Index: llvm/lib/Target/ARM/ARMISelLowering.cpp
===================================================================
--- llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -759,9 +759,7 @@
       addAllExtLoads(VT, InnerVT, Expand);
     }
 
-    setOperationAction(ISD::MULHS, VT, Expand);
     setOperationAction(ISD::SMUL_LOHI, VT, Expand);
-    setOperationAction(ISD::MULHU, VT, Expand);
     setOperationAction(ISD::UMUL_LOHI, VT, Expand);
 
     setOperationAction(ISD::BSWAP, VT, Expand);
@@ -940,6 +938,11 @@
     setOperationAction(ISD::CTTZ_ZERO_UNDEF, MVT::v4i32, Custom);
     setOperationAction(ISD::CTTZ_ZERO_UNDEF, MVT::v2i64, Custom);
 
+    for (MVT VT : MVT::fixedlen_vector_valuetypes()) {
+      setOperationAction(ISD::MULHS, VT, Expand);
+      setOperationAction(ISD::MULHU, VT, Expand);
+    }
+
     // NEON only has FMA instructions as of VFP4.
     if (!Subtarget->hasVFP4Base()) {
       setOperationAction(ISD::FMA, MVT::v2f32, Expand);
Index: llvm/lib/Target/ARM/ARMInstrMVE.td
===================================================================
--- llvm/lib/Target/ARM/ARMInstrMVE.td
+++ llvm/lib/Target/ARM/ARMInstrMVE.td
@@ -4707,6 +4707,15 @@
               (VTI.Vec (Inst (VTI.Vec MQPR:$Qm), (VTI.Vec MQPR:$Qn),
                              ARMVCCThen, (VTI.Pred VCCR:$mask),
                              (VTI.Vec MQPR:$inactive)))>;
+
+    // ISD::MULHU/MULHS
+    if !eq(round, 0b0) then {
+      defvar mulh = !if(VTI.Unsigned, mulhu, mulhs);
+      let Predicates = [HasMVEInt] in {
+        def : Pat<(VTI.Vec (mulh (VTI.Vec MQPR:$a), (VTI.Vec MQPR:$b))),
+                  (VTI.Vec (Inst MQPR:$a, MQPR:$b))>;
+      }
+    }
   }
 }
 
Index: llvm/test/CodeGen/Thumb2/mve-vmulh.ll
===================================================================
--- llvm/test/CodeGen/Thumb2/mve-vmulh.ll
+++ llvm/test/CodeGen/Thumb2/mve-vmulh.ll
@@ -48,28 +48,7 @@
 define arm_aapcs_vfpcc <4 x i32> @vmulhs_v4i32(<4 x i32> %s0, <4 x i32> %s1) {
 ; CHECK-LABEL: vmulhs_v4i32:
 ; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    vmov.f32 s8, s4
-; CHECK-NEXT:    vmov.f32 s12, s0
-; CHECK-NEXT:    vmov.f32 s14, s1
-; CHECK-NEXT:    vmov.f32 s10, s5
-; CHECK-NEXT:    vmov r2, s12
-; CHECK-NEXT:    vmov r1, s14
-; CHECK-NEXT:    vmov r0, s10
-; CHECK-NEXT:    vmov.f32 s12, s6
-; CHECK-NEXT:    vmov.f32 s14, s7
-; CHECK-NEXT:    vmov.f32 s4, s2
-; CHECK-NEXT:    vmov.f32 s6, s3
-; CHECK-NEXT:    vmullb.s32 q0, q1, q3
-; CHECK-NEXT:    smmul r0, r1, r0
-; CHECK-NEXT:    vmov r1, s8
-; CHECK-NEXT:    smmul r1, r2, r1
-; CHECK-NEXT:    vmov.32 q2[0], r1
-; CHECK-NEXT:    vmov.32 q2[1], r0
-; CHECK-NEXT:    vmov r0, s1
-; CHECK-NEXT:    vmov.32 q2[2], r0
-; CHECK-NEXT:    vmov r0, s3
-; CHECK-NEXT:    vmov.32 q2[3], r0
-; CHECK-NEXT:    vmov q0, q2
+; CHECK-NEXT:    vmulh.s32 q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
   %s0s = sext <4 x i32> %s0 to <4 x i64>
@@ -83,21 +62,7 @@
 define arm_aapcs_vfpcc <4 x i32> @vmulhu_v4i32(<4 x i32> %s0, <4 x i32> %s1) {
 ; CHECK-LABEL: vmulhu_v4i32:
 ; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .vsave {d8, d9}
-; CHECK-NEXT:    vpush {d8, d9}
-; CHECK-NEXT:    vmov.f32 s12, s6
-; CHECK-NEXT:    vmov.f32 s16, s2
-; CHECK-NEXT:    vmov.f32 s14, s7
-; CHECK-NEXT:    vmov.f32 s18, s3
-; CHECK-NEXT:    vmov.f32 s6, s5
-; CHECK-NEXT:    vmullb.u32 q2, q4, q3
-; CHECK-NEXT:    vmov.f32 s2, s1
-; CHECK-NEXT:    vmullb.u32 q3, q0, q1
-; CHECK-NEXT:    vmov.f32 s0, s13
-; CHECK-NEXT:    vmov.f32 s1, s15
-; CHECK-NEXT:    vmov.f32 s2, s9
-; CHECK-NEXT:    vmov.f32 s3, s11
-; CHECK-NEXT:    vpop {d8, d9}
+; CHECK-NEXT:    vmulh.u32 q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
   %s0s = zext <4 x i32> %s0 to <4 x i64>
@@ -141,59 +106,7 @@
 define arm_aapcs_vfpcc <8 x i16> @vmulhs_v8i16(<8 x i16> %s0, <8 x i16> %s1) {
 ; CHECK-LABEL: vmulhs_v8i16:
 ; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    vmov.u16 r0, q1[0]
-; CHECK-NEXT:    vmov.32 q2[0], r0
-; CHECK-NEXT:    vmov.u16 r0, q1[1]
-; CHECK-NEXT:    vmov.32 q2[1], r0
-; CHECK-NEXT:    vmov.u16 r0, q1[2]
-; CHECK-NEXT:    vmov.32 q2[2], r0
-; CHECK-NEXT:    vmov.u16 r0, q1[3]
-; CHECK-NEXT:    vmov.32 q2[3], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[0]
-; CHECK-NEXT:    vmov.32 q3[0], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[1]
-; CHECK-NEXT:    vmov.32 q3[1], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[2]
-; CHECK-NEXT:    vmov.32 q3[2], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[3]
-; CHECK-NEXT:    vmov.32 q3[3], r0
-; CHECK-NEXT:    vmullb.s16 q2, q3, q2
-; CHECK-NEXT:    vshr.s32 q3, q2, #16
-; CHECK-NEXT:    vmov r0, s12
-; CHECK-NEXT:    vmov.16 q2[0], r0
-; CHECK-NEXT:    vmov r0, s13
-; CHECK-NEXT:    vmov.16 q2[1], r0
-; CHECK-NEXT:    vmov r0, s14
-; CHECK-NEXT:    vmov.16 q2[2], r0
-; CHECK-NEXT:    vmov r0, s15
-; CHECK-NEXT:    vmov.16 q2[3], r0
-; CHECK-NEXT:    vmov.u16 r0, q1[4]
-; CHECK-NEXT:    vmov.32 q3[0], r0
-; CHECK-NEXT:    vmov.u16 r0, q1[5]
-; CHECK-NEXT:    vmov.32 q3[1], r0
-; CHECK-NEXT:    vmov.u16 r0, q1[6]
-; CHECK-NEXT:    vmov.32 q3[2], r0
-; CHECK-NEXT:    vmov.u16 r0, q1[7]
-; CHECK-NEXT:    vmov.32 q3[3], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[4]
-; CHECK-NEXT:    vmov.32 q1[0], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[5]
-; CHECK-NEXT:    vmov.32 q1[1], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[6]
-; CHECK-NEXT:    vmov.32 q1[2], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[7]
-; CHECK-NEXT:    vmov.32 q1[3], r0
-; CHECK-NEXT:    vmullb.s16 q0, q1, q3
-; CHECK-NEXT:    vshr.s32 q0, q0, #16
-; CHECK-NEXT:    vmov r0, s0
-; CHECK-NEXT:    vmov.16 q2[4], r0
-; CHECK-NEXT:    vmov r0, s1
-; CHECK-NEXT:    vmov.16 q2[5], r0
-; CHECK-NEXT:    vmov r0, s2
-; CHECK-NEXT:    vmov.16 q2[6], r0
-; CHECK-NEXT:    vmov r0, s3
-; CHECK-NEXT:    vmov.16 q2[7], r0
-; CHECK-NEXT:    vmov q0, q2
+; CHECK-NEXT:    vmulh.s16 q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
   %s0s = sext <8 x i16> %s0 to <8 x i32>
@@ -207,59 +120,7 @@
 define arm_aapcs_vfpcc <8 x i16> @vmulhu_v8i16(<8 x i16> %s0, <8 x i16> %s1) {
 ; CHECK-LABEL: vmulhu_v8i16:
 ; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    vmov.u16 r0, q1[0]
-; CHECK-NEXT:    vmov.32 q2[0], r0
-; CHECK-NEXT:    vmov.u16 r0, q1[1]
-; CHECK-NEXT:    vmov.32 q2[1], r0
-; CHECK-NEXT:    vmov.u16 r0, q1[2]
-; CHECK-NEXT:    vmov.32 q2[2], r0
-; CHECK-NEXT:    vmov.u16 r0, q1[3]
-; CHECK-NEXT:    vmov.32 q2[3], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[0]
-; CHECK-NEXT:    vmov.32 q3[0], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[1]
-; CHECK-NEXT:    vmov.32 q3[1], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[2]
-; CHECK-NEXT:    vmov.32 q3[2], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[3]
-; CHECK-NEXT:    vmov.32 q3[3], r0
-; CHECK-NEXT:    vmullb.u16 q2, q3, q2
-; CHECK-NEXT:    vshr.u32 q3, q2, #16
-; CHECK-NEXT:    vmov r0, s12
-; CHECK-NEXT:    vmov.16 q2[0], r0
-; CHECK-NEXT:    vmov r0, s13
-; CHECK-NEXT:    vmov.16 q2[1], r0
-; CHECK-NEXT:    vmov r0, s14
-; CHECK-NEXT:    vmov.16 q2[2], r0
-; CHECK-NEXT:    vmov r0, s15
-; CHECK-NEXT:    vmov.16 q2[3], r0
-; CHECK-NEXT:    vmov.u16 r0, q1[4]
-; CHECK-NEXT:    vmov.32 q3[0], r0
-; CHECK-NEXT:    vmov.u16 r0, q1[5]
-; CHECK-NEXT:    vmov.32 q3[1], r0
-; CHECK-NEXT:    vmov.u16 r0, q1[6]
-; CHECK-NEXT:    vmov.32 q3[2], r0
-; CHECK-NEXT:    vmov.u16 r0, q1[7]
-; CHECK-NEXT:    vmov.32 q3[3], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[4]
-; CHECK-NEXT:    vmov.32 q1[0], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[5]
-; CHECK-NEXT:    vmov.32 q1[1], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[6]
-; CHECK-NEXT:    vmov.32 q1[2], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[7]
-; CHECK-NEXT:    vmov.32 q1[3], r0
-; CHECK-NEXT:    vmullb.u16 q0, q1, q3
-; CHECK-NEXT:    vshr.u32 q0, q0, #16
-; CHECK-NEXT:    vmov r0, s0
-; CHECK-NEXT:    vmov.16 q2[4], r0
-; CHECK-NEXT:    vmov r0, s1
-; CHECK-NEXT:    vmov.16 q2[5], r0
-; CHECK-NEXT:    vmov r0, s2
-; CHECK-NEXT:    vmov.16 q2[6], r0
-; CHECK-NEXT:    vmov r0, s3
-; CHECK-NEXT:    vmov.16 q2[7], r0
-; CHECK-NEXT:    vmov q0, q2
+; CHECK-NEXT:    vmulh.u16 q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
   %s0s = zext <8 x i16> %s0 to <8 x i32>
@@ -303,107 +164,7 @@
 define arm_aapcs_vfpcc <16 x i8> @vmulhs_v16i8(<16 x i8> %s0, <16 x i8> %s1) {
 ; CHECK-LABEL: vmulhs_v16i8:
 ; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    vmov.u8 r0, q1[0]
-; CHECK-NEXT:    vmov.16 q2[0], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[1]
-; CHECK-NEXT:    vmov.16 q2[1], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[2]
-; CHECK-NEXT:    vmov.16 q2[2], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[3]
-; CHECK-NEXT:    vmov.16 q2[3], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[4]
-; CHECK-NEXT:    vmov.16 q2[4], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[5]
-; CHECK-NEXT:    vmov.16 q2[5], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[6]
-; CHECK-NEXT:    vmov.16 q2[6], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[7]
-; CHECK-NEXT:    vmov.16 q2[7], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[0]
-; CHECK-NEXT:    vmov.16 q3[0], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[1]
-; CHECK-NEXT:    vmov.16 q3[1], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[2]
-; CHECK-NEXT:    vmov.16 q3[2], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[3]
-; CHECK-NEXT:    vmov.16 q3[3], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[4]
-; CHECK-NEXT:    vmov.16 q3[4], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[5]
-; CHECK-NEXT:    vmov.16 q3[5], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[6]
-; CHECK-NEXT:    vmov.16 q3[6], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[7]
-; CHECK-NEXT:    vmov.16 q3[7], r0
-; CHECK-NEXT:    vmullb.s8 q2, q3, q2
-; CHECK-NEXT:    vshr.s16 q3, q2, #8
-; CHECK-NEXT:    vmov.u16 r0, q3[0]
-; CHECK-NEXT:    vmov.8 q2[0], r0
-; CHECK-NEXT:    vmov.u16 r0, q3[1]
-; CHECK-NEXT:    vmov.8 q2[1], r0
-; CHECK-NEXT:    vmov.u16 r0, q3[2]
-; CHECK-NEXT:    vmov.8 q2[2], r0
-; CHECK-NEXT:    vmov.u16 r0, q3[3]
-; CHECK-NEXT:    vmov.8 q2[3], r0
-; CHECK-NEXT:    vmov.u16 r0, q3[4]
-; CHECK-NEXT:    vmov.8 q2[4], r0
-; CHECK-NEXT:    vmov.u16 r0, q3[5]
-; CHECK-NEXT:    vmov.8 q2[5], r0
-; CHECK-NEXT:    vmov.u16 r0, q3[6]
-; CHECK-NEXT:    vmov.8 q2[6], r0
-; CHECK-NEXT:    vmov.u16 r0, q3[7]
-; CHECK-NEXT:    vmov.8 q2[7], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[8]
-; CHECK-NEXT:    vmov.16 q3[0], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[9]
-; CHECK-NEXT:    vmov.16 q3[1], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[10]
-; CHECK-NEXT:    vmov.16 q3[2], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[11]
-; CHECK-NEXT:    vmov.16 q3[3], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[12]
-; CHECK-NEXT:    vmov.16 q3[4], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[13]
-; CHECK-NEXT:    vmov.16 q3[5], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[14]
-; CHECK-NEXT:    vmov.16 q3[6], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[15]
-; CHECK-NEXT:    vmov.16 q3[7], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[8]
-; CHECK-NEXT:    vmov.16 q1[0], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[9]
-; CHECK-NEXT:    vmov.16 q1[1], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[10]
-; CHECK-NEXT:    vmov.16 q1[2], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[11]
-; CHECK-NEXT:    vmov.16 q1[3], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[12]
-; CHECK-NEXT:    vmov.16 q1[4], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[13]
-; CHECK-NEXT:    vmov.16 q1[5], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[14]
-; CHECK-NEXT:    vmov.16 q1[6], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[15]
-; CHECK-NEXT:    vmov.16 q1[7], r0
-; CHECK-NEXT:    vmullb.s8 q0, q1, q3
-; CHECK-NEXT:    vshr.s16 q0, q0, #8
-; CHECK-NEXT:    vmov.u16 r0, q0[0]
-; CHECK-NEXT:    vmov.8 q2[8], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[1]
-; CHECK-NEXT:    vmov.8 q2[9], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[2]
-; CHECK-NEXT:    vmov.8 q2[10], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[3]
-; CHECK-NEXT:    vmov.8 q2[11], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[4]
-; CHECK-NEXT:    vmov.8 q2[12], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[5]
-; CHECK-NEXT:    vmov.8 q2[13], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[6]
-; CHECK-NEXT:    vmov.8 q2[14], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[7]
-; CHECK-NEXT:    vmov.8 q2[15], r0
-; CHECK-NEXT:    vmov q0, q2
+; CHECK-NEXT:    vmulh.s8 q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
   %s0s = sext <16 x i8> %s0 to <16 x i16>
@@ -417,107 +178,7 @@
 define arm_aapcs_vfpcc <16 x i8> @vmulhu_v16i8(<16 x i8> %s0, <16 x i8> %s1) {
 ; CHECK-LABEL: vmulhu_v16i8:
 ; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    vmov.u8 r0, q1[0]
-; CHECK-NEXT:    vmov.16 q2[0], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[1]
-; CHECK-NEXT:    vmov.16 q2[1], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[2]
-; CHECK-NEXT:    vmov.16 q2[2], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[3]
-; CHECK-NEXT:    vmov.16 q2[3], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[4]
-; CHECK-NEXT:    vmov.16 q2[4], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[5]
-; CHECK-NEXT:    vmov.16 q2[5], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[6]
-; CHECK-NEXT:    vmov.16 q2[6], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[7]
-; CHECK-NEXT:    vmov.16 q2[7], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[0]
-; CHECK-NEXT:    vmov.16 q3[0], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[1]
-; CHECK-NEXT:    vmov.16 q3[1], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[2]
-; CHECK-NEXT:    vmov.16 q3[2], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[3]
-; CHECK-NEXT:    vmov.16 q3[3], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[4]
-; CHECK-NEXT:    vmov.16 q3[4], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[5]
-; CHECK-NEXT:    vmov.16 q3[5], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[6]
-; CHECK-NEXT:    vmov.16 q3[6], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[7]
-; CHECK-NEXT:    vmov.16 q3[7], r0
-; CHECK-NEXT:    vmullb.u8 q2, q3, q2
-; CHECK-NEXT:    vshr.u16 q3, q2, #8
-; CHECK-NEXT:    vmov.u16 r0, q3[0]
-; CHECK-NEXT:    vmov.8 q2[0], r0
-; CHECK-NEXT:    vmov.u16 r0, q3[1]
-; CHECK-NEXT:    vmov.8 q2[1], r0
-; CHECK-NEXT:    vmov.u16 r0, q3[2]
-; CHECK-NEXT:    vmov.8 q2[2], r0
-; CHECK-NEXT:    vmov.u16 r0, q3[3]
-; CHECK-NEXT:    vmov.8 q2[3], r0
-; CHECK-NEXT:    vmov.u16 r0, q3[4]
-; CHECK-NEXT:    vmov.8 q2[4], r0
-; CHECK-NEXT:    vmov.u16 r0, q3[5]
-; CHECK-NEXT:    vmov.8 q2[5], r0
-; CHECK-NEXT:    vmov.u16 r0, q3[6]
-; CHECK-NEXT:    vmov.8 q2[6], r0
-; CHECK-NEXT:    vmov.u16 r0, q3[7]
-; CHECK-NEXT:    vmov.8 q2[7], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[8]
-; CHECK-NEXT:    vmov.16 q3[0], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[9]
-; CHECK-NEXT:    vmov.16 q3[1], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[10]
-; CHECK-NEXT:    vmov.16 q3[2], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[11]
-; CHECK-NEXT:    vmov.16 q3[3], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[12]
-; CHECK-NEXT:    vmov.16 q3[4], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[13]
-; CHECK-NEXT:    vmov.16 q3[5], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[14]
-; CHECK-NEXT:    vmov.16 q3[6], r0
-; CHECK-NEXT:    vmov.u8 r0, q1[15]
-; CHECK-NEXT:    vmov.16 q3[7], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[8]
-; CHECK-NEXT:    vmov.16 q1[0], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[9]
-; CHECK-NEXT:    vmov.16 q1[1], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[10]
-; CHECK-NEXT:    vmov.16 q1[2], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[11]
-; CHECK-NEXT:    vmov.16 q1[3], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[12]
-; CHECK-NEXT:    vmov.16 q1[4], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[13]
-; CHECK-NEXT:    vmov.16 q1[5], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[14]
-; CHECK-NEXT:    vmov.16 q1[6], r0
-; CHECK-NEXT:    vmov.u8 r0, q0[15]
-; CHECK-NEXT:    vmov.16 q1[7], r0
-; CHECK-NEXT:    vmullb.u8 q0, q1, q3
-; CHECK-NEXT:    vshr.u16 q0, q0, #8
-; CHECK-NEXT:    vmov.u16 r0, q0[0]
-; CHECK-NEXT:    vmov.8 q2[8], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[1]
-; CHECK-NEXT:    vmov.8 q2[9], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[2]
-; CHECK-NEXT:    vmov.8 q2[10], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[3]
-; CHECK-NEXT:    vmov.8 q2[11], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[4]
-; CHECK-NEXT:    vmov.8 q2[12], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[5]
-; CHECK-NEXT:    vmov.8 q2[13], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[6]
-; CHECK-NEXT:    vmov.8 q2[14], r0
-; CHECK-NEXT:    vmov.u16 r0, q0[7]
-; CHECK-NEXT:    vmov.8 q2[15], r0
-; CHECK-NEXT:    vmov q0, q2
+; CHECK-NEXT:    vmulh.u8 q0, q0, q1
 ; CHECK-NEXT:    bx lr
 entry:
   %s0s = zext <16 x i8> %s0 to <16 x i16>