[llvm] c5d84d2 - GlobalISel/AArch64: don't optimize away redundant branches at -O0
Adrian Prantl via llvm-commits
llvm-commits at lists.llvm.org
Thu Jul 29 16:04:31 PDT 2021
Author: Adrian Prantl
Date: 2021-07-29T16:04:22-07:00
New Revision: c5d84d2eb35c1f0d3b08e1d1e95c1a22a28904d1
URL: https://github.com/llvm/llvm-project/commit/c5d84d2eb35c1f0d3b08e1d1e95c1a22a28904d1
DIFF: https://github.com/llvm/llvm-project/commit/c5d84d2eb35c1f0d3b08e1d1e95c1a22a28904d1.diff
LOG: GlobalISel/AArch64: don't optimize away redundant branches at -O0
This patch prevents GlobalISel from optimizing out redundant branch
instructions when compiling without optimizations.
The motivating example is code like the following common pattern in
Swift, where users expect to be able to set a breakpoint on the early
exit:
public func f(b: Bool) {
guard b else {
return // I would like to set a breakpoint here.
}
...
}
The patch modifies two places in GlobalISEL: The first one is in
IRTranslator.cpp where the removal of redundant branches is made
conditional on the optimization level. The second one is in
AArch64InstructionSelector.cpp where an -O0 *only* optimization is
being removed.
Disabling these optimizations increases code size at -O0 by
~8%. However, doing so improves debuggability, and debug builds are
the primary reason why developers compile without optimizations. We
thus concluded that this is the right trade-off.
rdar://79515454
This tenatively reapplies the patch without modifications, the LLDB
test that has blocked this from landing previously has since been
modified to hopefully no longer be sensitive to this change.
Differential Revision: https://reviews.llvm.org/D105238
Added:
llvm/test/DebugInfo/AArch64/fallthrough-branch.ll
Modified:
llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
llvm/lib/Target/AArch64/GISel/AArch64InstructionSelector.cpp
llvm/test/CodeGen/AArch64/GlobalISel/arm64-atomic-128.ll
llvm/test/CodeGen/AArch64/GlobalISel/arm64-atomic.ll
llvm/test/CodeGen/AArch64/GlobalISel/arm64-irtranslator.ll
llvm/test/CodeGen/AArch64/unwind-preserved.ll
llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/jump_table_and_brjt.ll
llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/long_ambiguous_chain_s32.ll
llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/long_ambiguous_chain_s64.ll
llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/phi.ll
Removed:
################################################################################
diff --git a/llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp b/llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
index 73b763710fdff..d4880f07a1274 100644
--- a/llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
@@ -566,7 +566,7 @@ bool IRTranslator::translateBr(const User &U, MachineIRBuilder &MIRBuilder) {
if (BrInst.isUnconditional()) {
// If the unconditional target is the layout successor, fallthrough.
- if (!CurMBB.isLayoutSuccessor(Succ0MBB))
+ if (OptLevel == CodeGenOpt::None || !CurMBB.isLayoutSuccessor(Succ0MBB))
MIRBuilder.buildBr(*Succ0MBB);
// Link successors.
diff --git a/llvm/lib/Target/AArch64/GISel/AArch64InstructionSelector.cpp b/llvm/lib/Target/AArch64/GISel/AArch64InstructionSelector.cpp
index a98248438e401..c88f0bcd70b9b 100644
--- a/llvm/lib/Target/AArch64/GISel/AArch64InstructionSelector.cpp
+++ b/llvm/lib/Target/AArch64/GISel/AArch64InstructionSelector.cpp
@@ -2145,17 +2145,8 @@ bool AArch64InstructionSelector::earlySelect(MachineInstr &I) {
I.eraseFromParent();
return true;
}
- case TargetOpcode::G_BR: {
- // If the branch jumps to the fallthrough block, don't bother emitting it.
- // Only do this for -O0 for a good code size improvement, because when
- // optimizations are enabled we want to leave this choice to
- // MachineBlockPlacement.
- bool EnableOpt = MF.getTarget().getOptLevel() != CodeGenOpt::None;
- if (EnableOpt || !MBB.isLayoutSuccessor(I.getOperand(0).getMBB()))
- return false;
- I.eraseFromParent();
- return true;
- }
+ case TargetOpcode::G_BR:
+ return false;
case TargetOpcode::G_SHL:
return earlySelectSHL(I, MRI);
case TargetOpcode::G_CONSTANT: {
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/arm64-atomic-128.ll b/llvm/test/CodeGen/AArch64/GlobalISel/arm64-atomic-128.ll
index 384f54396cbd0..db1b011c06ea4 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/arm64-atomic-128.ll
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/arm64-atomic-128.ll
@@ -377,6 +377,7 @@ define void @atomic_load_relaxed(i64, i64, i128* %p, i128* %p2) {
; CHECK-LLSC-O0-NEXT: .cfi_def_cfa_offset 64
; CHECK-LLSC-O0-NEXT: str x2, [sp, #48] // 8-byte Folded Spill
; CHECK-LLSC-O0-NEXT: str x3, [sp, #56] // 8-byte Folded Spill
+; CHECK-LLSC-O0-NEXT: b .LBB4_1
; CHECK-LLSC-O0-NEXT: .LBB4_1: // %atomicrmw.start
; CHECK-LLSC-O0-NEXT: // =>This Inner Loop Header: Depth=1
; CHECK-LLSC-O0-NEXT: ldr x11, [sp, #48] // 8-byte Folded Reload
@@ -417,7 +418,8 @@ define void @atomic_load_relaxed(i64, i64, i128* %p, i128* %p2) {
; CHECK-LLSC-O0-NEXT: csel x10, x9, x8, eq
; CHECK-LLSC-O0-NEXT: stxp w8, x9, x10, [x11]
; CHECK-LLSC-O0-NEXT: cbnz w8, .LBB4_1
-; CHECK-LLSC-O0-NEXT: // %bb.2: // %atomicrmw.end
+; CHECK-LLSC-O0-NEXT: b .LBB4_2
+; CHECK-LLSC-O0-NEXT: .LBB4_2: // %atomicrmw.end
; CHECK-LLSC-O0-NEXT: ldr q0, [sp, #32] // 16-byte Folded Reload
; CHECK-LLSC-O0-NEXT: ldr x8, [sp, #56] // 8-byte Folded Reload
; CHECK-LLSC-O0-NEXT: str q0, [x8]
@@ -430,6 +432,7 @@ define void @atomic_load_relaxed(i64, i64, i128* %p, i128* %p2) {
; CHECK-CAS-O0-NEXT: .cfi_def_cfa_offset 64
; CHECK-CAS-O0-NEXT: str x2, [sp, #48] // 8-byte Folded Spill
; CHECK-CAS-O0-NEXT: str x3, [sp, #56] // 8-byte Folded Spill
+; CHECK-CAS-O0-NEXT: b .LBB4_1
; CHECK-CAS-O0-NEXT: .LBB4_1: // %atomicrmw.start
; CHECK-CAS-O0-NEXT: // =>This Inner Loop Header: Depth=1
; CHECK-CAS-O0-NEXT: ldr x11, [sp, #48] // 8-byte Folded Reload
@@ -470,7 +473,8 @@ define void @atomic_load_relaxed(i64, i64, i128* %p, i128* %p2) {
; CHECK-CAS-O0-NEXT: csel x10, x9, x8, eq
; CHECK-CAS-O0-NEXT: stxp w8, x9, x10, [x11]
; CHECK-CAS-O0-NEXT: cbnz w8, .LBB4_1
-; CHECK-CAS-O0-NEXT: // %bb.2: // %atomicrmw.end
+; CHECK-CAS-O0-NEXT: b .LBB4_2
+; CHECK-CAS-O0-NEXT: .LBB4_2: // %atomicrmw.end
; CHECK-CAS-O0-NEXT: ldr q0, [sp, #32] // 16-byte Folded Reload
; CHECK-CAS-O0-NEXT: ldr x8, [sp, #56] // 8-byte Folded Reload
; CHECK-CAS-O0-NEXT: str q0, [x8]
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/arm64-atomic.ll b/llvm/test/CodeGen/AArch64/GlobalISel/arm64-atomic.ll
index 8810a5fd7887a..80e77e9ec842a 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/arm64-atomic.ll
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/arm64-atomic.ll
@@ -329,6 +329,7 @@ define i32 @fetch_and_nand(i32* %p) #0 {
; CHECK-NOLSE-O0-NEXT: str x0, [sp, #16] ; 8-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldr w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB6_1
; CHECK-NOLSE-O0-NEXT: LBB6_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB6_2 Depth 2
@@ -353,7 +354,8 @@ define i32 @fetch_and_nand(i32* %p) #0 {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB6_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB6_5
+; CHECK-NOLSE-O0-NEXT: LBB6_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -377,6 +379,7 @@ define i32 @fetch_and_nand(i32* %p) #0 {
; CHECK-LSE-O0-NEXT: str x0, [sp, #16] ; 8-byte Folded Spill
; CHECK-LSE-O0-NEXT: ldr w8, [x0]
; CHECK-LSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-LSE-O0-NEXT: b LBB6_1
; CHECK-LSE-O0-NEXT: LBB6_1: ; %atomicrmw.start
; CHECK-LSE-O0-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-LSE-O0-NEXT: ldr w8, [sp, #28] ; 4-byte Folded Reload
@@ -390,7 +393,8 @@ define i32 @fetch_and_nand(i32* %p) #0 {
; CHECK-LSE-O0-NEXT: cset w8, eq
; CHECK-LSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-LSE-O0-NEXT: tbz w8, #0, LBB6_1
-; CHECK-LSE-O0-NEXT: ; %bb.2: ; %atomicrmw.end
+; CHECK-LSE-O0-NEXT: b LBB6_2
+; CHECK-LSE-O0-NEXT: LBB6_2: ; %atomicrmw.end
; CHECK-LSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-LSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-LSE-O0-NEXT: ret
@@ -418,6 +422,7 @@ define i64 @fetch_and_nand_64(i64* %p) #0 {
; CHECK-NOLSE-O0-NEXT: str x0, [sp, #16] ; 8-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldr x8, [x0]
; CHECK-NOLSE-O0-NEXT: str x8, [sp, #24] ; 8-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB7_1
; CHECK-NOLSE-O0-NEXT: LBB7_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB7_2 Depth 2
@@ -442,7 +447,8 @@ define i64 @fetch_and_nand_64(i64* %p) #0 {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str x9, [sp, #24] ; 8-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB7_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB7_5
+; CHECK-NOLSE-O0-NEXT: LBB7_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr x0, [sp, #8] ; 8-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -466,6 +472,7 @@ define i64 @fetch_and_nand_64(i64* %p) #0 {
; CHECK-LSE-O0-NEXT: str x0, [sp, #16] ; 8-byte Folded Spill
; CHECK-LSE-O0-NEXT: ldr x8, [x0]
; CHECK-LSE-O0-NEXT: str x8, [sp, #24] ; 8-byte Folded Spill
+; CHECK-LSE-O0-NEXT: b LBB7_1
; CHECK-LSE-O0-NEXT: LBB7_1: ; %atomicrmw.start
; CHECK-LSE-O0-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-LSE-O0-NEXT: ldr x8, [sp, #24] ; 8-byte Folded Reload
@@ -479,7 +486,8 @@ define i64 @fetch_and_nand_64(i64* %p) #0 {
; CHECK-LSE-O0-NEXT: cset w8, eq
; CHECK-LSE-O0-NEXT: str x9, [sp, #24] ; 8-byte Folded Spill
; CHECK-LSE-O0-NEXT: tbz w8, #0, LBB7_1
-; CHECK-LSE-O0-NEXT: ; %bb.2: ; %atomicrmw.end
+; CHECK-LSE-O0-NEXT: b LBB7_2
+; CHECK-LSE-O0-NEXT: LBB7_2: ; %atomicrmw.end
; CHECK-LSE-O0-NEXT: ldr x0, [sp, #8] ; 8-byte Folded Reload
; CHECK-LSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-LSE-O0-NEXT: ret
@@ -507,6 +515,7 @@ define i32 @fetch_and_or(i32* %p) #0 {
; CHECK-NOLSE-O0-NEXT: str x0, [sp, #16] ; 8-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldr w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB8_1
; CHECK-NOLSE-O0-NEXT: LBB8_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB8_2 Depth 2
@@ -531,7 +540,8 @@ define i32 @fetch_and_or(i32* %p) #0 {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB8_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: LBB8_5
+; CHECK-NOLSE-O0-NEXT: LBB8_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -570,6 +580,7 @@ define i64 @fetch_and_or_64(i64* %p) #0 {
; CHECK-NOLSE-O0-NEXT: str x0, [sp, #16] ; 8-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldr x8, [x0]
; CHECK-NOLSE-O0-NEXT: str x8, [sp, #24] ; 8-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB9_1
; CHECK-NOLSE-O0-NEXT: LBB9_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB9_2 Depth 2
@@ -593,7 +604,8 @@ define i64 @fetch_and_or_64(i64* %p) #0 {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str x9, [sp, #24] ; 8-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB9_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB9_5
+; CHECK-NOLSE-O0-NEXT: LBB9_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr x0, [sp, #8] ; 8-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -1344,6 +1356,7 @@ define i8 @atomicrmw_add_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrb w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB27_1
; CHECK-NOLSE-O0-NEXT: LBB27_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB27_2 Depth 2
@@ -1369,7 +1382,8 @@ define i8 @atomicrmw_add_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB27_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB27_5
+; CHECK-NOLSE-O0-NEXT: LBB27_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -1408,6 +1422,7 @@ define i8 @atomicrmw_xchg_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrb w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB28_1
; CHECK-NOLSE-O0-NEXT: LBB28_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB28_2 Depth 2
@@ -1432,7 +1447,8 @@ define i8 @atomicrmw_xchg_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB28_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB28_5
+; CHECK-NOLSE-O0-NEXT: LBB28_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -1471,6 +1487,7 @@ define i8 @atomicrmw_sub_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrb w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB29_1
; CHECK-NOLSE-O0-NEXT: LBB29_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB29_2 Depth 2
@@ -1496,7 +1513,8 @@ define i8 @atomicrmw_sub_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB29_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB29_5
+; CHECK-NOLSE-O0-NEXT: LBB29_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -1537,6 +1555,7 @@ define i8 @atomicrmw_and_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrb w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB30_1
; CHECK-NOLSE-O0-NEXT: LBB30_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB30_2 Depth 2
@@ -1562,7 +1581,8 @@ define i8 @atomicrmw_and_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB30_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB30_5
+; CHECK-NOLSE-O0-NEXT: LBB30_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -1603,6 +1623,7 @@ define i8 @atomicrmw_or_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrb w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB31_1
; CHECK-NOLSE-O0-NEXT: LBB31_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB31_2 Depth 2
@@ -1628,7 +1649,8 @@ define i8 @atomicrmw_or_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB31_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB31_5
+; CHECK-NOLSE-O0-NEXT: LBB31_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -1667,6 +1689,7 @@ define i8 @atomicrmw_xor_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrb w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB32_1
; CHECK-NOLSE-O0-NEXT: LBB32_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB32_2 Depth 2
@@ -1692,7 +1715,8 @@ define i8 @atomicrmw_xor_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB32_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB32_5
+; CHECK-NOLSE-O0-NEXT: LBB32_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -1733,6 +1757,7 @@ define i8 @atomicrmw_min_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrb w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB33_1
; CHECK-NOLSE-O0-NEXT: LBB33_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB33_2 Depth 2
@@ -1761,7 +1786,8 @@ define i8 @atomicrmw_min_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB33_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB33_5
+; CHECK-NOLSE-O0-NEXT: LBB33_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -1802,6 +1828,7 @@ define i8 @atomicrmw_max_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrb w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB34_1
; CHECK-NOLSE-O0-NEXT: LBB34_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB34_2 Depth 2
@@ -1830,7 +1857,8 @@ define i8 @atomicrmw_max_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB34_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB34_5
+; CHECK-NOLSE-O0-NEXT: LBB34_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -1871,6 +1899,7 @@ define i8 @atomicrmw_umin_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrb w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB35_1
; CHECK-NOLSE-O0-NEXT: LBB35_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB35_2 Depth 2
@@ -1899,7 +1928,8 @@ define i8 @atomicrmw_umin_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB35_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB35_5
+; CHECK-NOLSE-O0-NEXT: LBB35_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -1940,6 +1970,7 @@ define i8 @atomicrmw_umax_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrb w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB36_1
; CHECK-NOLSE-O0-NEXT: LBB36_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB36_2 Depth 2
@@ -1968,7 +1999,8 @@ define i8 @atomicrmw_umax_i8(i8* %ptr, i8 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB36_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB36_5
+; CHECK-NOLSE-O0-NEXT: LBB36_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -2007,6 +2039,7 @@ define i16 @atomicrmw_add_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrh w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB37_1
; CHECK-NOLSE-O0-NEXT: LBB37_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB37_2 Depth 2
@@ -2032,7 +2065,8 @@ define i16 @atomicrmw_add_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB37_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB37_5
+; CHECK-NOLSE-O0-NEXT: LBB37_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -2071,6 +2105,7 @@ define i16 @atomicrmw_xchg_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrh w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB38_1
; CHECK-NOLSE-O0-NEXT: LBB38_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB38_2 Depth 2
@@ -2095,7 +2130,8 @@ define i16 @atomicrmw_xchg_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB38_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB38_5
+; CHECK-NOLSE-O0-NEXT: LBB38_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -2134,6 +2170,7 @@ define i16 @atomicrmw_sub_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrh w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB39_1
; CHECK-NOLSE-O0-NEXT: LBB39_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB39_2 Depth 2
@@ -2159,7 +2196,8 @@ define i16 @atomicrmw_sub_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB39_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB39_5
+; CHECK-NOLSE-O0-NEXT: LBB39_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -2200,6 +2238,7 @@ define i16 @atomicrmw_and_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrh w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB40_1
; CHECK-NOLSE-O0-NEXT: LBB40_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB40_2 Depth 2
@@ -2225,7 +2264,8 @@ define i16 @atomicrmw_and_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB40_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB40_5
+; CHECK-NOLSE-O0-NEXT: LBB40_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -2266,6 +2306,7 @@ define i16 @atomicrmw_or_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrh w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB41_1
; CHECK-NOLSE-O0-NEXT: LBB41_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB41_2 Depth 2
@@ -2291,7 +2332,8 @@ define i16 @atomicrmw_or_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB41_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB41_5
+; CHECK-NOLSE-O0-NEXT: LBB41_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -2330,6 +2372,7 @@ define i16 @atomicrmw_xor_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrh w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB42_1
; CHECK-NOLSE-O0-NEXT: LBB42_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB42_2 Depth 2
@@ -2355,7 +2398,8 @@ define i16 @atomicrmw_xor_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB42_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB42_5
+; CHECK-NOLSE-O0-NEXT: LBB42_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -2396,6 +2440,7 @@ define i16 @atomicrmw_min_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrh w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB43_1
; CHECK-NOLSE-O0-NEXT: LBB43_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB43_2 Depth 2
@@ -2424,7 +2469,8 @@ define i16 @atomicrmw_min_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB43_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB43_5
+; CHECK-NOLSE-O0-NEXT: LBB43_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -2465,6 +2511,7 @@ define i16 @atomicrmw_max_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrh w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB44_1
; CHECK-NOLSE-O0-NEXT: LBB44_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB44_2 Depth 2
@@ -2493,7 +2540,8 @@ define i16 @atomicrmw_max_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB44_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB44_5
+; CHECK-NOLSE-O0-NEXT: LBB44_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -2534,6 +2582,7 @@ define i16 @atomicrmw_umin_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrh w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB45_1
; CHECK-NOLSE-O0-NEXT: LBB45_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB45_2 Depth 2
@@ -2562,7 +2611,8 @@ define i16 @atomicrmw_umin_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB45_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB45_5
+; CHECK-NOLSE-O0-NEXT: LBB45_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
@@ -2603,6 +2653,7 @@ define i16 @atomicrmw_umax_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: str w1, [sp, #24] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: ldrh w8, [x0]
; CHECK-NOLSE-O0-NEXT: str w8, [sp, #28] ; 4-byte Folded Spill
+; CHECK-NOLSE-O0-NEXT: b LBB46_1
; CHECK-NOLSE-O0-NEXT: LBB46_1: ; %atomicrmw.start
; CHECK-NOLSE-O0-NEXT: ; =>This Loop Header: Depth=1
; CHECK-NOLSE-O0-NEXT: ; Child Loop BB46_2 Depth 2
@@ -2631,7 +2682,8 @@ define i16 @atomicrmw_umax_i16(i16* %ptr, i16 %rhs) {
; CHECK-NOLSE-O0-NEXT: cset w8, eq
; CHECK-NOLSE-O0-NEXT: str w9, [sp, #28] ; 4-byte Folded Spill
; CHECK-NOLSE-O0-NEXT: tbz w8, #0, LBB46_1
-; CHECK-NOLSE-O0-NEXT: ; %bb.5: ; %atomicrmw.end
+; CHECK-NOLSE-O0-NEXT: b LBB46_5
+; CHECK-NOLSE-O0-NEXT: LBB46_5: ; %atomicrmw.end
; CHECK-NOLSE-O0-NEXT: ldr w0, [sp, #12] ; 4-byte Folded Reload
; CHECK-NOLSE-O0-NEXT: add sp, sp, #32 ; =32
; CHECK-NOLSE-O0-NEXT: ret
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/arm64-irtranslator.ll b/llvm/test/CodeGen/AArch64/GlobalISel/arm64-irtranslator.ll
index b05aa3f16e6b3..d8a94c4015f27 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/arm64-irtranslator.ll
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/arm64-irtranslator.ll
@@ -87,8 +87,6 @@ bb2:
; CHECK: body:
; CHECK: bb.{{[0-9]+}}.{{[a-zA-Z0-9.]+}}:
; CHECK-NEXT: successors: %[[END:bb.[0-9]+]](0x80000000)
-; We don't emit a branch here, as we can fallthrough to the successor.
-; CHECK-NOT: G_BR
; CHECK: [[END]].{{[a-zA-Z0-9.]+}}:
; CHECK-NEXT: RET_ReallyLR
define void @uncondbr_fallthrough() {
@@ -137,7 +135,6 @@ false:
; CHECK: bb.{{[0-9]+.[a-zA-Z0-9.]+}}:
; Make sure we have one successor
; CHECK-NEXT: successors: %[[BB_L1:bb.[0-9]+]](0x80000000)
-; CHECK-NOT: G_BR
;
; Check basic block L1 has 2 successors: BBL1 and BBL2
; CHECK: [[BB_L1]].{{[a-zA-Z0-9.]+}} (address-taken):
diff --git a/llvm/test/CodeGen/AArch64/unwind-preserved.ll b/llvm/test/CodeGen/AArch64/unwind-preserved.ll
index 33bbdfaa2cfd1..0652b7b24d78e 100644
--- a/llvm/test/CodeGen/AArch64/unwind-preserved.ll
+++ b/llvm/test/CodeGen/AArch64/unwind-preserved.ll
@@ -365,7 +365,8 @@ define aarch64_vector_pcs <4 x i32> @invoke_callee_may_throw_neon(<4 x i32> %v)
; GISEL-NEXT: bl may_throw_neon
; GISEL-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
; GISEL-NEXT: .Ltmp4:
-; GISEL-NEXT: // %bb.1: // %.Lcontinue
+; GISEL-NEXT: b .LBB1_1
+; GISEL-NEXT: .LBB1_1: // %.Lcontinue
; GISEL-NEXT: ldr q0, [sp, #16] // 16-byte Folded Reload
; GISEL-NEXT: ldp x29, x30, [sp, #288] // 16-byte Folded Reload
; GISEL-NEXT: ldp q9, q8, [sp, #256] // 32-byte Folded Reload
diff --git a/llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/jump_table_and_brjt.ll b/llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/jump_table_and_brjt.ll
index 804a14853bedb..30a1b514ddafe 100644
--- a/llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/jump_table_and_brjt.ll
+++ b/llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/jump_table_and_brjt.ll
@@ -55,8 +55,9 @@ define i32 @mod4_0_to_11(i32 %a) {
; MIPS32-NEXT: jr $ra
; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB0_6: # %sw.default
-; MIPS32-NEXT: .insn
-; MIPS32-NEXT: # %bb.7: # %sw.epilog
+; MIPS32-NEXT: j $BB0_7
+; MIPS32-NEXT: nop
+; MIPS32-NEXT: $BB0_7: # %sw.epilog
; MIPS32-NEXT: lw $1, 8($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $2, 4($sp) # 4-byte Folded Reload
; MIPS32-NEXT: ori $3, $zero, 8
@@ -158,8 +159,9 @@ define i32 @mod4_0_to_11(i32 %a) {
; MIPS32_PIC-NEXT: jr $ra
; MIPS32_PIC-NEXT: nop
; MIPS32_PIC-NEXT: $BB0_6: # %sw.default
-; MIPS32_PIC-NEXT: .insn
-; MIPS32_PIC-NEXT: # %bb.7: # %sw.epilog
+; MIPS32_PIC-NEXT: b $BB0_7
+; MIPS32_PIC-NEXT: nop
+; MIPS32_PIC-NEXT: $BB0_7: # %sw.epilog
; MIPS32_PIC-NEXT: lw $1, 16($sp) # 4-byte Folded Reload
; MIPS32_PIC-NEXT: lw $2, 12($sp) # 4-byte Folded Reload
; MIPS32_PIC-NEXT: ori $3, $zero, 8
diff --git a/llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/long_ambiguous_chain_s32.ll b/llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/long_ambiguous_chain_s32.ll
index ce46bed175d65..0ff034bec1c50 100644
--- a/llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/long_ambiguous_chain_s32.ll
+++ b/llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/long_ambiguous_chain_s32.ll
@@ -57,6 +57,8 @@ define void @long_chain_ambiguous_i32_in_gpr(i1 %cnd0, i1 %cnd1, i1 %cnd2, i32*
; MIPS32-NEXT: lw $1, 40($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $1, 0($1)
; MIPS32-NEXT: sw $1, 16($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB0_9
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB0_9: # %b.PHI.1
; MIPS32-NEXT: lw $1, 28($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $2, 16($sp) # 4-byte Folded Reload
@@ -93,6 +95,8 @@ define void @long_chain_ambiguous_i32_in_gpr(i1 %cnd0, i1 %cnd1, i1 %cnd2, i32*
; MIPS32-NEXT: lw $1, 36($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $1, 0($1)
; MIPS32-NEXT: sw $1, 4($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB0_16
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB0_16: # %b.PHI.2
; MIPS32-NEXT: lw $1, 24($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $2, 4($sp) # 4-byte Folded Reload
@@ -244,6 +248,8 @@ define void @long_chain_i32_in_gpr(i1 %cnd0, i1 %cnd1, i1 %cnd2, i32* %a, i32* %
; MIPS32-NEXT: lw $1, 44($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $1, 0($1)
; MIPS32-NEXT: sw $1, 20($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB1_9
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB1_9: # %b.PHI.1
; MIPS32-NEXT: lw $2, 52($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $1, 32($sp) # 4-byte Folded Reload
@@ -282,6 +288,8 @@ define void @long_chain_i32_in_gpr(i1 %cnd0, i1 %cnd1, i1 %cnd2, i32* %a, i32* %
; MIPS32-NEXT: lw $1, 40($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $1, 0($1)
; MIPS32-NEXT: sw $1, 4($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB1_16
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB1_16: # %b.PHI.2
; MIPS32-NEXT: lw $1, 28($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $2, 4($sp) # 4-byte Folded Reload
@@ -432,6 +440,8 @@ define void @long_chain_ambiguous_float_in_fpr(i1 %cnd0, i1 %cnd1, i1 %cnd2, flo
; MIPS32-NEXT: lw $1, 40($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $1, 0($1)
; MIPS32-NEXT: sw $1, 16($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB2_9
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB2_9: # %b.PHI.1
; MIPS32-NEXT: lw $1, 28($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $2, 16($sp) # 4-byte Folded Reload
@@ -468,6 +478,8 @@ define void @long_chain_ambiguous_float_in_fpr(i1 %cnd0, i1 %cnd1, i1 %cnd2, flo
; MIPS32-NEXT: lw $1, 36($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $1, 0($1)
; MIPS32-NEXT: sw $1, 4($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB2_16
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB2_16: # %b.PHI.2
; MIPS32-NEXT: lw $1, 24($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $2, 4($sp) # 4-byte Folded Reload
@@ -620,6 +632,8 @@ define void @long_chain_float_in_fpr(i1 %cnd0, i1 %cnd1, i1 %cnd2, float* %a, fl
; MIPS32-NEXT: lw $1, 44($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lwc1 $f0, 0($1)
; MIPS32-NEXT: swc1 $f0, 20($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB3_9
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB3_9: # %b.PHI.1
; MIPS32-NEXT: lwc1 $f0, 52($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $1, 32($sp) # 4-byte Folded Reload
@@ -658,6 +672,8 @@ define void @long_chain_float_in_fpr(i1 %cnd0, i1 %cnd1, i1 %cnd2, float* %a, fl
; MIPS32-NEXT: lw $1, 40($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lwc1 $f0, 0($1)
; MIPS32-NEXT: swc1 $f0, 4($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB3_16
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB3_16: # %b.PHI.2
; MIPS32-NEXT: lw $1, 28($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lwc1 $f0, 4($sp) # 4-byte Folded Reload
diff --git a/llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/long_ambiguous_chain_s64.ll b/llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/long_ambiguous_chain_s64.ll
index 2a5afd5b1022b..7650194d30b1d 100644
--- a/llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/long_ambiguous_chain_s64.ll
+++ b/llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/long_ambiguous_chain_s64.ll
@@ -57,6 +57,8 @@ define void @long_chain_ambiguous_i64_in_fpr(i1 %cnd0, i1 %cnd1, i1 %cnd2, i64*
; MIPS32-NEXT: lw $1, 64($sp) # 4-byte Folded Reload
; MIPS32-NEXT: ldc1 $f0, 0($1)
; MIPS32-NEXT: sdc1 $f0, 32($sp) # 8-byte Folded Spill
+; MIPS32-NEXT: j $BB0_9
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB0_9: # %b.PHI.1
; MIPS32-NEXT: lw $1, 52($sp) # 4-byte Folded Reload
; MIPS32-NEXT: ldc1 $f0, 32($sp) # 8-byte Folded Reload
@@ -93,6 +95,8 @@ define void @long_chain_ambiguous_i64_in_fpr(i1 %cnd0, i1 %cnd1, i1 %cnd2, i64*
; MIPS32-NEXT: lw $1, 60($sp) # 4-byte Folded Reload
; MIPS32-NEXT: ldc1 $f0, 0($1)
; MIPS32-NEXT: sdc1 $f0, 8($sp) # 8-byte Folded Spill
+; MIPS32-NEXT: j $BB0_16
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB0_16: # %b.PHI.2
; MIPS32-NEXT: lw $1, 48($sp) # 4-byte Folded Reload
; MIPS32-NEXT: ldc1 $f0, 8($sp) # 8-byte Folded Reload
@@ -250,6 +254,8 @@ define void @long_chain_i64_in_gpr(i1 %cnd0, i1 %cnd1, i1 %cnd2, i64* %a, i64* %
; MIPS32-NEXT: lw $1, 4($1)
; MIPS32-NEXT: sw $2, 40($sp) # 4-byte Folded Spill
; MIPS32-NEXT: sw $1, 44($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB1_9
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB1_9: # %b.PHI.1
; MIPS32-NEXT: lw $2, 76($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $1, 56($sp) # 4-byte Folded Reload
@@ -299,6 +305,8 @@ define void @long_chain_i64_in_gpr(i1 %cnd0, i1 %cnd1, i1 %cnd2, i64* %a, i64* %
; MIPS32-NEXT: lw $1, 4($1)
; MIPS32-NEXT: sw $2, 8($sp) # 4-byte Folded Spill
; MIPS32-NEXT: sw $1, 12($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB1_16
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB1_16: # %b.PHI.2
; MIPS32-NEXT: lw $1, 52($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $3, 8($sp) # 4-byte Folded Reload
@@ -463,6 +471,8 @@ define void @long_chain_ambiguous_double_in_fpr(i1 %cnd0, i1 %cnd1, i1 %cnd2, do
; MIPS32-NEXT: lw $1, 64($sp) # 4-byte Folded Reload
; MIPS32-NEXT: ldc1 $f0, 0($1)
; MIPS32-NEXT: sdc1 $f0, 32($sp) # 8-byte Folded Spill
+; MIPS32-NEXT: j $BB2_9
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB2_9: # %b.PHI.1
; MIPS32-NEXT: lw $1, 52($sp) # 4-byte Folded Reload
; MIPS32-NEXT: ldc1 $f0, 32($sp) # 8-byte Folded Reload
@@ -499,6 +509,8 @@ define void @long_chain_ambiguous_double_in_fpr(i1 %cnd0, i1 %cnd1, i1 %cnd2, do
; MIPS32-NEXT: lw $1, 60($sp) # 4-byte Folded Reload
; MIPS32-NEXT: ldc1 $f0, 0($1)
; MIPS32-NEXT: sdc1 $f0, 8($sp) # 8-byte Folded Spill
+; MIPS32-NEXT: j $BB2_16
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB2_16: # %b.PHI.2
; MIPS32-NEXT: lw $1, 48($sp) # 4-byte Folded Reload
; MIPS32-NEXT: ldc1 $f0, 8($sp) # 8-byte Folded Reload
@@ -653,6 +665,8 @@ define void @long_chain_double_in_fpr(i1 %cnd0, i1 %cnd1, i1 %cnd2, double* %a,
; MIPS32-NEXT: lw $1, 72($sp) # 4-byte Folded Reload
; MIPS32-NEXT: ldc1 $f0, 0($1)
; MIPS32-NEXT: sdc1 $f0, 40($sp) # 8-byte Folded Spill
+; MIPS32-NEXT: j $BB3_9
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB3_9: # %b.PHI.1
; MIPS32-NEXT: ldc1 $f0, 80($sp) # 8-byte Folded Reload
; MIPS32-NEXT: lw $1, 60($sp) # 4-byte Folded Reload
@@ -691,6 +705,8 @@ define void @long_chain_double_in_fpr(i1 %cnd0, i1 %cnd1, i1 %cnd2, double* %a,
; MIPS32-NEXT: lw $1, 68($sp) # 4-byte Folded Reload
; MIPS32-NEXT: ldc1 $f0, 0($1)
; MIPS32-NEXT: sdc1 $f0, 8($sp) # 8-byte Folded Spill
+; MIPS32-NEXT: j $BB3_16
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB3_16: # %b.PHI.2
; MIPS32-NEXT: lw $1, 56($sp) # 4-byte Folded Reload
; MIPS32-NEXT: ldc1 $f0, 8($sp) # 8-byte Folded Reload
diff --git a/llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/phi.ll b/llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/phi.ll
index d44023bf7f0c8..100ea22d3cf29 100644
--- a/llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/phi.ll
+++ b/llvm/test/CodeGen/Mips/GlobalISel/llvm-ir/phi.ll
@@ -22,6 +22,8 @@ define i1 @phi_i1(i1 %cnd, i1 %a, i1 %b) {
; MIPS32-NEXT: $BB0_3: # %cond.false
; MIPS32-NEXT: lw $1, 12($sp) # 4-byte Folded Reload
; MIPS32-NEXT: sw $1, 4($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB0_4
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB0_4: # %cond.end
; MIPS32-NEXT: lw $2, 4($sp) # 4-byte Folded Reload
; MIPS32-NEXT: addiu $sp, $sp, 16
@@ -62,6 +64,8 @@ define i8 @phi_i8(i1 %cnd, i8 %a, i8 %b) {
; MIPS32-NEXT: $BB1_3: # %cond.false
; MIPS32-NEXT: lw $1, 12($sp) # 4-byte Folded Reload
; MIPS32-NEXT: sw $1, 4($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB1_4
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB1_4: # %cond.end
; MIPS32-NEXT: lw $2, 4($sp) # 4-byte Folded Reload
; MIPS32-NEXT: addiu $sp, $sp, 16
@@ -102,6 +106,8 @@ define i16 @phi_i16(i1 %cnd, i16 %a, i16 %b) {
; MIPS32-NEXT: $BB2_3: # %cond.false
; MIPS32-NEXT: lw $1, 12($sp) # 4-byte Folded Reload
; MIPS32-NEXT: sw $1, 4($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB2_4
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB2_4: # %cond.end
; MIPS32-NEXT: lw $2, 4($sp) # 4-byte Folded Reload
; MIPS32-NEXT: addiu $sp, $sp, 16
@@ -142,6 +148,8 @@ define i32 @phi_i32(i1 %cnd, i32 %a, i32 %b) {
; MIPS32-NEXT: $BB3_3: # %cond.false
; MIPS32-NEXT: lw $1, 12($sp) # 4-byte Folded Reload
; MIPS32-NEXT: sw $1, 4($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB3_4
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB3_4: # %cond.end
; MIPS32-NEXT: lw $2, 4($sp) # 4-byte Folded Reload
; MIPS32-NEXT: addiu $sp, $sp, 16
@@ -192,6 +200,8 @@ define i64 @phi_i64(i1 %cnd, i64 %a, i64 %b) {
; MIPS32-NEXT: lw $2, 16($sp) # 4-byte Folded Reload
; MIPS32-NEXT: sw $2, 0($sp) # 4-byte Folded Spill
; MIPS32-NEXT: sw $1, 4($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB4_4
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB4_4: # %cond.end
; MIPS32-NEXT: lw $2, 0($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $3, 4($sp) # 4-byte Folded Reload
@@ -236,6 +246,8 @@ define void @phi_ambiguous_i64_in_fpr(i1 %cnd, i64* %i64_ptr_a, i64* %i64_ptr_b,
; MIPS32-NEXT: $BB5_3: # %cond.false
; MIPS32-NEXT: ldc1 $f0, 24($sp) # 8-byte Folded Reload
; MIPS32-NEXT: sdc1 $f0, 0($sp) # 8-byte Folded Spill
+; MIPS32-NEXT: j $BB5_4
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB5_4: # %cond.end
; MIPS32-NEXT: lw $1, 12($sp) # 4-byte Folded Reload
; MIPS32-NEXT: ldc1 $f0, 0($sp) # 8-byte Folded Reload
@@ -281,6 +293,8 @@ define float @phi_float(i1 %cnd, float %a, float %b) {
; MIPS32-NEXT: $BB6_3: # %cond.false
; MIPS32-NEXT: lw $1, 12($sp) # 4-byte Folded Reload
; MIPS32-NEXT: sw $1, 4($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB6_4
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB6_4: # %cond.end
; MIPS32-NEXT: lw $1, 4($sp) # 4-byte Folded Reload
; MIPS32-NEXT: mtc1 $1, $f0
@@ -325,6 +339,8 @@ define void @phi_ambiguous_float_in_gpr(i1 %cnd, float* %f32_ptr_a, float* %f32_
; MIPS32-NEXT: $BB7_3: # %cond.false
; MIPS32-NEXT: lw $1, 12($sp) # 4-byte Folded Reload
; MIPS32-NEXT: sw $1, 0($sp) # 4-byte Folded Spill
+; MIPS32-NEXT: j $BB7_4
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB7_4: # %cond.end
; MIPS32-NEXT: lw $2, 4($sp) # 4-byte Folded Reload
; MIPS32-NEXT: lw $1, 0($sp) # 4-byte Folded Reload
@@ -372,6 +388,8 @@ define double @phi_double(double %a, double %b, i1 %cnd) {
; MIPS32-NEXT: $BB8_3: # %cond.false
; MIPS32-NEXT: ldc1 $f0, 16($sp) # 8-byte Folded Reload
; MIPS32-NEXT: sdc1 $f0, 0($sp) # 8-byte Folded Spill
+; MIPS32-NEXT: j $BB8_4
+; MIPS32-NEXT: nop
; MIPS32-NEXT: $BB8_4: # %cond.end
; MIPS32-NEXT: ldc1 $f0, 0($sp) # 8-byte Folded Reload
; MIPS32-NEXT: addiu $sp, $sp, 24
diff --git a/llvm/test/DebugInfo/AArch64/fallthrough-branch.ll b/llvm/test/DebugInfo/AArch64/fallthrough-branch.ll
new file mode 100644
index 0000000000000..3873f7fe61370
--- /dev/null
+++ b/llvm/test/DebugInfo/AArch64/fallthrough-branch.ll
@@ -0,0 +1,48 @@
+; RUN: llc -O0 -stop-before=livedebugvalues < %s | FileCheck %s
+
+; ModuleID = '/tmp/t.o'
+source_filename = "/tmp/t.o"
+target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
+target triple = "arm64-apple-macosx11.0.0"
+
+define swiftcc void @"$s1t1f1bySb_tF"(i1 %0) !dbg !35 {
+ %2 = alloca i1, align 8
+ %3 = bitcast i1* %2 to i8*
+ call void @llvm.memset.p0i8.i64(i8* align 8 %3, i8 0, i64 1, i1 false)
+ store i1 %0, i1* %2, align 8, !dbg !37
+; CHECK: B %bb.1, debug-location !{{[0-9]+}}
+ br i1 %0, label %4, label %5, !dbg !38
+
+4: ; preds = %1
+; Check that at -O0 the branches and their debug locations are not eliminated.
+; CHECK: B %bb.3, debug-location !{{[0-9]+}}
+ br label %6, !dbg !39
+
+5: ; preds = %1
+; CHECK: B %bb.3, debug-location !{{[0-9]+}}
+ br label %6, !dbg !40
+
+6: ; preds = %4, %5
+ ret void, !dbg !39
+}
+
+; Function Attrs: argmemonly nofree nosync nounwind willreturn writeonly
+declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1 immarg) #1
+attributes #1 = { argmemonly nofree nosync nounwind willreturn writeonly }
+
+!llvm.module.flags = !{!6, !7, !14}
+!llvm.dbg.cu = !{!15, !27}
+
+!6 = !{i32 7, !"Dwarf Version", i32 4}
+!7 = !{i32 2, !"Debug Info Version", i32 3}
+!14 = !{i32 1, !"Swift Version", i32 7}
+!15 = distinct !DICompileUnit(language: DW_LANG_Swift, file: !16, producer: "Swift", emissionKind: LineTablesOnly)
+!16 = !DIFile(filename: "t.swift", directory: "/tmp")
+!17 = !{}
+!27 = distinct !DICompileUnit(language: DW_LANG_ObjC, file: !16, emissionKind: LineTablesOnly)
+!35 = distinct !DISubprogram(name: "f", linkageName: "$s1t1f1bySb_tF", scope: !15, file: !16, line: 1, type: !36, scopeLine: 1, spFlags: DISPFlagDefinition, unit: !15, retainedNodes: !17)
+!36 = !DISubroutineType(types: null)
+!37 = !DILocation(line: 0, scope: !35)
+!38 = !DILocation(line: 2, column: 9, scope: !35)
+!39 = !DILocation(line: 3, column: 1, scope: !35)
+!40 = !DILocation(line: 2, column: 18, scope: !35)
More information about the llvm-commits
mailing list