Index: llvm/lib/Target/ARM/ARMTargetTransformInfo.h
===================================================================
--- llvm/lib/Target/ARM/ARMTargetTransformInfo.h
+++ llvm/lib/Target/ARM/ARMTargetTransformInfo.h
@@ -110,11 +110,15 @@
     if (!ST->hasMVEIntegerOps())
       return false;
 
-    unsigned VecWidth = DataTy->getPrimitiveSizeInBits();
-    if (VecWidth != 128)
+    Type *ScalarTy = DataTy->getScalarType();
+
+    if (ScalarTy->isFloatTy() || ScalarTy->isHalfTy())
+      return true;
+
+    if (!ScalarTy->isIntegerTy())
       return false;
 
-    unsigned EltWidth = DataTy->getScalarSizeInBits();
+    unsigned EltWidth = ScalarTy->getIntegerBitWidth();;
     return EltWidth == 32 || EltWidth == 16 || EltWidth == 8;
   }
 
Index: llvm/test/CodeGen/Thumb2/mve-masked-ldst.ll
===================================================================
--- llvm/test/CodeGen/Thumb2/mve-masked-ldst.ll
+++ llvm/test/CodeGen/Thumb2/mve-masked-ldst.ll
@@ -20,38 +20,30 @@
 }
 
 define void @foo_sext_v4i32_v4i8(<4 x i32> *%dest, <4 x i32> *%mask, <4 x i8> *%src) {
-; CHECK-LABEL: foo_sext_v4i32_v4i8:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .pad #4
-; CHECK-NEXT:    sub sp, #4
-; CHECK-NEXT:    vldrw.u32 q0, [r1]
-; CHECK-NEXT:    mov r3, sp
-; CHECK-NEXT:    vcmp.s32 gt, q0, zr
-; CHECK-NEXT:    @ implicit-def: $q0
-; CHECK-NEXT:    vstr p0, [r3]
-; CHECK-NEXT:    ldrb.w r1, [sp]
-; CHECK-NEXT:    lsls r3, r1, #31
-; CHECK-NEXT:    itt ne
-; CHECK-NEXT:    ldrbne r3, [r2]
-; CHECK-NEXT:    vmovne.32 q0[0], r3
-; CHECK-NEXT:    lsls r3, r1, #30
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r3, [r2, #1]
-; CHECK-NEXT:    vmovmi.32 q0[1], r3
-; CHECK-NEXT:    lsls r3, r1, #29
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r3, [r2, #2]
-; CHECK-NEXT:    vmovmi.32 q0[2], r3
-; CHECK-NEXT:    lsls r1, r1, #28
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r1, [r2, #3]
-; CHECK-NEXT:    vmovmi.32 q0[3], r1
-; CHECK-NEXT:    vmovlb.s8 q0, q0
-; CHECK-NEXT:    vmovlb.s16 q0, q0
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vstrwt.32 q0, [r0]
-; CHECK-NEXT:    add sp, #4
-; CHECK-NEXT:    bx lr
+; CHECK-LE-LABEL: foo_sext_v4i32_v4i8:
+; CHECK-LE:       @ %bb.0: @ %entry
+; CHECK-LE-NEXT:    vldrw.u32 q0, [r1]
+; CHECK-LE-NEXT:    vcmp.s32 gt, q0, zr
+; CHECK-LE-NEXT:    vpst
+; CHECK-LE-NEXT:    vldrbt.u8 q0, [r2]
+; CHECK-LE-NEXT:    vmovlb.s8 q0, q0
+; CHECK-LE-NEXT:    vmovlb.s16 q0, q0
+; CHECK-LE-NEXT:    vpst
+; CHECK-LE-NEXT:    vstrwt.32 q0, [r0]
+; CHECK-LE-NEXT:    bx lr
+;
+; CHECK-BE-LABEL: foo_sext_v4i32_v4i8:
+; CHECK-BE:       @ %bb.0: @ %entry
+; CHECK-BE-NEXT:    vldrw.u32 q0, [r1]
+; CHECK-BE-NEXT:    vcmp.s32 gt, q0, zr
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vldrbt.u8 q0, [r2]
+; CHECK-BE-NEXT:    vrev32.8 q0, q0
+; CHECK-BE-NEXT:    vmovlb.s8 q0, q0
+; CHECK-BE-NEXT:    vmovlb.s16 q0, q0
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vstrwt.32 q0, [r0]
+; CHECK-BE-NEXT:    bx lr
 entry:
   %0 = load <4 x i32>, <4 x i32>* %mask, align 4
   %1 = icmp sgt <4 x i32> %0, zeroinitializer
@@ -62,37 +54,28 @@
 }
 
 define void @foo_sext_v4i32_v4i16(<4 x i32> *%dest, <4 x i32> *%mask, <4 x i16> *%src) {
-; CHECK-LABEL: foo_sext_v4i32_v4i16:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .pad #4
-; CHECK-NEXT:    sub sp, #4
-; CHECK-NEXT:    vldrw.u32 q0, [r1]
-; CHECK-NEXT:    mov r3, sp
-; CHECK-NEXT:    vcmp.s32 gt, q0, zr
-; CHECK-NEXT:    @ implicit-def: $q0
-; CHECK-NEXT:    vstr p0, [r3]
-; CHECK-NEXT:    ldrb.w r1, [sp]
-; CHECK-NEXT:    lsls r3, r1, #31
-; CHECK-NEXT:    itt ne
-; CHECK-NEXT:    ldrhne r3, [r2]
-; CHECK-NEXT:    vmovne.32 q0[0], r3
-; CHECK-NEXT:    lsls r3, r1, #30
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrhmi r3, [r2, #2]
-; CHECK-NEXT:    vmovmi.32 q0[1], r3
-; CHECK-NEXT:    lsls r3, r1, #29
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrhmi r3, [r2, #4]
-; CHECK-NEXT:    vmovmi.32 q0[2], r3
-; CHECK-NEXT:    lsls r1, r1, #28
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrhmi r1, [r2, #6]
-; CHECK-NEXT:    vmovmi.32 q0[3], r1
-; CHECK-NEXT:    vmovlb.s16 q0, q0
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vstrwt.32 q0, [r0]
-; CHECK-NEXT:    add sp, #4
-; CHECK-NEXT:    bx lr
+; CHECK-LE-LABEL: foo_sext_v4i32_v4i16:
+; CHECK-LE:       @ %bb.0: @ %entry
+; CHECK-LE-NEXT:    vldrw.u32 q0, [r1]
+; CHECK-LE-NEXT:    vcmp.s32 gt, q0, zr
+; CHECK-LE-NEXT:    vpst
+; CHECK-LE-NEXT:    vldrbt.u8 q0, [r2]
+; CHECK-LE-NEXT:    vmovlb.s16 q0, q0
+; CHECK-LE-NEXT:    vpst
+; CHECK-LE-NEXT:    vstrwt.32 q0, [r0]
+; CHECK-LE-NEXT:    bx lr
+;
+; CHECK-BE-LABEL: foo_sext_v4i32_v4i16:
+; CHECK-BE:       @ %bb.0: @ %entry
+; CHECK-BE-NEXT:    vldrw.u32 q0, [r1]
+; CHECK-BE-NEXT:    vcmp.s32 gt, q0, zr
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vldrbt.u8 q0, [r2]
+; CHECK-BE-NEXT:    vrev32.8 q0, q0
+; CHECK-BE-NEXT:    vmovlb.s16 q0, q0
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vstrwt.32 q0, [r0]
+; CHECK-BE-NEXT:    bx lr
 entry:
   %0 = load <4 x i32>, <4 x i32>* %mask, align 4
   %1 = icmp sgt <4 x i32> %0, zeroinitializer
@@ -103,38 +86,30 @@
 }
 
 define void @foo_zext_v4i32_v4i8(<4 x i32> *%dest, <4 x i32> *%mask, <4 x i8> *%src) {
-; CHECK-LABEL: foo_zext_v4i32_v4i8:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .pad #4
-; CHECK-NEXT:    sub sp, #4
-; CHECK-NEXT:    vldrw.u32 q0, [r1]
-; CHECK-NEXT:    mov r3, sp
-; CHECK-NEXT:    vmov.i32 q1, #0xff
-; CHECK-NEXT:    vcmp.s32 gt, q0, zr
-; CHECK-NEXT:    @ implicit-def: $q0
-; CHECK-NEXT:    vstr p0, [r3]
-; CHECK-NEXT:    ldrb.w r1, [sp]
-; CHECK-NEXT:    lsls r3, r1, #31
-; CHECK-NEXT:    itt ne
-; CHECK-NEXT:    ldrbne r3, [r2]
-; CHECK-NEXT:    vmovne.32 q0[0], r3
-; CHECK-NEXT:    lsls r3, r1, #30
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r3, [r2, #1]
-; CHECK-NEXT:    vmovmi.32 q0[1], r3
-; CHECK-NEXT:    lsls r3, r1, #29
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r3, [r2, #2]
-; CHECK-NEXT:    vmovmi.32 q0[2], r3
-; CHECK-NEXT:    lsls r1, r1, #28
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r1, [r2, #3]
-; CHECK-NEXT:    vmovmi.32 q0[3], r1
-; CHECK-NEXT:    vand q0, q0, q1
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vstrwt.32 q0, [r0]
-; CHECK-NEXT:    add sp, #4
-; CHECK-NEXT:    bx lr
+; CHECK-LE-LABEL: foo_zext_v4i32_v4i8:
+; CHECK-LE:       @ %bb.0: @ %entry
+; CHECK-LE-NEXT:    vldrw.u32 q1, [r1]
+; CHECK-LE-NEXT:    vmov.i32 q0, #0xff
+; CHECK-LE-NEXT:    vcmp.s32 gt, q1, zr
+; CHECK-LE-NEXT:    vpst
+; CHECK-LE-NEXT:    vldrbt.u8 q1, [r2]
+; CHECK-LE-NEXT:    vand q0, q1, q0
+; CHECK-LE-NEXT:    vpst
+; CHECK-LE-NEXT:    vstrwt.32 q0, [r0]
+; CHECK-LE-NEXT:    bx lr
+;
+; CHECK-BE-LABEL: foo_zext_v4i32_v4i8:
+; CHECK-BE:       @ %bb.0: @ %entry
+; CHECK-BE-NEXT:    vldrw.u32 q0, [r1]
+; CHECK-BE-NEXT:    vcmp.s32 gt, q0, zr
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vldrbt.u8 q0, [r2]
+; CHECK-BE-NEXT:    vmov.i32 q1, #0xff
+; CHECK-BE-NEXT:    vrev32.8 q0, q0
+; CHECK-BE-NEXT:    vand q0, q0, q1
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vstrwt.32 q0, [r0]
+; CHECK-BE-NEXT:    bx lr
 entry:
   %0 = load <4 x i32>, <4 x i32>* %mask, align 4
   %1 = icmp sgt <4 x i32> %0, zeroinitializer
@@ -145,37 +120,28 @@
 }
 
 define void @foo_zext_v4i32_v4i16(<4 x i32> *%dest, <4 x i32> *%mask, <4 x i16> *%src) {
-; CHECK-LABEL: foo_zext_v4i32_v4i16:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .pad #4
-; CHECK-NEXT:    sub sp, #4
-; CHECK-NEXT:    vldrw.u32 q0, [r1]
-; CHECK-NEXT:    mov r3, sp
-; CHECK-NEXT:    vcmp.s32 gt, q0, zr
-; CHECK-NEXT:    @ implicit-def: $q0
-; CHECK-NEXT:    vstr p0, [r3]
-; CHECK-NEXT:    ldrb.w r1, [sp]
-; CHECK-NEXT:    lsls r3, r1, #31
-; CHECK-NEXT:    itt ne
-; CHECK-NEXT:    ldrhne r3, [r2]
-; CHECK-NEXT:    vmovne.32 q0[0], r3
-; CHECK-NEXT:    lsls r3, r1, #30
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrhmi r3, [r2, #2]
-; CHECK-NEXT:    vmovmi.32 q0[1], r3
-; CHECK-NEXT:    lsls r3, r1, #29
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrhmi r3, [r2, #4]
-; CHECK-NEXT:    vmovmi.32 q0[2], r3
-; CHECK-NEXT:    lsls r1, r1, #28
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrhmi r1, [r2, #6]
-; CHECK-NEXT:    vmovmi.32 q0[3], r1
-; CHECK-NEXT:    vmovlb.u16 q0, q0
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vstrwt.32 q0, [r0]
-; CHECK-NEXT:    add sp, #4
-; CHECK-NEXT:    bx lr
+; CHECK-LE-LABEL: foo_zext_v4i32_v4i16:
+; CHECK-LE:       @ %bb.0: @ %entry
+; CHECK-LE-NEXT:    vldrw.u32 q0, [r1]
+; CHECK-LE-NEXT:    vcmp.s32 gt, q0, zr
+; CHECK-LE-NEXT:    vpst
+; CHECK-LE-NEXT:    vldrbt.u8 q0, [r2]
+; CHECK-LE-NEXT:    vmovlb.u16 q0, q0
+; CHECK-LE-NEXT:    vpst
+; CHECK-LE-NEXT:    vstrwt.32 q0, [r0]
+; CHECK-LE-NEXT:    bx lr
+;
+; CHECK-BE-LABEL: foo_zext_v4i32_v4i16:
+; CHECK-BE:       @ %bb.0: @ %entry
+; CHECK-BE-NEXT:    vldrw.u32 q0, [r1]
+; CHECK-BE-NEXT:    vcmp.s32 gt, q0, zr
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vldrbt.u8 q0, [r2]
+; CHECK-BE-NEXT:    vrev32.8 q0, q0
+; CHECK-BE-NEXT:    vmovlb.u16 q0, q0
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vstrwt.32 q0, [r0]
+; CHECK-BE-NEXT:    bx lr
 entry:
   %0 = load <4 x i32>, <4 x i32>* %mask, align 4
   %1 = icmp sgt <4 x i32> %0, zeroinitializer
@@ -203,53 +169,28 @@
 }
 
 define void @foo_sext_v8i16_v8i8(<8 x i16> *%dest, <8 x i16> *%mask, <8 x i8> *%src) {
-; CHECK-LABEL: foo_sext_v8i16_v8i8:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .pad #8
-; CHECK-NEXT:    sub sp, #8
-; CHECK-NEXT:    vldrh.u16 q0, [r1]
-; CHECK-NEXT:    mov r3, sp
-; CHECK-NEXT:    vcmp.s16 gt, q0, zr
-; CHECK-NEXT:    @ implicit-def: $q0
-; CHECK-NEXT:    vstr p0, [r3]
-; CHECK-NEXT:    ldrb.w r1, [sp]
-; CHECK-NEXT:    lsls r3, r1, #31
-; CHECK-NEXT:    itt ne
-; CHECK-NEXT:    ldrbne r3, [r2]
-; CHECK-NEXT:    vmovne.16 q0[0], r3
-; CHECK-NEXT:    lsls r3, r1, #30
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r3, [r2, #1]
-; CHECK-NEXT:    vmovmi.16 q0[1], r3
-; CHECK-NEXT:    lsls r3, r1, #29
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r3, [r2, #2]
-; CHECK-NEXT:    vmovmi.16 q0[2], r3
-; CHECK-NEXT:    lsls r3, r1, #28
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r3, [r2, #3]
-; CHECK-NEXT:    vmovmi.16 q0[3], r3
-; CHECK-NEXT:    lsls r3, r1, #27
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r3, [r2, #4]
-; CHECK-NEXT:    vmovmi.16 q0[4], r3
-; CHECK-NEXT:    lsls r3, r1, #26
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r3, [r2, #5]
-; CHECK-NEXT:    vmovmi.16 q0[5], r3
-; CHECK-NEXT:    lsls r3, r1, #25
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r3, [r2, #6]
-; CHECK-NEXT:    vmovmi.16 q0[6], r3
-; CHECK-NEXT:    lsls r1, r1, #24
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r1, [r2, #7]
-; CHECK-NEXT:    vmovmi.16 q0[7], r1
-; CHECK-NEXT:    vmovlb.s8 q0, q0
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vstrht.16 q0, [r0]
-; CHECK-NEXT:    add sp, #8
-; CHECK-NEXT:    bx lr
+; CHECK-LE-LABEL: foo_sext_v8i16_v8i8:
+; CHECK-LE:       @ %bb.0: @ %entry
+; CHECK-LE-NEXT:    vldrh.u16 q0, [r1]
+; CHECK-LE-NEXT:    vcmp.s16 gt, q0, zr
+; CHECK-LE-NEXT:    vpst
+; CHECK-LE-NEXT:    vldrbt.u8 q0, [r2]
+; CHECK-LE-NEXT:    vmovlb.s8 q0, q0
+; CHECK-LE-NEXT:    vpst
+; CHECK-LE-NEXT:    vstrht.16 q0, [r0]
+; CHECK-LE-NEXT:    bx lr
+;
+; CHECK-BE-LABEL: foo_sext_v8i16_v8i8:
+; CHECK-BE:       @ %bb.0: @ %entry
+; CHECK-BE-NEXT:    vldrh.u16 q0, [r1]
+; CHECK-BE-NEXT:    vcmp.s16 gt, q0, zr
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vldrbt.u8 q0, [r2]
+; CHECK-BE-NEXT:    vrev16.8 q0, q0
+; CHECK-BE-NEXT:    vmovlb.s8 q0, q0
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vstrht.16 q0, [r0]
+; CHECK-BE-NEXT:    bx lr
 entry:
   %0 = load <8 x i16>, <8 x i16>* %mask, align 2
   %1 = icmp sgt <8 x i16> %0, zeroinitializer
@@ -260,53 +201,28 @@
 }
 
 define void @foo_zext_v8i16_v8i8(<8 x i16> *%dest, <8 x i16> *%mask, <8 x i8> *%src) {
-; CHECK-LABEL: foo_zext_v8i16_v8i8:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .pad #8
-; CHECK-NEXT:    sub sp, #8
-; CHECK-NEXT:    vldrh.u16 q0, [r1]
-; CHECK-NEXT:    mov r3, sp
-; CHECK-NEXT:    vcmp.s16 gt, q0, zr
-; CHECK-NEXT:    @ implicit-def: $q0
-; CHECK-NEXT:    vstr p0, [r3]
-; CHECK-NEXT:    ldrb.w r1, [sp]
-; CHECK-NEXT:    lsls r3, r1, #31
-; CHECK-NEXT:    itt ne
-; CHECK-NEXT:    ldrbne r3, [r2]
-; CHECK-NEXT:    vmovne.16 q0[0], r3
-; CHECK-NEXT:    lsls r3, r1, #30
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r3, [r2, #1]
-; CHECK-NEXT:    vmovmi.16 q0[1], r3
-; CHECK-NEXT:    lsls r3, r1, #29
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r3, [r2, #2]
-; CHECK-NEXT:    vmovmi.16 q0[2], r3
-; CHECK-NEXT:    lsls r3, r1, #28
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r3, [r2, #3]
-; CHECK-NEXT:    vmovmi.16 q0[3], r3
-; CHECK-NEXT:    lsls r3, r1, #27
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r3, [r2, #4]
-; CHECK-NEXT:    vmovmi.16 q0[4], r3
-; CHECK-NEXT:    lsls r3, r1, #26
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r3, [r2, #5]
-; CHECK-NEXT:    vmovmi.16 q0[5], r3
-; CHECK-NEXT:    lsls r3, r1, #25
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r3, [r2, #6]
-; CHECK-NEXT:    vmovmi.16 q0[6], r3
-; CHECK-NEXT:    lsls r1, r1, #24
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    ldrbmi r1, [r2, #7]
-; CHECK-NEXT:    vmovmi.16 q0[7], r1
-; CHECK-NEXT:    vmovlb.u8 q0, q0
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vstrht.16 q0, [r0]
-; CHECK-NEXT:    add sp, #8
-; CHECK-NEXT:    bx lr
+; CHECK-LE-LABEL: foo_zext_v8i16_v8i8:
+; CHECK-LE:       @ %bb.0: @ %entry
+; CHECK-LE-NEXT:    vldrh.u16 q0, [r1]
+; CHECK-LE-NEXT:    vcmp.s16 gt, q0, zr
+; CHECK-LE-NEXT:    vpst
+; CHECK-LE-NEXT:    vldrbt.u8 q0, [r2]
+; CHECK-LE-NEXT:    vmovlb.u8 q0, q0
+; CHECK-LE-NEXT:    vpst
+; CHECK-LE-NEXT:    vstrht.16 q0, [r0]
+; CHECK-LE-NEXT:    bx lr
+;
+; CHECK-BE-LABEL: foo_zext_v8i16_v8i8:
+; CHECK-BE:       @ %bb.0: @ %entry
+; CHECK-BE-NEXT:    vldrh.u16 q0, [r1]
+; CHECK-BE-NEXT:    vcmp.s16 gt, q0, zr
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vldrbt.u8 q0, [r2]
+; CHECK-BE-NEXT:    vrev16.8 q0, q0
+; CHECK-BE-NEXT:    vmovlb.u8 q0, q0
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vstrht.16 q0, [r0]
+; CHECK-BE-NEXT:    bx lr
 entry:
   %0 = load <8 x i16>, <8 x i16>* %mask, align 2
   %1 = icmp sgt <8 x i16> %0, zeroinitializer
@@ -334,51 +250,25 @@
 }
 
 define void @foo_trunc_v8i8_v8i16(<8 x i8> *%dest, <8 x i16> *%mask, <8 x i16> *%src) {
-; CHECK-LABEL: foo_trunc_v8i8_v8i16:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .pad #8
-; CHECK-NEXT:    sub sp, #8
-; CHECK-NEXT:    vldrh.u16 q0, [r1]
-; CHECK-NEXT:    mov r3, sp
-; CHECK-NEXT:    vcmp.s16 gt, q0, zr
-; CHECK-NEXT:    vstr p0, [r3]
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vldrht.u16 q0, [r2]
-; CHECK-NEXT:    ldrb.w r1, [sp]
-; CHECK-NEXT:    lsls r2, r1, #31
-; CHECK-NEXT:    itt ne
-; CHECK-NEXT:    vmovne.u16 r2, q0[0]
-; CHECK-NEXT:    strbne r2, [r0]
-; CHECK-NEXT:    lsls r2, r1, #30
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    vmovmi.u16 r2, q0[1]
-; CHECK-NEXT:    strbmi r2, [r0, #1]
-; CHECK-NEXT:    lsls r2, r1, #29
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    vmovmi.u16 r2, q0[2]
-; CHECK-NEXT:    strbmi r2, [r0, #2]
-; CHECK-NEXT:    lsls r2, r1, #28
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    vmovmi.u16 r2, q0[3]
-; CHECK-NEXT:    strbmi r2, [r0, #3]
-; CHECK-NEXT:    lsls r2, r1, #27
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    vmovmi.u16 r2, q0[4]
-; CHECK-NEXT:    strbmi r2, [r0, #4]
-; CHECK-NEXT:    lsls r2, r1, #26
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    vmovmi.u16 r2, q0[5]
-; CHECK-NEXT:    strbmi r2, [r0, #5]
-; CHECK-NEXT:    lsls r2, r1, #25
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    vmovmi.u16 r2, q0[6]
-; CHECK-NEXT:    strbmi r2, [r0, #6]
-; CHECK-NEXT:    lsls r1, r1, #24
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    vmovmi.u16 r1, q0[7]
-; CHECK-NEXT:    strbmi r1, [r0, #7]
-; CHECK-NEXT:    add sp, #8
-; CHECK-NEXT:    bx lr
+; CHECK-LE-LABEL: foo_trunc_v8i8_v8i16:
+; CHECK-LE:       @ %bb.0: @ %entry
+; CHECK-LE-NEXT:    vldrh.u16 q0, [r1]
+; CHECK-LE-NEXT:    vcmp.s16 gt, q0, zr
+; CHECK-LE-NEXT:    vpstt
+; CHECK-LE-NEXT:    vldrht.u16 q0, [r2]
+; CHECK-LE-NEXT:    vstrbt.8 q0, [r0]
+; CHECK-LE-NEXT:    bx lr
+;
+; CHECK-BE-LABEL: foo_trunc_v8i8_v8i16:
+; CHECK-BE:       @ %bb.0: @ %entry
+; CHECK-BE-NEXT:    vldrh.u16 q0, [r1]
+; CHECK-BE-NEXT:    vcmp.s16 gt, q0, zr
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vldrht.u16 q0, [r2]
+; CHECK-BE-NEXT:    vrev16.8 q0, q0
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vstrbt.8 q0, [r0]
+; CHECK-BE-NEXT:    bx lr
 entry:
   %0 = load <8 x i16>, <8 x i16>* %mask, align 2
   %1 = icmp sgt <8 x i16> %0, zeroinitializer
@@ -389,35 +279,25 @@
 }
 
 define void @foo_trunc_v4i8_v4i32(<4 x i8> *%dest, <4 x i32> *%mask, <4 x i32> *%src) {
-; CHECK-LABEL: foo_trunc_v4i8_v4i32:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .pad #4
-; CHECK-NEXT:    sub sp, #4
-; CHECK-NEXT:    vldrw.u32 q0, [r1]
-; CHECK-NEXT:    mov r3, sp
-; CHECK-NEXT:    vcmp.s32 gt, q0, zr
-; CHECK-NEXT:    vstr p0, [r3]
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vldrwt.u32 q0, [r2]
-; CHECK-NEXT:    ldrb.w r1, [sp]
-; CHECK-NEXT:    lsls r2, r1, #31
-; CHECK-NEXT:    itt ne
-; CHECK-NEXT:    vmovne r2, s0
-; CHECK-NEXT:    strbne r2, [r0]
-; CHECK-NEXT:    lsls r2, r1, #30
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    vmovmi r2, s1
-; CHECK-NEXT:    strbmi r2, [r0, #1]
-; CHECK-NEXT:    lsls r2, r1, #29
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    vmovmi r2, s2
-; CHECK-NEXT:    strbmi r2, [r0, #2]
-; CHECK-NEXT:    lsls r1, r1, #28
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    vmovmi r1, s3
-; CHECK-NEXT:    strbmi r1, [r0, #3]
-; CHECK-NEXT:    add sp, #4
-; CHECK-NEXT:    bx lr
+; CHECK-LE-LABEL: foo_trunc_v4i8_v4i32:
+; CHECK-LE:       @ %bb.0: @ %entry
+; CHECK-LE-NEXT:    vldrw.u32 q0, [r1]
+; CHECK-LE-NEXT:    vcmp.s32 gt, q0, zr
+; CHECK-LE-NEXT:    vpstt
+; CHECK-LE-NEXT:    vldrwt.u32 q0, [r2]
+; CHECK-LE-NEXT:    vstrbt.8 q0, [r0]
+; CHECK-LE-NEXT:    bx lr
+;
+; CHECK-BE-LABEL: foo_trunc_v4i8_v4i32:
+; CHECK-BE:       @ %bb.0: @ %entry
+; CHECK-BE-NEXT:    vldrw.u32 q0, [r1]
+; CHECK-BE-NEXT:    vcmp.s32 gt, q0, zr
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vldrwt.u32 q0, [r2]
+; CHECK-BE-NEXT:    vrev32.8 q0, q0
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vstrbt.8 q0, [r0]
+; CHECK-BE-NEXT:    bx lr
 entry:
   %0 = load <4 x i32>, <4 x i32>* %mask, align 4
   %1 = icmp sgt <4 x i32> %0, zeroinitializer
@@ -428,35 +308,25 @@
 }
 
 define void @foo_trunc_v4i16_v4i32(<4 x i16> *%dest, <4 x i32> *%mask, <4 x i32> *%src) {
-; CHECK-LABEL: foo_trunc_v4i16_v4i32:
-; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .pad #4
-; CHECK-NEXT:    sub sp, #4
-; CHECK-NEXT:    vldrw.u32 q0, [r1]
-; CHECK-NEXT:    mov r3, sp
-; CHECK-NEXT:    vcmp.s32 gt, q0, zr
-; CHECK-NEXT:    vstr p0, [r3]
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vldrwt.u32 q0, [r2]
-; CHECK-NEXT:    ldrb.w r1, [sp]
-; CHECK-NEXT:    lsls r2, r1, #31
-; CHECK-NEXT:    itt ne
-; CHECK-NEXT:    vmovne r2, s0
-; CHECK-NEXT:    strhne r2, [r0]
-; CHECK-NEXT:    lsls r2, r1, #30
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    vmovmi r2, s1
-; CHECK-NEXT:    strhmi r2, [r0, #2]
-; CHECK-NEXT:    lsls r2, r1, #29
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    vmovmi r2, s2
-; CHECK-NEXT:    strhmi r2, [r0, #4]
-; CHECK-NEXT:    lsls r1, r1, #28
-; CHECK-NEXT:    itt mi
-; CHECK-NEXT:    vmovmi r1, s3
-; CHECK-NEXT:    strhmi r1, [r0, #6]
-; CHECK-NEXT:    add sp, #4
-; CHECK-NEXT:    bx lr
+; CHECK-LE-LABEL: foo_trunc_v4i16_v4i32:
+; CHECK-LE:       @ %bb.0: @ %entry
+; CHECK-LE-NEXT:    vldrw.u32 q0, [r1]
+; CHECK-LE-NEXT:    vcmp.s32 gt, q0, zr
+; CHECK-LE-NEXT:    vpstt
+; CHECK-LE-NEXT:    vldrwt.u32 q0, [r2]
+; CHECK-LE-NEXT:    vstrbt.8 q0, [r0]
+; CHECK-LE-NEXT:    bx lr
+;
+; CHECK-BE-LABEL: foo_trunc_v4i16_v4i32:
+; CHECK-BE:       @ %bb.0: @ %entry
+; CHECK-BE-NEXT:    vldrw.u32 q0, [r1]
+; CHECK-BE-NEXT:    vcmp.s32 gt, q0, zr
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vldrwt.u32 q0, [r2]
+; CHECK-BE-NEXT:    vrev32.8 q0, q0
+; CHECK-BE-NEXT:    vpst
+; CHECK-BE-NEXT:    vstrbt.8 q0, [r0]
+; CHECK-BE-NEXT:    bx lr
 entry:
   %0 = load <4 x i32>, <4 x i32>* %mask, align 4
   %1 = icmp sgt <4 x i32> %0, zeroinitializer