Revert r368339 "[MBP] Disable aggressive loop rotate in plain mode"

It caused assertions to fire when building Chromium:

  lib/CodeGen/LiveDebugValues.cpp:331: bool
  {anonymous}::LiveDebugValues::OpenRangesSet::empty() const: Assertion
  `Vars.empty() == VarLocs.empty() && "open ranges are inconsistent"' failed.

See https://crbug.com/992871#c3 for how to reproduce.

> Patch https://reviews.llvm.org/D43256 introduced more aggressive loop layout optimization which depends on profile information. If profile information is not available, the statically estimated profile information(generated by BranchProbabilityInfo.cpp) is used. If user program doesn't behave as BranchProbabilityInfo.cpp expected, the layout may be worse.
>
> To be conservative this patch restores the original layout algorithm in plain mode. But user can still try the aggressive layout optimization with -force-precise-rotation-cost=true.
>
> Differential Revision: https://reviews.llvm.org/D65673

llvm-svn: 368579

5 files changed, 173 insertions, 197 deletions

diff --git a/llvm/test/CodeGen/PowerPC/atomics-regression.ll b/llvm/test/CodeGen/PowerPC/atomics-regression.ll
index 448f254aa88..7cfa4d2f6f0 100644
--- a/llvm/test/CodeGen/PowerPC/atomics-regression.ll
+++ b/llvm/test/CodeGen/PowerPC/atomics-regression.ll
@@ -401,16 +401,15 @@ define void @test40(i8* %ptr, i8 %cmp, i8 %val) {
 ; PPC64LE-LABEL: test40:
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    rlwinm 4, 4, 0, 24, 31
-; PPC64LE-NEXT:    b .LBB40_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB40_1:
-; PPC64LE-NEXT:    stbcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB40_2:
 ; PPC64LE-NEXT:    lbarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB40_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB40_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stbcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB40_1
+; PPC64LE-NEXT:  .LBB40_3:
 ; PPC64LE-NEXT:    stbcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i8* %ptr, i8 %cmp, i8 %val monotonic monotonic
@@ -466,16 +465,15 @@ define void @test43(i8* %ptr, i8 %cmp, i8 %val) {
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    rlwinm 4, 4, 0, 24, 31
 ; PPC64LE-NEXT:    lwsync
-; PPC64LE-NEXT:    b .LBB43_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB43_1:
-; PPC64LE-NEXT:    stbcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB43_2:
 ; PPC64LE-NEXT:    lbarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB43_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB43_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stbcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB43_1
+; PPC64LE-NEXT:  .LBB43_3:
 ; PPC64LE-NEXT:    stbcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i8* %ptr, i8 %cmp, i8 %val release monotonic
@@ -487,16 +485,15 @@ define void @test44(i8* %ptr, i8 %cmp, i8 %val) {
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    rlwinm 4, 4, 0, 24, 31
 ; PPC64LE-NEXT:    lwsync
-; PPC64LE-NEXT:    b .LBB44_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB44_1:
-; PPC64LE-NEXT:    stbcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB44_2:
 ; PPC64LE-NEXT:    lbarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB44_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB44_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stbcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB44_1
+; PPC64LE-NEXT:  .LBB44_3:
 ; PPC64LE-NEXT:    stbcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i8* %ptr, i8 %cmp, i8 %val release acquire
@@ -622,16 +619,15 @@ define void @test50(i16* %ptr, i16 %cmp, i16 %val) {
 ; PPC64LE-LABEL: test50:
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    rlwinm 4, 4, 0, 16, 31
-; PPC64LE-NEXT:    b .LBB50_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB50_1:
-; PPC64LE-NEXT:    sthcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB50_2:
 ; PPC64LE-NEXT:    lharx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB50_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB50_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    sthcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB50_1
+; PPC64LE-NEXT:  .LBB50_3:
 ; PPC64LE-NEXT:    sthcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i16* %ptr, i16 %cmp, i16 %val monotonic monotonic
@@ -687,16 +683,15 @@ define void @test53(i16* %ptr, i16 %cmp, i16 %val) {
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    rlwinm 4, 4, 0, 16, 31
 ; PPC64LE-NEXT:    lwsync
-; PPC64LE-NEXT:    b .LBB53_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB53_1:
-; PPC64LE-NEXT:    sthcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB53_2:
 ; PPC64LE-NEXT:    lharx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB53_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB53_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    sthcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB53_1
+; PPC64LE-NEXT:  .LBB53_3:
 ; PPC64LE-NEXT:    sthcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i16* %ptr, i16 %cmp, i16 %val release monotonic
@@ -708,16 +703,15 @@ define void @test54(i16* %ptr, i16 %cmp, i16 %val) {
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    rlwinm 4, 4, 0, 16, 31
 ; PPC64LE-NEXT:    lwsync
-; PPC64LE-NEXT:    b .LBB54_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB54_1:
-; PPC64LE-NEXT:    sthcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB54_2:
 ; PPC64LE-NEXT:    lharx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB54_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB54_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    sthcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB54_1
+; PPC64LE-NEXT:  .LBB54_3:
 ; PPC64LE-NEXT:    sthcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i16* %ptr, i16 %cmp, i16 %val release acquire
@@ -842,16 +836,15 @@ define void @test59(i16* %ptr, i16 %cmp, i16 %val) {
 define void @test60(i32* %ptr, i32 %cmp, i32 %val) {
 ; PPC64LE-LABEL: test60:
 ; PPC64LE:       # %bb.0:
-; PPC64LE-NEXT:    b .LBB60_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB60_1:
-; PPC64LE-NEXT:    stwcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB60_2:
 ; PPC64LE-NEXT:    lwarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB60_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB60_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stwcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB60_1
+; PPC64LE-NEXT:  .LBB60_3:
 ; PPC64LE-NEXT:    stwcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i32* %ptr, i32 %cmp, i32 %val monotonic monotonic
@@ -904,16 +897,15 @@ define void @test63(i32* %ptr, i32 %cmp, i32 %val) {
 ; PPC64LE-LABEL: test63:
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    lwsync
-; PPC64LE-NEXT:    b .LBB63_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB63_1:
-; PPC64LE-NEXT:    stwcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB63_2:
 ; PPC64LE-NEXT:    lwarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB63_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB63_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stwcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB63_1
+; PPC64LE-NEXT:  .LBB63_3:
 ; PPC64LE-NEXT:    stwcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i32* %ptr, i32 %cmp, i32 %val release monotonic
@@ -924,16 +916,15 @@ define void @test64(i32* %ptr, i32 %cmp, i32 %val) {
 ; PPC64LE-LABEL: test64:
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    lwsync
-; PPC64LE-NEXT:    b .LBB64_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB64_1:
-; PPC64LE-NEXT:    stwcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB64_2:
 ; PPC64LE-NEXT:    lwarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB64_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB64_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stwcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB64_1
+; PPC64LE-NEXT:  .LBB64_3:
 ; PPC64LE-NEXT:    stwcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i32* %ptr, i32 %cmp, i32 %val release acquire
@@ -1053,16 +1044,15 @@ define void @test69(i32* %ptr, i32 %cmp, i32 %val) {
 define void @test70(i64* %ptr, i64 %cmp, i64 %val) {
 ; PPC64LE-LABEL: test70:
 ; PPC64LE:       # %bb.0:
-; PPC64LE-NEXT:    b .LBB70_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB70_1:
-; PPC64LE-NEXT:    stdcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB70_2:
 ; PPC64LE-NEXT:    ldarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpd 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB70_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB70_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stdcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB70_1
+; PPC64LE-NEXT:  .LBB70_3:
 ; PPC64LE-NEXT:    stdcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i64* %ptr, i64 %cmp, i64 %val monotonic monotonic
@@ -1115,16 +1105,15 @@ define void @test73(i64* %ptr, i64 %cmp, i64 %val) {
 ; PPC64LE-LABEL: test73:
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    lwsync
-; PPC64LE-NEXT:    b .LBB73_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB73_1:
-; PPC64LE-NEXT:    stdcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB73_2:
 ; PPC64LE-NEXT:    ldarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpd 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB73_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB73_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stdcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB73_1
+; PPC64LE-NEXT:  .LBB73_3:
 ; PPC64LE-NEXT:    stdcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i64* %ptr, i64 %cmp, i64 %val release monotonic
@@ -1135,16 +1124,15 @@ define void @test74(i64* %ptr, i64 %cmp, i64 %val) {
 ; PPC64LE-LABEL: test74:
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    lwsync
-; PPC64LE-NEXT:    b .LBB74_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB74_1:
-; PPC64LE-NEXT:    stdcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB74_2:
 ; PPC64LE-NEXT:    ldarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpd 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB74_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB74_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stdcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB74_1
+; PPC64LE-NEXT:  .LBB74_3:
 ; PPC64LE-NEXT:    stdcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i64* %ptr, i64 %cmp, i64 %val release acquire
@@ -1265,16 +1253,15 @@ define void @test80(i8* %ptr, i8 %cmp, i8 %val) {
 ; PPC64LE-LABEL: test80:
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    rlwinm 4, 4, 0, 24, 31
-; PPC64LE-NEXT:    b .LBB80_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB80_1:
-; PPC64LE-NEXT:    stbcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB80_2:
 ; PPC64LE-NEXT:    lbarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB80_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB80_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stbcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB80_1
+; PPC64LE-NEXT:  .LBB80_3:
 ; PPC64LE-NEXT:    stbcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i8* %ptr, i8 %cmp, i8 %val syncscope("singlethread") monotonic monotonic
@@ -1330,16 +1317,15 @@ define void @test83(i8* %ptr, i8 %cmp, i8 %val) {
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    rlwinm 4, 4, 0, 24, 31
 ; PPC64LE-NEXT:    lwsync
-; PPC64LE-NEXT:    b .LBB83_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB83_1:
-; PPC64LE-NEXT:    stbcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB83_2:
 ; PPC64LE-NEXT:    lbarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB83_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB83_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stbcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB83_1
+; PPC64LE-NEXT:  .LBB83_3:
 ; PPC64LE-NEXT:    stbcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i8* %ptr, i8 %cmp, i8 %val syncscope("singlethread") release monotonic
@@ -1351,16 +1337,15 @@ define void @test84(i8* %ptr, i8 %cmp, i8 %val) {
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    rlwinm 4, 4, 0, 24, 31
 ; PPC64LE-NEXT:    lwsync
-; PPC64LE-NEXT:    b .LBB84_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB84_1:
-; PPC64LE-NEXT:    stbcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB84_2:
 ; PPC64LE-NEXT:    lbarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB84_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB84_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stbcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB84_1
+; PPC64LE-NEXT:  .LBB84_3:
 ; PPC64LE-NEXT:    stbcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i8* %ptr, i8 %cmp, i8 %val syncscope("singlethread") release acquire
@@ -1486,16 +1471,15 @@ define void @test90(i16* %ptr, i16 %cmp, i16 %val) {
 ; PPC64LE-LABEL: test90:
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    rlwinm 4, 4, 0, 16, 31
-; PPC64LE-NEXT:    b .LBB90_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB90_1:
-; PPC64LE-NEXT:    sthcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB90_2:
 ; PPC64LE-NEXT:    lharx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB90_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB90_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    sthcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b 
+; PPC64LE-NEXT:  .LBB90_3:
 ; PPC64LE-NEXT:    sthcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i16* %ptr, i16 %cmp, i16 %val syncscope("singlethread") monotonic monotonic
@@ -1551,16 +1535,15 @@ define void @test93(i16* %ptr, i16 %cmp, i16 %val) {
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    rlwinm 4, 4, 0, 16, 31
 ; PPC64LE-NEXT:    lwsync
-; PPC64LE-NEXT:    b .LBB93_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB93_1:
-; PPC64LE-NEXT:    sthcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB93_2:
 ; PPC64LE-NEXT:    lharx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB93_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB93_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    sthcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB93_1
+; PPC64LE-NEXT:  .LBB93_3:
 ; PPC64LE-NEXT:    sthcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i16* %ptr, i16 %cmp, i16 %val syncscope("singlethread") release monotonic
@@ -1572,16 +1555,15 @@ define void @test94(i16* %ptr, i16 %cmp, i16 %val) {
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    rlwinm 4, 4, 0, 16, 31
 ; PPC64LE-NEXT:    lwsync
-; PPC64LE-NEXT:    b .LBB94_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB94_1:
-; PPC64LE-NEXT:    sthcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB94_2:
 ; PPC64LE-NEXT:    lharx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB94_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB94_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    sthcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB94_1
+; PPC64LE-NEXT:  .LBB94_3:
 ; PPC64LE-NEXT:    sthcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i16* %ptr, i16 %cmp, i16 %val syncscope("singlethread") release acquire
@@ -1706,16 +1688,15 @@ define void @test99(i16* %ptr, i16 %cmp, i16 %val) {
 define void @test100(i32* %ptr, i32 %cmp, i32 %val) {
 ; PPC64LE-LABEL: test100:
 ; PPC64LE:       # %bb.0:
-; PPC64LE-NEXT:    b .LBB100_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB100_1:
-; PPC64LE-NEXT:    stwcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB100_2:
 ; PPC64LE-NEXT:    lwarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB100_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB100_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stwcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB100_1
+; PPC64LE-NEXT:  .LBB100_3:
 ; PPC64LE-NEXT:    stwcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i32* %ptr, i32 %cmp, i32 %val syncscope("singlethread") monotonic monotonic
@@ -1768,16 +1749,15 @@ define void @test103(i32* %ptr, i32 %cmp, i32 %val) {
 ; PPC64LE-LABEL: test103:
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    lwsync
-; PPC64LE-NEXT:    b .LBB103_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB103_1:
-; PPC64LE-NEXT:    stwcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB103_2:
 ; PPC64LE-NEXT:    lwarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB103_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB103_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stwcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB103_1
+; PPC64LE-NEXT:  .LBB103_3:
 ; PPC64LE-NEXT:    stwcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i32* %ptr, i32 %cmp, i32 %val syncscope("singlethread") release monotonic
@@ -1788,16 +1768,15 @@ define void @test104(i32* %ptr, i32 %cmp, i32 %val) {
 ; PPC64LE-LABEL: test104:
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    lwsync
-; PPC64LE-NEXT:    b .LBB104_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB104_1:
-; PPC64LE-NEXT:    stwcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB104_2:
 ; PPC64LE-NEXT:    lwarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpw 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB104_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB104_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stwcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB104_1
+; PPC64LE-NEXT:  .LBB104_3:
 ; PPC64LE-NEXT:    stwcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i32* %ptr, i32 %cmp, i32 %val syncscope("singlethread") release acquire
@@ -1917,16 +1896,15 @@ define void @test109(i32* %ptr, i32 %cmp, i32 %val) {
 define void @test110(i64* %ptr, i64 %cmp, i64 %val) {
 ; PPC64LE-LABEL: test110:
 ; PPC64LE:       # %bb.0:
-; PPC64LE-NEXT:    b .LBB110_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB110_1:
-; PPC64LE-NEXT:    stdcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB110_2:
 ; PPC64LE-NEXT:    ldarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpd 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB110_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB110_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stdcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB110_1
+; PPC64LE-NEXT:  .LBB110_3:
 ; PPC64LE-NEXT:    stdcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i64* %ptr, i64 %cmp, i64 %val syncscope("singlethread") monotonic monotonic
@@ -1979,16 +1957,15 @@ define void @test113(i64* %ptr, i64 %cmp, i64 %val) {
 ; PPC64LE-LABEL: test113:
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    lwsync
-; PPC64LE-NEXT:    b .LBB113_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB113_1:
-; PPC64LE-NEXT:    stdcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB113_2:
 ; PPC64LE-NEXT:    ldarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpd 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB113_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB113_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stdcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB113_1
+; PPC64LE-NEXT:  .LBB113_3:
 ; PPC64LE-NEXT:    stdcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i64* %ptr, i64 %cmp, i64 %val syncscope("singlethread") release monotonic
@@ -1999,16 +1976,15 @@ define void @test114(i64* %ptr, i64 %cmp, i64 %val) {
 ; PPC64LE-LABEL: test114:
 ; PPC64LE:       # %bb.0:
 ; PPC64LE-NEXT:    lwsync
-; PPC64LE-NEXT:    b .LBB114_2
-; PPC64LE-NEXT:    .p2align 5
 ; PPC64LE-NEXT:  .LBB114_1:
-; PPC64LE-NEXT:    stdcx. 5, 0, 3
-; PPC64LE-NEXT:    beqlr 0
-; PPC64LE-NEXT:  .LBB114_2:
 ; PPC64LE-NEXT:    ldarx 6, 0, 3
 ; PPC64LE-NEXT:    cmpd 4, 6
-; PPC64LE-NEXT:    beq 0, .LBB114_1
-; PPC64LE-NEXT:  # %bb.3:
+; PPC64LE-NEXT:    bne 0, .LBB114_3
+; PPC64LE-NEXT:  # %bb.2:
+; PPC64LE-NEXT:    stdcx. 5, 0, 3
+; PPC64LE-NEXT:    beqlr 0
+; PPC64LE-NEXT:    b .LBB114_1
+; PPC64LE-NEXT:  .LBB114_3:
 ; PPC64LE-NEXT:    stdcx. 6, 0, 3
 ; PPC64LE-NEXT:    blr
   %res = cmpxchg i64* %ptr, i64 %cmp, i64 %val syncscope("singlethread") release acquire
diff --git a/llvm/test/CodeGen/PowerPC/block-placement-1.mir b/llvm/test/CodeGen/PowerPC/block-placement-1.mir
index e756ba3aa46..01967e46da9 100644
--- a/llvm/test/CodeGen/PowerPC/block-placement-1.mir
+++ b/llvm/test/CodeGen/PowerPC/block-placement-1.mir
@@ -298,14 +298,14 @@ body:             |
   
   bb.11.unreachable:
 
+  ; CHECK:      bb.1.for.body:
+  ; CHECK:        successors: %bb.2(0x7ffff800), %bb.3(0x00000800)
+  ; CHECK:        B %bb.2
+
   ; CHECK:      bb.4.catch4:
   ; CHECK:        successors: %bb.11(0x7ffff800), %bb.6(0x00000800)
   ; CHECK:        B %bb.11
 
-  ; CHECK:      bb.1.for.body (align 4):
-  ; CHECK:        successors: %bb.2(0x7ffff800), %bb.3(0x00000800)
-  ; CHECK:        B %bb.2
-
   ; CHECK:      bb.2..noexc:
 
   ; CHECK:      bb.11.unreachable: 
diff --git a/llvm/test/CodeGen/PowerPC/cmp_elimination.ll b/llvm/test/CodeGen/PowerPC/cmp_elimination.ll
index 6bc8b8a041c..95fcb1796c8 100644
--- a/llvm/test/CodeGen/PowerPC/cmp_elimination.ll
+++ b/llvm/test/CodeGen/PowerPC/cmp_elimination.ll
@@ -718,13 +718,14 @@ if.end:
 define void @func28(i32 signext %a) {
 ; CHECK-LABEL: @func28
 ; CHECK: cmplwi	 [[REG1:[0-9]+]], [[REG2:[0-9]+]]
-; CHECK: .[[LABEL1:[A-Z0-9_]+]]:
+; CHECK: .[[LABEL2:[A-Z0-9_]+]]:
+; CHECK: cmpwi   [[REG1]], [[REG2]]
+; CHECK: ble     0, .[[LABEL1:[A-Z0-9_]+]]
 ; CHECK-NOT: cmp
-; CHECK: bne	 0, .[[LABEL2:[A-Z0-9_]+]]
+; CHECK: bne     0, .[[LABEL2]]
 ; CHECK: bl dummy1
-; CHECK: .[[LABEL2]]:
-; CHECK: cmpwi	 [[REG1]], [[REG2]]
-; CHECK: bgt	 0, .[[LABEL1]]
+; CHECK: b .[[LABEL2]]
+; CHECK: .[[LABEL1]]:
 ; CHECK: blr
 entry:
   br label %do.body
diff --git a/llvm/test/CodeGen/PowerPC/licm-remat.ll b/llvm/test/CodeGen/PowerPC/licm-remat.ll
index 045f7a4c07c..9fab26b6222 100644
--- a/llvm/test/CodeGen/PowerPC/licm-remat.ll
+++ b/llvm/test/CodeGen/PowerPC/licm-remat.ll
@@ -24,8 +24,7 @@ define linkonce_odr void @ZN6snappyDecompressor_(%"class.snappy::SnappyDecompres
 ; CHECK-DAG:   addi 25, 3, _ZN6snappy8internalL8wordmaskE@toc@l
 ; CHECK-DAG:   addis 5, 2, _ZN6snappy8internalL10char_tableE@toc@ha
 ; CHECK-DAG:   addi 24, 5, _ZN6snappy8internalL10char_tableE@toc@l
-; CHECK:       b .[[LABEL1:[A-Z0-9_]+]]
-; CHECK:       .[[LABEL1]]: # %for.cond
+; CHECK:       .LBB0_2: # %for.cond
 ; CHECK-NOT:   addis {{[0-9]+}}, 2, _ZN6snappy8internalL8wordmaskE@toc@ha
 ; CHECK-NOT:   addis {{[0-9]+}}, 2, _ZN6snappy8internalL10char_tableE@toc@ha
 ; CHECK:       bctrl
diff --git a/llvm/test/CodeGen/PowerPC/machine-pre.ll b/llvm/test/CodeGen/PowerPC/machine-pre.ll
index 2d7a5619c63..596c0a4624c 100644
--- a/llvm/test/CodeGen/PowerPC/machine-pre.ll
+++ b/llvm/test/CodeGen/PowerPC/machine-pre.ll
@@ -75,8 +75,19 @@ define dso_local signext i32 @foo(i32 signext %x, i32 signext %y) local_unnamed_
 ; CHECK-P9-NEXT:    lis r3, 21845
 ; CHECK-P9-NEXT:    add r28, r30, r29
 ; CHECK-P9-NEXT:    ori r27, r3, 21846
+; CHECK-P9-NEXT:    b .LBB1_4
 ; CHECK-P9-NEXT:    .p2align 4
-; CHECK-P9-NEXT:  .LBB1_1: # %while.cond
+; CHECK-P9-NEXT:  .LBB1_1: # %sw.bb3
+; CHECK-P9-NEXT:    #
+; CHECK-P9-NEXT:    mulli r3, r30, 23
+; CHECK-P9-NEXT:  .LBB1_2: # %sw.epilog
+; CHECK-P9-NEXT:    #
+; CHECK-P9-NEXT:    add r28, r3, r28
+; CHECK-P9-NEXT:  .LBB1_3: # %sw.epilog
+; CHECK-P9-NEXT:    #
+; CHECK-P9-NEXT:    cmpwi r28, 1025
+; CHECK-P9-NEXT:    bge cr0, .LBB1_7
+; CHECK-P9-NEXT:  .LBB1_4: # %while.cond
 ; CHECK-P9-NEXT:    #
 ; CHECK-P9-NEXT:    extsw r3, r29
 ; CHECK-P9-NEXT:    bl bar
@@ -95,27 +106,16 @@ define dso_local signext i32 @foo(i32 signext %x, i32 signext %y) local_unnamed_
 ; CHECK-P9-NEXT:    add r4, r4, r5
 ; CHECK-P9-NEXT:    subf r3, r4, r3
 ; CHECK-P9-NEXT:    cmplwi r3, 1
-; CHECK-P9-NEXT:    beq cr0, .LBB1_4
-; CHECK-P9-NEXT:  # %bb.2: # %while.cond
+; CHECK-P9-NEXT:    beq cr0, .LBB1_1
+; CHECK-P9-NEXT:  # %bb.5: # %while.cond
 ; CHECK-P9-NEXT:    #
 ; CHECK-P9-NEXT:    cmplwi r3, 0
-; CHECK-P9-NEXT:    bne cr0, .LBB1_6
-; CHECK-P9-NEXT:  # %bb.3: # %sw.bb
+; CHECK-P9-NEXT:    bne cr0, .LBB1_3
+; CHECK-P9-NEXT:  # %bb.6: # %sw.bb
 ; CHECK-P9-NEXT:    #
 ; CHECK-P9-NEXT:    mulli r3, r29, 13
-; CHECK-P9-NEXT:    b .LBB1_5
-; CHECK-P9-NEXT:    .p2align 4
-; CHECK-P9-NEXT:  .LBB1_4: # %sw.bb3
-; CHECK-P9-NEXT:    #   
-; CHECK-P9-NEXT:    mulli r3, r30, 23
-; CHECK-P9-NEXT:  .LBB1_5: # %sw.epilog
-; CHECK-P9-NEXT:    #   
-; CHECK-P9-NEXT:    add r28, r3, r28 
-; CHECK-P9-NEXT:  .LBB1_6: # %sw.epilog
-; CHECK-P9-NEXT:    #   
-; CHECK-P9-NEXT:    cmpwi r28, 1025
-; CHECK-P9-NEXT:    blt cr0, .LBB1_1
-; CHECK-P9-NEXT:  # %bb.7: # %while.end
+; CHECK-P9-NEXT:    b .LBB1_2
+; CHECK-P9-NEXT:  .LBB1_7: # %while.end
 ; CHECK-P9-NEXT:    lis r3, -13108
 ; CHECK-P9-NEXT:    ori r3, r3, 52429
 ; CHECK-P9-NEXT:    mullw r3, r28, r3