8, d9, d10, d11}
-; CHECK-NEXT:    bx lr
+; CHECK-LV-LABEL: shuffle9_i64:
+; CHECK-LV:       @ %bb.0: @ %entry
+; CHECK-LV-NEXT:    .vsave {d8, d9, d10, d11}
+; CHECK-LV-NEXT:    vpush {d8, d9, d10, d11}
+; CHECK-LV-NEXT:    vmov q5, q2
+; CHECK-LV-NEXT:    vmov.f32 s16, s0
+; CHECK-LV-NEXT:    vmov.f32 s18, s20
+; CHECK-LV-NEXT:    vmov.f32 s20, s2
+; CHECK-LV-NEXT:    vmov.f32 s10, s12
+; CHECK-LV-NEXT:    vmov.f32 s19, s21
+; CHECK-LV-NEXT:    vmov.f32 s8, s4
+; CHECK-LV-NEXT:    vmov.f32 s17, s1
+; CHECK-LV-NEXT:    vmov.f32 s21, s3
+; CHECK-LV-NEXT:    vmov q0, q4
+; CHECK-LV-NEXT:    vmov.f32 s12, s6
+; CHECK-LV-NEXT:    vmov.f32 s11, s13
+; CHECK-LV-NEXT:    vmov.f32 s9, s5
+; CHECK-LV-NEXT:    vmov.f32 s13, s7
+; CHECK-LV-NEXT:    vmov q1, q5
+; CHECK-LV-NEXT:    vpop {d8, d9, d10, d11}
+; CHECK-LV-NEXT:    bx lr
+
+; CHECK-LIS-LABEL: shuffle9_i64:
+; CHECK-LIS:       @ %bb.0: @ %entry
+; CHECK-LIS-NEXT:    .vsave {d8, d9, d10, d11}
+; CHECK-LIS-NEXT:    vpush {d8, d9, d10, d11}
+; CHECK-LIS-NEXT:    vmov q5, q2
+; CHECK-LIS-NEXT:    vmov q4, q0
+; CHECK-LIS-NEXT:    vmov.f32 s2, s20
+; CHECK-LIS-NEXT:    vmov.f32 s20, s18
+; CHECK-LIS-NEXT:    vmov.f32 s10, s12
+; CHECK-LIS-NEXT:    vmov.f32 s3, s21
+; CHECK-LIS-NEXT:    vmov.f32 s8, s4
+; CHECK-LIS-NEXT:    vmov.f32 s21, s19
+; CHECK-LIS-NEXT:    vmov.f32 s12, s6
+; CHECK-LIS-NEXT:    vmov.f32 s11, s13
+; CHECK-LIS-NEXT:    vmov.f32 s9, s5
+; CHECK-LIS-NEXT:    vmov.f32 s13, s7
+; CHECK-LIS-NEXT:    vmov q1, q5
+; CHECK-LIS-NEXT:    vpop {d8, d9, d10, d11}
+; CHECK-LIS-NEXT:    bx lr
 entry:
   %out = shufflevector <4 x i64> %src1, <4 x i64> %src2, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
   ret <8 x i64> %out
@@ -1822,4 +1888,4 @@ entry:
 
 ;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
 ; CHECK-LIS: {{.*}}
-; CHECK-LV: {{.*}}
+; CHECK-LV: {{.*}}
\ No newline at end of file
diff --git a/llvm/test/CodeGen/Thumb2/mve-vld3.ll b/llvm/test/CodeGen/Thumb2/mve-vld3.ll
index 0c58abaa1c86e..b6c8056891f83 100644
--- a/llvm/test/CodeGen/Thumb2/mve-vld3.ll
+++ b/llvm/test/CodeGen/Thumb2/mve-vld3.ll
@@ -33,29 +33,53 @@ entry:
 }
 
 define void @vld3_v4i32(ptr %src, ptr %dst) {
-; CHECK-LABEL: vld3_v4i32:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .vsave {d8, d9}
-; CHECK-NEXT:    vpush {d8, d9}
-; CHECK-NEXT:    vldrw.u32 q0, [r0, #16]
-; CHECK-NEXT:    vldrw.u32 q1, [r0]
-; CHECK-NEXT:    vldrw.u32 q4, [r0, #32]
-; CHECK-NEXT:    vmov.f32 s10, s2
-; CHECK-NEXT:    vmov.f32 s13, s0
-; CHECK-NEXT:    vmov.f32 s14, s3
-; CHECK-NEXT:    vmov.f32 s8, s4
-; CHECK-NEXT:    vmov.f32 s9, s7
-; CHECK-NEXT:    vmov.f32 s12, s5
-; CHECK-NEXT:    vmov.f32 s15, s18
-; CHECK-NEXT:    vmov.f32 s11, s17
-; CHECK-NEXT:    vadd.i32 q2, q2, q3
-; CHECK-NEXT:    vmov.f32 s0, s6
-; CHECK-NEXT:    vmov.f32 s2, s16
-; CHECK-NEXT:    vmov.f32 s3, s19
-; CHECK-NEXT:    vadd.i32 q0, q2, q0
-; CHECK-NEXT:    vstrw.32 q0, [r1]
-; CHECK-NEXT:    vpop {d8, d9}
-; CHECK-NEXT:    bx lr
+; CHECK-LV-LABEL: vld3_v4i32:
+; CHECK-LV:       @ %bb.0: @ %entry
+; CHECK-LV-NEXT:    .vsave {d8, d9}
+; CHECK-LV-NEXT:    vpush {d8, d9}
+; CHECK-LV-NEXT:    vldrw.u32 q0, [r0, #16]
+; CHECK-LV-NEXT:    vldrw.u32 q1, [r0]
+; CHECK-LV-NEXT:    vldrw.u32 q4, [r0, #32]
+; CHECK-LV-NEXT:    vmov.f32 s10, s2
+; CHECK-LV-NEXT:    vmov.f32 s13, s0
+; CHECK-LV-NEXT:    vmov.f32 s14, s3
+; CHECK-LV-NEXT:    vmov.f32 s8, s4
+; CHECK-LV-NEXT:    vmov.f32 s9, s7
+; CHECK-LV-NEXT:    vmov.f32 s12, s5
+; CHECK-LV-NEXT:    vmov.f32 s15, s18
+; CHECK-LV-NEXT:    vmov.f32 s11, s17
+; CHECK-LV-NEXT:    vadd.i32 q2, q2, q3
+; CHECK-LV-NEXT:    vmov.f32 s0, s6
+; CHECK-LV-NEXT:    vmov.f32 s2, s16
+; CHECK-LV-NEXT:    vmov.f32 s3, s19
+; CHECK-LV-NEXT:    vadd.i32 q0, q2, q0
+; CHECK-LV-NEXT:    vstrw.32 q0, [r1]
+; CHECK-LV-NEXT:    vpop {d8, d9}
+; CHECK-LV-NEXT:    bx lr
+
+; CHECK-LIS-LABEL: vld3_v4i32:
+; CHECK-LIS:       @ %bb.0: @ %entry
+; CHECK-LIS-NEXT:    .vsave {d8, d9}
+; CHECK-LIS-NEXT:    vpush {d8, d9}
+; CHECK-LIS-NEXT:    vldrw.u32 q0, [r0, #16]
+; CHECK-LIS-NEXT:    vldrw.u32 q1, [r0]
+; CHECK-LIS-NEXT:    vldrw.u32 q3, [r0, #32]
+; CHECK-LIS-NEXT:    vmov.f32 s10, s2
+; CHECK-LIS-NEXT:    vmov.f32 s17, s0
+; CHECK-LIS-NEXT:    vmov.f32 s18, s3
+; CHECK-LIS-NEXT:    vmov.f32 s8, s4
+; CHECK-LIS-NEXT:    vmov.f32 s9, s7
+; CHECK-LIS-NEXT:    vmov.f32 s16, s5
+; CHECK-LIS-NEXT:    vmov.f32 s19, s14
+; CHECK-LIS-NEXT:    vmov.f32 s11, s13
+; CHECK-LIS-NEXT:    vadd.i32 q2, q2, q4
+; CHECK-LIS-NEXT:    vmov.f32 s0, s6
+; CHECK-LIS-NEXT:    vmov.f32 s2, s12
+; CHECK-LIS-NEXT:    vmov.f32 s3, s15
+; CHECK-LIS-NEXT:    vadd.i32 q0, q2, q0
+; CHECK-LIS-NEXT:    vstrw.32 q0, [r1]
+; CHECK-LIS-NEXT:    vpop {d8, d9}
+; CHECK-LIS-NEXT:    bx lr
 entry:
   %l1 = load <12 x i32>, ptr %src, align 4
   %s1 = shufflevector <12 x i32> %l1, <12 x i32> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
@@ -68,46 +92,87 @@ entry:
 }
 
 define void @vld3_v8i32(ptr %src, ptr %dst) {
-; CHECK-LABEL: vld3_v8i32:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .vsave {d8, d9, d10, d11}
-; CHECK-NEXT:    vpush {d8, d9, d10, d11}
-; CHECK-NEXT:    vldrw.u32 q0, [r0, #64]
-; CHECK-NEXT:    vldrw.u32 q1, [r0, #48]
-; CHECK-NEXT:    vldrw.u32 q4, [r0, #80]
-; CHECK-NEXT:    vmov.f32 s10, s2
-; CHECK-NEXT:    vmov.f32 s13, s0
-; CHECK-NEXT:    vmov.f32 s14, s3
-; CHECK-NEXT:    vmov.f32 s8, s4
-; CHECK-NEXT:    vmov.f32 s9, s7
-; CHECK-NEXT:    vmov.f32 s12, s5
-; CHECK-NEXT:    vmov.f32 s15, s18
-; CHECK-NEXT:    vmov.f32 s11, s17
-; CHECK-NEXT:    vadd.i32 q2, q2, q3
-; CHECK-NEXT:    vmov.f32 s0, s6
-; CHECK-NEXT:    vmov.f32 s2, s16
-; CHECK-NEXT:    vldrw.u32 q1, [r0, #16]
-; CHECK-NEXT:    vmov.f32 s3, s19
-; CHECK-NEXT:    vldrw.u32 q3, [r0, #32]
-; CHECK-NEXT:    vadd.i32 q0, q2, q0
-; CHECK-NEXT:    vldrw.u32 q2, [r0]
-; CHECK-NEXT:    vmov.f32 s17, s4
-; CHECK-NEXT:    vstrw.32 q0, [r1, #16]
-; CHECK-NEXT:    vmov.f32 s18, s7
-; CHECK-NEXT:    vmov.f32 s22, s6
-; CHECK-NEXT:    vmov.f32 s16, s9
-; CHECK-NEXT:    vmov.f32 s19, s14
-; CHECK-NEXT:    vmov.f32 s20, s8
-; CHECK-NEXT:    vmov.f32 s21, s11
-; CHECK-NEXT:    vmov.f32 s23, s13
-; CHECK-NEXT:    vadd.i32 q4, q5, q4
-; CHECK-NEXT:    vmov.f32 s4, s10
-; CHECK-NEXT:    vmov.f32 s6, s12
-; CHECK-NEXT:    vmov.f32 s7, s15
-; CHECK-NEXT:    vadd.i32 q1, q4, q1
-; CHECK-NEXT:    vstrw.32 q1, [r1]
-; CHECK-NEXT:    vpop {d8, d9, d10, d11}
-; CHECK-NEXT:    bx lr
+; CHECK-LV-LABEL: vld3_v8i32:
+; CHECK-LV:       @ %bb.0: @ %entry
+; CHECK-LV-NEXT:    .vsave {d8, d9, d10, d11}
+; CHECK-LV-NEXT:    vpush {d8, d9, d10, d11}
+; CHECK-LV-NEXT:    vldrw.u32 q0, [r0, #64]
+; CHECK-LV-NEXT:    vldrw.u32 q1, [r0, #48]
+; CHECK-LV-NEXT:    vldrw.u32 q4, [r0, #80]
+; CHECK-LV-NEXT:    vmov.f32 s10, s2
+; CHECK-LV-NEXT:    vmov.f32 s13, s0
+; CHECK-LV-NEXT:    vmov.f32 s14, s3
+; CHECK-LV-NEXT:    vmov.f32 s8, s4
+; CHECK-LV-NEXT:    vmov.f32 s9, s7
+; CHECK-LV-NEXT:    vmov.f32 s12, s5
+; CHECK-LV-NEXT:    vmov.f32 s15, s18
+; CHECK-LV-NEXT:    vmov.f32 s11, s17
+; CHECK-LV-NEXT:    vadd.i32 q2, q2, q3
+; CHECK-LV-NEXT:    vmov.f32 s0, s6
+; CHECK-LV-NEXT:    vmov.f32 s2, s16
+; CHECK-LV-NEXT:    vldrw.u32 q1, [r0, #16]
+; CHECK-LV-NEXT:    vmov.f32 s3, s19
+; CHECK-LV-NEXT:    vldrw.u32 q3, [r0, #32]
+; CHECK-LV-NEXT:    vadd.i32 q0, q2, q0
+; CHECK-LV-NEXT:    vldrw.u32 q2, [r0]
+; CHECK-LV-NEXT:    vmov.f32 s17, s4
+; CHECK-LV-NEXT:    vstrw.32 q0, [r1, #16]
+; CHECK-LV-NEXT:    vmov.f32 s18, s7
+; CHECK-LV-NEXT:    vmov.f32 s22, s6
+; CHECK-LV-NEXT:    vmov.f32 s16, s9
+; CHECK-LV-NEXT:    vmov.f32 s19, s14
+; CHECK-LV-NEXT:    vmov.f32 s20, s8
+; CHECK-LV-NEXT:    vmov.f32 s21, s11
+; CHECK-LV-NEXT:    vmov.f32 s23, s13
+; CHECK-LV-NEXT:    vadd.i32 q4, q5, q4
+; CHECK-LV-NEXT:    vmov.f32 s4, s10
+; CHECK-LV-NEXT:    vmov.f32 s6, s12
+; CHECK-LV-NEXT:    vmov.f32 s7, s15
+; CHECK-LV-NEXT:    vadd.i32 q1, q4, q1
+; CHECK-LV-NEXT:    vstrw.32 q1, [r1]
+; CHECK-LV-NEXT:    vpop {d8, d9, d10, d11}
+; CHECK-LV-NEXT:    bx lr
+
+; CHECK-LIS-LABEL: vld3_v8i32:
+; CHECK-LIS:       @ %bb.0: @ %entry
+; CHECK-LIS-NEXT:    .vsave {d8, d9, d10, d11}
+; CHECK-LIS-NEXT:    vpush {d8, d9, d10, d11}
+; CHECK-LIS-NEXT:    vldrw.u32 q0, [r0, #64]
+; CHECK-LIS-NEXT:    vldrw.u32 q1, [r0, #48]
+; CHECK-LIS-NEXT:    vldrw.u32 q3, [r0, #80]
+; CHECK-LIS-NEXT:    vmov.f32 s10, s2
+; CHECK-LIS-NEXT:    vmov.f32 s17, s0
+; CHECK-LIS-NEXT:    vmov.f32 s18, s3
+; CHECK-LIS-NEXT:    vmov.f32 s8, s4
+; CHECK-LIS-NEXT:    vmov.f32 s9, s7
+; CHECK-LIS-NEXT:    vmov.f32 s16, s5
+; CHECK-LIS-NEXT:    vmov.f32 s19, s14
+; CHECK-LIS-NEXT:    vmov.f32 s11, s13
+; CHECK-LIS-NEXT:    vmov.f32 s0, s6
+; CHECK-LIS-NEXT:    vadd.i32 q2, q2, q4
+; CHECK-LIS-NEXT:    vmov.f32 s2, s12
+; CHECK-LIS-NEXT:    vldrw.u32 q1, [r0, #16]
+; CHECK-LIS-NEXT:    vmov.f32 s3, s15
+; CHECK-LIS-NEXT:    vldrw.u32 q3, [r0, #32]
+; CHECK-LIS-NEXT:    vadd.i32 q0, q2, q0
+; CHECK-LIS-NEXT:    vldrw.u32 q2, [r0]
+; CHECK-LIS-NEXT:    vmov.f32 s17, s4
+; CHECK-LIS-NEXT:    vstrw.32 q0, [r1, #16]
+; CHECK-LIS-NEXT:    vmov.f32 s18, s7
+; CHECK-LIS-NEXT:    vmov.f32 s22, s6
+; CHECK-LIS-NEXT:    vmov.f32 s16, s9
+; CHECK-LIS-NEXT:    vmov.f32 s19, s14
+; CHECK-LIS-NEXT:    vmov.f32 s20, s8
+; CHECK-LIS-NEXT:    vmov.f32 s21, s11
+; CHECK-LIS-NEXT:    vmov.f32 s23, s13
+; CHECK-LIS-NEXT:    vadd.i32 q4, q5, q4
+; CHECK-LIS-NEXT:    vmov.f32 s4, s10
+; CHECK-LIS-NEXT:    vmov.f32 s6, s12
+; CHECK-LIS-NEXT:    vmov.f32 s7, s15
+; CHECK-LIS-NEXT:    vadd.i32 q1, q4, q1
+; CHECK-LIS-NEXT:    vstrw.32 q1, [r1]
+; CHECK-LIS-NEXT:    vpop {d8, d9, d10, d11}
+; CHECK-LIS-NEXT:    bx lr
 entry:
   %l1 = load <24 x i32>, ptr %src, align 4
   %s1 = shufflevector <24 x i32> %l1, <24 x i32> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
@@ -120,80 +185,155 @@ entry:
 }
 
 define void @vld3_v16i32(ptr %src, ptr %dst) {
-; CHECK-LABEL: vld3_v16i32:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .vsave {d8, d9, d10, d11, d12, d13, d14, d15}
-; CHECK-NEXT:    vpush {d8, d9, d10, d11, d12, d13, d14, d15}
-; CHECK-NEXT:    vldrw.u32 q0, [r0, #64]
-; CHECK-NEXT:    vldrw.u32 q1, [r0, #48]
-; CHECK-NEXT:    vldrw.u32 q4, [r0, #80]
-; CHECK-NEXT:    vldrw.u32 q6, [r0, #176]
-; CHECK-NEXT:    vmov.f32 s10, s2
-; CHECK-NEXT:    vmov.f32 s13, s0
-; CHECK-NEXT:    vmov.f32 s14, s3
-; CHECK-NEXT:    vmov.f32 s8, s4
-; CHECK-NEXT:    vmov.f32 s9, s7
-; CHECK-NEXT:    vmov.f32 s12, s5
-; CHECK-NEXT:    vmov.f32 s15, s18
-; CHECK-NEXT:    vmov.f32 s11, s17
-; CHECK-NEXT:    vadd.i32 q2, q2, q3
-; CHECK-NEXT:    vmov.f32 s0, s6
-; CHECK-NEXT:    vmov.f32 s2, s16
-; CHECK-NEXT:    vldrw.u32 q1, [r0, #16]
-; CHECK-NEXT:    vmov.f32 s3, s19
-; CHECK-NEXT:    vldrw.u32 q3, [r0, #32]
-; CHECK-NEXT:    vadd.i32 q0, q2, q0
-; CHECK-NEXT:    vldrw.u32 q2, [r0]
-; CHECK-NEXT:    vmov.f32 s17, s4
-; CHECK-NEXT:    vmov.f32 s18, s7
-; CHECK-NEXT:    vmov.f32 s22, s6
-; CHECK-NEXT:    vmov.f32 s16, s9
-; CHECK-NEXT:    vmov.f32 s19, s14
-; CHECK-NEXT:    vmov.f32 s20, s8
-; CHECK-NEXT:    vmov.f32 s21, s11
-; CHECK-NEXT:    vmov.f32 s23, s13
-; CHECK-NEXT:    vmov.f32 s4, s10
-; CHECK-NEXT:    vldrw.u32 q2, [r0, #160]
-; CHECK-NEXT:    vmov.f32 s6, s12
-; CHECK-NEXT:    vadd.i32 q4, q5, q4
-; CHECK-NEXT:    vmov.f32 s7, s15
-; CHECK-NEXT:    vldrw.u32 q3, [r0, #144]
-; CHECK-NEXT:    vadd.i32 q1, q4, q1
-; CHECK-NEXT:    vmov.f32 s18, s10
-; CHECK-NEXT:    vmov.f32 s21, s8
-; CHECK-NEXT:    vmov.f32 s22, s11
-; CHECK-NEXT:    vmov.f32 s16, s12
-; CHECK-NEXT:    vmov.f32 s17, s15
-; CHECK-NEXT:    vmov.f32 s20, s13
-; CHECK-NEXT:    vmov.f32 s23, s26
-; CHECK-NEXT:    vmov.f32 s19, s25
-; CHECK-NEXT:    vadd.i32 q4, q4, q5
-; CHECK-NEXT:    vmov.f32 s8, s14
-; CHECK-NEXT:    vmov.f32 s10, s24
-; CHECK-NEXT:    vldrw.u32 q3, [r0, #112]
-; CHECK-NEXT:    vmov.f32 s11, s27
-; CHECK-NEXT:    vldrw.u32 q5, [r0, #128]
-; CHECK-NEXT:    vadd.i32 q2, q4, q2
-; CHECK-NEXT:    vldrw.u32 q4, [r0, #96]
-; CHECK-NEXT:    vmov.f32 s25, s12
-; CHECK-NEXT:    vstrw.32 q2, [r1, #48]
-; CHECK-NEXT:    vmov.f32 s26, s15
-; CHECK-NEXT:    vstrw.32 q0, [r1, #16]
-; CHECK-NEXT:    vmov.f32 s30, s14
-; CHECK-NEXT:    vstrw.32 q1, [r1]
-; CHECK-NEXT:    vmov.f32 s24, s17
-; CHECK-NEXT:    vmov.f32 s27, s22
-; CHECK-NEXT:    vmov.f32 s28, s16
-; CHECK-NEXT:    vmov.f32 s29, s19
-; CHECK-NEXT:    vmov.f32 s31, s21
-; CHECK-NEXT:    vadd.i32 q6, q7, q6
-; CHECK-NEXT:    vmov.f32 s12, s18
-; CHECK-NEXT:    vmov.f32 s14, s20
-; CHECK-NEXT:    vmov.f32 s15, s23
-; CHECK-NEXT:    vadd.i32 q3, q6, q3
-; CHECK-NEXT:    vstrw.32 q3, [r1, #32]
-; CHECK-NEXT:    vpop {d8, d9, d10, d11, d12, d13, d14, d15}
-; CHECK-NEXT:    bx lr
+; CHECK-LV-LABEL: vld3_v16i32:
+; CHECK-LV:       @ %bb.0: @ %entry
+; CHECK-LV-NEXT:    .vsave {d8, d9, d10, d11, d12, d13, d14, d15}
+; CHECK-LV-NEXT:    vpush {d8, d9, d10, d11, d12, d13, d14, d15}
+; CHECK-LV-NEXT:    vldrw.u32 q0, [r0, #64]
+; CHECK-LV-NEXT:    vldrw.u32 q1, [r0, #48]
+; CHECK-LV-NEXT:    vldrw.u32 q4, [r0, #80]
+; CHECK-LV-NEXT:    vldrw.u32 q6, [r0, #176]
+; CHECK-LV-NEXT:    vmov.f32 s10, s2
+; CHECK-LV-NEXT:    vmov.f32 s13, s0
+; CHECK-LV-NEXT:    vmov.f32 s14, s3
+; CHECK-LV-NEXT:    vmov.f32 s8, s4
+; CHECK-LV-NEXT:    vmov.f32 s9, s7
+; CHECK-LV-NEXT:    vmov.f32 s12, s5
+; CHECK-LV-NEXT:    vmov.f32 s15, s18
+; CHECK-LV-NEXT:    vmov.f32 s11, s17
+; CHECK-LV-NEXT:    vadd.i32 q2, q2, q3
+; CHECK-LV-NEXT:    vmov.f32 s0, s6
+; CHECK-LV-NEXT:    vmov.f32 s2, s16
+; CHECK-LV-NEXT:    vldrw.u32 q1, [r0, #16]
+; CHECK-LV-NEXT:    vmov.f32 s3, s19
+; CHECK-LV-NEXT:    vldrw.u32 q3, [r0, #32]
+; CHECK-LV-NEXT:    vadd.i32 q0, q2, q0
+; CHECK-LV-NEXT:    vldrw.u32 q2, [r0]
+; CHECK-LV-NEXT:    vmov.f32 s17, s4
+; CHECK-LV-NEXT:    vmov.f32 s18, s7
+; CHECK-LV-NEXT:    vmov.f32 s22, s6
+; CHECK-LV-NEXT:    vmov.f32 s16, s9
+; CHECK-LV-NEXT:    vmov.f32 s19, s14
+; CHECK-LV-NEXT:    vmov.f32 s20, s8
+; CHECK-LV-NEXT:    vmov.f32 s21, s11
+; CHECK-LV-NEXT:    vmov.f32 s23, s13
+; CHECK-LV-NEXT:    vmov.f32 s4, s10
+; CHECK-LV-NEXT:    vldrw.u32 q2, [r0, #160]
+; CHECK-LV-NEXT:    vmov.f32 s6, s12
+; CHECK-LV-NEXT:    vadd.i32 q4, q5, q4
+; CHECK-LV-NEXT:    vmov.f32 s7, s15
+; CHECK-LV-NEXT:    vldrw.u32 q3, [r0, #144]
+; CHECK-LV-NEXT:    vadd.i32 q1, q4, q1
+; CHECK-LV-NEXT:    vmov.f32 s18, s10
+; CHECK-LV-NEXT:    vmov.f32 s21, s8
+; CHECK-LV-NEXT:    vmov.f32 s22, s11
+; CHECK-LV-NEXT:    vmov.f32 s16, s12
+; CHECK-LV-NEXT:    vmov.f32 s17, s15
+; CHECK-LV-NEXT:    vmov.f32 s20, s13
+; CHECK-LV-NEXT:    vmov.f32 s23, s26
+; CHECK-LV-NEXT:    vmov.f32 s19, s25
+; CHECK-LV-NEXT:    vadd.i32 q4, q4, q5
+; CHECK-LV-NEXT:    vmov.f32 s8, s14
+; CHECK-LV-NEXT:    vmov.f32 s10, s24
+; CHECK-LV-NEXT:    vldrw.u32 q3, [r0, #112]
+; CHECK-LV-NEXT:    vmov.f32 s11, s27
+; CHECK-LV-NEXT:    vldrw.u32 q5, [r0, #128]
+; CHECK-LV-NEXT:    vadd.i32 q2, q4, q2
+; CHECK-LV-NEXT:    vldrw.u32 q4, [r0, #96]
+; CHECK-LV-NEXT:    vmov.f32 s25, s12
+; CHECK-LV-NEXT:    vstrw.32 q2, [r1, #48]
+; CHECK-LV-NEXT:    vmov.f32 s26, s15
+; CHECK-LV-NEXT:    vstrw.32 q0, [r1, #16]
+; CHECK-LV-NEXT:    vmov.f32 s30, s14
+; CHECK-LV-NEXT:    vstrw.32 q1, [r1]
+; CHECK-LV-NEXT:    vmov.f32 s24, s17
+; CHECK-LV-NEXT:    vmov.f32 s27, s22
+; CHECK-LV-NEXT:    vmov.f32 s28, s16
+; CHECK-LV-NEXT:    vmov.f32 s29, s19
+; CHECK-LV-NEXT:    vmov.f32 s31, s21
+; CHECK-LV-NEXT:    vadd.i32 q6, q7, q6
+; CHECK-LV-NEXT:    vmov.f32 s12, s18
+; CHECK-LV-NEXT:    vmov.f32 s14, s20
+; CHECK-LV-NEXT:    vmov.f32 s15, s23
+; CHECK-LV-NEXT:    vadd.i32 q3, q6, q3
+; CHECK-LV-NEXT:    vstrw.32 q3, [r1, #32]
+; CHECK-LV-NEXT:    vpop {d8, d9, d10, d11, d12, d13, d14, d15}
+; CHECK-LV-NEXT:    bx lr
+
+; CHECK-LIS-LABEL: vld3_v16i32:
+; CHECK-LIS:       @ %bb.0: @ %entry
+; CHECK-LIS-NEXT:    .vsave {d8, d9, d10, d11, d12, d13, d14, d15}
+; CHECK-LIS-NEXT:    vpush {d8, d9, d10, d11, d12, d13, d14, d15}
+; CHECK-LIS-NEXT:    vldrw.u32 q0, [r0, #64]
+; CHECK-LIS-NEXT:    vldrw.u32 q1, [r0, #48]
+; CHECK-LIS-NEXT:    vldrw.u32 q3, [r0, #80]
+; CHECK-LIS-NEXT:    vmov.f32 s10, s2
+; CHECK-LIS-NEXT:    vmov.f32 s17, s0
+; CHECK-LIS-NEXT:    vmov.f32 s18, s3
+; CHECK-LIS-NEXT:    vmov.f32 s8, s4
+; CHECK-LIS-NEXT:    vmov.f32 s9, s7
+; CHECK-LIS-NEXT:    vmov.f32 s16, s5
+; CHECK-LIS-NEXT:    vmov.f32 s19, s14
+; CHECK-LIS-NEXT:    vmov.f32 s11, s13
+; CHECK-LIS-NEXT:    vmov.f32 s0, s6
+; CHECK-LIS-NEXT:    vadd.i32 q2, q2, q4
+; CHECK-LIS-NEXT:    vmov.f32 s2, s12
+; CHECK-LIS-NEXT:    vldrw.u32 q1, [r0, #16]
+; CHECK-LIS-NEXT:    vmov.f32 s3, s15
+; CHECK-LIS-NEXT:    vldrw.u32 q3, [r0, #32]
+; CHECK-LIS-NEXT:    vadd.i32 q0, q2, q0
+; CHECK-LIS-NEXT:    vldrw.u32 q2, [r0]
+; CHECK-LIS-NEXT:    vmov.f32 s17, s4
+; CHECK-LIS-NEXT:    vmov.f32 s18, s7
+; CHECK-LIS-NEXT:    vmov.f32 s22, s6
+; CHECK-LIS-NEXT:    vmov.f32 s16, s9
+; CHECK-LIS-NEXT:    vmov.f32 s19, s14
+; CHECK-LIS-NEXT:    vmov.f32 s20, s8
+; CHECK-LIS-NEXT:    vmov.f32 s21, s11
+; CHECK-LIS-NEXT:    vmov.f32 s23, s13
+; CHECK-LIS-NEXT:    vadd.i32 q4, q5, q4
+; CHECK-LIS-NEXT:    vmov.f32 s4, s10
+; CHECK-LIS-NEXT:    vldrw.u32 q2, [r0, #160]
+; CHECK-LIS-NEXT:    vldrw.u32 q5, [r0, #176]
+; CHECK-LIS-NEXT:    vmov.f32 s6, s12
+; CHECK-LIS-NEXT:    vmov.f32 s7, s15
+; CHECK-LIS-NEXT:    vldrw.u32 q3, [r0, #144]
+; CHECK-LIS-NEXT:    vadd.i32 q1, q4, q1
+; CHECK-LIS-NEXT:    vmov.f32 s18, s10
+; CHECK-LIS-NEXT:    vmov.f32 s25, s8
+; CHECK-LIS-NEXT:    vmov.f32 s26, s11
+; CHECK-LIS-NEXT:    vmov.f32 s16, s12
+; CHECK-LIS-NEXT:    vmov.f32 s17, s15
+; CHECK-LIS-NEXT:    vmov.f32 s24, s13
+; CHECK-LIS-NEXT:    vmov.f32 s27, s22
+; CHECK-LIS-NEXT:    vmov.f32 s19, s21
+; CHECK-LIS-NEXT:    vmov.f32 s8, s14
+; CHECK-LIS-NEXT:    vadd.i32 q4, q4, q6
+; CHECK-LIS-NEXT:    vmov.f32 s10, s20
+; CHECK-LIS-NEXT:    vldrw.u32 q3, [r0, #112]
+; CHECK-LIS-NEXT:    vmov.f32 s11, s23
+; CHECK-LIS-NEXT:    vldrw.u32 q5, [r0, #128]
+; CHECK-LIS-NEXT:    vadd.i32 q2, q4, q2
+; CHECK-LIS-NEXT:    vldrw.u32 q4, [r0, #96]
+; CHECK-LIS-NEXT:    vmov.f32 s25, s12
+; CHECK-LIS-NEXT:    vstrw.32 q2, [r1, #48]
+; CHECK-LIS-NEXT:    vmov.f32 s26, s15
+; CHECK-LIS-NEXT:    vstrw.32 q0, [r1, #16]
+; CHECK-LIS-NEXT:    vmov.f32 s30, s14
+; CHECK-LIS-NEXT:    vstrw.32 q1, [r1]
+; CHECK-LIS-NEXT:    vmov.f32 s24, s17
+; CHECK-LIS-NEXT:    vmov.f32 s27, s22
+; CHECK-LIS-NEXT:    vmov.f32 s28, s16
+; CHECK-LIS-NEXT:    vmov.f32 s29, s19
+; CHECK-LIS-NEXT:    vmov.f32 s31, s21
+; CHECK-LIS-NEXT:    vadd.i32 q6, q7, q6
+; CHECK-LIS-NEXT:    vmov.f32 s12, s18
+; CHECK-LIS-NEXT:    vmov.f32 s14, s20
+; CHECK-LIS-NEXT:    vmov.f32 s15, s23
+; CHECK-LIS-NEXT:    vadd.i32 q3, q6, q3
+; CHECK-LIS-NEXT:    vstrw.32 q3, [r1, #32]
+; CHECK-LIS-NEXT:    vpop {d8, d9, d10, d11, d12, d13, d14, d15}
+; CHECK-LIS-NEXT:    bx lr
 entry:
   %l1 = load <48 x i32>, ptr %src, align 4
   %s1 = shufflevector <48 x i32> %l1, <48 x i32> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
@@ -792,35 +932,65 @@ entry:
 ; i64
 
 define void @vld3_v2i64(ptr %src, ptr %dst) {
-; CHECK-LABEL: vld3_v2i64:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .save {r4, r5, r6, r7, r8, lr}
-; CHECK-NEXT:    push.w {r4, r5, r6, r7, r8, lr}
-; CHECK-NEXT:    vldrw.u32 q0, [r0]
-; CHECK-NEXT:    vldrw.u32 q1, [r0, #32]
-; CHECK-NEXT:    vldrw.u32 q2, [r0, #16]
-; CHECK-NEXT:    vmov.f32 s12, s2
-; CHECK-NEXT:    vmov.f32 s13, s3
-; CHECK-NEXT:    vmov.f32 s2, s4
-; CHECK-NEXT:    vmov.f32 s3, s5
-; CHECK-NEXT:    vmov r0, r3, d5
-; CHECK-NEXT:    vmov r2, r4, d3
-; CHECK-NEXT:    vmov r6, r7, d0
-; CHECK-NEXT:    vmov r5, r8, d6
-; CHECK-NEXT:    vmov lr, r12, d1
-; CHECK-NEXT:    adds.w r0, r0, lr
-; CHECK-NEXT:    adc.w r3, r3, r12
-; CHECK-NEXT:    adds r0, r0, r2
-; CHECK-NEXT:    adc.w r2, r3, r4
-; CHECK-NEXT:    vmov r3, r4, d4
-; CHECK-NEXT:    adds r6, r6, r5
-; CHECK-NEXT:    adc.w r7, r7, r8
-; CHECK-NEXT:    adds r3, r3, r6
-; CHECK-NEXT:    adcs r7, r4
-; CHECK-NEXT:    vmov q0[2], q0[0], r3, r0
-; CHECK-NEXT:    vmov q0[3], q0[1], r7, r2
-; CHECK-NEXT:    vstrw.32 q0, [r1]
-; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, pc}
+; CHECK-LV-LABEL: vld3_v2i64:
+; CHECK-LV:       @ %bb.0: @ %entry
+; CHECK-LV-NEXT:    .save {r4, r5, r6, r7, r8, lr}
+; CHECK-LV-NEXT:    push.w {r4, r5, r6, r7, r8, lr}
+; CHECK-LV-NEXT:    vldrw.u32 q0, [r0]
+; CHECK-LV-NEXT:    vldrw.u32 q1, [r0, #32]
+; CHECK-LV-NEXT:    vldrw.u32 q2, [r0, #16]
+; CHECK-LV-NEXT:    vmov.f32 s12, s2
+; CHECK-LV-NEXT:    vmov.f32 s13, s3
+; CHECK-LV-NEXT:    vmov.f32 s2, s4
+; CHECK-LV-NEXT:    vmov.f32 s3, s5
+; CHECK-LV-NEXT:    vmov r0, r3, d5
+; CHECK-LV-NEXT:    vmov r2, r4, d3
+; CHECK-LV-NEXT:    vmov r6, r7, d0
+; CHECK-LV-NEXT:    vmov r5, r8, d6
+; CHECK-LV-NEXT:    vmov lr, r12, d1
+; CHECK-LV-NEXT:    adds.w r0, r0, lr
+; CHECK-LV-NEXT:    adc.w r3, r3, r12
+; CHECK-LV-NEXT:    adds r0, r0, r2
+; CHECK-LV-NEXT:    adc.w r2, r3, r4
+; CHECK-LV-NEXT:    vmov r3, r4, d4
+; CHECK-LV-NEXT:    adds r6, r6, r5
+; CHECK-LV-NEXT:    adc.w r7, r7, r8
+; CHECK-LV-NEXT:    adds r3, r3, r6
+; CHECK-LV-NEXT:    adcs r7, r4
+; CHECK-LV-NEXT:    vmov q0[2], q0[0], r3, r0
+; CHECK-LV-NEXT:    vmov q0[3], q0[1], r7, r2
+; CHECK-LV-NEXT:    vstrw.32 q0, [r1]
+; CHECK-LV-NEXT:    pop.w {r4, r5, r6, r7, r8, pc}
+
+; CHECK-LIS-LABEL: vld3_v2i64:
+; CHECK-LIS:       @ %bb.0: @ %entry
+; CHECK-LIS-NEXT:    .save {r4, r5, r6, r7, r8, lr}
+; CHECK-LIS-NEXT:    push.w {r4, r5, r6, r7, r8, lr}
+; CHECK-LIS-NEXT:    vldrw.u32 q0, [r0]
+; CHECK-LIS-NEXT:    vldrw.u32 q1, [r0, #32]
+; CHECK-LIS-NEXT:    vldrw.u32 q3, [r0, #16]
+; CHECK-LIS-NEXT:    vmov.f32 s8, s2
+; CHECK-LIS-NEXT:    vmov.f32 s9, s3
+; CHECK-LIS-NEXT:    vmov.f32 s2, s4
+; CHECK-LIS-NEXT:    vmov.f32 s3, s5
+; CHECK-LIS-NEXT:    vmov r0, r3, d7
+; CHECK-LIS-NEXT:    vmov r2, r4, d3
+; CHECK-LIS-NEXT:    vmov r6, r7, d0
+; CHECK-LIS-NEXT:    vmov r5, r8, d4
+; CHECK-LIS-NEXT:    vmov lr, r12, d1
+; CHECK-LIS-NEXT:    adds.w r0, r0, lr
+; CHECK-LIS-NEXT:    adc.w r3, r3, r12
+; CHECK-LIS-NEXT:    adds r0, r0, r2
+; CHECK-LIS-NEXT:    adc.w r2, r3, r4
+; CHECK-LIS-NEXT:    vmov r3, r4, d6
+; CHECK-LIS-NEXT:    adds r6, r6, r5
+; CHECK-LIS-NEXT:    adc.w r7, r7, r8
+; CHECK-LIS-NEXT:    adds r3, r3, r6
+; CHECK-LIS-NEXT:    adcs r7, r4
+; CHECK-LIS-NEXT:    vmov q0[2], q0[0], r3, r0
+; CHECK-LIS-NEXT:    vmov q0[3], q0[1], r7, r2
+; CHECK-LIS-NEXT:    vstrw.32 q0, [r1]
+; CHECK-LIS-NEXT:    pop.w {r4, r5, r6, r7, r8, pc}
 entry:
   %l1 = load <6 x i64>, ptr %src, align 4
   %s1 = shufflevector <6 x i64> %l1, <6 x i64> undef, <2 x i32> <i32 0, i32 3>
@@ -917,28 +1087,28 @@ define void @vld3_v4i64(ptr %src, ptr %dst) {
 ; CHECK-LIS-NEXT:    vmov lr, r12, d1
 ; CHECK-LIS-NEXT:    vmov.f32 s2, s12
 ; CHECK-LIS-NEXT:    vmov.f32 s3, s13
-; CHECK-LIS-NEXT:    vmov r6, r7, d12
+; CHECK-LIS-NEXT:    vmov r7, r6, d12
 ; CHECK-LIS-NEXT:    adds.w r0, r5, lr
 ; CHECK-LIS-NEXT:    adc.w r5, r4, r12
 ; CHECK-LIS-NEXT:    adds.w lr, r0, r3
 ; CHECK-LIS-NEXT:    vmov r4, r2, d8
 ; CHECK-LIS-NEXT:    adc.w r12, r5, r8
 ; CHECK-LIS-NEXT:    vmov r5, r0, d10
-; CHECK-LIS-NEXT:    adds r6, r6, r4
-; CHECK-LIS-NEXT:    adcs r2, r7
-; CHECK-LIS-NEXT:    adds r6, r6, r5
+; CHECK-LIS-NEXT:    adds r7, r7, r4
+; CHECK-LIS-NEXT:    adcs r2, r6
+; CHECK-LIS-NEXT:    adds r7, r7, r5
 ; CHECK-LIS-NEXT:    adc.w r8, r2, r0
-; CHECK-LIS-NEXT:    vmov r7, r4, d1
+; CHECK-LIS-NEXT:    vmov r6, r4, d1
 ; CHECK-LIS-NEXT:    vmov r2, r5, d3
 ; CHECK-LIS-NEXT:    vmov r3, r0, d0
-; CHECK-LIS-NEXT:    adds r2, r2, r7
-; CHECK-LIS-NEXT:    adc.w r7, r5, r4
+; CHECK-LIS-NEXT:    adds r2, r2, r6
+; CHECK-LIS-NEXT:    adc.w r6, r5, r4
 ; CHECK-LIS-NEXT:    vmov r5, r4, d7
 ; CHECK-LIS-NEXT:    adds r2, r2, r5
-; CHECK-LIS-NEXT:    adcs r7, r4
+; CHECK-LIS-NEXT:    adcs r6, r4
 ; CHECK-LIS-NEXT:    vmov r5, r4, d2
-; CHECK-LIS-NEXT:    vmov q1[2], q1[0], r6, r2
-; CHECK-LIS-NEXT:    vmov q1[3], q1[1], r8, r7
+; CHECK-LIS-NEXT:    vmov q1[2], q1[0], r7, r2
+; CHECK-LIS-NEXT:    vmov q1[3], q1[1], r8, r6
 ; CHECK-LIS-NEXT:    vstrw.32 q1, [r1, #16]
 ; CHECK-LIS-NEXT:    adds r3, r3, r5
 ; CHECK-LIS-NEXT:    adcs r0, r4
@@ -964,19 +1134,33 @@ entry:
 ; f32
 
 define void @vld3_v2f32(ptr %src, ptr %dst) {
-; CHECK-LABEL: vld3_v2f32:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    vldrw.u32 q2, [r0]
-; CHECK-NEXT:    vldr s1, [r0, #16]
-; CHECK-NEXT:    vldr s5, [r0, #20]
-; CHECK-NEXT:    vmov.f32 s12, s8
-; CHECK-NEXT:    vmov.f32 s13, s11
-; CHECK-NEXT:    vmov.f32 s0, s9
-; CHECK-NEXT:    vadd.f32 q0, q3, q0
-; CHECK-NEXT:    vmov.f32 s4, s10
-; CHECK-NEXT:    vadd.f32 q0, q0, q1
-; CHECK-NEXT:    vstmia r1, {s0, s1}
-; CHECK-NEXT:    bx lr
+; CHECK-LV-LABEL: vld3_v2f32:
+; CHECK-LV:       @ %bb.0: @ %entry
+; CHECK-LV-NEXT:    vldrw.u32 q2, [r0]
+; CHECK-LV-NEXT:    vldr s1, [r0, #16]
+; CHECK-LV-NEXT:    vldr s5, [r0, #20]
+; CHECK-LV-NEXT:    vmov.f32 s12, s8
+; CHECK-LV-NEXT:    vmov.f32 s13, s11
+; CHECK-LV-NEXT:    vmov.f32 s0, s9
+; CHECK-LV-NEXT:    vadd.f32 q0, q3, q0
+; CHECK-LV-NEXT:    vmov.f32 s4, s10
+; CHECK-LV-NEXT:    vadd.f32 q0, q0, q1
+; CHECK-LV-NEXT:    vstmia r1, {s0, s1}
+; CHECK-LV-NEXT:    bx lr
+
+; CHECK-LIS-LABEL: vld3_v2f32:
+; CHECK-LIS:       @ %bb.0: @ %entry
+; CHECK-LIS-NEXT:    vldrw.u32 q2, [r0]
+; CHECK-LIS-NEXT:    vldr s5, [r0, #16]
+; CHECK-LIS-NEXT:    vldr s1, [r0, #20]
+; CHECK-LIS-NEXT:    vmov.f32 s12, s8
+; CHECK-LIS-NEXT:    vmov.f32 s13, s11
+; CHECK-LIS-NEXT:    vmov.f32 s4, s9
+; CHECK-LIS-NEXT:    vadd.f32 q1, q3, q1
+; CHECK-LIS-NEXT:    vmov.f32 s0, s10
+; CHECK-LIS-NEXT:    vadd.f32 q0, q1, q0
+; CHECK-LIS-NEXT:    vstmia r1, {s0, s1}
+; CHECK-LIS-NEXT:    bx lr
 entry:
   %l1 = load <6 x float>, ptr %src, align 4
   %s1 = shufflevector <6 x float> %l1, <6 x float> undef, <2 x i32> <i32 0, i32 3>
@@ -989,29 +1173,53 @@ entry:
 }
 
 define void @vld3_v4f32(ptr %src, ptr %dst) {
-; CHECK-LABEL: vld3_v4f32:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .vsave {d8, d9}
-; CHECK-NEXT:    vpush {d8, d9}
-; CHECK-NEXT:    vldrw.u32 q0, [r0, #16]
-; CHECK-NEXT:    vldrw.u32 q1, [r0]
-; CHECK-NEXT:    vldrw.u32 q4, [r0, #32]
-; CHECK-NEXT:    vmov.f32 s10, s2
-; CHECK-NEXT:    vmov.f32 s13, s0
-; CHECK-NEXT:    vmov.f32 s14, s3
-; CHECK-NEXT:    vmov.f32 s8, s4
-; CHECK-NEXT:    vmov.f32 s9, s7
-; CHECK-NEXT:    vmov.f32 s12, s5
-; CHECK-NEXT:    vmov.f32 s15, s18
-; CHECK-NEXT:    vmov.f32 s11, s17
-; CHECK-NEXT:    vadd.f32 q2, q2, q3
-; CHECK-NEXT:    vmov.f32 s0, s6
-; CHECK-NEXT:    vmov.f32 s2, s16
-; CHECK-NEXT:    vmov.f32 s3, s19
-; CHECK-NEXT:    vadd.f32 q0, q2, q0
-; CHECK-NEXT:    vstrw.32 q0, [r1]
-; CHECK-NEXT:    vpop {d8, d9}
-; CHECK-NEXT:    bx lr
+; CHECK-LV-LABEL: vld3_v4f32:
+; CHECK-LV:       @ %bb.0: @ %entry
+; CHECK-LV-NEXT:    .vsave {d8, d9}
+; CHECK-LV-NEXT:    vpush {d8, d9}
+; CHECK-LV-NEXT:    vldrw.u32 q0, [r0, #16]
+; CHECK-LV-NEXT:    vldrw.u32 q1, [r0]
+; CHECK-LV-NEXT:    vldrw.u32 q4, [r0, #32]
+; CHECK-LV-NEXT:    vmov.f32 s10, s2
+; CHECK-LV-NEXT:    vmov.f32 s13, s0
+; CHECK-LV-NEXT:    vmov.f32 s14, s3
+; CHECK-LV-NEXT:    vmov.f32 s8, s4
+; CHECK-LV-NEXT:    vmov.f32 s9, s7
+; CHECK-LV-NEXT:    vmov.f32 s12, s5
+; CHECK-LV-NEXT:    vmov.f32 s15, s18
+; CHECK-LV-NEXT:    vmov.f32 s11, s17
+; CHECK-LV-NEXT:    vadd.f32 q2, q2, q3
+; CHECK-LV-NEXT:    vmov.f32 s0, s6
+; CHECK-LV-NEXT:    vmov.f32 s2, s16
+; CHECK-LV-NEXT:    vmov.f32 s3, s19
+; CHECK-LV-NEXT:    vadd.f32 q0, q2, q0
+; CHECK-LV-NEXT:    vstrw.32 q0, [r1]
+; CHECK-LV-NEXT:    vpop {d8, d9}
+; CHECK-LV-NEXT:    bx lr
+
+; CHECK-LIS-LABEL: vld3_v4f32:
+; CHECK-LIS:       @ %bb.0: @ %entry
+; CHECK-LIS-NEXT:    .vsave {d8, d9}
+; CHECK-LIS-NEXT:    vpush {d8, d9}
+; CHECK-LIS-NEXT:    vldrw.u32 q0, [r0, #16]
+; CHECK-LIS-NEXT:    vldrw.u32 q1, [r0]
+; CHECK-LIS-NEXT:    vldrw.u32 q4, [r0, #32]
+; CHECK-LIS-NEXT:    vmov.f32 s10, s2
+; CHECK-LIS-NEXT:    vmov.f32 s13, s0
+; CHECK-LIS-NEXT:    vmov.f32 s14, s3
+; CHECK-LIS-NEXT:    vmov.f32 s8, s4
+; CHECK-LIS-NEXT:    vmov.f32 s9, s7
+; CHECK-LIS-NEXT:    vmov.f32 s12, s5
+; CHECK-LIS-NEXT:    vmov.f32 s15, s18
+; CHECK-LIS-NEXT:    vmov.f32 s11, s17
+; CHECK-LIS-NEXT:    vadd.f32 q2, q2, q3
+; CHECK-LIS-NEXT:    vmov.f32 s0, s6
+; CHECK-LIS-NEXT:    vmov.f32 s2, s16
+; CHECK-LIS-NEXT:    vmov.f32 s3, s19
+; CHECK-LIS-NEXT:    vadd.f32 q0, q2, q0
+; CHECK-LIS-NEXT:    vstrw.32 q0, [r1]
+; CHECK-LIS-NEXT:    vpop {d8, d9}
+; CHECK-LIS-NEXT:    bx lr
 entry:
   %l1 = load <12 x float>, ptr %src, align 4
   %s1 = shufflevector <12 x float> %l1, <12 x float> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
@@ -1024,46 +1232,87 @@ entry:
 }
 
 define void @vld3_v8f32(ptr %src, ptr %dst) {
-; CHECK-LABEL: vld3_v8f32:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .vsave {d8, d9, d10, d11}
-; CHECK-NEXT:    vpush {d8, d9, d10, d11}
-; CHECK-NEXT:    vldrw.u32 q0, [r0, #64]
-; CHECK-NEXT:    vldrw.u32 q1, [r0, #48]
-; CHECK-NEXT:    vldrw.u32 q4, [r0, #80]
-; CHECK-NEXT:    vmov.f32 s10, s2
-; CHECK-NEXT:    vmov.f32 s13, s0
-; CHECK-NEXT:    vmov.f32 s14, s3
-; CHECK-NEXT:    vmov.f32 s8, s4
-; CHECK-NEXT:    vmov.f32 s9, s7
-; CHECK-NEXT:    vmov.f32 s12, s5
-; CHECK-NEXT:    vmov.f32 s15, s18
-; CHECK-NEXT:    vmov.f32 s11, s17
-; CHECK-NEXT:    vadd.f32 q2, q2, q3
-; CHECK-NEXT:    vmov.f32 s0, s6
-; CHECK-NEXT:    vmov.f32 s2, s16
-; CHECK-NEXT:    vldrw.u32 q1, [r0, #16]
-; CHECK-NEXT:    vmov.f32 s3, s19
-; CHECK-NEXT:    vldrw.u32 q3, [r0, #32]
-; CHECK-NEXT:    vadd.f32 q0, q2, q0
-; CHECK-NEXT:    vldrw.u32 q2, [r0]
-; CHECK-NEXT:    vmov.f32 s17, s4
-; CHECK-NEXT:    vstrw.32 q0, [r1, #16]
-; CHECK-NEXT:    vmov.f32 s18, s7
-; CHECK-NEXT:    vmov.f32 s22, s6
-; CHECK-NEXT:    vmov.f32 s16, s9
-; CHECK-NEXT:    vmov.f32 s19, s14
-; CHECK-NEXT:    vmov.f32 s20, s8
-; CHECK-NEXT:    vmov.f32 s21, s11
-; CHECK-NEXT:    vmov.f32 s23, s13
-; CHECK-NEXT:    vadd.f32 q4, q5, q4
-; CHECK-NEXT:    vmov.f32 s4, s10
-; CHECK-NEXT:    vmov.f32 s6, s12
-; CHECK-NEXT:    vmov.f32 s7, s15
-; CHECK-NEXT:    vadd.f32 q1, q4, q1
-; CHECK-NEXT:    vstrw.32 q1, [r1]
-; CHECK-NEXT:    vpop {d8, d9, d10, d11}
-; CHECK-NEXT:    bx lr
+; CHECK-LV-LABEL: vld3_v8f32:
+; CHECK-LV:       @ %bb.0: @ %entry
+; CHECK-LV-NEXT:    .vsave {d8, d9, d10, d11}
+; CHECK-LV-NEXT:    vpush {d8, d9, d10, d11}
+; CHECK-LV-NEXT:    vldrw.u32 q0, [r0, #64]
+; CHECK-LV-NEXT:    vldrw.u32 q1, [r0, #48]
+; CHECK-LV-NEXT:    vldrw.u32 q4, [r0, #80]
+; CHECK-LV-NEXT:    vmov.f32 s10, s2
+; CHECK-LV-NEXT:    vmov.f32 s13, s0
+; CHECK-LV-NEXT:    vmov.f32 s14, s3
+; CHECK-LV-NEXT:    vmov.f32 s8, s4
+; CHECK-LV-NEXT:    vmov.f32 s9, s7
+; CHECK-LV-NEXT:    vmov.f32 s12, s5
+; CHECK-LV-NEXT:    vmov.f32 s15, s18
+; CHECK-LV-NEXT:    vmov.f32 s11, s17
+; CHECK-LV-NEXT:    vadd.f32 q2, q2, q3
+; CHECK-LV-NEXT:    vmov.f32 s0, s6
+; CHECK-LV-NEXT:    vmov.f32 s2, s16
+; CHECK-LV-NEXT:    vldrw.u32 q1, [r0, #16]
+; CHECK-LV-NEXT:    vmov.f32 s3, s19
+; CHECK-LV-NEXT:    vldrw.u32 q3, [r0, #32]
+; CHECK-LV-NEXT:    vadd.f32 q0, q2, q0
+; CHECK-LV-NEXT:    vldrw.u32 q2, [r0]
+; CHECK-LV-NEXT:    vmov.f32 s17, s4
+; CHECK-LV-NEXT:    vstrw.32 q0, [r1, #16]
+; CHECK-LV-NEXT:    vmov.f32 s18, s7
+; CHECK-LV-NEXT:    vmov.f32 s22, s6
+; CHECK-LV-NEXT:    vmov.f32 s16, s9
+; CHECK-LV-NEXT:    vmov.f32 s19, s14
+; CHECK-LV-NEXT:    vmov.f32 s20, s8
+; CHECK-LV-NEXT:    vmov.f32 s21, s11
+; CHECK-LV-NEXT:    vmov.f32 s23, s13
+; CHECK-LV-NEXT:    vadd.f32 q4, q5, q4
+; CHECK-LV-NEXT:    vmov.f32 s4, s10
+; CHECK-LV-NEXT:    vmov.f32 s6, s12
+; CHECK-LV-NEXT:    vmov.f32 s7, s15
+; CHECK-LV-NEXT:    vadd.f32 q1, q4, q1
+; CHECK-LV-NEXT:    vstrw.32 q1, [r1]
+; CHECK-LV-NEXT:    vpop {d8, d9, d10, d11}
+; CHECK-LV-NEXT:    bx lr
+
+; CHECK-LIS-LABEL: vld3_v8f32:
+; CHECK-LIS:       @ %bb.0: @ %entry
+; CHECK-LIS-NEXT:    .vsave {d8, d9, d10, d11}
+; CHECK-LIS-NEXT:    vpush {d8, d9, d10, d11}
+; CHECK-LIS-NEXT:    vldrw.u32 q0, [r0, #64]
+; CHECK-LIS-NEXT:    vldrw.u32 q1, [r0, #48]
+; CHECK-LIS-NEXT:    vldrw.u32 q4, [r0, #80]
+; CHECK-LIS-NEXT:    vmov.f32 s10, s2
+; CHECK-LIS-NEXT:    vmov.f32 s13, s0
+; CHECK-LIS-NEXT:    vmov.f32 s14, s3
+; CHECK-LIS-NEXT:    vmov.f32 s8, s4
+; CHECK-LIS-NEXT:    vmov.f32 s9, s7
+; CHECK-LIS-NEXT:    vmov.f32 s12, s5
+; CHECK-LIS-NEXT:    vmov.f32 s15, s18
+; CHECK-LIS-NEXT:    vmov.f32 s11, s17
+; CHECK-LIS-NEXT:    vadd.f32 q2, q2, q3
+; CHECK-LIS-NEXT:    vmov.f32 s0, s6
+; CHECK-LIS-NEXT:    vmov.f32 s2, s16
+; CHECK-LIS-NEXT:    vldrw.u32 q1, [r0, #16]
+; CHECK-LIS-NEXT:    vmov.f32 s3, s19
+; CHECK-LIS-NEXT:    vldrw.u32 q3, [r0, #32]
+; CHECK-LIS-NEXT:    vadd.f32 q0, q2, q0
+; CHECK-LIS-NEXT:    vldrw.u32 q2, [r0]
+; CHECK-LIS-NEXT:    vmov.f32 s17, s4
+; CHECK-LIS-NEXT:    vstrw.32 q0, [r1, #16]
+; CHECK-LIS-NEXT:    vmov.f32 s18, s7
+; CHECK-LIS-NEXT:    vmov.f32 s22, s6
+; CHECK-LIS-NEXT:    vmov.f32 s16, s9
+; CHECK-LIS-NEXT:    vmov.f32 s19, s14
+; CHECK-LIS-NEXT:    vmov.f32 s20, s8
+; CHECK-LIS-NEXT:    vmov.f32 s21, s11
+; CHECK-LIS-NEXT:    vmov.f32 s23, s13
+; CHECK-LIS-NEXT:    vadd.f32 q4, q5, q4
+; CHECK-LIS-NEXT:    vmov.f32 s4, s10
+; CHECK-LIS-NEXT:    vmov.f32 s6, s12
+; CHECK-LIS-NEXT:    vmov.f32 s7, s15
+; CHECK-LIS-NEXT:    vadd.f32 q1, q4, q1
+; CHECK-LIS-NEXT:    vstrw.32 q1, [r1]
+; CHECK-LIS-NEXT:    vpop {d8, d9, d10, d11}
+; CHECK-LIS-NEXT:    bx lr
 entry:
   %l1 = load <24 x float>, ptr %src, align 4
   %s1 = shufflevector <24 x float> %l1, <24 x float> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
@@ -1076,80 +1325,155 @@ entry:
 }
 
 define void @vld3_v16f32(ptr %src, ptr %dst) {
-; CHECK-LABEL: vld3_v16f32:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .vsave {d8, d9, d10, d11, d12, d13, d14, d15}
-; CHECK-NEXT:    vpush {d8, d9, d10, d11, d12, d13, d14, d15}
-; CHECK-NEXT:    vldrw.u32 q0, [r0, #64]
-; CHECK-NEXT:    vldrw.u32 q1, [r0, #48]
-; CHECK-NEXT:    vldrw.u32 q4, [r0, #80]
-; CHECK-NEXT:    vldrw.u32 q6, [r0, #176]
-; CHECK-NEXT:    vmov.f32 s10, s2
-; CHECK-NEXT:    vmov.f32 s13, s0
-; CHECK-NEXT:    vmov.f32 s14, s3
-; CHECK-NEXT:    vmov.f32 s8, s4
-; CHECK-NEXT:    vmov.f32 s9, s7
-; CHECK-NEXT:    vmov.f32 s12, s5
-; CHECK-NEXT:    vmov.f32 s15, s18
-; CHECK-NEXT:    vmov.f32 s11, s17
-; CHECK-NEXT:    vadd.f32 q2, q2, q3
-; CHECK-NEXT:    vmov.f32 s0, s6
-; CHECK-NEXT:    vmov.f32 s2, s16
-; CHECK-NEXT:    vldrw.u32 q1, [r0, #16]
-; CHECK-NEXT:    vmov.f32 s3, s19
-; CHECK-NEXT:    vldrw.u32 q3, [r0, #32]
-; CHECK-NEXT:    vadd.f32 q0, q2, q0
-; CHECK-NEXT:    vldrw.u32 q2, [r0]
-; CHECK-NEXT:    vmov.f32 s17, s4
-; CHECK-NEXT:    vmov.f32 s18, s7
-; CHECK-NEXT:    vmov.f32 s22, s6
-; CHECK-NEXT:    vmov.f32 s16, s9
-; CHECK-NEXT:    vmov.f32 s19, s14
-; CHECK-NEXT:    vmov.f32 s20, s8
-; CHECK-NEXT:    vmov.f32 s21, s11
-; CHECK-NEXT:    vmov.f32 s23, s13
-; CHECK-NEXT:    vmov.f32 s4, s10
-; CHECK-NEXT:    vldrw.u32 q2, [r0, #160]
-; CHECK-NEXT:    vmov.f32 s6, s12
-; CHECK-NEXT:    vadd.f32 q4, q5, q4
-; CHECK-NEXT:    vmov.f32 s7, s15
-; CHECK-NEXT:    vldrw.u32 q3, [r0, #144]
-; CHECK-NEXT:    vadd.f32 q1, q4, q1
-; CHECK-NEXT:    vmov.f32 s18, s10
-; CHECK-NEXT:    vmov.f32 s21, s8
-; CHECK-NEXT:    vmov.f32 s22, s11
-; CHECK-NEXT:    vmov.f32 s16, s12
-; CHECK-NEXT:    vmov.f32 s17, s15
-; CHECK-NEXT:    vmov.f32 s20, s13
-; CHECK-NEXT:    vmov.f32 s23, s26
-; CHECK-NEXT:    vmov.f32 s19, s25
-; CHECK-NEXT:    vadd.f32 q4, q4, q5
-; CHECK-NEXT:    vmov.f32 s8, s14
-; CHECK-NEXT:    vmov.f32 s10, s24
-; CHECK-NEXT:    vldrw.u32 q3, [r0, #112]
-; CHECK-NEXT:    vmov.f32 s11, s27
-; CHECK-NEXT:    vldrw.u32 q5, [r0, #128]
-; CHECK-NEXT:    vadd.f32 q2, q4, q2
-; CHECK-NEXT:    vldrw.u32 q4, [r0, #96]
-; CHECK-NEXT:    vmov.f32 s25, s12
-; CHECK-NEXT:    vstrw.32 q2, [r1, #48]
-; CHECK-NEXT:    vmov.f32 s26, s15
-; CHECK-NEXT:    vstrw.32 q0, [r1, #16]
-; CHECK-NEXT:    vmov.f32 s30, s14
-; CHECK-NEXT:    vstrw.32 q1, [r1]
-; CHECK-NEXT:    vmov.f32 s24, s17
-; CHECK-NEXT:    vmov.f32 s27, s22
-; CHECK-NEXT:    vmov.f32 s28, s16
-; CHECK-NEXT:    vmov.f32 s29, s19
-; CHECK-NEXT:    vmov.f32 s31, s21
-; CHECK-NEXT:    vadd.f32 q6, q7, q6
-; CHECK-NEXT:    vmov.f32 s12, s18
-; CHECK-NEXT:    vmov.f32 s14, s20
-; CHECK-NEXT:    vmov.f32 s15, s23
-; CHECK-NEXT:    vadd.f32 q3, q6, q3
-; CHECK-NEXT:    vstrw.32 q3, [r1, #32]
-; CHECK-NEXT:    vpop {d8, d9, d10, d11, d12, d13, d14, d15}
-; CHECK-NEXT:    bx lr
+; CHECK-LV-LABEL: vld3_v16f32:
+; CHECK-LV:       @ %bb.0: @ %entry
+; CHECK-LV-NEXT:    .vsave {d8, d9, d10, d11, d12, d13, d14, d15}
+; CHECK-LV-NEXT:    vpush {d8, d9, d10, d11, d12, d13, d14, d15}
+; CHECK-LV-NEXT:    vldrw.u32 q0, [r0, #64]
+; CHECK-LV-NEXT:    vldrw.u32 q1, [r0, #48]
+; CHECK-LV-NEXT:    vldrw.u32 q4, [r0, #80]
+; CHECK-LV-NEXT:    vldrw.u32 q6, [r0, #176]
+; CHECK-LV-NEXT:    vmov.f32 s10, s2
+; CHECK-LV-NEXT:    vmov.f32 s13, s0
+; CHECK-LV-NEXT:    vmov.f32 s14, s3
+; CHECK-LV-NEXT:    vmov.f32 s8, s4
+; CHECK-LV-NEXT:    vmov.f32 s9, s7
+; CHECK-LV-NEXT:    vmov.f32 s12, s5
+; CHECK-LV-NEXT:    vmov.f32 s15, s18
+; CHECK-LV-NEXT:    vmov.f32 s11, s17
+; CHECK-LV-NEXT:    vadd.f32 q2, q2, q3
+; CHECK-LV-NEXT:    vmov.f32 s0, s6
+; CHECK-LV-NEXT:    vmov.f32 s2, s16
+; CHECK-LV-NEXT:    vldrw.u32 q1, [r0, #16]
+; CHECK-LV-NEXT:    vmov.f32 s3, s19
+; CHECK-LV-NEXT:    vldrw.u32 q3, [r0, #32]
+; CHECK-LV-NEXT:    vadd.f32 q0, q2, q0
+; CHECK-LV-NEXT:    vldrw.u32 q2, [r0]
+; CHECK-LV-NEXT:    vmov.f32 s17, s4
+; CHECK-LV-NEXT:    vmov.f32 s18, s7
+; CHECK-LV-NEXT:    vmov.f32 s22, s6
+; CHECK-LV-NEXT:    vmov.f32 s16, s9
+; CHECK-LV-NEXT:    vmov.f32 s19, s14
+; CHECK-LV-NEXT:    vmov.f32 s20, s8
+; CHECK-LV-NEXT:    vmov.f32 s21, s11
+; CHECK-LV-NEXT:    vmov.f32 s23, s13
+; CHECK-LV-NEXT:    vmov.f32 s4, s10
+; CHECK-LV-NEXT:    vldrw.u32 q2, [r0, #160]
+; CHECK-LV-NEXT:    vmov.f32 s6, s12
+; CHECK-LV-NEXT:    vadd.f32 q4, q5, q4
+; CHECK-LV-NEXT:    vmov.f32 s7, s15
+; CHECK-LV-NEXT:    vldrw.u32 q3, [r0, #144]
+; CHECK-LV-NEXT:    vadd.f32 q1, q4, q1
+; CHECK-LV-NEXT:    vmov.f32 s18, s10
+; CHECK-LV-NEXT:    vmov.f32 s21, s8
+; CHECK-LV-NEXT:    vmov.f32 s22, s11
+; CHECK-LV-NEXT:    vmov.f32 s16, s12
+; CHECK-LV-NEXT:    vmov.f32 s17, s15
+; CHECK-LV-NEXT:    vmov.f32 s20, s13
+; CHECK-LV-NEXT:    vmov.f32 s23, s26
+; CHECK-LV-NEXT:    vmov.f32 s19, s25
+; CHECK-LV-NEXT:    vadd.f32 q4, q4, q5
+; CHECK-LV-NEXT:    vmov.f32 s8, s14
+; CHECK-LV-NEXT:    vmov.f32 s10, s24
+; CHECK-LV-NEXT:    vldrw.u32 q3, [r0, #112]
+; CHECK-LV-NEXT:    vmov.f32 s11, s27
+; CHECK-LV-NEXT:    vldrw.u32 q5, [r0, #128]
+; CHECK-LV-NEXT:    vadd.f32 q2, q4, q2
+; CHECK-LV-NEXT:    vldrw.u32 q4, [r0, #96]
+; CHECK-LV-NEXT:    vmov.f32 s25, s12
+; CHECK-LV-NEXT:    vstrw.32 q2, [r1, #48]
+; CHECK-LV-NEXT:    vmov.f32 s26, s15
+; CHECK-LV-NEXT:    vstrw.32 q0, [r1, #16]
+; CHECK-LV-NEXT:    vmov.f32 s30, s14
+; CHECK-LV-NEXT:    vstrw.32 q1, [r1]
+; CHECK-LV-NEXT:    vmov.f32 s24, s17
+; CHECK-LV-NEXT:    vmov.f32 s27, s22
+; CHECK-LV-NEXT:    vmov.f32 s28, s16
+; CHECK-LV-NEXT:    vmov.f32 s29, s19
+; CHECK-LV-NEXT:    vmov.f32 s31, s21
+; CHECK-LV-NEXT:    vadd.f32 q6, q7, q6
+; CHECK-LV-NEXT:    vmov.f32 s12, s18
+; CHECK-LV-NEXT:    vmov.f32 s14, s20
+; CHECK-LV-NEXT:    vmov.f32 s15, s23
+; CHECK-LV-NEXT:    vadd.f32 q3, q6, q3
+; CHECK-LV-NEXT:    vstrw.32 q3, [r1, #32]
+; CHECK-LV-NEXT:    vpop {d8, d9, d10, d11, d12, d13, d14, d15}
+; CHECK-LV-NEXT:    bx lr
+
+; CHECK-LIS-LABEL: vld3_v16f32:
+; CHECK-LIS:       @ %bb.0: @ %entry
+; CHECK-LIS-NEXT:    .vsave {d8, d9, d10, d11, d12, d13, d14, d15}
+; CHECK-LIS-NEXT:    vpush {d8, d9, d10, d11, d12, d13, d14, d15}
+; CHECK-LIS-NEXT:    vldrw.u32 q0, [r0, #64]
+; CHECK-LIS-NEXT:    vldrw.u32 q1, [r0, #48]
+; CHECK-LIS-NEXT:    vldrw.u32 q4, [r0, #80]
+; CHECK-LIS-NEXT:    vldrw.u32 q6, [r0, #176]
+; CHECK-LIS-NEXT:    vmov.f32 s10, s2
+; CHECK-LIS-NEXT:    vmov.f32 s13, s0
+; CHECK-LIS-NEXT:    vmov.f32 s14, s3
+; CHECK-LIS-NEXT:    vmov.f32 s8, s4
+; CHECK-LIS-NEXT:    vmov.f32 s9, s7
+; CHECK-LIS-NEXT:    vmov.f32 s12, s5
+; CHECK-LIS-NEXT:    vmov.f32 s15, s18
+; CHECK-LIS-NEXT:    vmov.f32 s11, s17
+; CHECK-LIS-NEXT:    vadd.f32 q2, q2, q3
+; CHECK-LIS-NEXT:    vmov.f32 s0, s6
+; CHECK-LIS-NEXT:    vmov.f32 s2, s16
+; CHECK-LIS-NEXT:    vldrw.u32 q1, [r0, #16]
+; CHECK-LIS-NEXT:    vmov.f32 s3, s19
+; CHECK-LIS-NEXT:    vldrw.u32 q3, [r0, #32]
+; CHECK-LIS-NEXT:    vadd.f32 q0, q2, q0
+; CHECK-LIS-NEXT:    vldrw.u32 q2, [r0]
+; CHECK-LIS-NEXT:    vmov.f32 s17, s4
+; CHECK-LIS-NEXT:    vmov.f32 s18, s7
+; CHECK-LIS-NEXT:    vmov.f32 s22, s6
+; CHECK-LIS-NEXT:    vmov.f32 s16, s9
+; CHECK-LIS-NEXT:    vmov.f32 s19, s14
+; CHECK-LIS-NEXT:    vmov.f32 s20, s8
+; CHECK-LIS-NEXT:    vmov.f32 s21, s11
+; CHECK-LIS-NEXT:    vmov.f32 s23, s13
+; CHECK-LIS-NEXT:    vmov.f32 s4, s10
+; CHECK-LIS-NEXT:    vldrw.u32 q2, [r0, #160]
+; CHECK-LIS-NEXT:    vmov.f32 s6, s12
+; CHECK-LIS-NEXT:    vadd.f32 q4, q5, q4
+; CHECK-LIS-NEXT:    vmov.f32 s7, s15
+; CHECK-LIS-NEXT:    vldrw.u32 q3, [r0, #144]
+; CHECK-LIS-NEXT:    vadd.f32 q1, q4, q1
+; CHECK-LIS-NEXT:    vmov.f32 s18, s10
+; CHECK-LIS-NEXT:    vmov.f32 s21, s8
+; CHECK-LIS-NEXT:    vmov.f32 s22, s11
+; CHECK-LIS-NEXT:    vmov.f32 s16, s12
+; CHECK-LIS-NEXT:    vmov.f32 s17, s15
+; CHECK-LIS-NEXT:    vmov.f32 s20, s13
+; CHECK-LIS-NEXT:    vmov.f32 s23, s26
+; CHECK-LIS-NEXT:    vmov.f32 s19, s25
+; CHECK-LIS-NEXT:    vadd.f32 q4, q4, q5
+; CHECK-LIS-NEXT:    vmov.f32 s8, s14
+; CHECK-LIS-NEXT:    vmov.f32 s10, s24
+; CHECK-LIS-NEXT:    vldrw.u32 q3, [r0, #112]
+; CHECK-LIS-NEXT:    vmov.f32 s11, s27
+; CHECK-LIS-NEXT:    vldrw.u32 q5, [r0, #128]
+; CHECK-LIS-NEXT:    vadd.f32 q2, q4, q2
+; CHECK-LIS-NEXT:    vldrw.u32 q4, [r0, #96]
+; CHECK-LIS-NEXT:    vmov.f32 s25, s12
+; CHECK-LIS-NEXT:    vstrw.32 q2, [r1, #48]
+; CHECK-LIS-NEXT:    vmov.f32 s26, s15
+; CHECK-LIS-NEXT:    vstrw.32 q0, [r1, #16]
+; CHECK-LIS-NEXT:    vmov.f32 s30, s14
+; CHECK-LIS-NEXT:    vstrw.32 q1, [r1]
+; CHECK-LIS-NEXT:    vmov.f32 s24, s17
+; CHECK-LIS-NEXT:    vmov.f32 s27, s22
+; CHECK-LIS-NEXT:    vmov.f32 s28, s16
+; CHECK-LIS-NEXT:    vmov.f32 s29, s19
+; CHECK-LIS-NEXT:    vmov.f32 s31, s21
+; CHECK-LIS-NEXT:    vadd.f32 q6, q7, q6
+; CHECK-LIS-NEXT:    vmov.f32 s12, s18
+; CHECK-LIS-NEXT:    vmov.f32 s14, s20
+; CHECK-LIS-NEXT:    vmov.f32 s15, s23
+; CHECK-LIS-NEXT:    vadd.f32 q3, q6, q3
+; CHECK-LIS-NEXT:    vstrw.32 q3, [r1, #32]
+; CHECK-LIS-NEXT:    vpop {d8, d9, d10, d11, d12, d13, d14, d15}
+; CHECK-LIS-NEXT:    bx lr
 entry:
   %l1 = load <48 x float>, ptr %src, align 4
   %s1 = shufflevector <48 x float> %l1, <48 x float> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
@@ -1288,86 +1612,167 @@ entry:
 }
 
 define void @vld3_v16f16(ptr %src, ptr %dst) {
-; CHECK-LABEL: vld3_v16f16:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .vsave {d8, d9}
-; CHECK-NEXT:    vpush {d8, d9}
-; CHECK-NEXT:    vldrw.u32 q0, [r0, #48]
-; CHECK-NEXT:    vldrw.u32 q2, [r0, #64]
-; CHECK-NEXT:    vldrw.u32 q3, [r0, #80]
-; CHECK-NEXT:    vmovx.f16 s6, s2
-; CHECK-NEXT:    vmov.f32 s4, s1
-; CHECK-NEXT:    vins.f16 s4, s6
-; CHECK-NEXT:    vmovx.f16 s6, s9
-; CHECK-NEXT:    vmov.f32 s5, s8
-; CHECK-NEXT:    vmovx.f16 s7, s12
-; CHECK-NEXT:    vins.f16 s5, s6
-; CHECK-NEXT:    vmov.f32 s6, s11
-; CHECK-NEXT:    vins.f16 s6, s7
-; CHECK-NEXT:    vmovx.f16 s16, s15
-; CHECK-NEXT:    vmov.f32 s7, s14
-; CHECK-NEXT:    vmovx.f16 s17, s3
-; CHECK-NEXT:    vins.f16 s7, s16
-; CHECK-NEXT:    vmovx.f16 s16, s0
-; CHECK-NEXT:    vins.f16 s16, s2
-; CHECK-NEXT:    vmovx.f16 s2, s1
-; CHECK-NEXT:    vins.f16 s0, s2
-; CHECK-NEXT:    vmovx.f16 s2, s8
-; CHECK-NEXT:    vins.f16 s3, s2
-; CHECK-NEXT:    vmovx.f16 s2, s11
-; CHECK-NEXT:    vmovx.f16 s18, s10
-; CHECK-NEXT:    vins.f16 s10, s2
-; CHECK-NEXT:    vmovx.f16 s2, s14
-; CHECK-NEXT:    vmovx.f16 s19, s13
-; CHECK-NEXT:    vins.f16 s13, s2
-; CHECK-NEXT:    vmov.f32 s1, s3
-; CHECK-NEXT:    vins.f16 s18, s12
-; CHECK-NEXT:    vins.f16 s19, s15
-; CHECK-NEXT:    vins.f16 s17, s9
-; CHECK-NEXT:    vmov.f32 s2, s10
-; CHECK-NEXT:    vmov.f32 s3, s13
-; CHECK-NEXT:    vldrw.u32 q2, [r0, #16]
-; CHECK-NEXT:    vadd.f16 q0, q0, q4
-; CHECK-NEXT:    vadd.f16 q3, q0, q1
-; CHECK-NEXT:    vldrw.u32 q1, [r0]
-; CHECK-NEXT:    vldrw.u32 q0, [r0, #32]
-; CHECK-NEXT:    vstrw.32 q3, [r1, #16]
-; CHECK-NEXT:    vmovx.f16 s14, s6
-; CHECK-NEXT:    vmov.f32 s12, s5
-; CHECK-NEXT:    vins.f16 s12, s14
-; CHECK-NEXT:    vmovx.f16 s14, s9
-; CHECK-NEXT:    vmov.f32 s13, s8
-; CHECK-NEXT:    vmovx.f16 s18, s10
-; CHECK-NEXT:    vins.f16 s13, s14
-; CHECK-NEXT:    vmovx.f16 s15, s0
-; CHECK-NEXT:    vmov.f32 s14, s11
-; CHECK-NEXT:    vins.f16 s18, s0
-; CHECK-NEXT:    vins.f16 s14, s15
-; CHECK-NEXT:    vmovx.f16 s16, s3
-; CHECK-NEXT:    vmov.f32 s15, s2
-; CHECK-NEXT:    vmovx.f16 s0, s5
-; CHECK-NEXT:    vins.f16 s15, s16
-; CHECK-NEXT:    vmovx.f16 s16, s4
-; CHECK-NEXT:    vins.f16 s4, s0
-; CHECK-NEXT:    vmovx.f16 s0, s8
-; CHECK-NEXT:    vmovx.f16 s17, s7
-; CHECK-NEXT:    vins.f16 s7, s0
-; CHECK-NEXT:    vmovx.f16 s0, s11
-; CHECK-NEXT:    vmovx.f16 s19, s1
-; CHECK-NEXT:    vins.f16 s10, s0
-; CHECK-NEXT:    vmovx.f16 s0, s2
-; CHECK-NEXT:    vins.f16 s1, s0
-; CHECK-NEXT:    vins.f16 s16, s6
-; CHECK-NEXT:    vmov.f32 s5, s7
-; CHECK-NEXT:    vins.f16 s19, s3
-; CHECK-NEXT:    vins.f16 s17, s9
-; CHECK-NEXT:    vmov.f32 s6, s10
-; CHECK-NEXT:    vmov.f32 s7, s1
-; CHECK-NEXT:    vadd.f16 q0, q1, q4
-; CHECK-NEXT:    vadd.f16 q0, q0, q3
-; CHECK-NEXT:    vstrw.32 q0, [r1]
-; CHECK-NEXT:    vpop {d8, d9}
-; CHECK-NEXT:    bx lr
+; CHECK-LV-LABEL: vld3_v16f16:
+; CHECK-LV:       @ %bb.0: @ %entry
+; CHECK-LV-NEXT:    .vsave {d8, d9}
+; CHECK-LV-NEXT:    vpush {d8, d9}
+; CHECK-LV-NEXT:    vldrw.u32 q0, [r0, #48]
+; CHECK-LV-NEXT:    vldrw.u32 q2, [r0, #64]
+; CHECK-LV-NEXT:    vldrw.u32 q3, [r0, #80]
+; CHECK-LV-NEXT:    vmovx.f16 s6, s2
+; CHECK-LV-NEXT:    vmov.f32 s4, s1
+; CHECK-LV-NEXT:    vins.f16 s4, s6
+; CHECK-LV-NEXT:    vmovx.f16 s6, s9
+; CHECK-LV-NEXT:    vmov.f32 s5, s8
+; CHECK-LV-NEXT:    vmovx.f16 s7, s12
+; CHECK-LV-NEXT:    vins.f16 s5, s6
+; CHECK-LV-NEXT:    vmov.f32 s6, s11
+; CHECK-LV-NEXT:    vins.f16 s6, s7
+; CHECK-LV-NEXT:    vmovx.f16 s16, s15
+; CHECK-LV-NEXT:    vmov.f32 s7, s14
+; CHECK-LV-NEXT:    vmovx.f16 s17, s3
+; CHECK-LV-NEXT:    vins.f16 s7, s16
+; CHECK-LV-NEXT:    vmovx.f16 s16, s0
+; CHECK-LV-NEXT:    vins.f16 s16, s2
+; CHECK-LV-NEXT:    vmovx.f16 s2, s1
+; CHECK-LV-NEXT:    vins.f16 s0, s2
+; CHECK-LV-NEXT:    vmovx.f16 s2, s8
+; CHECK-LV-NEXT:    vins.f16 s3, s2
+; CHECK-LV-NEXT:    vmovx.f16 s2, s11
+; CHECK-LV-NEXT:    vmovx.f16 s18, s10
+; CHECK-LV-NEXT:    vins.f16 s10, s2
+; CHECK-LV-NEXT:    vmovx.f16 s2, s14
+; CHECK-LV-NEXT:    vmovx.f16 s19, s13
+; CHECK-LV-NEXT:    vins.f16 s13, s2
+; CHECK-LV-NEXT:    vmov.f32 s1, s3
+; CHECK-LV-NEXT:    vins.f16 s18, s12
+; CHECK-LV-NEXT:    vins.f16 s19, s15
+; CHECK-LV-NEXT:    vins.f16 s17, s9
+; CHECK-LV-NEXT:    vmov.f32 s2, s10
+; CHECK-LV-NEXT:    vmov.f32 s3, s13
+; CHECK-LV-NEXT:    vldrw.u32 q2, [r0, #16]
+; CHECK-LV-NEXT:    vadd.f16 q0, q0, q4
+; CHECK-LV-NEXT:    vadd.f16 q3, q0, q1
+; CHECK-LV-NEXT:    vldrw.u32 q1, [r0]
+; CHECK-LV-NEXT:    vldrw.u32 q0, [r0, #32]
+; CHECK-LV-NEXT:    vstrw.32 q3, [r1, #16]
+; CHECK-LV-NEXT:    vmovx.f16 s14, s6
+; CHECK-LV-NEXT:    vmov.f32 s12, s5
+; CHECK-LV-NEXT:    vins.f16 s12, s14
+; CHECK-LV-NEXT:    vmovx.f16 s14, s9
+; CHECK-LV-NEXT:    vmov.f32 s13, s8
+; CHECK-LV-NEXT:    vmovx.f16 s18, s10
+; CHECK-LV-NEXT:    vins.f16 s13, s14
+; CHECK-LV-NEXT:    vmovx.f16 s15, s0
+; CHECK-LV-NEXT:    vmov.f32 s14, s11
+; CHECK-LV-NEXT:    vins.f16 s18, s0
+; CHECK-LV-NEXT:    vins.f16 s14, s15
+; CHECK-LV-NEXT:    vmovx.f16 s16, s3
+; CHECK-LV-NEXT:    vmov.f32 s15, s2
+; CHECK-LV-NEXT:    vmovx.f16 s0, s5
+; CHECK-LV-NEXT:    vins.f16 s15, s16
+; CHECK-LV-NEXT:    vmovx.f16 s16, s4
+; CHECK-LV-NEXT:    vins.f16 s4, s0
+; CHECK-LV-NEXT:    vmovx.f16 s0, s8
+; CHECK-LV-NEXT:    vmovx.f16 s17, s7
+; CHECK-LV-NEXT:    vins.f16 s7, s0
+; CHECK-LV-NEXT:    vmovx.f16 s0, s11
+; CHECK-LV-NEXT:    vmovx.f16 s19, s1
+; CHECK-LV-NEXT:    vins.f16 s10, s0
+; CHECK-LV-NEXT:    vmovx.f16 s0, s2
+; CHECK-LV-NEXT:    vins.f16 s1, s0
+; CHECK-LV-NEXT:    vins.f16 s16, s6
+; CHECK-LV-NEXT:    vmov.f32 s5, s7
+; CHECK-LV-NEXT:    vins.f16 s19, s3
+; CHECK-LV-NEXT:    vins.f16 s17, s9
+; CHECK-LV-NEXT:    vmov.f32 s6, s10
+; CHECK-LV-NEXT:    vmov.f32 s7, s1
+; CHECK-LV-NEXT:    vadd.f16 q0, q1, q4
+; CHECK-LV-NEXT:    vadd.f16 q0, q0, q3
+; CHECK-LV-NEXT:    vstrw.32 q0, [r1]
+; CHECK-LV-NEXT:    vpop {d8, d9}
+; CHECK-LV-NEXT:    bx lr
+
+; CHECK-LIS-LABEL: vld3_v16f16:
+; CHECK-LIS:       @ %bb.0: @ %entry
+; CHECK-LIS-NEXT:    .vsave {d8, d9}
+; CHECK-LIS-NEXT:    vpush {d8, d9}
+; CHECK-LIS-NEXT:    vldrw.u32 q0, [r0, #48]
+; CHECK-LIS-NEXT:    vldrw.u32 q2, [r0, #64]
+; CHECK-LIS-NEXT:    vldrw.u32 q3, [r0, #80]
+; CHECK-LIS-NEXT:    vmovx.f16 s6, s2
+; CHECK-LIS-NEXT:    vmov.f32 s4, s1
+; CHECK-LIS-NEXT:    vins.f16 s4, s6
+; CHECK-LIS-NEXT:    vmovx.f16 s6, s9
+; CHECK-LIS-NEXT:    vmov.f32 s5, s8
+; CHECK-LIS-NEXT:    vmovx.f16 s7, s12
+; CHECK-LIS-NEXT:    vins.f16 s5, s6
+; CHECK-LIS-NEXT:    vmov.f32 s6, s11
+; CHECK-LIS-NEXT:    vins.f16 s6, s7
+; CHECK-LIS-NEXT:    vmovx.f16 s16, s15
+; CHECK-LIS-NEXT:    vmov.f32 s7, s14
+; CHECK-LIS-NEXT:    vmovx.f16 s17, s3
+; CHECK-LIS-NEXT:    vins.f16 s7, s16
+; CHECK-LIS-NEXT:    vmovx.f16 s16, s0
+; CHECK-LIS-NEXT:    vins.f16 s16, s2
+; CHECK-LIS-NEXT:    vmovx.f16 s2, s1
+; CHECK-LIS-NEXT:    vins.f16 s0, s2
+; CHECK-LIS-NEXT:    vmovx.f16 s2, s8
+; CHECK-LIS-NEXT:    vins.f16 s3, s2
+; CHECK-LIS-NEXT:    vmovx.f16 s2, s11
+; CHECK-LIS-NEXT:    vmovx.f16 s18, s10
+; CHECK-LIS-NEXT:    vins.f16 s10, s2
+; CHECK-LIS-NEXT:    vmovx.f16 s2, s14
+; CHECK-LIS-NEXT:    vmovx.f16 s19, s13
+; CHECK-LIS-NEXT:    vins.f16 s13, s2
+; CHECK-LIS-NEXT:    vmov.f32 s1, s3
+; CHECK-LIS-NEXT:    vins.f16 s18, s12
+; CHECK-LIS-NEXT:    vins.f16 s19, s15
+; CHECK-LIS-NEXT:    vins.f16 s17, s9
+; CHECK-LIS-NEXT:    vmov.f32 s2, s10
+; CHECK-LIS-NEXT:    vmov.f32 s3, s13
+; CHECK-LIS-NEXT:    vldrw.u32 q2, [r0, #16]
+; CHECK-LIS-NEXT:    vadd.f16 q0, q0, q4
+; CHECK-LIS-NEXT:    vadd.f16 q3, q0, q1
+; CHECK-LIS-NEXT:    vldrw.u32 q0, [r0]
+; CHECK-LIS-NEXT:    vldrw.u32 q1, [r0, #32]
+; CHECK-LIS-NEXT:    vstrw.32 q3, [r1, #16]
+; CHECK-LIS-NEXT:    vmovx.f16 s14, s2
+; CHECK-LIS-NEXT:    vmov.f32 s12, s1
+; CHECK-LIS-NEXT:    vins.f16 s12, s14
+; CHECK-LIS-NEXT:    vmovx.f16 s14, s9
+; CHECK-LIS-NEXT:    vmov.f32 s13, s8
+; CHECK-LIS-NEXT:    vmovx.f16 s15, s4
+; CHECK-LIS-NEXT:    vins.f16 s13, s14
+; CHECK-LIS-NEXT:    vmov.f32 s14, s11
+; CHECK-LIS-NEXT:    vins.f16 s14, s15
+; CHECK-LIS-NEXT:    vmovx.f16 s16, s7
+; CHECK-LIS-NEXT:    vmov.f32 s15, s6
+; CHECK-LIS-NEXT:    vmovx.f16 s17, s3
+; CHECK-LIS-NEXT:    vins.f16 s15, s16
+; CHECK-LIS-NEXT:    vmovx.f16 s16, s0
+; CHECK-LIS-NEXT:    vins.f16 s16, s2
+; CHECK-LIS-NEXT:    vmovx.f16 s2, s1
+; CHECK-LIS-NEXT:    vins.f16 s0, s2
+; CHECK-LIS-NEXT:    vmovx.f16 s2, s8
+; CHECK-LIS-NEXT:    vins.f16 s3, s2
+; CHECK-LIS-NEXT:    vmovx.f16 s2, s11
+; CHECK-LIS-NEXT:    vmovx.f16 s18, s10
+; CHECK-LIS-NEXT:    vins.f16 s10, s2
+; CHECK-LIS-NEXT:    vmovx.f16 s2, s6
+; CHECK-LIS-NEXT:    vmovx.f16 s19, s5
+; CHECK-LIS-NEXT:    vins.f16 s5, s2
+; CHECK-LIS-NEXT:    vmov.f32 s1, s3
+; CHECK-LIS-NEXT:    vins.f16 s18, s4
+; CHECK-LIS-NEXT:    vins.f16 s19, s7
+; CHECK-LIS-NEXT:    vins.f16 s17, s9
+; CHECK-LIS-NEXT:    vmov.f32 s2, s10
+; CHECK-LIS-NEXT:    vmov.f32 s3, s5
+; CHECK-LIS-NEXT:    vadd.f16 q0, q0, q4
+; CHECK-LIS-NEXT:    vadd.f16 q0, q0, q3
+; CHECK-LIS-NEXT:    vstrw.32 q0, [r1]
+; CHECK-LIS-NEXT:    vpop {d8, d9}
+; CHECK-LIS-NEXT:    bx lr
 entry:
   %l1 = load <48 x half>, ptr %src, align 4
   %s1 = shufflevector <48 x half> %l1, <48 x half> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
@@ -1436,4 +1841,4 @@ entry:
   %a = fadd <4 x double> %a1, %s3
   store <4 x double> %a, ptr %dst
   ret void
-}
+}
\ No newline at end of file



More information about the llvm-commits mailing list