From ada258617b2cfdb6a4a34478cc86a8c68341c644 Mon Sep 17 00:00:00 2001
From: Amaury Sechet <deadalnix@gmail.com>
Date: Fri, 23 Aug 2019 13:30:45 +0000
Subject: [PATCH] [PowerPC] Automatically generate various tests. NFC

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@369754 91177308-0d34-0410-b5e6-96231b3b80d8
---
 .../PowerPC/ppc64-align-long-double.ll        |  78 +--
 .../umulo-128-legalisation-lowering.ll        | 314 +++++-----
 test/CodeGen/PowerPC/unal-vec-ldst.ll         | 573 ++++++++++--------
 3 files changed, 508 insertions(+), 457 deletions(-)

diff --git a/test/CodeGen/PowerPC/ppc64-align-long-double.ll b/test/CodeGen/PowerPC/ppc64-align-long-double.ll
index 8a5c5731865..c9a45a881f1 100644
--- a/test/CodeGen/PowerPC/ppc64-align-long-double.ll
+++ b/test/CodeGen/PowerPC/ppc64-align-long-double.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -verify-machineinstrs -mcpu=pwr7 -O2 -fast-isel=false -mattr=-vsx < %s | FileCheck %s
 ; RUN: llc -verify-machineinstrs -mcpu=pwr7 -O2 -fast-isel=false -mattr=+vsx < %s | FileCheck -check-prefix=CHECK-VSX %s
 ; RUN: llc -verify-machineinstrs -mcpu=pwr9 -O2 -fast-isel=false -mattr=+vsx < %s | FileCheck -check-prefix=CHECK-P9 %s
@@ -12,49 +13,48 @@ target triple = "powerpc64-unknown-linux-gnu"
 
 %struct.S = type { double, ppc_fp128 }
 
+; The additional stores are caused because we forward the value in the
+; store->load->bitcast path to make a store and bitcast of the same
+; value. Since the target does bitcast through memory and we no longer
+; remember the address we need to do the store in a fresh local
+; address.
 define ppc_fp128 @test(%struct.S* byval %x) nounwind {
+; CHECK-LABEL: test:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    std 5, -16(1)
+; CHECK-NEXT:    std 6, -8(1)
+; CHECK-NEXT:    lfd 1, -16(1)
+; CHECK-NEXT:    lfd 2, -8(1)
+; CHECK-NEXT:    std 6, 72(1)
+; CHECK-NEXT:    std 5, 64(1)
+; CHECK-NEXT:    std 3, 48(1)
+; CHECK-NEXT:    std 4, 56(1)
+; CHECK-NEXT:    blr
+;
+; CHECK-VSX-LABEL: test:
+; CHECK-VSX:       # %bb.0: # %entry
+; CHECK-VSX-NEXT:    std 3, 48(1)
+; CHECK-VSX-NEXT:    std 6, 72(1)
+; CHECK-VSX-NEXT:    std 5, 64(1)
+; CHECK-VSX-NEXT:    std 4, 56(1)
+; CHECK-VSX-NEXT:    std 5, -16(1)
+; CHECK-VSX-NEXT:    std 6, -8(1)
+; CHECK-VSX-NEXT:    lfd 1, -16(1)
+; CHECK-VSX-NEXT:    lfd 2, -8(1)
+; CHECK-VSX-NEXT:    blr
+;
+; CHECK-P9-LABEL: test:
+; CHECK-P9:       # %bb.0: # %entry
+; CHECK-P9-NEXT:    mtvsrd 1, 5
+; CHECK-P9-NEXT:    mtvsrd 2, 6
+; CHECK-P9-NEXT:    std 6, 72(1)
+; CHECK-P9-NEXT:    std 5, 64(1)
+; CHECK-P9-NEXT:    std 3, 48(1)
+; CHECK-P9-NEXT:    std 4, 56(1)
+; CHECK-P9-NEXT:    blr
 entry:
   %b = getelementptr inbounds %struct.S, %struct.S* %x, i32 0, i32 1
   %0 = load ppc_fp128, ppc_fp128* %b, align 16
   ret ppc_fp128 %0
 }
 
-; The additional stores are caused because we forward the value in the
-; store->load->bitcast path to make a store and bitcast of the same
-; value. Since the target does bitcast through memory and we no longer
-; remember the address we need to do the store in a fresh local
-; address. 
-
-; CHECK-DAG: std 6, 72(1)
-; CHECK-DAG: std 5, 64(1)
-; CHECK-DAG: std 4, 56(1)
-; CHECK-DAG: std 3, 48(1)
-
-; CHECK-DAG: std 5, -16(1)
-; CHECK-DAG: std 6, -8(1)
-; CHECK-DAG: lfd 1, -16(1)
-; CHECK-DAG: lfd 2, -8(1)
-
-; FIXMECHECK: lfd 1, 64(1)
-; FIXMECHECK: lfd 2, 72(1)
-
-; CHECK-VSX-DAG: std 6, 72(1)
-; CHECK-VSX-DAG: std 5, 64(1)
-; CHECK-VSX-DAG: std 4, 56(1)
-; CHECK-VSX-DAG: std 3, 48(1)
-; CHECK-VSX-DAG: std 5, -16(1)
-; CHECK-VSX-DAG: std 6, -8(1)
-; CHECK-VSX: lfd 1, -16(1)
-; CHECK-VSX: lfd 2, -8(1)
-
-; FIXME-VSX: addi 4, 1, 48
-; FIXME-VSX: lxsdx 1, 4, 3
-; FIXME-VSX: li 3, 24
-; FIXME-VSX: lxsdx 2, 4, 3
-
-; CHECK-P9-DAG: std 6, 72(1)
-; CHECK-P9-DAG: std 5, 64(1)
-; CHECK-P9-DAG: std 4, 56(1)
-; CHECK-P9-DAG: std 3, 48(1)
-; CHECK-P9-DAG: mtvsrd 1, 5
-; CHECK-P9-DAG: mtvsrd 2, 6
diff --git a/test/CodeGen/PowerPC/umulo-128-legalisation-lowering.ll b/test/CodeGen/PowerPC/umulo-128-legalisation-lowering.ll
index 2ca96df78c5..b3c9012b6e0 100644
--- a/test/CodeGen/PowerPC/umulo-128-legalisation-lowering.ll
+++ b/test/CodeGen/PowerPC/umulo-128-legalisation-lowering.ll
@@ -1,164 +1,170 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu | FileCheck %s --check-prefixes=PPC64
 ; RUN: llc < %s -mtriple=powerpc-unknown-linux-gnu | FileCheck %s --check-prefixes=PPC32
 
 define { i128, i8 } @muloti_test(i128 %l, i128 %r) unnamed_addr #0 {
-
 ; PPC64-LABEL muloti_test:
-; PPC64: mulld 8, 5, 4
-; PPC64-NEXT: cmpdi 5, 3, 0
-; PPC64-NEXT: mulhdu. 9, 3, 6
-; PPC64-NEXT: mulld 3, 3, 6
-; PPC64-NEXT: mcrf 1, 0
-; PPC64-NEXT: add 3, 3, 8
-; PPC64-NEXT: cmpdi   5, 0
-; PPC64-NEXT: crnor 20, 2, 22
-; PPC64-NEXT: cmpldi  3, 0
-; PPC64-NEXT: mulhdu 8, 4, 6
-; PPC64-NEXT: add 3, 8, 3
-; PPC64-NEXT: cmpld 6, 3, 8
-; PPC64-NEXT: crandc 21, 24, 2
-; PPC64-NEXT: crorc 20, 20, 6
-; PPC64-NEXT: li 7, 1
-; PPC64-NEXT: mulhdu. 5, 5, 4
-; PPC64-NEXT: crorc 20, 20, 2
-; PPC64-NEXT: crnor 20, 20, 21
-; PPC64-NEXT: mulld 4, 4, 6
-; PPC64-NEXT: bc 12, 20, .LBB0_2
-; PPC64: ori 5, 7, 0
-; PPC64-NEXT: blr
-; PPC64-NEXT: .LBB0_2:
-; PPC64-NEXT: addi 5, 0, 0
-; PPC64-NEXT: blr
+; PPC64-LABEL: muloti_test:
+; PPC64:       # %bb.0: # %start
+; PPC64-NEXT:    mulld 8, 5, 4
+; PPC64-NEXT:    cmpdi 5, 3, 0
+; PPC64-NEXT:    mulhdu. 9, 3, 6
+; PPC64-NEXT:    mulld 3, 3, 6
+; PPC64-NEXT:    mcrf 1, 0
+; PPC64-NEXT:    add 3, 3, 8
+; PPC64-NEXT:    cmpdi 5, 0
+; PPC64-NEXT:    crnor 20, 2, 22
+; PPC64-NEXT:    cmpldi 3, 0
+; PPC64-NEXT:    mulhdu 8, 4, 6
+; PPC64-NEXT:    add 3, 8, 3
+; PPC64-NEXT:    cmpld 6, 3, 8
+; PPC64-NEXT:    crandc 21, 24, 2
+; PPC64-NEXT:    crorc 20, 20, 6
+; PPC64-NEXT:    li 7, 1
+; PPC64-NEXT:    mulhdu. 5, 5, 4
+; PPC64-NEXT:    crorc 20, 20, 2
+; PPC64-NEXT:    crnor 20, 20, 21
+; PPC64-NEXT:    mulld 4, 4, 6
+; PPC64-NEXT:    bc 12, 20, .LBB0_2
+; PPC64-NEXT:  # %bb.1: # %start
+; PPC64-NEXT:    ori 5, 7, 0
+; PPC64-NEXT:    blr
+; PPC64-NEXT:  .LBB0_2: # %start
+; PPC64-NEXT:    addi 5, 0, 0
+; PPC64-NEXT:    blr
 ;
+; PPC32-LABEL: muloti_test:
+; PPC32:       # %bb.0: # %start
+; PPC32-NEXT:    mflr 0
+; PPC32-NEXT:    stw 0, 4(1)
+; PPC32-NEXT:    stwu 1, -80(1)
+; PPC32-NEXT:    .cfi_def_cfa_offset 80
+; PPC32-NEXT:    .cfi_offset lr, 4
+; PPC32-NEXT:    .cfi_offset r20, -48
+; PPC32-NEXT:    .cfi_offset r21, -44
+; PPC32-NEXT:    .cfi_offset r22, -40
+; PPC32-NEXT:    .cfi_offset r23, -36
+; PPC32-NEXT:    .cfi_offset r24, -32
+; PPC32-NEXT:    .cfi_offset r25, -28
+; PPC32-NEXT:    .cfi_offset r26, -24
+; PPC32-NEXT:    .cfi_offset r27, -20
+; PPC32-NEXT:    .cfi_offset r28, -16
+; PPC32-NEXT:    .cfi_offset r29, -12
+; PPC32-NEXT:    .cfi_offset r30, -8
+; PPC32-NEXT:    stw 26, 56(1) # 4-byte Folded Spill
+; PPC32-NEXT:    stw 27, 60(1) # 4-byte Folded Spill
+; PPC32-NEXT:    stw 29, 68(1) # 4-byte Folded Spill
+; PPC32-NEXT:    stw 30, 72(1) # 4-byte Folded Spill
+; PPC32-NEXT:    mfcr 12
+; PPC32-NEXT:    mr 30, 8
+; PPC32-NEXT:    mr 29, 7
+; PPC32-NEXT:    mr 27, 4
+; PPC32-NEXT:    mr 26, 3
+; PPC32-NEXT:    li 3, 0
+; PPC32-NEXT:    li 4, 0
+; PPC32-NEXT:    li 7, 0
+; PPC32-NEXT:    li 8, 0
+; PPC32-NEXT:    stw 20, 32(1) # 4-byte Folded Spill
+; PPC32-NEXT:    stw 21, 36(1) # 4-byte Folded Spill
+; PPC32-NEXT:    stw 22, 40(1) # 4-byte Folded Spill
+; PPC32-NEXT:    stw 23, 44(1) # 4-byte Folded Spill
+; PPC32-NEXT:    stw 24, 48(1) # 4-byte Folded Spill
+; PPC32-NEXT:    stw 25, 52(1) # 4-byte Folded Spill
+; PPC32-NEXT:    stw 28, 64(1) # 4-byte Folded Spill
+; PPC32-NEXT:    mr 25, 10
+; PPC32-NEXT:    stw 12, 28(1)
+; PPC32-NEXT:    mr 28, 9
+; PPC32-NEXT:    mr 23, 6
+; PPC32-NEXT:    mr 24, 5
+; PPC32-NEXT:    bl __multi3@PLT
+; PPC32-NEXT:    mr 7, 4
+; PPC32-NEXT:    mullw 4, 24, 30
+; PPC32-NEXT:    mullw 8, 29, 23
+; PPC32-NEXT:    mullw 10, 28, 27
+; PPC32-NEXT:    mullw 11, 26, 25
+; PPC32-NEXT:    mulhwu 9, 30, 23
+; PPC32-NEXT:    mulhwu 12, 27, 25
+; PPC32-NEXT:    mullw 0, 30, 23
+; PPC32-NEXT:    mullw 22, 27, 25
+; PPC32-NEXT:    add 21, 8, 4
+; PPC32-NEXT:    add 10, 11, 10
+; PPC32-NEXT:    addc 4, 22, 0
+; PPC32-NEXT:    add 11, 9, 21
+; PPC32-NEXT:    add 0, 12, 10
+; PPC32-NEXT:    adde 8, 0, 11
+; PPC32-NEXT:    addc 4, 7, 4
+; PPC32-NEXT:    adde 8, 3, 8
+; PPC32-NEXT:    xor 22, 4, 7
+; PPC32-NEXT:    xor 20, 8, 3
+; PPC32-NEXT:    or. 22, 22, 20
+; PPC32-NEXT:    mcrf 1, 0
+; PPC32-NEXT:    cmpwi 29, 0
+; PPC32-NEXT:    cmpwi 5, 24, 0
+; PPC32-NEXT:    cmpwi 6, 26, 0
+; PPC32-NEXT:    cmpwi 7, 28, 0
+; PPC32-NEXT:    crnor 8, 22, 2
+; PPC32-NEXT:    mulhwu. 23, 29, 23
+; PPC32-NEXT:    crnor 9, 30, 26
+; PPC32-NEXT:    mcrf 5, 0
+; PPC32-NEXT:    cmplwi 21, 0
+; PPC32-NEXT:    cmplw 6, 11, 9
+; PPC32-NEXT:    cmplwi 7, 10, 0
+; PPC32-NEXT:    crandc 10, 24, 2
+; PPC32-NEXT:    cmplw 3, 0, 12
+; PPC32-NEXT:    mulhwu. 9, 24, 30
+; PPC32-NEXT:    mcrf 6, 0
+; PPC32-NEXT:    crandc 11, 12, 30
+; PPC32-NEXT:    cmplw 4, 7
+; PPC32-NEXT:    cmplw 7, 8, 3
+; PPC32-NEXT:    crand 12, 30, 0
+; PPC32-NEXT:    crandc 13, 28, 30
+; PPC32-NEXT:    mulhwu. 3, 26, 25
+; PPC32-NEXT:    mcrf 7, 0
+; PPC32-NEXT:    cror 0, 12, 13
+; PPC32-NEXT:    crandc 12, 0, 6
+; PPC32-NEXT:    crorc 20, 8, 22
+; PPC32-NEXT:    crorc 20, 20, 26
+; PPC32-NEXT:    mulhwu. 3, 28, 27
+; PPC32-NEXT:    mcrf 1, 0
+; PPC32-NEXT:    crorc 25, 9, 30
+; PPC32-NEXT:    or. 3, 27, 26
+; PPC32-NEXT:    cror 24, 20, 10
+; PPC32-NEXT:    mcrf 5, 0
+; PPC32-NEXT:    crorc 25, 25, 6
+; PPC32-NEXT:    or. 3, 30, 29
+; PPC32-NEXT:    cror 25, 25, 11
+; PPC32-NEXT:    crnor 20, 2, 22
+; PPC32-NEXT:    lwz 12, 28(1)
+; PPC32-NEXT:    cror 20, 20, 25
+; PPC32-NEXT:    cror 20, 20, 24
+; PPC32-NEXT:    crnor 20, 20, 12
+; PPC32-NEXT:    li 3, 1
+; PPC32-NEXT:    bc 12, 20, .LBB0_2
+; PPC32-NEXT:  # %bb.1: # %start
+; PPC32-NEXT:    ori 7, 3, 0
+; PPC32-NEXT:    b .LBB0_3
+; PPC32-NEXT:  .LBB0_2: # %start
+; PPC32-NEXT:    addi 7, 0, 0
+; PPC32-NEXT:  .LBB0_3: # %start
+; PPC32-NEXT:    mr 3, 8
+; PPC32-NEXT:    mtcrf 32, 12 # cr2
+; PPC32-NEXT:    mtcrf 16, 12 # cr3
+; PPC32-NEXT:    lwz 30, 72(1) # 4-byte Folded Reload
+; PPC32-NEXT:    lwz 29, 68(1) # 4-byte Folded Reload
+; PPC32-NEXT:    lwz 28, 64(1) # 4-byte Folded Reload
+; PPC32-NEXT:    lwz 27, 60(1) # 4-byte Folded Reload
+; PPC32-NEXT:    lwz 26, 56(1) # 4-byte Folded Reload
+; PPC32-NEXT:    lwz 25, 52(1) # 4-byte Folded Reload
+; PPC32-NEXT:    lwz 24, 48(1) # 4-byte Folded Reload
+; PPC32-NEXT:    lwz 23, 44(1) # 4-byte Folded Reload
+; PPC32-NEXT:    lwz 22, 40(1) # 4-byte Folded Reload
+; PPC32-NEXT:    lwz 21, 36(1) # 4-byte Folded Reload
+; PPC32-NEXT:    lwz 20, 32(1) # 4-byte Folded Reload
+; PPC32-NEXT:    lwz 0, 84(1)
+; PPC32-NEXT:    addi 1, 1, 80
+; PPC32-NEXT:    mtlr 0
+; PPC32-NEXT:    blr
 ; PPC32-LABEL muloti_test:
-; PPC32: mflr 0
-; PPC32-NEXT: stw 0, 4(1)
-; PPC32-NEXT: stwu 1, -80(1)
-; PPC32-NEXT: .cfi_def_cfa_offset 80
-; PPC32-NEXT: .cfi_offset lr, 4
-; PPC32-NEXT: .cfi_offset r20, -48
-; PPC32-NEXT: .cfi_offset r21, -44
-; PPC32-NEXT: .cfi_offset r22, -40
-; PPC32-NEXT: .cfi_offset r23, -36
-; PPC32-NEXT: .cfi_offset r24, -32
-; PPC32-NEXT: .cfi_offset r25, -28
-; PPC32-NEXT: .cfi_offset r26, -24
-; PPC32-NEXT: .cfi_offset r27, -20
-; PPC32-NEXT: .cfi_offset r28, -16
-; PPC32-NEXT: .cfi_offset r29, -12
-; PPC32-NEXT: .cfi_offset r30, -8
-; PPC32-NEXT: stw 26, 56(1)
-; PPC32-NEXT: stw 27, 60(1)
-; PPC32-NEXT: stw 29, 68(1)
-; PPC32-NEXT: stw 30, 72(1)
-; PPC32-NEXT: mfcr 12
-; PPC32-NEXT: mr 30, 8
-; PPC32-NEXT: mr 29, 7
-; PPC32-NEXT: mr 27, 4
-; PPC32-NEXT: mr 26, 3
-; PPC32-NEXT: li 3, 0
-; PPC32-NEXT: li 4, 0
-; PPC32-NEXT: li 7, 0
-; PPC32-NEXT: li 8, 0
-; PPC32-NEXT: stw 20, 32(1)
-; PPC32-NEXT: stw 21, 36(1)
-; PPC32-NEXT: stw 22, 40(1)
-; PPC32-NEXT: stw 23, 44(1)
-; PPC32-NEXT: stw 24, 48(1)
-; PPC32-NEXT: stw 25, 52(1)
-; PPC32-NEXT: stw 28, 64(1)
-; PPC32-NEXT: mr 25, 10
-; PPC32-NEXT: stw 12, 28(1)
-; PPC32-NEXT: mr 28, 9
-; PPC32-NEXT: mr 23, 6
-; PPC32-NEXT: mr 24, 5
-; PPC32-NEXT: bl __multi3@PLT
-; PPC32-NEXT: mr 7, 4
-; PPC32-NEXT: mullw 4, 24, 30
-; PPC32-NEXT: mullw 8, 29, 23
-; PPC32-NEXT: mullw 10, 28, 27
-; PPC32-NEXT: mullw 11, 26, 25
-; PPC32-NEXT: mulhwu 9, 30, 23
-; PPC32-NEXT: mulhwu 12, 27, 25
-; PPC32-NEXT: mullw 0, 30, 23
-; PPC32-NEXT: mullw 22, 27, 25
-; PPC32-NEXT: add 21, 8, 4
-; PPC32-NEXT: add 10, 11, 10
-; PPC32-NEXT: addc 4, 22, 0
-; PPC32-NEXT: add 11, 9, 21
-; PPC32-NEXT: add 0, 12, 10
-; PPC32-NEXT: adde 8, 0, 11
-; PPC32-NEXT: addc 4, 7, 4
-; PPC32-NEXT: adde 8, 3, 8
-; PPC32-NEXT: xor 22, 4, 7
-; PPC32-NEXT: xor 20, 8, 3
-; PPC32-NEXT: or. 22, 22, 20
-; PPC32-NEXT: mcrf 1, 0
-; PPC32-NEXT: cmpwi   29, 0
-; PPC32-NEXT: cmpwi 5, 24, 0
-; PPC32-NEXT: cmpwi 6, 26, 0
-; PPC32-NEXT: cmpwi 7, 28, 0
-; PPC32-NEXT: crnor 8, 22, 2
-; PPC32-NEXT: mulhwu. 23, 29, 23
-; PPC32-NEXT: crnor 9, 30, 26
-; PPC32-NEXT: mcrf 5, 0
-; PPC32-NEXT: cmplwi  21, 0
-; PPC32-NEXT: cmplw 6, 11, 9
-; PPC32-NEXT: cmplwi 7, 10, 0
-; PPC32-NEXT: crandc 10, 24, 2
-; PPC32-NEXT: cmplw 3, 0, 12
-; PPC32-NEXT: mulhwu. 9, 24, 30
-; PPC32-NEXT: mcrf 6, 0
-; PPC32-NEXT: crandc 11, 12, 30
-; PPC32-NEXT: cmplw   4, 7
-; PPC32-NEXT: cmplw 7, 8, 3
-; PPC32-NEXT: crand 12, 30, 0
-; PPC32-NEXT: crandc 13, 28, 30
-; PPC32-NEXT: mulhwu. 3, 26, 25
-; PPC32-NEXT: mcrf 7, 0
-; PPC32-NEXT: cror 0, 12, 13
-; PPC32-NEXT: crandc 12, 0, 6
-; PPC32-NEXT: crorc 20, 8, 22
-; PPC32-NEXT: crorc 20, 20, 26
-; PPC32-NEXT: mulhwu. 3, 28, 27
-; PPC32-NEXT: mcrf 1, 0
-; PPC32-NEXT: crorc 25, 9, 30
-; PPC32-NEXT: or. 3, 27, 26
-; PPC32-NEXT: cror 24, 20, 10
-; PPC32-NEXT: mcrf 5, 0
-; PPC32-NEXT: crorc 25, 25, 6
-; PPC32-NEXT: or. 3, 30, 29
-; PPC32-NEXT: cror 25, 25, 11
-; PPC32-NEXT: crnor 20, 2, 22
-; PPC32-NEXT: lwz 12, 28(1)
-; PPC32-NEXT: cror 20, 20, 25
-; PPC32-NEXT: cror 20, 20, 24
-; PPC32-NEXT: crnor 20, 20, 12
-; PPC32-NEXT: li 3, 1
-; PPC32-NEXT: bc 12, 20, .LBB0_2
-; PPC32: ori 7, 3, 0
-; PPC32-NEXT: b .LBB0_3
-; PPC32-NEXT:.LBB0_2:
-; PPC32-NEXT: addi 7, 0, 0
-; PPC32-NEXT:.LBB0_3:
-; PPC32-NEXT: mr 3, 8
-; PPC32-NEXT: mtcrf 32, 12
-; PPC32-NEXT: mtcrf 16, 12
-; PPC32-NEXT: lwz 30, 72(1)
-; PPC32-NEXT: lwz 29, 68(1)
-; PPC32-NEXT: lwz 28, 64(1)
-; PPC32-NEXT: lwz 27, 60(1)
-; PPC32-NEXT: lwz 26, 56(1)
-; PPC32-NEXT: lwz 25, 52(1)
-; PPC32-NEXT: lwz 24, 48(1)
-; PPC32-NEXT: lwz 23, 44(1)
-; PPC32-NEXT: lwz 22, 40(1)
-; PPC32-NEXT: lwz 21, 36(1)
-; PPC32-NEXT: lwz 20, 32(1)
-; PPC32-NEXT: lwz 0, 84(1)
-; PPC32-NEXT: addi 1, 1, 80
-; PPC32-NEXT: mtlr 0
-; PPC32-NEXT: blr
 start:
   %0 = tail call { i128, i1 } @llvm.umul.with.overflow.i128(i128 %l, i128 %r) #2
   %1 = extractvalue { i128, i1 } %0, 0
diff --git a/test/CodeGen/PowerPC/unal-vec-ldst.ll b/test/CodeGen/PowerPC/unal-vec-ldst.ll
index f1bd2af4c40..497add38e04 100644
--- a/test/CodeGen/PowerPC/unal-vec-ldst.ll
+++ b/test/CodeGen/PowerPC/unal-vec-ldst.ll
@@ -1,577 +1,622 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -verify-machineinstrs < %s | FileCheck %s
 target datalayout = "E-m:e-i64:64-n32:64"
 target triple = "powerpc64-unknown-linux-gnu"
 
 define <16 x i8> @test_l_v16i8(<16 x i8>* %p) #0 {
+; CHECK-LABEL: test_l_v16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 15
+; CHECK-NEXT:    lvsl 3, 0, 3
+; CHECK-NEXT:    lvx 2, 3, 4
+; CHECK-NEXT:    lvx 4, 0, 3
+; CHECK-NEXT:    vperm 2, 4, 2, 3
+; CHECK-NEXT:    blr
 entry:
   %r = load <16 x i8>, <16 x i8>* %p, align 1
   ret <16 x i8> %r
 
-; CHECK-LABEL: @test_l_v16i8
-; CHECK-DAG: li [[REG1:[0-9]+]], 15
-; CHECK-DAG: lvsl [[REG2:[0-9]+]], 0, 3
-; CHECK-DAG: lvx [[REG3:[0-9]+]], 3, [[REG1]]
-; CHECK-DAG: lvx [[REG4:[0-9]+]], 0, 3
-; CHECK: vperm 2, [[REG4]], [[REG3]], [[REG2]]
-; CHECK: blr
 }
 
 define <32 x i8> @test_l_v32i8(<32 x i8>* %p) #0 {
+; CHECK-LABEL: test_l_v32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 31
+; CHECK-NEXT:    lvsl 5, 0, 3
+; CHECK-NEXT:    lvx 2, 3, 4
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    lvx 4, 3, 4
+; CHECK-NEXT:    lvx 0, 0, 3
+; CHECK-NEXT:    vperm 3, 4, 2, 5
+; CHECK-NEXT:    vperm 2, 0, 4, 5
+; CHECK-NEXT:    blr
 entry:
   %r = load <32 x i8>, <32 x i8>* %p, align 1
   ret <32 x i8> %r
 
-; CHECK-LABEL: @test_l_v32i8
-; CHECK-DAG: li [[REG1:[0-9]+]], 31
-; CHECK-DAG: li [[REG2:[0-9]+]], 16
-; CHECK-DAG: lvsl [[REG3:[0-9]+]], 0, 3
-; CHECK-DAG: lvx [[REG4:[0-9]+]], 3, [[REG1]]
-; CHECK-DAG: lvx [[REG5:[0-9]+]], 3, [[REG2]]
-; CHECK-DAG: lvx [[REG6:[0-9]+]], 0, 3
-; CHECK-DAG: vperm 3, {{[0-9]+}}, {{[0-9]+}}, [[REG3]]
-; CHECK-DAG: vperm 2, {{[0-9]+}}, {{[0-9]+}}, [[REG3]]
-; CHECK: blr
 }
 
 define <8 x i16> @test_l_v8i16(<8 x i16>* %p) #0 {
+; CHECK-LABEL: test_l_v8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 15
+; CHECK-NEXT:    lvsl 3, 0, 3
+; CHECK-NEXT:    lvx 2, 3, 4
+; CHECK-NEXT:    lvx 4, 0, 3
+; CHECK-NEXT:    vperm 2, 4, 2, 3
+; CHECK-NEXT:    blr
 entry:
   %r = load <8 x i16>, <8 x i16>* %p, align 2
   ret <8 x i16> %r
 
-; CHECK-LABEL: @test_l_v8i16
-; CHECK-DAG: li [[REG1:[0-9]+]], 15
-; CHECK-DAG: lvsl [[REG2:[0-9]+]], 0, 3
-; CHECK-DAG: lvx [[REG3:[0-9]+]], 3, [[REG1]]
-; CHECK-DAG: lvx [[REG4:[0-9]+]], 0, 3
-; CHECK: vperm 2, [[REG4]], [[REG3]], [[REG2]]
-; CHECK: blr
 }
 
 define <16 x i16> @test_l_v16i16(<16 x i16>* %p) #0 {
+; CHECK-LABEL: test_l_v16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 31
+; CHECK-NEXT:    lvsl 5, 0, 3
+; CHECK-NEXT:    lvx 2, 3, 4
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    lvx 4, 3, 4
+; CHECK-NEXT:    lvx 0, 0, 3
+; CHECK-NEXT:    vperm 3, 4, 2, 5
+; CHECK-NEXT:    vperm 2, 0, 4, 5
+; CHECK-NEXT:    blr
 entry:
   %r = load <16 x i16>, <16 x i16>* %p, align 2
   ret <16 x i16> %r
 
-; CHECK-LABEL: @test_l_v16i16
-; CHECK-DAG: li [[REG1:[0-9]+]], 31
-; CHECK-DAG: li [[REG2:[0-9]+]], 16
-; CHECK-DAG: lvsl [[REG3:[0-9]+]], 0, 3
-; CHECK-DAG: lvx [[REG4:[0-9]+]], 3, [[REG1]]
-; CHECK-DAG: lvx [[REG5:[0-9]+]], 3, [[REG2]]
-; CHECK-DAG: lvx [[REG6:[0-9]+]], 0, 3
-; CHECK-DAG: vperm 3, {{[0-9]+}}, {{[0-9]+}}, [[REG3]]
-; CHECK-DAG: vperm 2, {{[0-9]+}}, {{[0-9]+}}, [[REG3]]
-; CHECK: blr
 }
 
 define <4 x i32> @test_l_v4i32(<4 x i32>* %p) #0 {
+; CHECK-LABEL: test_l_v4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 15
+; CHECK-NEXT:    lvsl 3, 0, 3
+; CHECK-NEXT:    lvx 2, 3, 4
+; CHECK-NEXT:    lvx 4, 0, 3
+; CHECK-NEXT:    vperm 2, 4, 2, 3
+; CHECK-NEXT:    blr
 entry:
   %r = load <4 x i32>, <4 x i32>* %p, align 4
   ret <4 x i32> %r
 
-; CHECK-LABEL: @test_l_v4i32
-; CHECK-DAG: li [[REG1:[0-9]+]], 15
-; CHECK-DAG: lvsl [[REG2:[0-9]+]], 0, 3
-; CHECK-DAG: lvx [[REG3:[0-9]+]], 3, [[REG1]]
-; CHECK-DAG: lvx [[REG4:[0-9]+]], 0, 3
-; CHECK: vperm 2, [[REG4]], [[REG3]], [[REG2]]
-; CHECK: blr
 }
 
 define <8 x i32> @test_l_v8i32(<8 x i32>* %p) #0 {
+; CHECK-LABEL: test_l_v8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 31
+; CHECK-NEXT:    lvsl 5, 0, 3
+; CHECK-NEXT:    lvx 2, 3, 4
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    lvx 4, 3, 4
+; CHECK-NEXT:    lvx 0, 0, 3
+; CHECK-NEXT:    vperm 3, 4, 2, 5
+; CHECK-NEXT:    vperm 2, 0, 4, 5
+; CHECK-NEXT:    blr
 entry:
   %r = load <8 x i32>, <8 x i32>* %p, align 4
   ret <8 x i32> %r
 
-; CHECK-LABEL: @test_l_v8i32
-; CHECK-DAG: li [[REG1:[0-9]+]], 31
-; CHECK-DAG: li [[REG2:[0-9]+]], 16
-; CHECK-DAG: lvsl [[REG3:[0-9]+]], 0, 3
-; CHECK-DAG: lvx [[REG4:[0-9]+]], 3, [[REG1]]
-; CHECK-DAG: lvx [[REG5:[0-9]+]], 3, [[REG2]]
-; CHECK-DAG: lvx [[REG6:[0-9]+]], 0, 3
-; CHECK-DAG: vperm 3, {{[0-9]+}}, {{[0-9]+}}, [[REG3]]
-; CHECK-DAG: vperm 2, {{[0-9]+}}, {{[0-9]+}}, [[REG3]]
-; CHECK: blr
 }
 
 define <2 x i64> @test_l_v2i64(<2 x i64>* %p) #0 {
+; CHECK-LABEL: test_l_v2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    lxvd2x 34, 0, 3
+; CHECK-NEXT:    blr
 entry:
   %r = load <2 x i64>, <2 x i64>* %p, align 8
   ret <2 x i64> %r
 
-; CHECK-LABEL: @test_l_v2i64
-; CHECK: lxvd2x 34, 0, 3
-; CHECK: blr
 }
 
 define <4 x i64> @test_l_v4i64(<4 x i64>* %p) #0 {
+; CHECK-LABEL: test_l_v4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    lxvd2x 34, 0, 3
+; CHECK-NEXT:    lxvd2x 35, 3, 4
+; CHECK-NEXT:    blr
 entry:
   %r = load <4 x i64>, <4 x i64>* %p, align 8
   ret <4 x i64> %r
 
-; CHECK-LABEL: @test_l_v4i64
-; CHECK-DAG: li [[REG1:[0-9]+]], 16
-; CHECK-DAG: lxvd2x 34, 0, 3
-; CHECK-DAG: lxvd2x 35, 3, [[REG1]]
-; CHECK: blr
 }
 
 define <4 x float> @test_l_v4float(<4 x float>* %p) #0 {
+; CHECK-LABEL: test_l_v4float:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 15
+; CHECK-NEXT:    lvsl 3, 0, 3
+; CHECK-NEXT:    lvx 2, 3, 4
+; CHECK-NEXT:    lvx 4, 0, 3
+; CHECK-NEXT:    vperm 2, 4, 2, 3
+; CHECK-NEXT:    blr
 entry:
   %r = load <4 x float>, <4 x float>* %p, align 4
   ret <4 x float> %r
 
-; CHECK-LABEL: @test_l_v4float
-; CHECK-DAG: li [[REG1:[0-9]+]], 15
-; CHECK-DAG: lvsl [[REG2:[0-9]+]], 0, 3
-; CHECK-DAG: lvx [[REG3:[0-9]+]], 3, [[REG1]]
-; CHECK-DAG: lvx [[REG4:[0-9]+]], 0, 3
-; CHECK: vperm 2, [[REG4]], [[REG3]], [[REG2]]
-; CHECK: blr
 }
 
 define <8 x float> @test_l_v8float(<8 x float>* %p) #0 {
+; CHECK-LABEL: test_l_v8float:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 31
+; CHECK-NEXT:    lvsl 5, 0, 3
+; CHECK-NEXT:    lvx 2, 3, 4
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    lvx 4, 3, 4
+; CHECK-NEXT:    lvx 0, 0, 3
+; CHECK-NEXT:    vperm 3, 4, 2, 5
+; CHECK-NEXT:    vperm 2, 0, 4, 5
+; CHECK-NEXT:    blr
 entry:
   %r = load <8 x float>, <8 x float>* %p, align 4
   ret <8 x float> %r
 
-; CHECK-LABEL: @test_l_v8float
-; CHECK-DAG: li [[REG1:[0-9]+]], 31
-; CHECK-DAG: li [[REG2:[0-9]+]], 16
-; CHECK-DAG: lvsl [[REG3:[0-9]+]], 0, 3
-; CHECK-DAG: lvx [[REG4:[0-9]+]], 3, [[REG1]]
-; CHECK-DAG: lvx [[REG5:[0-9]+]], 3, [[REG2]]
-; CHECK-DAG: lvx [[REG6:[0-9]+]], 0, 3
-; CHECK-DAG: vperm 3, {{[0-9]+}}, {{[0-9]+}}, [[REG3]]
-; CHECK-DAG: vperm 2, {{[0-9]+}}, {{[0-9]+}}, [[REG3]]
-; CHECK: blr
 }
 
 define <2 x double> @test_l_v2double(<2 x double>* %p) #0 {
+; CHECK-LABEL: test_l_v2double:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    lxvd2x 34, 0, 3
+; CHECK-NEXT:    blr
 entry:
   %r = load <2 x double>, <2 x double>* %p, align 8
   ret <2 x double> %r
 
-; CHECK-LABEL: @test_l_v2double
-; CHECK: lxvd2x 34, 0, 3
-; CHECK: blr
 }
 
 define <4 x double> @test_l_v4double(<4 x double>* %p) #0 {
+; CHECK-LABEL: test_l_v4double:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    lxvd2x 34, 0, 3
+; CHECK-NEXT:    lxvd2x 35, 3, 4
+; CHECK-NEXT:    blr
 entry:
   %r = load <4 x double>, <4 x double>* %p, align 8
   ret <4 x double> %r
 
-; CHECK-LABEL: @test_l_v4double
-; CHECK-DAG: li [[REG1:[0-9]+]], 16
-; CHECK-DAG: lxvd2x 34, 0, 3
-; CHECK-DAG: lxvd2x 35, 3, [[REG1]]
-; CHECK: blr
 }
 
 define <16 x i8> @test_l_p8v16i8(<16 x i8>* %p) #2 {
+; CHECK-LABEL: test_l_p8v16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    lxvw4x 34, 0, 3
+; CHECK-NEXT:    blr
 entry:
   %r = load <16 x i8>, <16 x i8>* %p, align 1
   ret <16 x i8> %r
 
-; CHECK-LABEL: @test_l_p8v16i8
-; CHECK: lxvw4x 34, 0, 3
-; CHECK: blr
 }
 
 define <32 x i8> @test_l_p8v32i8(<32 x i8>* %p) #2 {
+; CHECK-LABEL: test_l_p8v32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    lxvw4x 34, 0, 3
+; CHECK-NEXT:    lxvw4x 35, 3, 4
+; CHECK-NEXT:    blr
 entry:
   %r = load <32 x i8>, <32 x i8>* %p, align 1
   ret <32 x i8> %r
 
-; CHECK-LABEL: @test_l_p8v32i8
-; CHECK-DAG: li [[REG1:[0-9]+]], 16
-; CHECK-DAG: lxvw4x 34, 0, 3
-; CHECK-DAG: lxvw4x 35, 3, [[REG1]]
-; CHECK: blr
 }
 
 define <8 x i16> @test_l_p8v8i16(<8 x i16>* %p) #2 {
+; CHECK-LABEL: test_l_p8v8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    lxvw4x 34, 0, 3
+; CHECK-NEXT:    blr
 entry:
   %r = load <8 x i16>, <8 x i16>* %p, align 2
   ret <8 x i16> %r
 
-; CHECK-LABEL: @test_l_p8v8i16
-; CHECK: lxvw4x 34, 0, 3
-; CHECK: blr
 }
 
 define <16 x i16> @test_l_p8v16i16(<16 x i16>* %p) #2 {
+; CHECK-LABEL: test_l_p8v16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    lxvw4x 34, 0, 3
+; CHECK-NEXT:    lxvw4x 35, 3, 4
+; CHECK-NEXT:    blr
 entry:
   %r = load <16 x i16>, <16 x i16>* %p, align 2
   ret <16 x i16> %r
 
-; CHECK-LABEL: @test_l_p8v16i16
-; CHECK-DAG: li [[REG1:[0-9]+]], 16
-; CHECK-DAG: lxvw4x 34, 0, 3
-; CHECK-DAG: lxvw4x 35, 3, [[REG1]]
-; CHECK: blr
 }
 
 define <4 x i32> @test_l_p8v4i32(<4 x i32>* %p) #2 {
+; CHECK-LABEL: test_l_p8v4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    lxvw4x 34, 0, 3
+; CHECK-NEXT:    blr
 entry:
   %r = load <4 x i32>, <4 x i32>* %p, align 4
   ret <4 x i32> %r
 
-; CHECK-LABEL: @test_l_p8v4i32
-; CHECK: lxvw4x 34, 0, 3
-; CHECK: blr
 }
 
 define <8 x i32> @test_l_p8v8i32(<8 x i32>* %p) #2 {
+; CHECK-LABEL: test_l_p8v8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    lxvw4x 34, 0, 3
+; CHECK-NEXT:    lxvw4x 35, 3, 4
+; CHECK-NEXT:    blr
 entry:
   %r = load <8 x i32>, <8 x i32>* %p, align 4
   ret <8 x i32> %r
 
-; CHECK-LABEL: @test_l_p8v8i32
-; CHECK-DAG: li [[REG1:[0-9]+]], 16
-; CHECK-DAG: lxvw4x 34, 0, 3
-; CHECK-DAG: lxvw4x 35, 3, [[REG1]]
-; CHECK: blr
 }
 
 define <2 x i64> @test_l_p8v2i64(<2 x i64>* %p) #2 {
+; CHECK-LABEL: test_l_p8v2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    lxvd2x 34, 0, 3
+; CHECK-NEXT:    blr
 entry:
   %r = load <2 x i64>, <2 x i64>* %p, align 8
   ret <2 x i64> %r
 
-; CHECK-LABEL: @test_l_p8v2i64
-; CHECK: lxvd2x 34, 0, 3
-; CHECK: blr
 }
 
 define <4 x i64> @test_l_p8v4i64(<4 x i64>* %p) #2 {
+; CHECK-LABEL: test_l_p8v4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    lxvd2x 34, 0, 3
+; CHECK-NEXT:    lxvd2x 35, 3, 4
+; CHECK-NEXT:    blr
 entry:
   %r = load <4 x i64>, <4 x i64>* %p, align 8
   ret <4 x i64> %r
 
-; CHECK-LABEL: @test_l_p8v4i64
-; CHECK-DAG: li [[REG1:[0-9]+]], 16
-; CHECK-DAG: lxvd2x 34, 0, 3
-; CHECK-DAG: lxvd2x 35, 3, [[REG1]]
-; CHECK: blr
 }
 
 define <4 x float> @test_l_p8v4float(<4 x float>* %p) #2 {
+; CHECK-LABEL: test_l_p8v4float:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    lxvw4x 34, 0, 3
+; CHECK-NEXT:    blr
 entry:
   %r = load <4 x float>, <4 x float>* %p, align 4
   ret <4 x float> %r
 
-; CHECK-LABEL: @test_l_p8v4float
-; CHECK: lxvw4x 34, 0, 3
-; CHECK: blr
 }
 
 define <8 x float> @test_l_p8v8float(<8 x float>* %p) #2 {
+; CHECK-LABEL: test_l_p8v8float:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    lxvw4x 34, 0, 3
+; CHECK-NEXT:    lxvw4x 35, 3, 4
+; CHECK-NEXT:    blr
 entry:
   %r = load <8 x float>, <8 x float>* %p, align 4
   ret <8 x float> %r
 
-; CHECK-LABEL: @test_l_p8v8float
-; CHECK-DAG: li [[REG1:[0-9]+]], 16
-; CHECK-DAG: lxvw4x 34, 0, 3
-; CHECK-DAG: lxvw4x 35, 3, [[REG1]]
-; CHECK: blr
 }
 
 define <2 x double> @test_l_p8v2double(<2 x double>* %p) #2 {
+; CHECK-LABEL: test_l_p8v2double:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    lxvd2x 34, 0, 3
+; CHECK-NEXT:    blr
 entry:
   %r = load <2 x double>, <2 x double>* %p, align 8
   ret <2 x double> %r
 
-; CHECK-LABEL: @test_l_p8v2double
-; CHECK: lxvd2x 34, 0, 3
-; CHECK: blr
 }
 
 define <4 x double> @test_l_p8v4double(<4 x double>* %p) #2 {
+; CHECK-LABEL: test_l_p8v4double:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    lxvd2x 34, 0, 3
+; CHECK-NEXT:    lxvd2x 35, 3, 4
+; CHECK-NEXT:    blr
 entry:
   %r = load <4 x double>, <4 x double>* %p, align 8
   ret <4 x double> %r
 
-; CHECK-LABEL: @test_l_p8v4double
-; CHECK-DAG: li [[REG1:[0-9]+]], 16
-; CHECK-DAG: lxvd2x 34, 0, 3
-; CHECK-DAG: lxvd2x 35, 3, [[REG1]]
-; CHECK: blr
 }
 
 define <4 x float> @test_l_qv4float(<4 x float>* %p) #1 {
+; CHECK-LABEL: test_l_qv4float:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 15
+; CHECK-NEXT:    qvlpclsx 0, 0, 3
+; CHECK-NEXT:    qvlfsx 1, 3, 4
+; CHECK-NEXT:    qvlfsx 2, 0, 3
+; CHECK-NEXT:    qvfperm 1, 2, 1, 0
+; CHECK-NEXT:    blr
 entry:
   %r = load <4 x float>, <4 x float>* %p, align 4
   ret <4 x float> %r
 
-; CHECK-LABEL: @test_l_qv4float
-; CHECK-DAG: li [[REG1:[0-9]+]], 15
-; CHECK-DAG: qvlpclsx 0, 0, 3
-; CHECK-DAG: qvlfsx [[REG2:[0-9]+]], 3, [[REG1]]
-; CHECK-DAG: qvlfsx [[REG3:[0-9]+]], 0, 3
-; CHECK: qvfperm 1, [[REG3]], [[REG2]], 0
-; CHECK: blr
 }
 
 define <8 x float> @test_l_qv8float(<8 x float>* %p) #1 {
+; CHECK-LABEL: test_l_qv8float:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 31
+; CHECK-NEXT:    qvlpclsx 1, 0, 3
+; CHECK-NEXT:    qvlfsx 0, 3, 4
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    qvlfsx 3, 3, 4
+; CHECK-NEXT:    qvlfsx 4, 0, 3
+; CHECK-NEXT:    qvfperm 2, 3, 0, 1
+; CHECK-NEXT:    qvfperm 1, 4, 3, 1
+; CHECK-NEXT:    blr
 entry:
   %r = load <8 x float>, <8 x float>* %p, align 4
   ret <8 x float> %r
 
-; CHECK-LABEL: @test_l_qv8float
-; CHECK-DAG: li [[REG1:[0-9]+]], 31
-; CHECK-DAG: li [[REG2:[0-9]+]], 16
-; CHECK-DAG: qvlfsx [[REG3:[0-9]+]], 3, [[REG1]]
-; CHECK-DAG: qvlfsx [[REG4:[0-9]+]], 3, [[REG2]]
-; CHECK-DAG: qvlpclsx [[REG5:[0-5]+]], 0, 3
-; CHECK-DAG: qvlfsx [[REG6:[0-9]+]], 0, 3
-; CHECK-DAG: qvfperm 2, {{[0-9]+}}, {{[0-9]+}}, [[REG5]]
-; CHECK-DAG: qvfperm 1, {{[0-9]+}}, {{[0-9]+}}, [[REG5]]
-; CHECK: blr
 }
 
 define <4 x double> @test_l_qv4double(<4 x double>* %p) #1 {
+; CHECK-LABEL: test_l_qv4double:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 31
+; CHECK-NEXT:    qvlpcldx 0, 0, 3
+; CHECK-NEXT:    qvlfdx 1, 3, 4
+; CHECK-NEXT:    qvlfdx 2, 0, 3
+; CHECK-NEXT:    qvfperm 1, 2, 1, 0
+; CHECK-NEXT:    blr
 entry:
   %r = load <4 x double>, <4 x double>* %p, align 8
   ret <4 x double> %r
 
-; CHECK-LABEL: @test_l_qv4double
-; CHECK-DAG: li [[REG1:[0-9]+]], 31
-; CHECK-DAG: qvlpcldx 0, 0, 3
-; CHECK-DAG: qvlfdx [[REG2:[0-9]+]], 3, [[REG1]]
-; CHECK-DAG: qvlfdx [[REG3:[0-9]+]], 0, 3
-; CHECK: qvfperm 1, [[REG3]], [[REG2]], 0
-; CHECK: blr
 }
 
 define <8 x double> @test_l_qv8double(<8 x double>* %p) #1 {
+; CHECK-LABEL: test_l_qv8double:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 63
+; CHECK-NEXT:    qvlpcldx 1, 0, 3
+; CHECK-NEXT:    qvlfdx 0, 3, 4
+; CHECK-NEXT:    li 4, 32
+; CHECK-NEXT:    qvlfdx 3, 3, 4
+; CHECK-NEXT:    qvlfdx 4, 0, 3
+; CHECK-NEXT:    qvfperm 2, 3, 0, 1
+; CHECK-NEXT:    qvfperm 1, 4, 3, 1
+; CHECK-NEXT:    blr
 entry:
   %r = load <8 x double>, <8 x double>* %p, align 8
   ret <8 x double> %r
 
-; CHECK-LABEL: @test_l_qv8double
-; CHECK-DAG: li [[REG1:[0-9]+]], 63
-; CHECK-DAG: li [[REG2:[0-9]+]], 32
-; CHECK-DAG: qvlfdx [[REG3:[0-9]+]], 3, [[REG1]]
-; CHECK-DAG: qvlfdx [[REG4:[0-9]+]], 3, [[REG2]]
-; CHECK-DAG: qvlpcldx [[REG5:[0-5]+]], 0, 3
-; CHECK-DAG: qvlfdx [[REG6:[0-9]+]], 0, 3
-; CHECK-DAG: qvfperm 2, {{[0-9]+}}, {{[0-9]+}}, [[REG5]]
-; CHECK-DAG: qvfperm 1, {{[0-9]+}}, {{[0-9]+}}, [[REG5]]
-; CHECK: blr
 }
 
 define void @test_s_v16i8(<16 x i8>* %p, <16 x i8> %v) #0 {
+; CHECK-LABEL: test_s_v16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    stxvw4x 34, 0, 3
+; CHECK-NEXT:    blr
 entry:
   store <16 x i8> %v, <16 x i8>* %p, align 1
   ret void
 
-; CHECK-LABEL: @test_s_v16i8
-; CHECK: stxvw4x 34, 0, 3
-; CHECK: blr
 }
 
 define void @test_s_v32i8(<32 x i8>* %p, <32 x i8> %v) #0 {
+; CHECK-LABEL: test_s_v32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    stxvw4x 34, 0, 3
+; CHECK-NEXT:    stxvw4x 35, 3, 4
+; CHECK-NEXT:    blr
 entry:
   store <32 x i8> %v, <32 x i8>* %p, align 1
   ret void
 
-; CHECK-LABEL: @test_s_v32i8
-; CHECK-DAG: li [[REG1:[0-9]+]], 16
-; CHECK-DAG: stxvw4x 35, 3, [[REG1]]
-; CHECK-DAG: stxvw4x 34, 0, 3
-; CHECK: blr
 }
 
 define void @test_s_v8i16(<8 x i16>* %p, <8 x i16> %v) #0 {
+; CHECK-LABEL: test_s_v8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    stxvw4x 34, 0, 3
+; CHECK-NEXT:    blr
 entry:
   store <8 x i16> %v, <8 x i16>* %p, align 2
   ret void
 
-; CHECK-LABEL: @test_s_v8i16
-; CHECK: stxvw4x 34, 0, 3
-; CHECK: blr
 }
 
 define void @test_s_v16i16(<16 x i16>* %p, <16 x i16> %v) #0 {
+; CHECK-LABEL: test_s_v16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    stxvw4x 34, 0, 3
+; CHECK-NEXT:    stxvw4x 35, 3, 4
+; CHECK-NEXT:    blr
 entry:
   store <16 x i16> %v, <16 x i16>* %p, align 2
   ret void
 
-; CHECK-LABEL: @test_s_v16i16
-; CHECK-DAG: li [[REG1:[0-9]+]], 16
-; CHECK-DAG: stxvw4x 35, 3, [[REG1]]
-; CHECK-DAG: stxvw4x 34, 0, 3
-; CHECK: blr
 }
 
 define void @test_s_v4i32(<4 x i32>* %p, <4 x i32> %v) #0 {
+; CHECK-LABEL: test_s_v4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    stxvw4x 34, 0, 3
+; CHECK-NEXT:    blr
 entry:
   store <4 x i32> %v, <4 x i32>* %p, align 4
   ret void
 
-; CHECK-LABEL: @test_s_v4i32
-; CHECK: stxvw4x 34, 0, 3
-; CHECK: blr
 }
 
 define void @test_s_v8i32(<8 x i32>* %p, <8 x i32> %v) #0 {
+; CHECK-LABEL: test_s_v8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    stxvw4x 34, 0, 3
+; CHECK-NEXT:    stxvw4x 35, 3, 4
+; CHECK-NEXT:    blr
 entry:
   store <8 x i32> %v, <8 x i32>* %p, align 4
   ret void
 
-; CHECK-LABEL: @test_s_v8i32
-; CHECK-DAG: li [[REG1:[0-9]+]], 16
-; CHECK-DAG: stxvw4x 35, 3, [[REG1]]
-; CHECK-DAG: stxvw4x 34, 0, 3
-; CHECK: blr
 }
 
 define void @test_s_v2i64(<2 x i64>* %p, <2 x i64> %v) #0 {
+; CHECK-LABEL: test_s_v2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    stxvd2x 34, 0, 3
+; CHECK-NEXT:    blr
 entry:
   store <2 x i64> %v, <2 x i64>* %p, align 8
   ret void
 
-; CHECK-LABEL: @test_s_v2i64
-; CHECK: stxvd2x 34, 0, 3
-; CHECK: blr
 }
 
 define void @test_s_v4i64(<4 x i64>* %p, <4 x i64> %v) #0 {
+; CHECK-LABEL: test_s_v4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    stxvd2x 34, 0, 3
+; CHECK-NEXT:    stxvd2x 35, 3, 4
+; CHECK-NEXT:    blr
 entry:
   store <4 x i64> %v, <4 x i64>* %p, align 8
   ret void
 
-; CHECK-LABEL: @test_s_v4i64
-; CHECK-DAG: li [[REG1:[0-9]+]], 16
-; CHECK-DAG: stxvd2x 35, 3, [[REG1]]
-; CHECK-DAG: stxvd2x 34, 0, 3
-; CHECK: blr
 }
 
 define void @test_s_v4float(<4 x float>* %p, <4 x float> %v) #0 {
+; CHECK-LABEL: test_s_v4float:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    stxvw4x 34, 0, 3
+; CHECK-NEXT:    blr
 entry:
   store <4 x float> %v, <4 x float>* %p, align 4
   ret void
 
-; CHECK-LABEL: @test_s_v4float
-; CHECK: stxvw4x 34, 0, 3
-; CHECK: blr
 }
 
 define void @test_s_v8float(<8 x float>* %p, <8 x float> %v) #0 {
+; CHECK-LABEL: test_s_v8float:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    stxvw4x 34, 0, 3
+; CHECK-NEXT:    stxvw4x 35, 3, 4
+; CHECK-NEXT:    blr
 entry:
   store <8 x float> %v, <8 x float>* %p, align 4
   ret void
 
-; CHECK-LABEL: @test_s_v8float
-; CHECK-DAG: li [[REG1:[0-9]+]], 16
-; CHECK-DAG: stxvw4x 35, 3, [[REG1]]
-; CHECK-DAG: stxvw4x 34, 0, 3
-; CHECK: blr
 }
 
 define void @test_s_v2double(<2 x double>* %p, <2 x double> %v) #0 {
+; CHECK-LABEL: test_s_v2double:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    stxvd2x 34, 0, 3
+; CHECK-NEXT:    blr
 entry:
   store <2 x double> %v, <2 x double>* %p, align 8
   ret void
 
-; CHECK-LABEL: @test_s_v2double
-; CHECK: stxvd2x 34, 0, 3
-; CHECK: blr
 }
 
 define void @test_s_v4double(<4 x double>* %p, <4 x double> %v) #0 {
+; CHECK-LABEL: test_s_v4double:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    li 4, 16
+; CHECK-NEXT:    stxvd2x 34, 0, 3
+; CHECK-NEXT:    stxvd2x 35, 3, 4
+; CHECK-NEXT:    blr
 entry:
   store <4 x double> %v, <4 x double>* %p, align 8
   ret void
 
-; CHECK-LABEL: @test_s_v4double
-; CHECK-DAG: li [[REG1:[0-9]+]], 16
-; CHECK-DAG: stxvd2x 35, 3, [[REG1]]
-; CHECK-DAG: stxvd2x 34, 0, 3
-; CHECK: blr
 }
 
 define void @test_s_qv4float(<4 x float>* %p, <4 x float> %v) #1 {
+; CHECK-LABEL: test_s_qv4float:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    qvesplati 0, 1, 3
+; CHECK-NEXT:    stfs 1, 0(3)
+; CHECK-NEXT:    stfs 0, 12(3)
+; CHECK-NEXT:    qvesplati 0, 1, 2
+; CHECK-NEXT:    qvesplati 1, 1, 1
+; CHECK-NEXT:    stfs 0, 8(3)
+; CHECK-NEXT:    stfs 1, 4(3)
+; CHECK-NEXT:    blr
 entry:
   store <4 x float> %v, <4 x float>* %p, align 4
   ret void
 
-; CHECK-LABEL: @test_s_qv4float
-; CHECK-DAG: qvesplati [[REG1:[0-9]+]], 1, 3
-; CHECK-DAG: qvesplati [[REG2:[0-9]+]], 1, 2
-; CHECK-DAG: qvesplati [[REG3:[0-9]+]], 1, 1
-; CHECK-DAG: stfs 1, 0(3)
-; CHECK-DAG: stfs [[REG1]], 12(3)
-; CHECK-DAG: stfs [[REG2]], 8(3)
-; CHECK-DAG: stfs [[REG3]], 4(3)
-; CHECK: blr
 }
 
 define void @test_s_qv8float(<8 x float>* %p, <8 x float> %v) #1 {
+; CHECK-LABEL: test_s_qv8float:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    qvesplati 0, 2, 3
+; CHECK-NEXT:    stfs 2, 16(3)
+; CHECK-NEXT:    stfs 0, 28(3)
+; CHECK-NEXT:    qvesplati 0, 2, 2
+; CHECK-NEXT:    qvesplati 2, 2, 1
+; CHECK-NEXT:    stfs 1, 0(3)
+; CHECK-NEXT:    stfs 0, 24(3)
+; CHECK-NEXT:    qvesplati 0, 1, 3
+; CHECK-NEXT:    stfs 2, 20(3)
+; CHECK-NEXT:    qvesplati 2, 1, 2
+; CHECK-NEXT:    qvesplati 1, 1, 1
+; CHECK-NEXT:    stfs 0, 12(3)
+; CHECK-NEXT:    stfs 2, 8(3)
+; CHECK-NEXT:    stfs 1, 4(3)
+; CHECK-NEXT:    blr
 entry:
   store <8 x float> %v, <8 x float>* %p, align 4
   ret void
 
-; CHECK-LABEL: @test_s_qv8float
-; CHECK-DAG: qvesplati [[REG1:[0-9]+]], 2, 3
-; CHECK-DAG: qvesplati [[REG2:[0-9]+]], 2, 2
-; CHECK-DAG: qvesplati [[REG3:[0-9]+]], 2, 1
-; CHECK-DAG: qvesplati [[REG4:[0-9]+]], 1, 3
-; CHECK-DAG: qvesplati [[REG5:[0-9]+]], 1, 2
-; CHECK-DAG: qvesplati [[REG6:[0-9]+]], 1, 1
-; CHECK-DAG: stfs 2, 16(3)
-; CHECK-DAG: stfs 1, 0(3)
-; CHECK-DAG: stfs [[REG1]], 28(3)
-; CHECK-DAG: stfs [[REG2]], 24(3)
-; CHECK-DAG: stfs [[REG3]], 20(3)
-; CHECK-DAG: stfs [[REG4]], 12(3)
-; CHECK-DAG: stfs [[REG5]], 8(3)
-; CHECK-DAG: stfs [[REG6]], 4(3)
-; CHECK: blr
 }
 
 define void @test_s_qv4double(<4 x double>* %p, <4 x double> %v) #1 {
+; CHECK-LABEL: test_s_qv4double:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    qvesplati 0, 1, 3
+; CHECK-NEXT:    stfd 1, 0(3)
+; CHECK-NEXT:    stfd 0, 24(3)
+; CHECK-NEXT:    qvesplati 0, 1, 2
+; CHECK-NEXT:    qvesplati 1, 1, 1
+; CHECK-NEXT:    stfd 0, 16(3)
+; CHECK-NEXT:    stfd 1, 8(3)
+; CHECK-NEXT:    blr
 entry:
   store <4 x double> %v, <4 x double>* %p, align 8
   ret void
 
-; CHECK-LABEL: @test_s_qv4double
-; CHECK-DAG: qvesplati [[REG1:[0-9]+]], 1, 3
-; CHECK-DAG: qvesplati [[REG2:[0-9]+]], 1, 2
-; CHECK-DAG: qvesplati [[REG3:[0-9]+]], 1, 1
-; CHECK-DAG: stfd 1, 0(3)
-; CHECK-DAG: stfd [[REG1]], 24(3)
-; CHECK-DAG: stfd [[REG2]], 16(3)
-; CHECK-DAG: stfd [[REG3]], 8(3)
-; CHECK: blr
 }
 
 define void @test_s_qv8double(<8 x double>* %p, <8 x double> %v) #1 {
+; CHECK-LABEL: test_s_qv8double:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    qvesplati 0, 2, 3
+; CHECK-NEXT:    stfd 2, 32(3)
+; CHECK-NEXT:    stfd 0, 56(3)
+; CHECK-NEXT:    qvesplati 0, 2, 2
+; CHECK-NEXT:    qvesplati 2, 2, 1
+; CHECK-NEXT:    stfd 1, 0(3)
+; CHECK-NEXT:    stfd 0, 48(3)
+; CHECK-NEXT:    qvesplati 0, 1, 3
+; CHECK-NEXT:    stfd 2, 40(3)
+; CHECK-NEXT:    qvesplati 2, 1, 2
+; CHECK-NEXT:    qvesplati 1, 1, 1
+; CHECK-NEXT:    stfd 0, 24(3)
+; CHECK-NEXT:    stfd 2, 16(3)
+; CHECK-NEXT:    stfd 1, 8(3)
+; CHECK-NEXT:    blr
 entry:
   store <8 x double> %v, <8 x double>* %p, align 8
   ret void
 
-; CHECK-LABEL: @test_s_qv8double
-; CHECK-DAG: qvesplati [[REG1:[0-9]+]], 2, 3
-; CHECK-DAG: qvesplati [[REG2:[0-9]+]], 2, 2
-; CHECK-DAG: qvesplati [[REG3:[0-9]+]], 2, 1
-; CHECK-DAG: qvesplati [[REG4:[0-9]+]], 1, 3
-; CHECK-DAG: qvesplati [[REG5:[0-9]+]], 1, 2
-; CHECK-DAG: qvesplati [[REG6:[0-9]+]], 1, 1
-; CHECK-DAG: stfd 2, 32(3)
-; CHECK-DAG: stfd 1, 0(3)
-; CHECK-DAG: stfd [[REG1]], 56(3)
-; CHECK-DAG: stfd [[REG2]], 48(3)
-; CHECK-DAG: stfd [[REG3]], 40(3)
-; CHECK-DAG: stfd [[REG4]], 24(3)
-; CHECK-DAG: stfd [[REG5]], 16(3)
-; CHECK-DAG: stfd [[REG6]], 8(3)
-; CHECK: blr
 }
 
 attributes #0 = { nounwind "target-cpu"="pwr7" }
-- 
2.40.0