[Mips] Always save RA when disabling frame pointer elimination

This ensures that frame-based unwinding will continue to work when
calling a noreturn function; there is not much use having the caller's
frame pointer saved if you don't also have the caller's program counter.

Patch by James Clarke.

Differential Revision: https://reviews.llvm.org/D68542

llvm-svn: 373907

6 files changed, 271 insertions, 158 deletions

diff --git a/llvm/test/CodeGen/Mips/cconv/vector.ll b/llvm/test/CodeGen/Mips/cconv/vector.ll
index 7881bf861c2..4a1f9cb6a6a 100644
--- a/llvm/test/CodeGen/Mips/cconv/vector.ll
+++ b/llvm/test/CodeGen/Mips/cconv/vector.ll
@@ -50,23 +50,25 @@ define <2 x i8> @i8_2(<2 x i8> %a, <2 x i8> %b) {
 ;
 ; MIPS32R5EB-LABEL: i8_2:
 ; MIPS32R5EB:       # %bb.0:
-; MIPS32R5EB-NEXT:    addiu $sp, $sp, -48
-; MIPS32R5EB-NEXT:    .cfi_def_cfa_offset 48
-; MIPS32R5EB-NEXT:    sw $fp, 44($sp) # 4-byte Folded Spill
-; MIPS32R5EB-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EB-NEXT:    addiu $sp, $sp, -64
+; MIPS32R5EB-NEXT:    .cfi_def_cfa_offset 64
+; MIPS32R5EB-NEXT:    sw $ra, 60($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    sw $fp, 56($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EB-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EB-NEXT:    move $fp, $sp
 ; MIPS32R5EB-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EB-NEXT:    addiu $1, $zero, -16
 ; MIPS32R5EB-NEXT:    and $sp, $sp, $1
-; MIPS32R5EB-NEXT:    sw $5, 36($sp)
-; MIPS32R5EB-NEXT:    sw $4, 40($sp)
-; MIPS32R5EB-NEXT:    lbu $1, 37($sp)
+; MIPS32R5EB-NEXT:    sw $5, 48($sp)
+; MIPS32R5EB-NEXT:    sw $4, 52($sp)
+; MIPS32R5EB-NEXT:    lbu $1, 49($sp)
 ; MIPS32R5EB-NEXT:    sw $1, 28($sp)
-; MIPS32R5EB-NEXT:    lbu $1, 36($sp)
+; MIPS32R5EB-NEXT:    lbu $1, 48($sp)
 ; MIPS32R5EB-NEXT:    sw $1, 20($sp)
-; MIPS32R5EB-NEXT:    lbu $1, 41($sp)
+; MIPS32R5EB-NEXT:    lbu $1, 53($sp)
 ; MIPS32R5EB-NEXT:    sw $1, 12($sp)
-; MIPS32R5EB-NEXT:    lbu $1, 40($sp)
+; MIPS32R5EB-NEXT:    lbu $1, 52($sp)
 ; MIPS32R5EB-NEXT:    sw $1, 4($sp)
 ; MIPS32R5EB-NEXT:    ld.d $w0, 16($sp)
 ; MIPS32R5EB-NEXT:    ld.d $w1, 0($sp)
@@ -74,12 +76,13 @@ define <2 x i8> @i8_2(<2 x i8> %a, <2 x i8> %b) {
 ; MIPS32R5EB-NEXT:    shf.w $w0, $w0, 177
 ; MIPS32R5EB-NEXT:    copy_s.w $1, $w0[1]
 ; MIPS32R5EB-NEXT:    copy_s.w $2, $w0[3]
-; MIPS32R5EB-NEXT:    sb $2, 33($sp)
-; MIPS32R5EB-NEXT:    sb $1, 32($sp)
-; MIPS32R5EB-NEXT:    lhu $2, 32($sp)
+; MIPS32R5EB-NEXT:    sb $2, 45($sp)
+; MIPS32R5EB-NEXT:    sb $1, 44($sp)
+; MIPS32R5EB-NEXT:    lhu $2, 44($sp)
 ; MIPS32R5EB-NEXT:    move $sp, $fp
-; MIPS32R5EB-NEXT:    lw $fp, 44($sp) # 4-byte Folded Reload
-; MIPS32R5EB-NEXT:    addiu $sp, $sp, 48
+; MIPS32R5EB-NEXT:    lw $fp, 56($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    lw $ra, 60($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    addiu $sp, $sp, 64
 ; MIPS32R5EB-NEXT:    jr $ra
 ; MIPS32R5EB-NEXT:    nop
 ;
@@ -151,35 +154,38 @@ define <2 x i8> @i8_2(<2 x i8> %a, <2 x i8> %b) {
 ;
 ; MIPS32R5EL-LABEL: i8_2:
 ; MIPS32R5EL:       # %bb.0:
-; MIPS32R5EL-NEXT:    addiu $sp, $sp, -48
-; MIPS32R5EL-NEXT:    .cfi_def_cfa_offset 48
-; MIPS32R5EL-NEXT:    sw $fp, 44($sp) # 4-byte Folded Spill
-; MIPS32R5EL-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EL-NEXT:    addiu $sp, $sp, -64
+; MIPS32R5EL-NEXT:    .cfi_def_cfa_offset 64
+; MIPS32R5EL-NEXT:    sw $ra, 60($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    sw $fp, 56($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EL-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EL-NEXT:    move $fp, $sp
 ; MIPS32R5EL-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EL-NEXT:    addiu $1, $zero, -16
 ; MIPS32R5EL-NEXT:    and $sp, $sp, $1
-; MIPS32R5EL-NEXT:    sw $5, 36($sp)
-; MIPS32R5EL-NEXT:    sw $4, 40($sp)
-; MIPS32R5EL-NEXT:    lbu $1, 37($sp)
+; MIPS32R5EL-NEXT:    sw $5, 48($sp)
+; MIPS32R5EL-NEXT:    sw $4, 52($sp)
+; MIPS32R5EL-NEXT:    lbu $1, 49($sp)
 ; MIPS32R5EL-NEXT:    sw $1, 24($sp)
-; MIPS32R5EL-NEXT:    lbu $1, 36($sp)
+; MIPS32R5EL-NEXT:    lbu $1, 48($sp)
 ; MIPS32R5EL-NEXT:    sw $1, 16($sp)
-; MIPS32R5EL-NEXT:    lbu $1, 41($sp)
+; MIPS32R5EL-NEXT:    lbu $1, 53($sp)
 ; MIPS32R5EL-NEXT:    sw $1, 8($sp)
-; MIPS32R5EL-NEXT:    lbu $1, 40($sp)
+; MIPS32R5EL-NEXT:    lbu $1, 52($sp)
 ; MIPS32R5EL-NEXT:    sw $1, 0($sp)
 ; MIPS32R5EL-NEXT:    ld.d $w0, 16($sp)
 ; MIPS32R5EL-NEXT:    ld.d $w1, 0($sp)
 ; MIPS32R5EL-NEXT:    addv.d $w0, $w1, $w0
 ; MIPS32R5EL-NEXT:    copy_s.w $1, $w0[0]
 ; MIPS32R5EL-NEXT:    copy_s.w $2, $w0[2]
-; MIPS32R5EL-NEXT:    sb $2, 33($sp)
-; MIPS32R5EL-NEXT:    sb $1, 32($sp)
-; MIPS32R5EL-NEXT:    lhu $2, 32($sp)
+; MIPS32R5EL-NEXT:    sb $2, 45($sp)
+; MIPS32R5EL-NEXT:    sb $1, 44($sp)
+; MIPS32R5EL-NEXT:    lhu $2, 44($sp)
 ; MIPS32R5EL-NEXT:    move $sp, $fp
-; MIPS32R5EL-NEXT:    lw $fp, 44($sp) # 4-byte Folded Reload
-; MIPS32R5EL-NEXT:    addiu $sp, $sp, 48
+; MIPS32R5EL-NEXT:    lw $fp, 56($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    lw $ra, 60($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    addiu $sp, $sp, 64
 ; MIPS32R5EL-NEXT:    jr $ra
 ; MIPS32R5EL-NEXT:    nop
 ;
@@ -312,36 +318,38 @@ define <2 x i8> @i8x2_7(<2 x i8> %a, <2 x i8> %b, <2 x i8> %c, <2 x i8> %d, <2 x
 ; MIPS32R5EB:       # %bb.0: # %entry
 ; MIPS32R5EB-NEXT:    addiu $sp, $sp, -144
 ; MIPS32R5EB-NEXT:    .cfi_def_cfa_offset 144
-; MIPS32R5EB-NEXT:    sw $fp, 140($sp) # 4-byte Folded Spill
-; MIPS32R5EB-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EB-NEXT:    sw $ra, 140($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    sw $fp, 136($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EB-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EB-NEXT:    move $fp, $sp
 ; MIPS32R5EB-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EB-NEXT:    addiu $1, $zero, -16
 ; MIPS32R5EB-NEXT:    and $sp, $sp, $1
-; MIPS32R5EB-NEXT:    sw $5, 132($sp)
-; MIPS32R5EB-NEXT:    sw $4, 136($sp)
-; MIPS32R5EB-NEXT:    lbu $1, 133($sp)
+; MIPS32R5EB-NEXT:    sw $5, 128($sp)
+; MIPS32R5EB-NEXT:    sw $4, 132($sp)
+; MIPS32R5EB-NEXT:    lbu $1, 129($sp)
 ; MIPS32R5EB-NEXT:    sw $1, 76($sp)
-; MIPS32R5EB-NEXT:    lbu $1, 132($sp)
+; MIPS32R5EB-NEXT:    lbu $1, 128($sp)
 ; MIPS32R5EB-NEXT:    sw $1, 68($sp)
-; MIPS32R5EB-NEXT:    lbu $1, 137($sp)
+; MIPS32R5EB-NEXT:    lbu $1, 133($sp)
 ; MIPS32R5EB-NEXT:    sw $1, 60($sp)
-; MIPS32R5EB-NEXT:    lbu $1, 136($sp)
+; MIPS32R5EB-NEXT:    lbu $1, 132($sp)
 ; MIPS32R5EB-NEXT:    sw $1, 52($sp)
 ; MIPS32R5EB-NEXT:    ld.d $w0, 64($sp)
 ; MIPS32R5EB-NEXT:    ld.d $w1, 48($sp)
 ; MIPS32R5EB-NEXT:    addv.d $w0, $w1, $w0
-; MIPS32R5EB-NEXT:    sw $6, 128($sp)
-; MIPS32R5EB-NEXT:    lbu $1, 129($sp)
+; MIPS32R5EB-NEXT:    sw $6, 124($sp)
+; MIPS32R5EB-NEXT:    lbu $1, 125($sp)
 ; MIPS32R5EB-NEXT:    sw $1, 92($sp)
-; MIPS32R5EB-NEXT:    lbu $1, 128($sp)
+; MIPS32R5EB-NEXT:    lbu $1, 124($sp)
 ; MIPS32R5EB-NEXT:    sw $1, 84($sp)
 ; MIPS32R5EB-NEXT:    ld.d $w1, 80($sp)
 ; MIPS32R5EB-NEXT:    addv.d $w0, $w0, $w1
-; MIPS32R5EB-NEXT:    sw $7, 124($sp)
-; MIPS32R5EB-NEXT:    lbu $1, 125($sp)
+; MIPS32R5EB-NEXT:    sw $7, 120($sp)
+; MIPS32R5EB-NEXT:    lbu $1, 121($sp)
 ; MIPS32R5EB-NEXT:    sw $1, 108($sp)
-; MIPS32R5EB-NEXT:    lbu $1, 124($sp)
+; MIPS32R5EB-NEXT:    lbu $1, 120($sp)
 ; MIPS32R5EB-NEXT:    sw $1, 100($sp)
 ; MIPS32R5EB-NEXT:    ld.d $w1, 96($sp)
 ; MIPS32R5EB-NEXT:    addv.d $w0, $w0, $w1
@@ -366,11 +374,12 @@ define <2 x i8> @i8x2_7(<2 x i8> %a, <2 x i8> %b, <2 x i8> %c, <2 x i8> %d, <2 x
 ; MIPS32R5EB-NEXT:    shf.w $w0, $w0, 177
 ; MIPS32R5EB-NEXT:    copy_s.w $1, $w0[1]
 ; MIPS32R5EB-NEXT:    copy_s.w $2, $w0[3]
-; MIPS32R5EB-NEXT:    sb $2, 121($sp)
-; MIPS32R5EB-NEXT:    sb $1, 120($sp)
-; MIPS32R5EB-NEXT:    lhu $2, 120($sp)
+; MIPS32R5EB-NEXT:    sb $2, 117($sp)
+; MIPS32R5EB-NEXT:    sb $1, 116($sp)
+; MIPS32R5EB-NEXT:    lhu $2, 116($sp)
 ; MIPS32R5EB-NEXT:    move $sp, $fp
-; MIPS32R5EB-NEXT:    lw $fp, 140($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    lw $fp, 136($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    lw $ra, 140($sp) # 4-byte Folded Reload
 ; MIPS32R5EB-NEXT:    addiu $sp, $sp, 144
 ; MIPS32R5EB-NEXT:    jr $ra
 ; MIPS32R5EB-NEXT:    nop
@@ -550,36 +559,38 @@ define <2 x i8> @i8x2_7(<2 x i8> %a, <2 x i8> %b, <2 x i8> %c, <2 x i8> %d, <2 x
 ; MIPS32R5EL:       # %bb.0: # %entry
 ; MIPS32R5EL-NEXT:    addiu $sp, $sp, -144
 ; MIPS32R5EL-NEXT:    .cfi_def_cfa_offset 144
-; MIPS32R5EL-NEXT:    sw $fp, 140($sp) # 4-byte Folded Spill
-; MIPS32R5EL-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EL-NEXT:    sw $ra, 140($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    sw $fp, 136($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EL-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EL-NEXT:    move $fp, $sp
 ; MIPS32R5EL-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EL-NEXT:    addiu $1, $zero, -16
 ; MIPS32R5EL-NEXT:    and $sp, $sp, $1
-; MIPS32R5EL-NEXT:    sw $5, 132($sp)
-; MIPS32R5EL-NEXT:    sw $4, 136($sp)
-; MIPS32R5EL-NEXT:    lbu $1, 133($sp)
+; MIPS32R5EL-NEXT:    sw $5, 128($sp)
+; MIPS32R5EL-NEXT:    sw $4, 132($sp)
+; MIPS32R5EL-NEXT:    lbu $1, 129($sp)
 ; MIPS32R5EL-NEXT:    sw $1, 72($sp)
-; MIPS32R5EL-NEXT:    lbu $1, 132($sp)
+; MIPS32R5EL-NEXT:    lbu $1, 128($sp)
 ; MIPS32R5EL-NEXT:    sw $1, 64($sp)
-; MIPS32R5EL-NEXT:    lbu $1, 137($sp)
+; MIPS32R5EL-NEXT:    lbu $1, 133($sp)
 ; MIPS32R5EL-NEXT:    sw $1, 56($sp)
-; MIPS32R5EL-NEXT:    lbu $1, 136($sp)
+; MIPS32R5EL-NEXT:    lbu $1, 132($sp)
 ; MIPS32R5EL-NEXT:    sw $1, 48($sp)
 ; MIPS32R5EL-NEXT:    ld.d $w0, 64($sp)
 ; MIPS32R5EL-NEXT:    ld.d $w1, 48($sp)
 ; MIPS32R5EL-NEXT:    addv.d $w0, $w1, $w0
-; MIPS32R5EL-NEXT:    sw $6, 128($sp)
-; MIPS32R5EL-NEXT:    lbu $1, 129($sp)
+; MIPS32R5EL-NEXT:    sw $6, 124($sp)
+; MIPS32R5EL-NEXT:    lbu $1, 125($sp)
 ; MIPS32R5EL-NEXT:    sw $1, 88($sp)
-; MIPS32R5EL-NEXT:    lbu $1, 128($sp)
+; MIPS32R5EL-NEXT:    lbu $1, 124($sp)
 ; MIPS32R5EL-NEXT:    sw $1, 80($sp)
 ; MIPS32R5EL-NEXT:    ld.d $w1, 80($sp)
 ; MIPS32R5EL-NEXT:    addv.d $w0, $w0, $w1
-; MIPS32R5EL-NEXT:    sw $7, 124($sp)
-; MIPS32R5EL-NEXT:    lbu $1, 125($sp)
+; MIPS32R5EL-NEXT:    sw $7, 120($sp)
+; MIPS32R5EL-NEXT:    lbu $1, 121($sp)
 ; MIPS32R5EL-NEXT:    sw $1, 104($sp)
-; MIPS32R5EL-NEXT:    lbu $1, 124($sp)
+; MIPS32R5EL-NEXT:    lbu $1, 120($sp)
 ; MIPS32R5EL-NEXT:    sw $1, 96($sp)
 ; MIPS32R5EL-NEXT:    ld.d $w1, 96($sp)
 ; MIPS32R5EL-NEXT:    addv.d $w0, $w0, $w1
@@ -603,11 +614,12 @@ define <2 x i8> @i8x2_7(<2 x i8> %a, <2 x i8> %b, <2 x i8> %c, <2 x i8> %d, <2 x
 ; MIPS32R5EL-NEXT:    addv.d $w0, $w0, $w1
 ; MIPS32R5EL-NEXT:    copy_s.w $1, $w0[0]
 ; MIPS32R5EL-NEXT:    copy_s.w $2, $w0[2]
-; MIPS32R5EL-NEXT:    sb $2, 121($sp)
-; MIPS32R5EL-NEXT:    sb $1, 120($sp)
-; MIPS32R5EL-NEXT:    lhu $2, 120($sp)
+; MIPS32R5EL-NEXT:    sb $2, 117($sp)
+; MIPS32R5EL-NEXT:    sb $1, 116($sp)
+; MIPS32R5EL-NEXT:    lhu $2, 116($sp)
 ; MIPS32R5EL-NEXT:    move $sp, $fp
-; MIPS32R5EL-NEXT:    lw $fp, 140($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    lw $fp, 136($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    lw $ra, 140($sp) # 4-byte Folded Reload
 ; MIPS32R5EL-NEXT:    addiu $sp, $sp, 144
 ; MIPS32R5EL-NEXT:    jr $ra
 ; MIPS32R5EL-NEXT:    nop
@@ -952,8 +964,10 @@ define <8 x i8> @i8_8(<8 x i8> %a, <8 x i8> %b) {
 ; MIPS32R5EB:       # %bb.0:
 ; MIPS32R5EB-NEXT:    addiu $sp, $sp, -48
 ; MIPS32R5EB-NEXT:    .cfi_def_cfa_offset 48
-; MIPS32R5EB-NEXT:    sw $fp, 44($sp) # 4-byte Folded Spill
-; MIPS32R5EB-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EB-NEXT:    sw $ra, 44($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    sw $fp, 40($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EB-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EB-NEXT:    move $fp, $sp
 ; MIPS32R5EB-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EB-NEXT:    addiu $1, $zero, -16
@@ -1019,7 +1033,8 @@ define <8 x i8> @i8_8(<8 x i8> %a, <8 x i8> %b) {
 ; MIPS32R5EB-NEXT:    copy_s.w $2, $w0[1]
 ; MIPS32R5EB-NEXT:    copy_s.w $3, $w0[3]
 ; MIPS32R5EB-NEXT:    move $sp, $fp
-; MIPS32R5EB-NEXT:    lw $fp, 44($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    lw $fp, 40($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    lw $ra, 44($sp) # 4-byte Folded Reload
 ; MIPS32R5EB-NEXT:    addiu $sp, $sp, 48
 ; MIPS32R5EB-NEXT:    jr $ra
 ; MIPS32R5EB-NEXT:    nop
@@ -1088,8 +1103,10 @@ define <8 x i8> @i8_8(<8 x i8> %a, <8 x i8> %b) {
 ; MIPS32R5EL:       # %bb.0:
 ; MIPS32R5EL-NEXT:    addiu $sp, $sp, -48
 ; MIPS32R5EL-NEXT:    .cfi_def_cfa_offset 48
-; MIPS32R5EL-NEXT:    sw $fp, 44($sp) # 4-byte Folded Spill
-; MIPS32R5EL-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EL-NEXT:    sw $ra, 44($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    sw $fp, 40($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EL-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EL-NEXT:    move $fp, $sp
 ; MIPS32R5EL-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EL-NEXT:    addiu $1, $zero, -16
@@ -1155,7 +1172,8 @@ define <8 x i8> @i8_8(<8 x i8> %a, <8 x i8> %b) {
 ; MIPS32R5EL-NEXT:    copy_s.w $2, $w0[0]
 ; MIPS32R5EL-NEXT:    copy_s.w $3, $w0[2]
 ; MIPS32R5EL-NEXT:    move $sp, $fp
-; MIPS32R5EL-NEXT:    lw $fp, 44($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    lw $fp, 40($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    lw $ra, 44($sp) # 4-byte Folded Reload
 ; MIPS32R5EL-NEXT:    addiu $sp, $sp, 48
 ; MIPS32R5EL-NEXT:    jr $ra
 ; MIPS32R5EL-NEXT:    nop
@@ -1471,23 +1489,25 @@ define <2 x i16> @i16_2(<2 x i16> %a, <2 x i16> %b) {
 ;
 ; MIPS32R5EB-LABEL: i16_2:
 ; MIPS32R5EB:       # %bb.0:
-; MIPS32R5EB-NEXT:    addiu $sp, $sp, -48
-; MIPS32R5EB-NEXT:    .cfi_def_cfa_offset 48
-; MIPS32R5EB-NEXT:    sw $fp, 44($sp) # 4-byte Folded Spill
-; MIPS32R5EB-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EB-NEXT:    addiu $sp, $sp, -64
+; MIPS32R5EB-NEXT:    .cfi_def_cfa_offset 64
+; MIPS32R5EB-NEXT:    sw $ra, 60($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    sw $fp, 56($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EB-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EB-NEXT:    move $fp, $sp
 ; MIPS32R5EB-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EB-NEXT:    addiu $1, $zero, -16
 ; MIPS32R5EB-NEXT:    and $sp, $sp, $1
-; MIPS32R5EB-NEXT:    sw $5, 36($sp)
-; MIPS32R5EB-NEXT:    sw $4, 40($sp)
-; MIPS32R5EB-NEXT:    lhu $1, 38($sp)
+; MIPS32R5EB-NEXT:    sw $5, 48($sp)
+; MIPS32R5EB-NEXT:    sw $4, 52($sp)
+; MIPS32R5EB-NEXT:    lhu $1, 50($sp)
 ; MIPS32R5EB-NEXT:    sw $1, 28($sp)
-; MIPS32R5EB-NEXT:    lhu $1, 36($sp)
+; MIPS32R5EB-NEXT:    lhu $1, 48($sp)
 ; MIPS32R5EB-NEXT:    sw $1, 20($sp)
-; MIPS32R5EB-NEXT:    lhu $1, 42($sp)
+; MIPS32R5EB-NEXT:    lhu $1, 54($sp)
 ; MIPS32R5EB-NEXT:    sw $1, 12($sp)
-; MIPS32R5EB-NEXT:    lhu $1, 40($sp)
+; MIPS32R5EB-NEXT:    lhu $1, 52($sp)
 ; MIPS32R5EB-NEXT:    sw $1, 4($sp)
 ; MIPS32R5EB-NEXT:    ld.d $w0, 16($sp)
 ; MIPS32R5EB-NEXT:    ld.d $w1, 0($sp)
@@ -1495,12 +1515,13 @@ define <2 x i16> @i16_2(<2 x i16> %a, <2 x i16> %b) {
 ; MIPS32R5EB-NEXT:    shf.w $w0, $w0, 177
 ; MIPS32R5EB-NEXT:    copy_s.w $1, $w0[1]
 ; MIPS32R5EB-NEXT:    copy_s.w $2, $w0[3]
-; MIPS32R5EB-NEXT:    sh $2, 34($sp)
-; MIPS32R5EB-NEXT:    sh $1, 32($sp)
-; MIPS32R5EB-NEXT:    lw $2, 32($sp)
+; MIPS32R5EB-NEXT:    sh $2, 46($sp)
+; MIPS32R5EB-NEXT:    sh $1, 44($sp)
+; MIPS32R5EB-NEXT:    lw $2, 44($sp)
 ; MIPS32R5EB-NEXT:    move $sp, $fp
-; MIPS32R5EB-NEXT:    lw $fp, 44($sp) # 4-byte Folded Reload
-; MIPS32R5EB-NEXT:    addiu $sp, $sp, 48
+; MIPS32R5EB-NEXT:    lw $fp, 56($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    lw $ra, 60($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    addiu $sp, $sp, 64
 ; MIPS32R5EB-NEXT:    jr $ra
 ; MIPS32R5EB-NEXT:    nop
 ;
@@ -1532,35 +1553,38 @@ define <2 x i16> @i16_2(<2 x i16> %a, <2 x i16> %b) {
 ;
 ; MIPS32R5EL-LABEL: i16_2:
 ; MIPS32R5EL:       # %bb.0:
-; MIPS32R5EL-NEXT:    addiu $sp, $sp, -48
-; MIPS32R5EL-NEXT:    .cfi_def_cfa_offset 48
-; MIPS32R5EL-NEXT:    sw $fp, 44($sp) # 4-byte Folded Spill
-; MIPS32R5EL-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EL-NEXT:    addiu $sp, $sp, -64
+; MIPS32R5EL-NEXT:    .cfi_def_cfa_offset 64
+; MIPS32R5EL-NEXT:    sw $ra, 60($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    sw $fp, 56($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EL-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EL-NEXT:    move $fp, $sp
 ; MIPS32R5EL-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EL-NEXT:    addiu $1, $zero, -16
 ; MIPS32R5EL-NEXT:    and $sp, $sp, $1
-; MIPS32R5EL-NEXT:    sw $5, 36($sp)
-; MIPS32R5EL-NEXT:    sw $4, 40($sp)
-; MIPS32R5EL-NEXT:    lhu $1, 38($sp)
+; MIPS32R5EL-NEXT:    sw $5, 48($sp)
+; MIPS32R5EL-NEXT:    sw $4, 52($sp)
+; MIPS32R5EL-NEXT:    lhu $1, 50($sp)
 ; MIPS32R5EL-NEXT:    sw $1, 24($sp)
-; MIPS32R5EL-NEXT:    lhu $1, 36($sp)
+; MIPS32R5EL-NEXT:    lhu $1, 48($sp)
 ; MIPS32R5EL-NEXT:    sw $1, 16($sp)
-; MIPS32R5EL-NEXT:    lhu $1, 42($sp)
+; MIPS32R5EL-NEXT:    lhu $1, 54($sp)
 ; MIPS32R5EL-NEXT:    sw $1, 8($sp)
-; MIPS32R5EL-NEXT:    lhu $1, 40($sp)
+; MIPS32R5EL-NEXT:    lhu $1, 52($sp)
 ; MIPS32R5EL-NEXT:    sw $1, 0($sp)
 ; MIPS32R5EL-NEXT:    ld.d $w0, 16($sp)
 ; MIPS32R5EL-NEXT:    ld.d $w1, 0($sp)
 ; MIPS32R5EL-NEXT:    addv.d $w0, $w1, $w0
 ; MIPS32R5EL-NEXT:    copy_s.w $1, $w0[0]
 ; MIPS32R5EL-NEXT:    copy_s.w $2, $w0[2]
-; MIPS32R5EL-NEXT:    sh $2, 34($sp)
-; MIPS32R5EL-NEXT:    sh $1, 32($sp)
-; MIPS32R5EL-NEXT:    lw $2, 32($sp)
+; MIPS32R5EL-NEXT:    sh $2, 46($sp)
+; MIPS32R5EL-NEXT:    sh $1, 44($sp)
+; MIPS32R5EL-NEXT:    lw $2, 44($sp)
 ; MIPS32R5EL-NEXT:    move $sp, $fp
-; MIPS32R5EL-NEXT:    lw $fp, 44($sp) # 4-byte Folded Reload
-; MIPS32R5EL-NEXT:    addiu $sp, $sp, 48
+; MIPS32R5EL-NEXT:    lw $fp, 56($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    lw $ra, 60($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    addiu $sp, $sp, 64
 ; MIPS32R5EL-NEXT:    jr $ra
 ; MIPS32R5EL-NEXT:    nop
   %1 = add <2 x i16> %a, %b
@@ -1622,8 +1646,10 @@ define <4 x i16> @i16_4(<4 x i16> %a, <4 x i16> %b) {
 ; MIPS32R5EB:       # %bb.0:
 ; MIPS32R5EB-NEXT:    addiu $sp, $sp, -48
 ; MIPS32R5EB-NEXT:    .cfi_def_cfa_offset 48
-; MIPS32R5EB-NEXT:    sw $fp, 44($sp) # 4-byte Folded Spill
-; MIPS32R5EB-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EB-NEXT:    sw $ra, 44($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    sw $fp, 40($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EB-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EB-NEXT:    move $fp, $sp
 ; MIPS32R5EB-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EB-NEXT:    addiu $1, $zero, -16
@@ -1665,7 +1691,8 @@ define <4 x i16> @i16_4(<4 x i16> %a, <4 x i16> %b) {
 ; MIPS32R5EB-NEXT:    copy_s.w $2, $w0[1]
 ; MIPS32R5EB-NEXT:    copy_s.w $3, $w0[3]
 ; MIPS32R5EB-NEXT:    move $sp, $fp
-; MIPS32R5EB-NEXT:    lw $fp, 44($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    lw $fp, 40($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    lw $ra, 44($sp) # 4-byte Folded Reload
 ; MIPS32R5EB-NEXT:    addiu $sp, $sp, 48
 ; MIPS32R5EB-NEXT:    jr $ra
 ; MIPS32R5EB-NEXT:    nop
@@ -1710,8 +1737,10 @@ define <4 x i16> @i16_4(<4 x i16> %a, <4 x i16> %b) {
 ; MIPS32R5EL:       # %bb.0:
 ; MIPS32R5EL-NEXT:    addiu $sp, $sp, -48
 ; MIPS32R5EL-NEXT:    .cfi_def_cfa_offset 48
-; MIPS32R5EL-NEXT:    sw $fp, 44($sp) # 4-byte Folded Spill
-; MIPS32R5EL-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EL-NEXT:    sw $ra, 44($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    sw $fp, 40($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EL-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EL-NEXT:    move $fp, $sp
 ; MIPS32R5EL-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EL-NEXT:    addiu $1, $zero, -16
@@ -1753,7 +1782,8 @@ define <4 x i16> @i16_4(<4 x i16> %a, <4 x i16> %b) {
 ; MIPS32R5EL-NEXT:    copy_s.w $2, $w0[0]
 ; MIPS32R5EL-NEXT:    copy_s.w $3, $w0[2]
 ; MIPS32R5EL-NEXT:    move $sp, $fp
-; MIPS32R5EL-NEXT:    lw $fp, 44($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    lw $fp, 40($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    lw $ra, 44($sp) # 4-byte Folded Reload
 ; MIPS32R5EL-NEXT:    addiu $sp, $sp, 48
 ; MIPS32R5EL-NEXT:    jr $ra
 ; MIPS32R5EL-NEXT:    nop
@@ -1962,8 +1992,10 @@ define <2 x i32> @i32_2(<2 x i32> %a, <2 x i32> %b) {
 ; MIPS32R5EB:       # %bb.0:
 ; MIPS32R5EB-NEXT:    addiu $sp, $sp, -48
 ; MIPS32R5EB-NEXT:    .cfi_def_cfa_offset 48
-; MIPS32R5EB-NEXT:    sw $fp, 44($sp) # 4-byte Folded Spill
-; MIPS32R5EB-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EB-NEXT:    sw $ra, 44($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    sw $fp, 40($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EB-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EB-NEXT:    move $fp, $sp
 ; MIPS32R5EB-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EB-NEXT:    addiu $1, $zero, -16
@@ -1979,7 +2011,8 @@ define <2 x i32> @i32_2(<2 x i32> %a, <2 x i32> %b) {
 ; MIPS32R5EB-NEXT:    copy_s.w $2, $w0[1]
 ; MIPS32R5EB-NEXT:    copy_s.w $3, $w0[3]
 ; MIPS32R5EB-NEXT:    move $sp, $fp
-; MIPS32R5EB-NEXT:    lw $fp, 44($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    lw $fp, 40($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    lw $ra, 44($sp) # 4-byte Folded Reload
 ; MIPS32R5EB-NEXT:    addiu $sp, $sp, 48
 ; MIPS32R5EB-NEXT:    jr $ra
 ; MIPS32R5EB-NEXT:    nop
@@ -2010,8 +2043,10 @@ define <2 x i32> @i32_2(<2 x i32> %a, <2 x i32> %b) {
 ; MIPS32R5EL:       # %bb.0:
 ; MIPS32R5EL-NEXT:    addiu $sp, $sp, -48
 ; MIPS32R5EL-NEXT:    .cfi_def_cfa_offset 48
-; MIPS32R5EL-NEXT:    sw $fp, 44($sp) # 4-byte Folded Spill
-; MIPS32R5EL-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EL-NEXT:    sw $ra, 44($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    sw $fp, 40($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EL-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EL-NEXT:    move $fp, $sp
 ; MIPS32R5EL-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EL-NEXT:    addiu $1, $zero, -16
@@ -2026,7 +2061,8 @@ define <2 x i32> @i32_2(<2 x i32> %a, <2 x i32> %b) {
 ; MIPS32R5EL-NEXT:    copy_s.w $2, $w0[0]
 ; MIPS32R5EL-NEXT:    copy_s.w $3, $w0[2]
 ; MIPS32R5EL-NEXT:    move $sp, $fp
-; MIPS32R5EL-NEXT:    lw $fp, 44($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    lw $fp, 40($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    lw $ra, 44($sp) # 4-byte Folded Reload
 ; MIPS32R5EL-NEXT:    addiu $sp, $sp, 48
 ; MIPS32R5EL-NEXT:    jr $ra
 ; MIPS32R5EL-NEXT:    nop
@@ -2312,8 +2348,10 @@ define void @float_2(<2 x float> %a, <2 x float> %b) {
 ; MIPS32R5:       # %bb.0:
 ; MIPS32R5-NEXT:    addiu $sp, $sp, -48
 ; MIPS32R5-NEXT:    .cfi_def_cfa_offset 48
-; MIPS32R5-NEXT:    sw $fp, 44($sp) # 4-byte Folded Spill
-; MIPS32R5-NEXT:    .cfi_offset 30, -4
+; MIPS32R5-NEXT:    sw $ra, 44($sp) # 4-byte Folded Spill
+; MIPS32R5-NEXT:    sw $fp, 40($sp) # 4-byte Folded Spill
+; MIPS32R5-NEXT:    .cfi_offset 31, -4
+; MIPS32R5-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5-NEXT:    move $fp, $sp
 ; MIPS32R5-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5-NEXT:    addiu $1, $zero, -16
@@ -2331,7 +2369,8 @@ define void @float_2(<2 x float> %a, <2 x float> %b) {
 ; MIPS32R5-NEXT:    swc1 $f1, 4($2)
 ; MIPS32R5-NEXT:    swc1 $f0, %lo(float_res_v2f32)($1)
 ; MIPS32R5-NEXT:    move $sp, $fp
-; MIPS32R5-NEXT:    lw $fp, 44($sp) # 4-byte Folded Reload
+; MIPS32R5-NEXT:    lw $fp, 40($sp) # 4-byte Folded Reload
+; MIPS32R5-NEXT:    lw $ra, 44($sp) # 4-byte Folded Reload
 ; MIPS32R5-NEXT:    addiu $sp, $sp, 48
 ; MIPS32R5-NEXT:    jr $ra
 ; MIPS32R5-NEXT:    nop
@@ -2794,8 +2833,10 @@ define <8 x i8> @ret_8_i8() {
 ; MIPS32R5EB:       # %bb.0:
 ; MIPS32R5EB-NEXT:    addiu $sp, $sp, -32
 ; MIPS32R5EB-NEXT:    .cfi_def_cfa_offset 32
-; MIPS32R5EB-NEXT:    sw $fp, 28($sp) # 4-byte Folded Spill
-; MIPS32R5EB-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EB-NEXT:    sw $ra, 28($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    sw $fp, 24($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EB-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EB-NEXT:    move $fp, $sp
 ; MIPS32R5EB-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EB-NEXT:    addiu $1, $zero, -16
@@ -2810,7 +2851,8 @@ define <8 x i8> @ret_8_i8() {
 ; MIPS32R5EB-NEXT:    copy_s.w $2, $w0[1]
 ; MIPS32R5EB-NEXT:    copy_s.w $3, $w0[3]
 ; MIPS32R5EB-NEXT:    move $sp, $fp
-; MIPS32R5EB-NEXT:    lw $fp, 28($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    lw $fp, 24($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    lw $ra, 28($sp) # 4-byte Folded Reload
 ; MIPS32R5EB-NEXT:    addiu $sp, $sp, 32
 ; MIPS32R5EB-NEXT:    jr $ra
 ; MIPS32R5EB-NEXT:    nop
@@ -2829,8 +2871,10 @@ define <8 x i8> @ret_8_i8() {
 ; MIPS32R5EL:       # %bb.0:
 ; MIPS32R5EL-NEXT:    addiu $sp, $sp, -32
 ; MIPS32R5EL-NEXT:    .cfi_def_cfa_offset 32
-; MIPS32R5EL-NEXT:    sw $fp, 28($sp) # 4-byte Folded Spill
-; MIPS32R5EL-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EL-NEXT:    sw $ra, 28($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    sw $fp, 24($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EL-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EL-NEXT:    move $fp, $sp
 ; MIPS32R5EL-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EL-NEXT:    addiu $1, $zero, -16
@@ -2845,7 +2889,8 @@ define <8 x i8> @ret_8_i8() {
 ; MIPS32R5EL-NEXT:    copy_s.w $2, $w0[0]
 ; MIPS32R5EL-NEXT:    copy_s.w $3, $w0[2]
 ; MIPS32R5EL-NEXT:    move $sp, $fp
-; MIPS32R5EL-NEXT:    lw $fp, 28($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    lw $fp, 24($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    lw $ra, 28($sp) # 4-byte Folded Reload
 ; MIPS32R5EL-NEXT:    addiu $sp, $sp, 32
 ; MIPS32R5EL-NEXT:    jr $ra
 ; MIPS32R5EL-NEXT:    nop
@@ -2965,8 +3010,10 @@ define <4 x i16> @ret_4_i16() {
 ; MIPS32R5EB:       # %bb.0:
 ; MIPS32R5EB-NEXT:    addiu $sp, $sp, -32
 ; MIPS32R5EB-NEXT:    .cfi_def_cfa_offset 32
-; MIPS32R5EB-NEXT:    sw $fp, 28($sp) # 4-byte Folded Spill
-; MIPS32R5EB-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EB-NEXT:    sw $ra, 28($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    sw $fp, 24($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EB-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EB-NEXT:    move $fp, $sp
 ; MIPS32R5EB-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EB-NEXT:    addiu $1, $zero, -16
@@ -2981,7 +3028,8 @@ define <4 x i16> @ret_4_i16() {
 ; MIPS32R5EB-NEXT:    copy_s.w $2, $w0[1]
 ; MIPS32R5EB-NEXT:    copy_s.w $3, $w0[3]
 ; MIPS32R5EB-NEXT:    move $sp, $fp
-; MIPS32R5EB-NEXT:    lw $fp, 28($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    lw $fp, 24($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    lw $ra, 28($sp) # 4-byte Folded Reload
 ; MIPS32R5EB-NEXT:    addiu $sp, $sp, 32
 ; MIPS32R5EB-NEXT:    jr $ra
 ; MIPS32R5EB-NEXT:    nop
@@ -3000,8 +3048,10 @@ define <4 x i16> @ret_4_i16() {
 ; MIPS32R5EL:       # %bb.0:
 ; MIPS32R5EL-NEXT:    addiu $sp, $sp, -32
 ; MIPS32R5EL-NEXT:    .cfi_def_cfa_offset 32
-; MIPS32R5EL-NEXT:    sw $fp, 28($sp) # 4-byte Folded Spill
-; MIPS32R5EL-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EL-NEXT:    sw $ra, 28($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    sw $fp, 24($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EL-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EL-NEXT:    move $fp, $sp
 ; MIPS32R5EL-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EL-NEXT:    addiu $1, $zero, -16
@@ -3016,7 +3066,8 @@ define <4 x i16> @ret_4_i16() {
 ; MIPS32R5EL-NEXT:    copy_s.w $2, $w0[0]
 ; MIPS32R5EL-NEXT:    copy_s.w $3, $w0[2]
 ; MIPS32R5EL-NEXT:    move $sp, $fp
-; MIPS32R5EL-NEXT:    lw $fp, 28($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    lw $fp, 24($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    lw $ra, 28($sp) # 4-byte Folded Reload
 ; MIPS32R5EL-NEXT:    addiu $sp, $sp, 32
 ; MIPS32R5EL-NEXT:    jr $ra
 ; MIPS32R5EL-NEXT:    nop
@@ -3098,8 +3149,10 @@ define <2 x i32> @ret_2_i32() {
 ; MIPS32R5EB:       # %bb.0:
 ; MIPS32R5EB-NEXT:    addiu $sp, $sp, -32
 ; MIPS32R5EB-NEXT:    .cfi_def_cfa_offset 32
-; MIPS32R5EB-NEXT:    sw $fp, 28($sp) # 4-byte Folded Spill
-; MIPS32R5EB-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EB-NEXT:    sw $ra, 28($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    sw $fp, 24($sp) # 4-byte Folded Spill
+; MIPS32R5EB-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EB-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EB-NEXT:    move $fp, $sp
 ; MIPS32R5EB-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EB-NEXT:    addiu $1, $zero, -16
@@ -3114,7 +3167,8 @@ define <2 x i32> @ret_2_i32() {
 ; MIPS32R5EB-NEXT:    copy_s.w $2, $w0[1]
 ; MIPS32R5EB-NEXT:    copy_s.w $3, $w0[3]
 ; MIPS32R5EB-NEXT:    move $sp, $fp
-; MIPS32R5EB-NEXT:    lw $fp, 28($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    lw $fp, 24($sp) # 4-byte Folded Reload
+; MIPS32R5EB-NEXT:    lw $ra, 28($sp) # 4-byte Folded Reload
 ; MIPS32R5EB-NEXT:    addiu $sp, $sp, 32
 ; MIPS32R5EB-NEXT:    jr $ra
 ; MIPS32R5EB-NEXT:    nop
@@ -3133,8 +3187,10 @@ define <2 x i32> @ret_2_i32() {
 ; MIPS32R5EL:       # %bb.0:
 ; MIPS32R5EL-NEXT:    addiu $sp, $sp, -32
 ; MIPS32R5EL-NEXT:    .cfi_def_cfa_offset 32
-; MIPS32R5EL-NEXT:    sw $fp, 28($sp) # 4-byte Folded Spill
-; MIPS32R5EL-NEXT:    .cfi_offset 30, -4
+; MIPS32R5EL-NEXT:    sw $ra, 28($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    sw $fp, 24($sp) # 4-byte Folded Spill
+; MIPS32R5EL-NEXT:    .cfi_offset 31, -4
+; MIPS32R5EL-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5EL-NEXT:    move $fp, $sp
 ; MIPS32R5EL-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5EL-NEXT:    addiu $1, $zero, -16
@@ -3149,7 +3205,8 @@ define <2 x i32> @ret_2_i32() {
 ; MIPS32R5EL-NEXT:    copy_s.w $2, $w0[0]
 ; MIPS32R5EL-NEXT:    copy_s.w $3, $w0[2]
 ; MIPS32R5EL-NEXT:    move $sp, $fp
-; MIPS32R5EL-NEXT:    lw $fp, 28($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    lw $fp, 24($sp) # 4-byte Folded Reload
+; MIPS32R5EL-NEXT:    lw $ra, 28($sp) # 4-byte Folded Reload
 ; MIPS32R5EL-NEXT:    addiu $sp, $sp, 32
 ; MIPS32R5EL-NEXT:    jr $ra
 ; MIPS32R5EL-NEXT:    nop
@@ -6073,8 +6130,10 @@ define float @mixed_i8(<2 x float> %a, i8 %b, <2 x float> %c) {
 ; MIPS32R5:       # %bb.0: # %entry
 ; MIPS32R5-NEXT:    addiu $sp, $sp, -64
 ; MIPS32R5-NEXT:    .cfi_def_cfa_offset 64
-; MIPS32R5-NEXT:    sw $fp, 60($sp) # 4-byte Folded Spill
-; MIPS32R5-NEXT:    .cfi_offset 30, -4
+; MIPS32R5-NEXT:    sw $ra, 60($sp) # 4-byte Folded Spill
+; MIPS32R5-NEXT:    sw $fp, 56($sp) # 4-byte Folded Spill
+; MIPS32R5-NEXT:    .cfi_offset 31, -4
+; MIPS32R5-NEXT:    .cfi_offset 30, -8
 ; MIPS32R5-NEXT:    move $fp, $sp
 ; MIPS32R5-NEXT:    .cfi_def_cfa_register 30
 ; MIPS32R5-NEXT:    addiu $1, $zero, -16
@@ -6098,7 +6157,8 @@ define float @mixed_i8(<2 x float> %a, i8 %b, <2 x float> %c) {
 ; MIPS32R5-NEXT:    splati.w $w1, $w0[1]
 ; MIPS32R5-NEXT:    add.s $f0, $f0, $f1
 ; MIPS32R5-NEXT:    move $sp, $fp
-; MIPS32R5-NEXT:    lw $fp, 60($sp) # 4-byte Folded Reload
+; MIPS32R5-NEXT:    lw $fp, 56($sp) # 4-byte Folded Reload
+; MIPS32R5-NEXT:    lw $ra, 60($sp) # 4-byte Folded Reload
 ; MIPS32R5-NEXT:    addiu $sp, $sp, 64
 ; MIPS32R5-NEXT:    jr $ra
 ; MIPS32R5-NEXT:    nop
diff --git a/llvm/test/CodeGen/Mips/dynamic-stack-realignment.ll b/llvm/test/CodeGen/Mips/dynamic-stack-realignment.ll
index 5054b9cd02f..50acd8ffb1e 100644
--- a/llvm/test/CodeGen/Mips/dynamic-stack-realignment.ll
+++ b/llvm/test/CodeGen/Mips/dynamic-stack-realignment.ll
@@ -163,8 +163,9 @@ entry:
   ; GP32-M:     addiu   $sp, $sp, -1024
   ; GP32-MMR2:  addiusp -1024
   ; GP32-MMR6:  addiu   $sp, $sp, -1024
-  ; GP32:       sw      $fp, 1020($sp)
-  ; GP32:       sw      $23, 1016($sp)
+  ; GP32:       sw      $ra, 1020($sp)
+  ; GP32:       sw      $fp, 1016($sp)
+  ; GP32:       sw      $23, 1012($sp)
   ;
   ; GP32:       move    $fp, $sp
   ; GP32:       addiu   $[[T0:[0-9]+|gp]], $zero, -512
@@ -177,8 +178,9 @@ entry:
 
   ; epilogue
   ; GP32:       move    $sp, $fp
-  ; GP32:       lw      $23, 1016($sp)
-  ; GP32:       lw      $fp, 1020($sp)
+  ; GP32:       lw      $23, 1012($sp)
+  ; GP32:       lw      $fp, 1016($sp)
+  ; GP32:       lw      $ra, 1020($sp)
   ; GP32-M:     addiu   $sp, $sp, 1024
   ; GP32-MMR2:  addiusp 1024
   ; GP32-MMR6:  addiu   $sp, $sp, 1024
@@ -201,8 +203,9 @@ entry:
   ; FIXME: We are currently over-allocating stack space.
   ; N32:        addiu   $sp, $sp, -1024
   ; N64:        daddiu  $sp, $sp, -1024
-  ; GP64:       sd      $fp, 1016($sp)
-  ; GP64:       sd      $23, 1008($sp)
+  ; GP64:       sd      $ra, 1016($sp)
+  ; GP64:       sd      $fp, 1008($sp)
+  ; GP64:       sd      $23, 1000($sp)
   ;
   ; GP64:       move    $fp, $sp
   ; GP64:       addiu   $[[T0:[0-9]+|gp]], $zero, -512
@@ -215,8 +218,9 @@ entry:
 
   ; epilogue
   ; GP64:       move    $sp, $fp
-  ; GP64:       ld      $23, 1008($sp)
-  ; GP64:       ld      $fp, 1016($sp)
+  ; GP64:       ld      $23, 1000($sp)
+  ; GP64:       ld      $fp, 1008($sp)
+  ; GP64:       ld      $ra, 1016($sp)
   ; N32:        addiu   $sp, $sp, 1024
   ; N64:        daddiu  $sp, $sp, 1024
 
diff --git a/llvm/test/CodeGen/Mips/frame-address.ll b/llvm/test/CodeGen/Mips/frame-address.ll
index 0ab7da30e78..f7ceb575c65 100644
--- a/llvm/test/CodeGen/Mips/frame-address.ll
+++ b/llvm/test/CodeGen/Mips/frame-address.ll
@@ -1,17 +1,26 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -march=mipsel < %s | FileCheck %s
 
 declare i8* @llvm.frameaddress(i32) nounwind readnone
 
 define i8* @f() nounwind uwtable {
+; CHECK-LABEL: f:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    addiu $sp, $sp, -8
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    sw $ra, 4($sp) # 4-byte Folded Spill
+; CHECK-NEXT:    sw $fp, 0($sp) # 4-byte Folded Spill
+; CHECK-NEXT:    .cfi_offset 31, -4
+; CHECK-NEXT:    .cfi_offset 30, -8
+; CHECK-NEXT:    move $fp, $sp
+; CHECK-NEXT:    .cfi_def_cfa_register 30
+; CHECK-NEXT:    move $2, $fp
+; CHECK-NEXT:    move $sp, $fp
+; CHECK-NEXT:    lw $fp, 0($sp) # 4-byte Folded Reload
+; CHECK-NEXT:    lw $ra, 4($sp) # 4-byte Folded Reload
+; CHECK-NEXT:    jr $ra
+; CHECK-NEXT:    addiu $sp, $sp, 8
 entry:
   %0 = call i8* @llvm.frameaddress(i32 0)
   ret i8* %0
-
-; CHECK: .cfi_startproc
-; CHECK: .cfi_def_cfa_offset 8
-; CHECK: .cfi_offset 30, -4
-; CHECK:   move    $fp, $sp
-; CHECK: .cfi_def_cfa_register 30
-; CHECK:   move    $2, $fp
-; CHECK: .cfi_endproc
 }
diff --git a/llvm/test/CodeGen/Mips/no-frame-pointer-elim.ll b/llvm/test/CodeGen/Mips/no-frame-pointer-elim.ll
new file mode 100644
index 00000000000..5242ff46129
--- /dev/null
+++ b/llvm/test/CodeGen/Mips/no-frame-pointer-elim.ll
@@ -0,0 +1,37 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -march=mips64 -relocation-model=static < %s \
+; RUN:   | FileCheck %s --check-prefix STATIC
+; RUN: llc -march=mips64 -relocation-model=pic < %s \
+; RUN:   | FileCheck %s --check-prefix PIC
+
+declare dso_local void @callee() noreturn nounwind
+
+define dso_local void @caller() nounwind "no-frame-pointer-elim-non-leaf" {
+; STATIC-LABEL: caller:
+; STATIC:       # %bb.0: # %entry
+; STATIC-NEXT:    daddiu $sp, $sp, -16
+; STATIC-NEXT:    sd $ra, 8($sp) # 8-byte Folded Spill
+; STATIC-NEXT:    sd $fp, 0($sp) # 8-byte Folded Spill
+; STATIC-NEXT:    move $fp, $sp
+; STATIC-NEXT:    jal callee
+; STATIC-NEXT:    nop
+;
+; PIC-LABEL: caller:
+; PIC:       # %bb.0: # %entry
+; PIC-NEXT:    daddiu $sp, $sp, -32
+; PIC-NEXT:    sd $ra, 24($sp) # 8-byte Folded Spill
+; PIC-NEXT:    sd $fp, 16($sp) # 8-byte Folded Spill
+; PIC-NEXT:    sd $gp, 8($sp) # 8-byte Folded Spill
+; PIC-NEXT:    move $fp, $sp
+; PIC-NEXT:    lui $1, %hi(%neg(%gp_rel(caller)))
+; PIC-NEXT:    daddu $1, $1, $25
+; PIC-NEXT:    daddiu $gp, $1, %lo(%neg(%gp_rel(caller)))
+; PIC-NEXT:    ld $25, %call16(callee)($gp)
+; PIC-NEXT:    .reloc .Ltmp0, R_MIPS_JALR, callee
+; PIC-NEXT:  .Ltmp0:
+; PIC-NEXT:    jalr $25
+; PIC-NEXT:    nop
+entry:
+  tail call void @callee()
+  unreachable
+}
diff --git a/llvm/test/CodeGen/Mips/tnaked.ll b/llvm/test/CodeGen/Mips/tnaked.ll
index 7dff19c5d00..e88396bac50 100644
--- a/llvm/test/CodeGen/Mips/tnaked.ll
+++ b/llvm/test/CodeGen/Mips/tnaked.ll
@@ -21,7 +21,7 @@ entry:
 ; CHECK: 	.ent	tnonaked
 ; CHECK-LABEL:         tnonaked:
 ; CHECK:	.frame	$fp,8,$ra
-; CHECK:        .mask 	0x40000000,-4
+; CHECK:        .mask 	0xc0000000,-4
 ; CHECK:	.fmask	0x00000000,0
 ; CHECK: 	addiu	$sp, $sp, -8
 
diff --git a/llvm/test/CodeGen/Mips/v2i16tof32.ll b/llvm/test/CodeGen/Mips/v2i16tof32.ll
index 334413b03d5..ab9fa9eefd4 100644
--- a/llvm/test/CodeGen/Mips/v2i16tof32.ll
+++ b/llvm/test/CodeGen/Mips/v2i16tof32.ll
@@ -9,8 +9,10 @@ define float @f(<8 x i16>* %a) {
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    addiu $sp, $sp, -32
 ; CHECK-NEXT:    .cfi_def_cfa_offset 32
-; CHECK-NEXT:    sw $fp, 28($sp) # 4-byte Folded Spill
-; CHECK-NEXT:    .cfi_offset 30, -4
+; CHECK-NEXT:    sw $ra, 28($sp) # 4-byte Folded Spill
+; CHECK-NEXT:    sw $fp, 24($sp) # 4-byte Folded Spill
+; CHECK-NEXT:    .cfi_offset 31, -4
+; CHECK-NEXT:    .cfi_offset 30, -8
 ; CHECK-NEXT:    move $fp, $sp
 ; CHECK-NEXT:    .cfi_def_cfa_register 30
 ; CHECK-NEXT:    addiu $1, $zero, -16
@@ -25,7 +27,8 @@ define float @f(<8 x i16>* %a) {
 ; CHECK-NEXT:    sw $1, 4($sp)
 ; CHECK-NEXT:    mtc1 $2, $f0
 ; CHECK-NEXT:    move $sp, $fp
-; CHECK-NEXT:    lw $fp, 28($sp) # 4-byte Folded Reload
+; CHECK-NEXT:    lw $fp, 24($sp) # 4-byte Folded Reload
+; CHECK-NEXT:    lw $ra, 28($sp) # 4-byte Folded Reload
 ; CHECK-NEXT:    jr $ra
 ; CHECK-NEXT:    addiu $sp, $sp, 32
 entry: