[BPI] Improve static heuristics for integer comparisons

Similarly as for pointers, even for integers a == b is usually false.

GCC also uses this heuristic.

Reviewed By: ebrevnov

Differential Revision: https://reviews.llvm.org/D85781
This commit is contained in:
Dávid Bolvanský 2020-08-13 12:45:14 +02:00
parent 612b4dda76
commit 50c743fa71
63 changed files with 4771 additions and 1946 deletions

View File

@ -2,7 +2,7 @@
// RUN: rm -fr %t.nopromo.prof
// RUN: %clang_pgogen=%t.promo.prof/ -o %t.promo.gen -O2 %s
// RUN: %clang_pgogen=%t.promo.prof/ -o %t.promo.gen.ll -emit-llvm -S -O2 %s
// RUN: cat %t.promo.gen.ll | FileCheck --check-prefix=PROMO %s
// RUN: cp %t.promo.gen.ll /tmp/d.txt ; cat %t.promo.gen.ll | FileCheck --check-prefix=PROMO %s
// RUN: %run %t.promo.gen
// RUN: llvm-profdata merge -o %t.promo.profdata %t.promo.prof/
// RUN: llvm-profdata show --counts --all-functions %t.promo.profdata > %t.promo.dump
@ -22,23 +22,23 @@ __attribute__((noinline)) void foo(int n, int N) {
// PROMO: load{{.*}}@__profc_foo{{.*}} 3){{.*}}
// PROMO-NEXT: add
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 3){{.*}}
// PROMO: load{{.*}}@__profc_foo{{.*}} 0){{.*}}
// PROMO-NEXT: add
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 0){{.*}}
// PROMO-NEXT: load{{.*}}@__profc_foo{{.*}} 1){{.*}}
// PROMO: load{{.*}}@__profc_foo{{.*}} 1){{.*}}
// PROMO-NEXT: add
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 1){{.*}}
// PROMO-NEXT: load{{.*}}@__profc_foo{{.*}} 0){{.*}}
// PROMO-NEXT: add
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 0){{.*}}
// PROMO: load{{.*}}@__profc_foo{{.*}} 2){{.*}}
// PROMO-NEXT: add
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 2){{.*}}
//
// NOPROMO-LABEL: @foo
// NOPROMO: load{{.*}}@__profc_foo{{.*}} 0){{.*}}
// NOPROMO-NEXT: add
// NOPROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 0){{.*}}
// NOPROMO: load{{.*}}@__profc_foo{{.*}} 1){{.*}}
// NOPROMO-NEXT: add
// NOPROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 1){{.*}}
// NOPROMO: load{{.*}}@__profc_foo{{.*}} 0){{.*}}
// NOPROMO-NEXT: add
// NOPROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 0){{.*}}
// NOPROMO: load{{.*}}@__profc_foo{{.*}} 2){{.*}}
// NOPROMO-NEXT: add
// NOPROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 2){{.*}}

View File

@ -17,23 +17,23 @@ int g;
__attribute__((noinline)) void bar(int i) { g += i; }
__attribute__((noinline)) void foo(int n, int N) {
// PROMO-LABEL: @foo
// PROMO: load{{.*}}@__profc_foo{{.*}} 0){{.*}}
// PROMO-NEXT: add
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 0){{.*}}
// PROMO-NEXT: load{{.*}}@__profc_foo{{.*}} 1){{.*}}
// PROMO: load{{.*}}@__profc_foo{{.*}} 1){{.*}}
// PROMO-NEXT: add
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 1){{.*}}
// PROMO-NEXT: load{{.*}}@__profc_foo{{.*}} 0){{.*}}
// PROMO-NEXT: add
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 0){{.*}}
// PROMO-NEXT: load{{.*}}@__profc_foo{{.*}} 2){{.*}}
// PROMO-NEXT: add
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 2){{.*}}
//
// NOPROMO-LABEL: @foo
// NOPROMO: load{{.*}}@__profc_foo{{.*}} 0){{.*}}
// NOPROMO-NEXT: add
// NOPROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 0){{.*}}
// NOPROMO: load{{.*}}@__profc_foo{{.*}} 1){{.*}}
// NOPROMO-NEXT: add
// NOPROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 1){{.*}}
// NOPROMO: load{{.*}}@__profc_foo{{.*}} 0){{.*}}
// NOPROMO-NEXT: add
// NOPROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 0){{.*}}
// NOPROMO: load{{.*}}@__profc_foo{{.*}} 2){{.*}}
// NOPROMO-NEXT: add
// NOPROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 2){{.*}}

View File

@ -315,7 +315,7 @@ private:
bool calcColdCallHeuristics(const BasicBlock *BB);
bool calcPointerHeuristics(const BasicBlock *BB);
bool calcLoopBranchHeuristics(const BasicBlock *BB, const LoopInfo &LI);
bool calcZeroHeuristics(const BasicBlock *BB, const TargetLibraryInfo *TLI);
bool calcIntegerHeuristics(const BasicBlock *BB, const TargetLibraryInfo *TLI);
bool calcFloatingPointHeuristics(const BasicBlock *BB);
bool calcInvokeHeuristics(const BasicBlock *BB);
};

View File

@ -122,8 +122,8 @@ static const uint32_t CC_NONTAKEN_WEIGHT = 64;
static const uint32_t PH_TAKEN_WEIGHT = 20;
static const uint32_t PH_NONTAKEN_WEIGHT = 12;
static const uint32_t ZH_TAKEN_WEIGHT = 20;
static const uint32_t ZH_NONTAKEN_WEIGHT = 12;
static const uint32_t INTH_TAKEN_WEIGHT = 20;
static const uint32_t INTH_NONTAKEN_WEIGHT = 12;
static const uint32_t FPH_TAKEN_WEIGHT = 20;
static const uint32_t FPH_NONTAKEN_WEIGHT = 12;
@ -856,7 +856,7 @@ bool BranchProbabilityInfo::calcLoopBranchHeuristics(const BasicBlock *BB,
return true;
}
bool BranchProbabilityInfo::calcZeroHeuristics(const BasicBlock *BB,
bool BranchProbabilityInfo::calcIntegerHeuristics(const BasicBlock *BB,
const TargetLibraryInfo *TLI) {
const BranchInst *BI = dyn_cast<BranchInst>(BB->getTerminator());
if (!BI || !BI->isConditional())
@ -873,10 +873,21 @@ bool BranchProbabilityInfo::calcZeroHeuristics(const BasicBlock *BB,
return dyn_cast<ConstantInt>(V);
};
BranchProbability TakenProb(INTH_TAKEN_WEIGHT,
INTH_TAKEN_WEIGHT + INTH_NONTAKEN_WEIGHT);
BranchProbability UntakenProb(INTH_NONTAKEN_WEIGHT,
INTH_TAKEN_WEIGHT + INTH_NONTAKEN_WEIGHT);
Value *RHS = CI->getOperand(1);
ConstantInt *CV = GetConstantInt(RHS);
if (!CV)
return false;
if (!CV) {
// X == Y -> Unlikely
// Otherwise -> Likely
if (CI->isTrueWhenEqual())
std::swap(TakenProb, UntakenProb);
setEdgeProbability(
BB, SmallVector<BranchProbability, 2>({TakenProb, UntakenProb}));
return true;
}
// If the LHS is the result of AND'ing a value with a single bit bitmask,
// we don't have information about probabilities.
@ -964,10 +975,6 @@ bool BranchProbabilityInfo::calcZeroHeuristics(const BasicBlock *BB,
return false;
}
BranchProbability TakenProb(ZH_TAKEN_WEIGHT,
ZH_TAKEN_WEIGHT + ZH_NONTAKEN_WEIGHT);
BranchProbability UntakenProb(ZH_NONTAKEN_WEIGHT,
ZH_TAKEN_WEIGHT + ZH_NONTAKEN_WEIGHT);
if (!isProb)
std::swap(TakenProb, UntakenProb);
@ -1221,7 +1228,7 @@ void BranchProbabilityInfo::calculate(const Function &F, const LoopInfo &LI,
continue;
if (calcPointerHeuristics(BB))
continue;
if (calcZeroHeuristics(BB, TLI))
if (calcIntegerHeuristics(BB, TLI))
continue;
if (calcFloatingPointHeuristics(BB))
continue;

View File

@ -101,3 +101,54 @@ for.inc:
exit:
ret void
}
declare void @foo()
; CHECK-LABEL: foo1
define i32 @foo1(i32 %x, i32 %y, i8 signext %z, i8 signext %w) {
entry:
%c = icmp eq i32 %x, %y
br i1 %c, label %then, label %else
; CHECK: edge entry -> then probability is 0x30000000 / 0x80000000 = 37.50%
; CHECK: edge entry -> else probability is 0x50000000 / 0x80000000 = 62.50%
then:
tail call void @foo()
br label %else
; CHECK: edge then -> else probability is 0x80000000 / 0x80000000 = 100.00% [HOT edge]
else:
%v = phi i8 [ %z, %then ], [ %w, %entry ]
%r = sext i8 %v to i32
ret i32 %r
}
; CHECK-LABEL: foo2
define i32 @foo2(i32 %x, i32 %y, i8 signext %z, i8 signext %w) {
entry:
%c = icmp ne i32 %x, %y
br i1 %c, label %then, label %else
; CHECK: edge entry -> then probability is 0x50000000 / 0x80000000 = 62.50%
; CHECK: edge entry -> else probability is 0x30000000 / 0x80000000 = 37.50%
then:
br label %else
; CHECK: edge then -> else probability is 0x80000000 / 0x80000000 = 100.00% [HOT edge]
else:
%v = phi i8 [ %z, %then ], [ %w, %entry ]
%r = sext i8 %v to i32
ret i32 %r
}
; CHECK-LABEL: foo3
define i32 @foo3(i32 %x, i32 %y, i8 signext %z, i8 signext %w) {
entry:
%c = icmp ult i32 %x, %y
br i1 %c, label %then, label %else
; CHECK: edge entry -> then probability is 0x50000000 / 0x80000000 = 62.50%
; CHECK: edge entry -> else probability is 0x30000000 / 0x80000000 = 37.50%
then:
br label %else
; CHECK: edge then -> else probability is 0x80000000 / 0x80000000 = 100.00% [HOT edge]
else:
%v = phi i8 [ %z, %then ], [ %w, %entry ]
%r = sext i8 %v to i32
ret i32 %r
}

View File

@ -263,8 +263,8 @@ for.body:
%0 = load i32, i32* %c, align 4
%cmp1 = icmp eq i32 %0, %i.011
br i1 %cmp1, label %for.inc5, label %if.end
; CHECK: edge for.body -> for.inc5 probability is 0x40000000 / 0x80000000 = 50.00%
; CHECK: edge for.body -> if.end probability is 0x40000000 / 0x80000000 = 50.00%
; CHECK: edge for.body -> for.inc5 probability is 0x30000000 / 0x80000000 = 37.50%
; CHECK: edge for.body -> if.end probability is 0x50000000 / 0x80000000 = 62.50%
if.end:
call void @g1()
@ -324,22 +324,22 @@ for.body3:
%0 = load i32, i32* %c, align 4
%cmp4 = icmp eq i32 %0, %j.017
br i1 %cmp4, label %for.inc, label %if.end
; CHECK: edge for.body3 -> for.inc probability is 0x40000000 / 0x80000000 = 50.00%
; CHECK: edge for.body3 -> if.end probability is 0x40000000 / 0x80000000 = 50.00%
; CHECK: edge for.body3 -> for.inc probability is 0x30000000 / 0x80000000 = 37.50%
; CHECK: edge for.body3 -> if.end probability is 0x50000000 / 0x80000000 = 62.50%
if.end:
%1 = load i32, i32* %arrayidx5, align 4
%cmp6 = icmp eq i32 %1, %j.017
br i1 %cmp6, label %for.inc, label %if.end8
; CHECK: edge if.end -> for.inc probability is 0x40000000 / 0x80000000 = 50.00%
; CHECK: edge if.end -> if.end8 probability is 0x40000000 / 0x80000000 = 50.00%
; CHECK: edge if.end -> for.inc probability is 0x30000000 / 0x80000000 = 37.50%
; CHECK: edge if.end -> if.end8 probability is 0x50000000 / 0x80000000 = 62.50%
if.end8:
%2 = load i32, i32* %arrayidx9, align 4
%cmp10 = icmp eq i32 %2, %j.017
br i1 %cmp10, label %for.inc, label %if.end12
; CHECK: edge if.end8 -> for.inc probability is 0x40000000 / 0x80000000 = 50.00%
; CHECK: edge if.end8 -> if.end12 probability is 0x40000000 / 0x80000000 = 50.00%
; CHECK: edge if.end8 -> for.inc probability is 0x30000000 / 0x80000000 = 37.50%
; CHECK: edge if.end8 -> if.end12 probability is 0x50000000 / 0x80000000 = 62.50%
if.end12:
call void @g2()

View File

@ -88,7 +88,6 @@ exit:
; CHECK-LABEL: test_GEP_across_BB:
; CHECK: ldr {{w[0-9]+}}, [{{x[0-9]+}}, #528]
; CHECK: ldr {{w[0-9]+}}, [{{x[0-9]+}}, #532]
; CHECK-NOT: add
; CHECK: str {{w[0-9]+}}, [{{x[0-9]+}}, #532]
; CHECK: str {{w[0-9]+}}, [{{x[0-9]+}}, #528]

View File

@ -1,19 +1,26 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-apple-darwin -aarch64-bcc-offset-bits=4 -align-all-nofallthru-blocks=4 < %s | FileCheck %s
; Long branch is assumed because the block has a higher alignment
; requirement than the function.
; CHECK-LABEL: invert_bcc_block_align_higher_func:
; CHECK: b.eq [[JUMP_BB1:LBB[0-9]+_[0-9]+]]
; CHECK-NEXT: b [[JUMP_BB2:LBB[0-9]+_[0-9]+]]
; CHECK: [[JUMP_BB1]]:
; CHECK: ret
; CHECK: .p2align 4
; CHECK: [[JUMP_BB2]]:
; CHECK: ret
define i32 @invert_bcc_block_align_higher_func(i32 %x, i32 %y) align 4 #0 {
; CHECK-LABEL: invert_bcc_block_align_higher_func:
; CHECK: ; %bb.0:
; CHECK-NEXT: cmp w0, w1
; CHECK-NEXT: b.ne LBB0_1
; CHECK-NEXT: b LBB0_2
; CHECK-NEXT: LBB0_1: ; %bb2
; CHECK-NEXT: mov w8, #9
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: str w8, [x8]
; CHECK-NEXT: ret
; CHECK-NEXT: .p2align 4
; CHECK-NEXT: LBB0_2: ; %bb1
; CHECK-NEXT: mov w8, #42
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: str w8, [x8]
; CHECK-NEXT: ret
%1 = icmp eq i32 %x, %y
br i1 %1, label %bb1, label %bb2

View File

@ -1,3 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -debugify-and-strip-all-safe < %s -mtriple=aarch64-linux-gnu | FileCheck %s
; marked as external to prevent possible optimizations
@ -8,12 +9,34 @@
; (a > 10 && b == c) || (a >= 10 && b == d)
define i32 @combine_gt_ge_10() #0 {
; CHECK-LABEL: combine_gt_ge_10
; CHECK: cmp
; CHECK: b.le
; CHECK: ret
; CHECK-NOT: cmp
; CHECK: b.lt
; CHECK-LABEL: combine_gt_ge_10:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, a
; CHECK-NEXT: ldr w8, [x8, :lo12:a]
; CHECK-NEXT: cmp w8, #10 // =10
; CHECK-NEXT: adrp x8, b
; CHECK-NEXT: b.le .LBB0_2
; CHECK-NEXT: // %bb.1: // %land.lhs.true
; CHECK-NEXT: adrp x10, c
; CHECK-NEXT: ldr w9, [x8, :lo12:b]
; CHECK-NEXT: ldr w10, [x10, :lo12:c]
; CHECK-NEXT: cmp w9, w10
; CHECK-NEXT: b.ne .LBB0_3
; CHECK-NEXT: b .LBB0_5
; CHECK-NEXT: .LBB0_2: // %lor.lhs.false
; CHECK-NEXT: b.lt .LBB0_4
; CHECK-NEXT: .LBB0_3: // %land.lhs.true3
; CHECK-NEXT: adrp x9, d
; CHECK-NEXT: ldr w8, [x8, :lo12:b]
; CHECK-NEXT: ldr w9, [x9, :lo12:d]
; CHECK-NEXT: cmp w8, w9
; CHECK-NEXT: b.eq .LBB0_5
; CHECK-NEXT: .LBB0_4: // %if.end
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB0_5:
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
entry:
%0 = load i32, i32* @a, align 4
%cmp = icmp sgt i32 %0, 10
@ -45,12 +68,35 @@ return: ; preds = %if.end, %land.lhs.t
; (a > 5 && b == c) || (a < 5 && b == d)
define i32 @combine_gt_lt_5() #0 {
; CHECK-LABEL: combine_gt_lt_5
; CHECK: cmp
; CHECK: b.le
; CHECK: ret
; CHECK-NOT: cmp
; CHECK: b.ge
; CHECK-LABEL: combine_gt_lt_5:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, a
; CHECK-NEXT: ldr w8, [x8, :lo12:a]
; CHECK-NEXT: cmp w8, #5 // =5
; CHECK-NEXT: b.le .LBB1_2
; CHECK-NEXT: // %bb.1: // %land.lhs.true
; CHECK-NEXT: adrp x8, b
; CHECK-NEXT: adrp x9, c
; CHECK-NEXT: ldr w8, [x8, :lo12:b]
; CHECK-NEXT: ldr w9, [x9, :lo12:c]
; CHECK-NEXT: cmp w8, w9
; CHECK-NEXT: b.ne .LBB1_4
; CHECK-NEXT: b .LBB1_5
; CHECK-NEXT: .LBB1_2: // %lor.lhs.false
; CHECK-NEXT: b.ge .LBB1_4
; CHECK-NEXT: // %bb.3: // %land.lhs.true3
; CHECK-NEXT: adrp x8, b
; CHECK-NEXT: adrp x9, d
; CHECK-NEXT: ldr w8, [x8, :lo12:b]
; CHECK-NEXT: ldr w9, [x9, :lo12:d]
; CHECK-NEXT: cmp w8, w9
; CHECK-NEXT: b.eq .LBB1_5
; CHECK-NEXT: .LBB1_4: // %if.end
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB1_5:
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
entry:
%0 = load i32, i32* @a, align 4
%cmp = icmp sgt i32 %0, 5
@ -82,12 +128,34 @@ return: ; preds = %if.end, %land.lhs.t
; (a < 5 && b == c) || (a <= 5 && b == d)
define i32 @combine_lt_ge_5() #0 {
; CHECK-LABEL: combine_lt_ge_5
; CHECK: cmp
; CHECK: b.ge
; CHECK: ret
; CHECK-NOT: cmp
; CHECK: b.gt
; CHECK-LABEL: combine_lt_ge_5:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, a
; CHECK-NEXT: ldr w8, [x8, :lo12:a]
; CHECK-NEXT: cmp w8, #5 // =5
; CHECK-NEXT: adrp x8, b
; CHECK-NEXT: b.ge .LBB2_2
; CHECK-NEXT: // %bb.1: // %land.lhs.true
; CHECK-NEXT: adrp x10, c
; CHECK-NEXT: ldr w9, [x8, :lo12:b]
; CHECK-NEXT: ldr w10, [x10, :lo12:c]
; CHECK-NEXT: cmp w9, w10
; CHECK-NEXT: b.ne .LBB2_3
; CHECK-NEXT: b .LBB2_5
; CHECK-NEXT: .LBB2_2: // %lor.lhs.false
; CHECK-NEXT: b.gt .LBB2_4
; CHECK-NEXT: .LBB2_3: // %land.lhs.true3
; CHECK-NEXT: adrp x9, d
; CHECK-NEXT: ldr w8, [x8, :lo12:b]
; CHECK-NEXT: ldr w9, [x9, :lo12:d]
; CHECK-NEXT: cmp w8, w9
; CHECK-NEXT: b.eq .LBB2_5
; CHECK-NEXT: .LBB2_4: // %if.end
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB2_5:
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
entry:
%0 = load i32, i32* @a, align 4
%cmp = icmp slt i32 %0, 5
@ -119,12 +187,35 @@ return: ; preds = %if.end, %land.lhs.t
; (a < 5 && b == c) || (a > 5 && b == d)
define i32 @combine_lt_gt_5() #0 {
; CHECK-LABEL: combine_lt_gt_5
; CHECK: cmp
; CHECK: b.ge
; CHECK: ret
; CHECK-NOT: cmp
; CHECK: b.le
; CHECK-LABEL: combine_lt_gt_5:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, a
; CHECK-NEXT: ldr w8, [x8, :lo12:a]
; CHECK-NEXT: cmp w8, #5 // =5
; CHECK-NEXT: b.ge .LBB3_2
; CHECK-NEXT: // %bb.1: // %land.lhs.true
; CHECK-NEXT: adrp x8, b
; CHECK-NEXT: adrp x9, c
; CHECK-NEXT: ldr w8, [x8, :lo12:b]
; CHECK-NEXT: ldr w9, [x9, :lo12:c]
; CHECK-NEXT: cmp w8, w9
; CHECK-NEXT: b.ne .LBB3_4
; CHECK-NEXT: b .LBB3_5
; CHECK-NEXT: .LBB3_2: // %lor.lhs.false
; CHECK-NEXT: b.le .LBB3_4
; CHECK-NEXT: // %bb.3: // %land.lhs.true3
; CHECK-NEXT: adrp x8, b
; CHECK-NEXT: adrp x9, d
; CHECK-NEXT: ldr w8, [x8, :lo12:b]
; CHECK-NEXT: ldr w9, [x9, :lo12:d]
; CHECK-NEXT: cmp w8, w9
; CHECK-NEXT: b.eq .LBB3_5
; CHECK-NEXT: .LBB3_4: // %if.end
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB3_5:
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
entry:
%0 = load i32, i32* @a, align 4
%cmp = icmp slt i32 %0, 5
@ -156,12 +247,35 @@ return: ; preds = %if.end, %land.lhs.t
; (a > -5 && b == c) || (a < -5 && b == d)
define i32 @combine_gt_lt_n5() #0 {
; CHECK-LABEL: combine_gt_lt_n5
; CHECK: cmn
; CHECK: b.le
; CHECK: ret
; CHECK-NOT: cmn
; CHECK: b.ge
; CHECK-LABEL: combine_gt_lt_n5:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, a
; CHECK-NEXT: ldr w8, [x8, :lo12:a]
; CHECK-NEXT: cmn w8, #5 // =5
; CHECK-NEXT: b.le .LBB4_2
; CHECK-NEXT: // %bb.1: // %land.lhs.true
; CHECK-NEXT: adrp x8, b
; CHECK-NEXT: adrp x9, c
; CHECK-NEXT: ldr w8, [x8, :lo12:b]
; CHECK-NEXT: ldr w9, [x9, :lo12:c]
; CHECK-NEXT: cmp w8, w9
; CHECK-NEXT: b.ne .LBB4_4
; CHECK-NEXT: b .LBB4_5
; CHECK-NEXT: .LBB4_2: // %lor.lhs.false
; CHECK-NEXT: b.ge .LBB4_4
; CHECK-NEXT: // %bb.3: // %land.lhs.true3
; CHECK-NEXT: adrp x8, b
; CHECK-NEXT: adrp x9, d
; CHECK-NEXT: ldr w8, [x8, :lo12:b]
; CHECK-NEXT: ldr w9, [x9, :lo12:d]
; CHECK-NEXT: cmp w8, w9
; CHECK-NEXT: b.eq .LBB4_5
; CHECK-NEXT: .LBB4_4: // %if.end
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB4_5:
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
entry:
%0 = load i32, i32* @a, align 4
%cmp = icmp sgt i32 %0, -5
@ -193,12 +307,35 @@ return: ; preds = %if.end, %land.lhs.t
; (a < -5 && b == c) || (a > -5 && b == d)
define i32 @combine_lt_gt_n5() #0 {
; CHECK-LABEL: combine_lt_gt_n5
; CHECK: cmn
; CHECK: b.ge
; CHECK: ret
; CHECK-NOT: cmn
; CHECK: b.le
; CHECK-LABEL: combine_lt_gt_n5:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, a
; CHECK-NEXT: ldr w8, [x8, :lo12:a]
; CHECK-NEXT: cmn w8, #5 // =5
; CHECK-NEXT: b.ge .LBB5_2
; CHECK-NEXT: // %bb.1: // %land.lhs.true
; CHECK-NEXT: adrp x8, b
; CHECK-NEXT: adrp x9, c
; CHECK-NEXT: ldr w8, [x8, :lo12:b]
; CHECK-NEXT: ldr w9, [x9, :lo12:c]
; CHECK-NEXT: cmp w8, w9
; CHECK-NEXT: b.ne .LBB5_4
; CHECK-NEXT: b .LBB5_5
; CHECK-NEXT: .LBB5_2: // %lor.lhs.false
; CHECK-NEXT: b.le .LBB5_4
; CHECK-NEXT: // %bb.3: // %land.lhs.true3
; CHECK-NEXT: adrp x8, b
; CHECK-NEXT: adrp x9, d
; CHECK-NEXT: ldr w8, [x8, :lo12:b]
; CHECK-NEXT: ldr w9, [x9, :lo12:d]
; CHECK-NEXT: cmp w8, w9
; CHECK-NEXT: b.eq .LBB5_5
; CHECK-NEXT: .LBB5_4: // %if.end
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB5_5:
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
entry:
%0 = load i32, i32* @a, align 4
%cmp = icmp slt i32 %0, -5
@ -236,6 +373,38 @@ declare %struct.Struct* @Update(%struct.Struct*) #1
; no checks for this case, it just should be processed without errors
define void @combine_non_adjacent_cmp_br(%struct.Struct* nocapture readonly %hdCall) #0 {
; CHECK-LABEL: combine_non_adjacent_cmp_br:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: str x30, [sp, #-48]! // 8-byte Folded Spill
; CHECK-NEXT: stp x22, x21, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: stp x20, x19, [sp, #32] // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 48
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w20, -16
; CHECK-NEXT: .cfi_offset w21, -24
; CHECK-NEXT: .cfi_offset w22, -32
; CHECK-NEXT: .cfi_offset w30, -48
; CHECK-NEXT: ldr x19, [x0]
; CHECK-NEXT: mov w20, #24
; CHECK-NEXT: adrp x22, glob
; CHECK-NEXT: add x21, x19, #2 // =2
; CHECK-NEXT: .LBB6_1: // %land.rhs
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr x8, [x20]
; CHECK-NEXT: cmp x8, #1 // =1
; CHECK-NEXT: b.lt .LBB6_3
; CHECK-NEXT: // %bb.2: // %while.body
; CHECK-NEXT: // in Loop: Header=BB6_1 Depth=1
; CHECK-NEXT: ldr x0, [x22, :lo12:glob]
; CHECK-NEXT: bl Update
; CHECK-NEXT: sub x21, x21, #2 // =2
; CHECK-NEXT: cmp x19, x21
; CHECK-NEXT: b.lt .LBB6_1
; CHECK-NEXT: .LBB6_3: // %while.end
; CHECK-NEXT: ldp x20, x19, [sp, #32] // 16-byte Folded Reload
; CHECK-NEXT: ldp x22, x21, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x30, [sp], #48 // 8-byte Folded Reload
; CHECK-NEXT: ret
entry:
%size = getelementptr inbounds %struct.Struct, %struct.Struct* %hdCall, i64 0, i32 0
%0 = load i64, i64* %size, align 8
@ -262,11 +431,49 @@ while.end:
declare void @do_something() #1
define i32 @do_nothing_if_resultant_opcodes_would_differ() #0 {
; CHECK-LABEL: do_nothing_if_resultant_opcodes_would_differ
; CHECK: cmn
; CHECK: b.gt
; CHECK: cmp
; CHECK: b.gt
; CHECK-LABEL: do_nothing_if_resultant_opcodes_would_differ:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: str x30, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 32
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w20, -16
; CHECK-NEXT: .cfi_offset w30, -32
; CHECK-NEXT: adrp x19, a
; CHECK-NEXT: ldr w8, [x19, :lo12:a]
; CHECK-NEXT: cmn w8, #2 // =2
; CHECK-NEXT: b.le .LBB7_2
; CHECK-NEXT: // %bb.1: // %while.end
; CHECK-NEXT: cmp w8, #1 // =1
; CHECK-NEXT: b.le .LBB7_5
; CHECK-NEXT: b .LBB7_6
; CHECK-NEXT: .LBB7_2: // %while.body.preheader
; CHECK-NEXT: sub w20, w8, #1 // =1
; CHECK-NEXT: .LBB7_3: // %while.body
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
; CHECK-NEXT: bl do_something
; CHECK-NEXT: adds w20, w20, #1 // =1
; CHECK-NEXT: b.mi .LBB7_3
; CHECK-NEXT: // %bb.4: // %while.cond.while.end_crit_edge
; CHECK-NEXT: ldr w8, [x19, :lo12:a]
; CHECK-NEXT: cmp w8, #1 // =1
; CHECK-NEXT: b.gt .LBB7_6
; CHECK-NEXT: .LBB7_5: // %land.lhs.true
; CHECK-NEXT: adrp x8, b
; CHECK-NEXT: adrp x9, d
; CHECK-NEXT: ldr w8, [x8, :lo12:b]
; CHECK-NEXT: ldr w9, [x9, :lo12:d]
; CHECK-NEXT: cmp w8, w9
; CHECK-NEXT: b.eq .LBB7_7
; CHECK-NEXT: .LBB7_6: // %if.end
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: b .LBB7_8
; CHECK-NEXT: .LBB7_7:
; CHECK-NEXT: mov w0, #123
; CHECK-NEXT: .LBB7_8: // %return
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ret
entry:
%0 = load i32, i32* @a, align 4
%cmp4 = icmp slt i32 %0, -1
@ -306,11 +513,43 @@ return: ; preds = %if.end, %land.lhs.t
}
define i32 @do_nothing_if_compares_can_not_be_adjusted_to_each_other() #0 {
; CHECK-LABEL: do_nothing_if_compares_can_not_be_adjusted_to_each_other
; CHECK: cmp
; CHECK: b.gt
; CHECK: cmn
; CHECK: b.lt
; CHECK-LABEL: do_nothing_if_compares_can_not_be_adjusted_to_each_other:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: stp x30, x19, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: adrp x8, a
; CHECK-NEXT: ldr w8, [x8, :lo12:a]
; CHECK-NEXT: cmp w8, #0 // =0
; CHECK-NEXT: b.gt .LBB8_3
; CHECK-NEXT: // %bb.1: // %while.body.preheader
; CHECK-NEXT: sub w19, w8, #1 // =1
; CHECK-NEXT: .LBB8_2: // %while.body
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
; CHECK-NEXT: bl do_something
; CHECK-NEXT: adds w19, w19, #1 // =1
; CHECK-NEXT: b.mi .LBB8_2
; CHECK-NEXT: .LBB8_3: // %while.end
; CHECK-NEXT: adrp x8, c
; CHECK-NEXT: ldr w8, [x8, :lo12:c]
; CHECK-NEXT: cmn w8, #2 // =2
; CHECK-NEXT: b.lt .LBB8_5
; CHECK-NEXT: // %bb.4: // %land.lhs.true
; CHECK-NEXT: adrp x8, b
; CHECK-NEXT: adrp x9, d
; CHECK-NEXT: ldr w8, [x8, :lo12:b]
; CHECK-NEXT: ldr w9, [x9, :lo12:d]
; CHECK-NEXT: cmp w8, w9
; CHECK-NEXT: b.eq .LBB8_6
; CHECK-NEXT: .LBB8_5: // %if.end
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB8_6:
; CHECK-NEXT: mov w0, #123
; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
entry:
%0 = load i32, i32* @a, align 4
%cmp4 = icmp slt i32 %0, 1
@ -356,19 +595,44 @@ return: ; preds = %if.end, %land.lhs.t
; b.gt .LBB0_5
define i32 @fcmpri(i32 %argc, i8** nocapture readonly %argv) {
; CHECK-LABEL: fcmpri:
; CHECK: cmp w0, #2
; CHECK: b.lt .LBB9_3
; CHECK-NOT: cmp w0, #1
; CHECK-NOT: b.le .LBB9_3
; CHECK-LABEL-DAG: .LBB9_3
; CHECK: cmp w19, #0
; CHECK: fcmp d8, #0.0
; CHECK-NOT: cmp w19, #1
; CHECK-NOT: b.ge .LBB9_5
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: str d8, [sp, #-32]! // 8-byte Folded Spill
; CHECK-NEXT: stp x30, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 32
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: .cfi_offset b8, -32
; CHECK-NEXT: cmp w0, #2 // =2
; CHECK-NEXT: b.lt .LBB9_3
; CHECK-NEXT: // %bb.1: // %land.lhs.true
; CHECK-NEXT: ldr x8, [x1, #8]
; CHECK-NEXT: cbz x8, .LBB9_3
; CHECK-NEXT: // %bb.2:
; CHECK-NEXT: mov w0, #3
; CHECK-NEXT: b .LBB9_4
; CHECK-NEXT: .LBB9_3: // %if.end
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: bl zoo
; CHECK-NEXT: mov w19, w0
; CHECK-NEXT: mov w0, #-1
; CHECK-NEXT: bl yoo
; CHECK-NEXT: cmp w19, #0 // =0
; CHECK-NEXT: cinc w0, w19, gt
; CHECK-NEXT: mov w1, #2
; CHECK-NEXT: mov v8.16b, v0.16b
; CHECK-NEXT: bl xoo
; CHECK-NEXT: fmov d0, #-1.00000000
; CHECK-NEXT: fadd d0, d8, d0
; CHECK-NEXT: fcmp d8, #0.0
; CHECK-NEXT: fcsel d0, d8, d0, gt
; CHECK-NEXT: fmov d1, #-2.00000000
; CHECK-NEXT: bl woo
; CHECK-NEXT: mov w0, #4
; CHECK-NEXT: .LBB9_4: // %return
; CHECK-NEXT: ldp x30, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr d8, [sp], #32 // 8-byte Folded Reload
; CHECK-NEXT: ret
entry:
%cmp = icmp sgt i32 %argc, 1
br i1 %cmp, label %land.lhs.true, label %if.end
@ -405,10 +669,27 @@ return: ; preds = %land.lhs.true, %con
define void @cmp_shifted(i32 %in, i32 %lhs, i32 %rhs) {
; CHECK-LABEL: cmp_shifted:
; CHECK: cmp w0, #2, lsl #12
; [...]
; CHECK: cmp w0, #1
; CHECK: // %bb.0:
; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: cmp w0, #2, lsl #12 // =8192
; CHECK-NEXT: b.lt .LBB10_2
; CHECK-NEXT: // %bb.1: // %true
; CHECK-NEXT: mov w0, #128
; CHECK-NEXT: b .LBB10_5
; CHECK-NEXT: .LBB10_2: // %false
; CHECK-NEXT: cmp w0, #1 // =1
; CHECK-NEXT: b.lt .LBB10_4
; CHECK-NEXT: // %bb.3: // %truer
; CHECK-NEXT: mov w0, #42
; CHECK-NEXT: b .LBB10_5
; CHECK-NEXT: .LBB10_4: // %falser
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: .LBB10_5: // %true
; CHECK-NEXT: bl zoo
; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: ret
%tst_low = icmp sgt i32 %in, 8191
br i1 %tst_low, label %true, label %false
@ -430,10 +711,38 @@ falser:
}
define i32 @combine_gt_ge_sel(i64 %v, i64* %p) #0 {
; CHECK-LABEL: combine_gt_ge_sel
; CHECK: ldr [[reg1:w[0-9]*]],
; CHECK: cmp [[reg1]], #0
; CHECK: csel {{.*}}, gt
; CHECK-LABEL: combine_gt_ge_sel:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, a
; CHECK-NEXT: ldr w8, [x8, :lo12:a]
; CHECK-NEXT: cmp w8, #0 // =0
; CHECK-NEXT: csel x9, x0, xzr, gt
; CHECK-NEXT: str x9, [x1]
; CHECK-NEXT: b.le .LBB11_2
; CHECK-NEXT: // %bb.1: // %lor.lhs.false
; CHECK-NEXT: cmp w8, #2 // =2
; CHECK-NEXT: b.ge .LBB11_3
; CHECK-NEXT: b .LBB11_4
; CHECK-NEXT: .LBB11_2: // %land.lhs.true
; CHECK-NEXT: adrp x8, b
; CHECK-NEXT: adrp x9, c
; CHECK-NEXT: ldr w8, [x8, :lo12:b]
; CHECK-NEXT: ldr w9, [x9, :lo12:c]
; CHECK-NEXT: cmp w8, w9
; CHECK-NEXT: b.eq .LBB11_5
; CHECK-NEXT: .LBB11_3: // %land.lhs.true3
; CHECK-NEXT: adrp x8, b
; CHECK-NEXT: adrp x9, d
; CHECK-NEXT: ldr w8, [x8, :lo12:b]
; CHECK-NEXT: ldr w9, [x9, :lo12:d]
; CHECK-NEXT: cmp w8, w9
; CHECK-NEXT: b.eq .LBB11_5
; CHECK-NEXT: .LBB11_4: // %if.end
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB11_5:
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
entry:
%0 = load i32, i32* @a, align 4
%cmp = icmp sgt i32 %0, 0

View File

@ -1,14 +1,22 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -debugify-and-strip-all-safe < %s -O3 -mtriple=aarch64-eabi -verify-machineinstrs | FileCheck %s
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
target triple = "aarch64-linaro-linux-gnueabi"
; CMN is an alias of ADDS.
; CHECK-LABEL: test_add_cbz:
; CHECK: cmn w0, w1
; CHECK: b.eq
; CHECK: ret
define void @test_add_cbz(i32 %a, i32 %b, i32* %ptr) {
; CHECK-LABEL: test_add_cbz:
; CHECK: // %bb.0:
; CHECK-NEXT: cmn w0, w1
; CHECK-NEXT: b.eq .LBB0_2
; CHECK-NEXT: // %bb.1: // %L1
; CHECK-NEXT: str wzr, [x2]
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB0_2: // %L2
; CHECK-NEXT: mov w8, #1
; CHECK-NEXT: str w8, [x2]
; CHECK-NEXT: ret
%c = add nsw i32 %a, %b
%d = icmp ne i32 %c, 0
br i1 %d, label %L1, label %L2
@ -20,11 +28,17 @@ L2:
ret void
}
; CHECK-LABEL: test_add_cbz_multiple_use:
; CHECK: adds
; CHECK: b.eq
; CHECK: ret
define void @test_add_cbz_multiple_use(i32 %a, i32 %b, i32* %ptr) {
; CHECK-LABEL: test_add_cbz_multiple_use:
; CHECK: // %bb.0:
; CHECK-NEXT: adds w8, w0, w1
; CHECK-NEXT: b.eq .LBB1_2
; CHECK-NEXT: // %bb.1: // %L1
; CHECK-NEXT: str wzr, [x2]
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB1_2: // %L2
; CHECK-NEXT: str w8, [x2]
; CHECK-NEXT: ret
%c = add nsw i32 %a, %b
%d = icmp ne i32 %c, 0
br i1 %d, label %L1, label %L2
@ -36,10 +50,18 @@ L2:
ret void
}
; CHECK-LABEL: test_add_cbz_64:
; CHECK: cmn x0, x1
; CHECK: b.eq
define void @test_add_cbz_64(i64 %a, i64 %b, i64* %ptr) {
; CHECK-LABEL: test_add_cbz_64:
; CHECK: // %bb.0:
; CHECK-NEXT: cmn x0, x1
; CHECK-NEXT: b.eq .LBB2_2
; CHECK-NEXT: // %bb.1: // %L1
; CHECK-NEXT: str xzr, [x2]
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB2_2: // %L2
; CHECK-NEXT: mov w8, #1
; CHECK-NEXT: str x8, [x2]
; CHECK-NEXT: ret
%c = add nsw i64 %a, %b
%d = icmp ne i64 %c, 0
br i1 %d, label %L1, label %L2
@ -51,10 +73,18 @@ L2:
ret void
}
; CHECK-LABEL: test_and_cbz:
; CHECK: tst w0, #0x6
; CHECK: b.eq
define void @test_and_cbz(i32 %a, i32* %ptr) {
; CHECK-LABEL: test_and_cbz:
; CHECK: // %bb.0:
; CHECK-NEXT: tst w0, #0x6
; CHECK-NEXT: b.eq .LBB3_2
; CHECK-NEXT: // %bb.1: // %L1
; CHECK-NEXT: str wzr, [x1]
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB3_2: // %L2
; CHECK-NEXT: mov w8, #1
; CHECK-NEXT: str w8, [x1]
; CHECK-NEXT: ret
%c = and i32 %a, 6
%d = icmp ne i32 %c, 0
br i1 %d, label %L1, label %L2
@ -66,10 +96,18 @@ L2:
ret void
}
; CHECK-LABEL: test_bic_cbnz:
; CHECK: bics wzr, w1, w0
; CHECK: b.ne
define void @test_bic_cbnz(i32 %a, i32 %b, i32* %ptr) {
; CHECK-LABEL: test_bic_cbnz:
; CHECK: // %bb.0:
; CHECK-NEXT: bics wzr, w1, w0
; CHECK-NEXT: b.eq .LBB4_2
; CHECK-NEXT: // %bb.1: // %L2
; CHECK-NEXT: mov w8, #1
; CHECK-NEXT: str w8, [x2]
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB4_2: // %L1
; CHECK-NEXT: str wzr, [x2]
; CHECK-NEXT: ret
%c = and i32 %a, %b
%d = icmp eq i32 %c, %b
br i1 %d, label %L1, label %L2
@ -81,11 +119,15 @@ L2:
ret void
}
; CHECK-LABEL: test_add_tbz:
; CHECK: adds
; CHECK: b.pl
; CHECK: ret
define void @test_add_tbz(i32 %a, i32 %b, i32* %ptr) {
; CHECK-LABEL: test_add_tbz:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adds w8, w0, w1
; CHECK-NEXT: b.pl .LBB5_2
; CHECK-NEXT: // %bb.1: // %L1
; CHECK-NEXT: str w8, [x2]
; CHECK-NEXT: .LBB5_2: // %L2
; CHECK-NEXT: ret
entry:
%add = add nsw i32 %a, %b
%cmp36 = icmp sge i32 %add, 0
@ -97,11 +139,15 @@ L2:
ret void
}
; CHECK-LABEL: test_subs_tbz:
; CHECK: subs
; CHECK: b.pl
; CHECK: ret
define void @test_subs_tbz(i32 %a, i32 %b, i32* %ptr) {
; CHECK-LABEL: test_subs_tbz:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: subs w8, w0, w1
; CHECK-NEXT: b.pl .LBB6_2
; CHECK-NEXT: // %bb.1: // %L1
; CHECK-NEXT: str w8, [x2]
; CHECK-NEXT: .LBB6_2: // %L2
; CHECK-NEXT: ret
entry:
%sub = sub nsw i32 %a, %b
%cmp36 = icmp sge i32 %sub, 0
@ -113,11 +159,15 @@ L2:
ret void
}
; CHECK-LABEL: test_add_tbnz
; CHECK: adds
; CHECK: b.mi
; CHECK: ret
define void @test_add_tbnz(i32 %a, i32 %b, i32* %ptr) {
; CHECK-LABEL: test_add_tbnz:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adds w8, w0, w1
; CHECK-NEXT: b.mi .LBB7_2
; CHECK-NEXT: // %bb.1: // %L1
; CHECK-NEXT: str w8, [x2]
; CHECK-NEXT: .LBB7_2: // %L2
; CHECK-NEXT: ret
entry:
%add = add nsw i32 %a, %b
%cmp36 = icmp slt i32 %add, 0
@ -129,11 +179,15 @@ L2:
ret void
}
; CHECK-LABEL: test_subs_tbnz
; CHECK: subs
; CHECK: b.mi
; CHECK: ret
define void @test_subs_tbnz(i32 %a, i32 %b, i32* %ptr) {
; CHECK-LABEL: test_subs_tbnz:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: subs w8, w0, w1
; CHECK-NEXT: b.mi .LBB8_2
; CHECK-NEXT: // %bb.1: // %L1
; CHECK-NEXT: str w8, [x2]
; CHECK-NEXT: .LBB8_2: // %L2
; CHECK-NEXT: ret
entry:
%sub = sub nsw i32 %a, %b
%cmp36 = icmp slt i32 %sub, 0
@ -149,11 +203,22 @@ declare void @foo()
declare void @bar(i32)
; Don't transform since the call will clobber the NZCV bits.
; CHECK-LABEL: test_call_clobber:
; CHECK: and w[[DST:[0-9]+]], w1, #0x6
; CHECK: bl bar
; CHECK: cbnz w[[DST]]
define void @test_call_clobber(i32 %unused, i32 %a) {
; CHECK-LABEL: test_call_clobber:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: stp x30, x19, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: and w19, w1, #0x6
; CHECK-NEXT: mov w0, w19
; CHECK-NEXT: bl bar
; CHECK-NEXT: cbnz w19, .LBB9_2
; CHECK-NEXT: // %bb.1: // %if.end
; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB9_2: // %if.then
; CHECK-NEXT: bl foo
entry:
%c = and i32 %a, 6
call void @bar(i32 %c)

View File

@ -1,10 +1,18 @@
; RUN: llc -aarch64-enable-atomic-cfg-tidy=0 -mtriple=aarch64-apple-darwin < %s | FileCheck %s
; RUN: llc -fast-isel -fast-isel-abort=1 -aarch64-enable-atomic-cfg-tidy=0 -mtriple=aarch64-apple-darwin < %s | FileCheck %s
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -aarch64-enable-atomic-cfg-tidy=0 -mtriple=aarch64-apple-darwin < %s | FileCheck %s --check-prefixes=CHECK,NOFASTISEL
; RUN: llc -fast-isel -fast-isel-abort=1 -aarch64-enable-atomic-cfg-tidy=0 -mtriple=aarch64-apple-darwin < %s | FileCheck %s --check-prefixes=CHECK,FASTISEL
define i32 @fcmp_oeq(float %x, float %y) {
; CHECK-LABEL: fcmp_oeq
; CHECK: fcmp s0, s1
; CHECK-NEXT: b.ne {{LBB.+_2}}
; CHECK-LABEL: fcmp_oeq:
; CHECK: ; %bb.0:
; CHECK-NEXT: fcmp s0, s1
; CHECK-NEXT: b.ne LBB0_2
; CHECK-NEXT: ; %bb.1: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: LBB0_2: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
%1 = fcmp oeq float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -14,9 +22,16 @@ bb1:
}
define i32 @fcmp_ogt(float %x, float %y) {
; CHECK-LABEL: fcmp_ogt
; CHECK: fcmp s0, s1
; CHECK-NEXT: b.le {{LBB.+_2}}
; CHECK-LABEL: fcmp_ogt:
; CHECK: ; %bb.0:
; CHECK-NEXT: fcmp s0, s1
; CHECK-NEXT: b.le LBB1_2
; CHECK-NEXT: ; %bb.1: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: LBB1_2: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
%1 = fcmp ogt float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -26,9 +41,16 @@ bb1:
}
define i32 @fcmp_oge(float %x, float %y) {
; CHECK-LABEL: fcmp_oge
; CHECK: fcmp s0, s1
; CHECK-NEXT: b.lt {{LBB.+_2}}
; CHECK-LABEL: fcmp_oge:
; CHECK: ; %bb.0:
; CHECK-NEXT: fcmp s0, s1
; CHECK-NEXT: b.lt LBB2_2
; CHECK-NEXT: ; %bb.1: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: LBB2_2: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
%1 = fcmp oge float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -38,9 +60,16 @@ bb1:
}
define i32 @fcmp_olt(float %x, float %y) {
; CHECK-LABEL: fcmp_olt
; CHECK: fcmp s0, s1
; CHECK-NEXT: b.pl {{LBB.+_2}}
; CHECK-LABEL: fcmp_olt:
; CHECK: ; %bb.0:
; CHECK-NEXT: fcmp s0, s1
; CHECK-NEXT: b.pl LBB3_2
; CHECK-NEXT: ; %bb.1: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: LBB3_2: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
%1 = fcmp olt float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -50,9 +79,16 @@ bb1:
}
define i32 @fcmp_ole(float %x, float %y) {
; CHECK-LABEL: fcmp_ole
; CHECK: fcmp s0, s1
; CHECK-NEXT: b.hi {{LBB.+_2}}
; CHECK-LABEL: fcmp_ole:
; CHECK: ; %bb.0:
; CHECK-NEXT: fcmp s0, s1
; CHECK-NEXT: b.hi LBB4_2
; CHECK-NEXT: ; %bb.1: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: LBB4_2: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
%1 = fcmp ole float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -62,10 +98,30 @@ bb1:
}
define i32 @fcmp_one(float %x, float %y) {
; CHECK-LABEL: fcmp_one
; CHECK: fcmp s0, s1
; CHECK-NEXT: b.mi
; CHECK-NEXT: b.gt
; NOFASTISEL-LABEL: fcmp_one:
; NOFASTISEL: ; %bb.0:
; NOFASTISEL-NEXT: fcmp s0, s1
; NOFASTISEL-NEXT: b.mi LBB5_1
; NOFASTISEL-NEXT: b.gt LBB5_1
; NOFASTISEL-NEXT: b LBB5_2
; NOFASTISEL-NEXT: LBB5_1: ; %bb1
; NOFASTISEL-NEXT: mov w0, wzr
; NOFASTISEL-NEXT: ret
; NOFASTISEL-NEXT: LBB5_2: ; %bb2
; NOFASTISEL-NEXT: mov w0, #1
; NOFASTISEL-NEXT: ret
;
; FASTISEL-LABEL: fcmp_one:
; FASTISEL: ; %bb.0:
; FASTISEL-NEXT: fcmp s0, s1
; FASTISEL-NEXT: b.mi LBB5_2
; FASTISEL-NEXT: b.gt LBB5_2
; FASTISEL-NEXT: ; %bb.1: ; %bb2
; FASTISEL-NEXT: mov w0, #1
; FASTISEL-NEXT: ret
; FASTISEL-NEXT: LBB5_2: ; %bb1
; FASTISEL-NEXT: mov w0, wzr
; FASTISEL-NEXT: ret
%1 = fcmp one float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -75,9 +131,16 @@ bb1:
}
define i32 @fcmp_ord(float %x, float %y) {
; CHECK-LABEL: fcmp_ord
; CHECK: fcmp s0, s1
; CHECK-NEXT: b.vs {{LBB.+_2}}
; CHECK-LABEL: fcmp_ord:
; CHECK: ; %bb.0:
; CHECK-NEXT: fcmp s0, s1
; CHECK-NEXT: b.vs LBB6_2
; CHECK-NEXT: ; %bb.1: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: LBB6_2: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
%1 = fcmp ord float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -87,9 +150,16 @@ bb1:
}
define i32 @fcmp_uno(float %x, float %y) {
; CHECK-LABEL: fcmp_uno
; CHECK: fcmp s0, s1
; CHECK-NEXT: b.vs {{LBB.+_2}}
; CHECK-LABEL: fcmp_uno:
; CHECK: ; %bb.0:
; CHECK-NEXT: fcmp s0, s1
; CHECK-NEXT: b.vs LBB7_2
; CHECK-NEXT: ; %bb.1: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
; CHECK-NEXT: LBB7_2: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
%1 = fcmp uno float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -99,10 +169,30 @@ bb1:
}
define i32 @fcmp_ueq(float %x, float %y) {
; CHECK-LABEL: fcmp_ueq
; CHECK: fcmp s0, s1
; CHECK-NEXT: b.eq {{LBB.+_2}}
; CHECK-NEXT: b.vs {{LBB.+_2}}
; NOFASTISEL-LABEL: fcmp_ueq:
; NOFASTISEL: ; %bb.0:
; NOFASTISEL-NEXT: fcmp s0, s1
; NOFASTISEL-NEXT: b.eq LBB8_2
; NOFASTISEL-NEXT: b.vs LBB8_2
; NOFASTISEL-NEXT: b LBB8_1
; NOFASTISEL-NEXT: LBB8_1: ; %bb2
; NOFASTISEL-NEXT: mov w0, #1
; NOFASTISEL-NEXT: ret
; NOFASTISEL-NEXT: LBB8_2: ; %bb1
; NOFASTISEL-NEXT: mov w0, wzr
; NOFASTISEL-NEXT: ret
;
; FASTISEL-LABEL: fcmp_ueq:
; FASTISEL: ; %bb.0:
; FASTISEL-NEXT: fcmp s0, s1
; FASTISEL-NEXT: b.eq LBB8_2
; FASTISEL-NEXT: b.vs LBB8_2
; FASTISEL-NEXT: ; %bb.1: ; %bb2
; FASTISEL-NEXT: mov w0, #1
; FASTISEL-NEXT: ret
; FASTISEL-NEXT: LBB8_2: ; %bb1
; FASTISEL-NEXT: mov w0, wzr
; FASTISEL-NEXT: ret
%1 = fcmp ueq float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -112,9 +202,16 @@ bb1:
}
define i32 @fcmp_ugt(float %x, float %y) {
; CHECK-LABEL: fcmp_ugt
; CHECK: fcmp s0, s1
; CHECK-NEXT: b.ls {{LBB.+_2}}
; CHECK-LABEL: fcmp_ugt:
; CHECK: ; %bb.0:
; CHECK-NEXT: fcmp s0, s1
; CHECK-NEXT: b.ls LBB9_2
; CHECK-NEXT: ; %bb.1: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: LBB9_2: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
%1 = fcmp ugt float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -124,9 +221,16 @@ bb1:
}
define i32 @fcmp_uge(float %x, float %y) {
; CHECK-LABEL: fcmp_uge
; CHECK: fcmp s0, s1
; CHECK-NEXT: b.mi {{LBB.+_2}}
; CHECK-LABEL: fcmp_uge:
; CHECK: ; %bb.0:
; CHECK-NEXT: fcmp s0, s1
; CHECK-NEXT: b.mi LBB10_2
; CHECK-NEXT: ; %bb.1: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: LBB10_2: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
%1 = fcmp uge float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -136,9 +240,16 @@ bb1:
}
define i32 @fcmp_ult(float %x, float %y) {
; CHECK-LABEL: fcmp_ult
; CHECK: fcmp s0, s1
; CHECK-NEXT: b.ge {{LBB.+_2}}
; CHECK-LABEL: fcmp_ult:
; CHECK: ; %bb.0:
; CHECK-NEXT: fcmp s0, s1
; CHECK-NEXT: b.ge LBB11_2
; CHECK-NEXT: ; %bb.1: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: LBB11_2: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
%1 = fcmp ult float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -148,9 +259,16 @@ bb1:
}
define i32 @fcmp_ule(float %x, float %y) {
; CHECK-LABEL: fcmp_ule
; CHECK: fcmp s0, s1
; CHECK-NEXT: b.gt {{LBB.+_2}}
; CHECK-LABEL: fcmp_ule:
; CHECK: ; %bb.0:
; CHECK-NEXT: fcmp s0, s1
; CHECK-NEXT: b.gt LBB12_2
; CHECK-NEXT: ; %bb.1: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: LBB12_2: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
%1 = fcmp ule float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -160,9 +278,16 @@ bb1:
}
define i32 @fcmp_une(float %x, float %y) {
; CHECK-LABEL: fcmp_une
; CHECK: fcmp s0, s1
; CHECK-NEXT: b.eq {{LBB.+_2}}
; CHECK-LABEL: fcmp_une:
; CHECK: ; %bb.0:
; CHECK-NEXT: fcmp s0, s1
; CHECK-NEXT: b.eq LBB13_2
; CHECK-NEXT: ; %bb.1: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: LBB13_2: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
%1 = fcmp une float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -172,9 +297,16 @@ bb1:
}
define i32 @icmp_eq(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_eq
; CHECK: cmp w0, w1
; CHECK-NEXT: b.ne {{LBB.+_2}}
; CHECK-LABEL: icmp_eq:
; CHECK: ; %bb.0:
; CHECK-NEXT: cmp w0, w1
; CHECK-NEXT: b.eq LBB14_2
; CHECK-NEXT: ; %bb.1: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
; CHECK-NEXT: LBB14_2: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
%1 = icmp eq i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -184,9 +316,16 @@ bb1:
}
define i32 @icmp_ne(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_ne
; CHECK: cmp w0, w1
; CHECK-NEXT: b.eq {{LBB.+_2}}
; CHECK-LABEL: icmp_ne:
; CHECK: ; %bb.0:
; CHECK-NEXT: cmp w0, w1
; CHECK-NEXT: b.eq LBB15_2
; CHECK-NEXT: ; %bb.1: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: LBB15_2: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
%1 = icmp ne i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -196,9 +335,16 @@ bb1:
}
define i32 @icmp_ugt(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_ugt
; CHECK: cmp w0, w1
; CHECK-NEXT: b.ls {{LBB.+_2}}
; CHECK-LABEL: icmp_ugt:
; CHECK: ; %bb.0:
; CHECK-NEXT: cmp w0, w1
; CHECK-NEXT: b.ls LBB16_2
; CHECK-NEXT: ; %bb.1: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: LBB16_2: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
%1 = icmp ugt i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -208,9 +354,16 @@ bb1:
}
define i32 @icmp_uge(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_uge
; CHECK: cmp w0, w1
; CHECK-NEXT: b.lo {{LBB.+_2}}
; CHECK-LABEL: icmp_uge:
; CHECK: ; %bb.0:
; CHECK-NEXT: cmp w0, w1
; CHECK-NEXT: b.hs LBB17_2
; CHECK-NEXT: ; %bb.1: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
; CHECK-NEXT: LBB17_2: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
%1 = icmp uge i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -220,9 +373,16 @@ bb1:
}
define i32 @icmp_ult(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_ult
; CHECK: cmp w0, w1
; CHECK-NEXT: b.hs {{LBB.+_2}}
; CHECK-LABEL: icmp_ult:
; CHECK: ; %bb.0:
; CHECK-NEXT: cmp w0, w1
; CHECK-NEXT: b.hs LBB18_2
; CHECK-NEXT: ; %bb.1: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: LBB18_2: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
%1 = icmp ult i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -232,9 +392,16 @@ bb1:
}
define i32 @icmp_ule(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_ule
; CHECK: cmp w0, w1
; CHECK-NEXT: b.hi {{LBB.+_2}}
; CHECK-LABEL: icmp_ule:
; CHECK: ; %bb.0:
; CHECK-NEXT: cmp w0, w1
; CHECK-NEXT: b.ls LBB19_2
; CHECK-NEXT: ; %bb.1: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
; CHECK-NEXT: LBB19_2: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
%1 = icmp ule i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -244,9 +411,16 @@ bb1:
}
define i32 @icmp_sgt(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_sgt
; CHECK: cmp w0, w1
; CHECK-NEXT: b.le {{LBB.+_2}}
; CHECK-LABEL: icmp_sgt:
; CHECK: ; %bb.0:
; CHECK-NEXT: cmp w0, w1
; CHECK-NEXT: b.le LBB20_2
; CHECK-NEXT: ; %bb.1: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: LBB20_2: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
%1 = icmp sgt i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -256,9 +430,16 @@ bb1:
}
define i32 @icmp_sge(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_sge
; CHECK: cmp w0, w1
; CHECK-NEXT: b.lt {{LBB.+_2}}
; CHECK-LABEL: icmp_sge:
; CHECK: ; %bb.0:
; CHECK-NEXT: cmp w0, w1
; CHECK-NEXT: b.ge LBB21_2
; CHECK-NEXT: ; %bb.1: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
; CHECK-NEXT: LBB21_2: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
%1 = icmp sge i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -268,9 +449,16 @@ bb1:
}
define i32 @icmp_slt(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_slt
; CHECK: cmp w0, w1
; CHECK-NEXT: b.ge {{LBB.+_2}}
; CHECK-LABEL: icmp_slt:
; CHECK: ; %bb.0:
; CHECK-NEXT: cmp w0, w1
; CHECK-NEXT: b.ge LBB22_2
; CHECK-NEXT: ; %bb.1: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
; CHECK-NEXT: LBB22_2: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
%1 = icmp slt i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -280,9 +468,16 @@ bb1:
}
define i32 @icmp_sle(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_sle
; CHECK: cmp w0, w1
; CHECK-NEXT: b.gt {{LBB.+_2}}
; CHECK-LABEL: icmp_sle:
; CHECK: ; %bb.0:
; CHECK-NEXT: cmp w0, w1
; CHECK-NEXT: b.le LBB23_2
; CHECK-NEXT: ; %bb.1: ; %bb2
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
; CHECK-NEXT: LBB23_2: ; %bb1
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
%1 = icmp sle i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:

View File

@ -1,9 +1,14 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; REQUIRES: asserts
; RUN: llc < %s -o /dev/null -stats 2>&1 | FileCheck %s -check-prefix=STATS
; Radar 10266272
target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:32:64-v128:32:128-a0:0:32-n32-S32"
target triple = "thumbv7-apple-ios4.0.0"
; STATS-NOT: machine-sink
; STATS: 1 machine-cse - Number of common subexpression eliminated
; STATS: 1 machine-sink - Number of critical edges split
; STATS: 1 machine-sink - Number of machine instructions sunk
define i32 @foo(i32 %h, i32 %arg1) nounwind readonly ssp {
entry:

View File

@ -5,27 +5,27 @@ define void @test_cmpxchg_weak(i32 *%addr, i32 %desired, i32 %new) {
%pair = cmpxchg weak i32* %addr, i32 %desired, i32 %new seq_cst monotonic
%oldval = extractvalue { i32, i1 } %pair, 0
; CHECK-NEXT: %bb.0:
; CHECK-NEXT: ldrex [[LOADED:r[0-9]+]], [r0]
; CHECK-NEXT: cmp [[LOADED]], r1
; CHECK-NEXT: bne [[LDFAILBB:LBB[0-9]+_[0-9]+]]
; CHECK-NEXT: %bb.1:
; CHECK-NEXT: dmb ish
; CHECK-NEXT: strex [[SUCCESS:r[0-9]+]], r2, [r0]
; CHECK-NEXT: cmp [[SUCCESS]], #0
; CHECK-NEXT: beq [[SUCCESSBB:LBB[0-9]+_[0-9]+]]
; CHECK-NEXT: %bb.2:
; CHECK-NEXT: str r3, [r0]
; CHECK-NEXT: bx lr
; CHECK-NEXT: [[LDFAILBB]]:
; CHECK-NEXT: @ %bb.0: @ %cmpxchg.start
; CHECK-NEXT: ldrex r3, [r0]
; CHECK-NEXT: cmp r3, r1
; CHECK-NEXT: beq LBB0_2
; CHECK-NEXT: @ %bb.1: @ %cmpxchg.nostore
; CHECK-NEXT: clrex
; CHECK-NEXT: b LBB0_3
; CHECK-NEXT: LBB0_2: @ %cmpxchg.fencedstore
; CHECK-NEXT: dmb ish
; CHECK-NEXT: strex r1, r2, [r0]
; CHECK-NEXT: cmp r1, #0
; CHECK-NEXT: beq LBB0_4
; CHECK-NEXT: LBB0_3: @ %cmpxchg.end
; CHECK-NEXT: str r3, [r0]
; CHECK-NEXT: bx lr
; CHECK-NEXT: [[SUCCESSBB]]:
; CHECK-NEXT: LBB0_4: @ %cmpxchg.success
; CHECK-NEXT: dmb ish
; CHECK-NEXT: str r3, [r0]
; CHECK-NEXT: bx lr
store i32 %oldval, i32* %addr
ret void
}
@ -37,23 +37,24 @@ define i1 @test_cmpxchg_weak_to_bool(i32, i32 *%addr, i32 %desired, i32 %new) {
%pair = cmpxchg weak i32* %addr, i32 %desired, i32 %new seq_cst monotonic
%success = extractvalue { i32, i1 } %pair, 1
; CHECK-NEXT: %bb.0:
; CHECK-NEXT: ldrex [[LOADED:r[0-9]+]], [r1]
; CHECK-NEXT: cmp [[LOADED]], r2
; CHECK-NEXT: bne [[LDFAILBB:LBB[0-9]+_[0-9]+]]
; CHECK-NEXT: %bb.1:
; CHECK-NEXT: dmb ish
; CHECK-NEXT: @ %bb.0: @ %cmpxchg.start
; CHECK-NEXT: ldrex r0, [r1]
; CHECK-NEXT: cmp r0, r2
; CHECK-NEXT: beq LBB1_2
; CHECK-NEXT: @ %bb.1: @ %cmpxchg.nostore
; CHECK-NEXT: mov r0, #0
; CHECK-NEXT: strex [[SUCCESS:r[0-9]+]], r3, [r1]
; CHECK-NEXT: cmp [[SUCCESS]], #0
; CHECK-NEXT: clrex
; CHECK-NEXT: bx lr
; CHECK-NEXT: LBB1_2: @ %cmpxchg.fencedstore
; CHECK-NEXT: dmb ish
; CHECK-NEXT: mov r0, #0
; CHECK-NEXT: strex r2, r3, [r1]
; CHECK-NEXT: cmp r2, #0
; CHECK-NEXT: bxne lr
; CHECK-NEXT: mov r0, #1
; CHECK-NEXT: dmb ish
; CHECK-NEXT: bx lr
; CHECK-NEXT: [[LDFAILBB]]:
; CHECK-NEXT: mov r0, #0
; CHECK-NEXT: clrex
; CHECK-NEXT: bx lr
ret i1 %success
}

View File

@ -1,3 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -regalloc=greedy -arm-atomic-cfg-tidy=0 < %s | FileCheck %s
; LSR shouldn't introduce more induction variables than needed, increasing
@ -7,8 +8,11 @@
; CHECK: sub sp, #{{40|36|32|28|24}}
; CHECK: %for.inc
; CHECK-NOT: ldr
; CHECK: add
; CHECK: adds r6, #1
; CHECK: adds r4, #24
; CHECK: cmp r1, r6
; CHECK: bne LBB0_3
target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:32-f32:32:32-f64:32:32-v64:32:64-v128:32:128-a0:0:32-n32"
target triple = "thumbv7-apple-ios"

View File

@ -52,7 +52,7 @@ entry:
; CHECK-LABEL: f3:
; CHECK-NOT: sub
; CHECK: cmp
; CHECK: blt
; CHECK: bge
%0 = load i32, i32* %offset, align 4
%cmp = icmp slt i32 %0, %size
%s = sub nsw i32 %0, %size

View File

@ -1,3 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=hexagon -mcpu=hexagonv5 -disable-hexagon-misched < %s \
; RUN: | FileCheck %s
; Check that we generate new value jump, both registers, with one
@ -5,8 +6,35 @@
@Reg = common global i32 0, align 4
define i32 @main() nounwind {
; CHECK-LABEL: main:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: {
; CHECK-NEXT: r1 = memw(gp+#Reg)
; CHECK-NEXT: allocframe(r29,#8):raw
; CHECK-NEXT: }
; CHECK-NEXT: {
; CHECK-NEXT: r0 = memw(r29+#4)
; CHECK-NEXT: if (!cmp.gt(r0.new,r1)) jump:nt .LBB0_1
; CHECK-NEXT: }
; CHECK-NEXT: // %bb.2: // %if.else
; CHECK-NEXT: {
; CHECK-NEXT: call baz
; CHECK-NEXT: r1:0 = combine(#20,#10)
; CHECK-NEXT: }
; CHECK-NEXT: {
; CHECK-NEXT: r0 = #0
; CHECK-NEXT: dealloc_return
; CHECK-NEXT: }
; CHECK-NEXT: .LBB0_1: // %if.then
; CHECK-NEXT: {
; CHECK-NEXT: call bar
; CHECK-NEXT: r1:0 = combine(#2,#1)
; CHECK-NEXT: }
; CHECK-NEXT: {
; CHECK-NEXT: r0 = #0
; CHECK-NEXT: dealloc_return
; CHECK-NEXT: }
entry:
; CHECK: if (cmp.gt(r{{[0-9]+}}.new,r{{[0-9]+}})) jump:{{[t|nt]}} .LBB{{[0-9]+}}_{{[0-9]+}}
%Reg2 = alloca i32, align 4
%0 = load i32, i32* %Reg2, align 4
%1 = load i32, i32* @Reg, align 4

View File

@ -1,3 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=mipsel -mattr=mips16 -relocation-model=pic -O3 < %s | FileCheck %s -check-prefix=16
@i = global i32 5, align 4
@ -6,14 +7,32 @@
@result = global i32 0, align 4
define void @test() nounwind {
; 16-LABEL: test:
; 16: # %bb.0: # %entry
; 16-NEXT: lui $2, %hi(_gp_disp)
; 16-NEXT: addiu $2, $2, %lo(_gp_disp)
; 16-NEXT: li $2, %hi(_gp_disp)
; 16-NEXT: addiu $3, $pc, %lo(_gp_disp)
; 16-NEXT: sll $2, $2, 16
; 16-NEXT: addu $2, $3, $2
; 16-NEXT: lw $3, %got(i)($2)
; 16-NEXT: lw $4, %got(j)($2)
; 16-NEXT: lw $3, 0($3)
; 16-NEXT: lw $4, 0($4)
; 16-NEXT: slt $4, $3
; 16-NEXT: bteqz $BB0_2 # 16 bit inst
; 16-NEXT: # %bb.1: # %if.end
; 16-NEXT: jrc $ra
; 16-NEXT: $BB0_2: # %if.then
; 16-NEXT: lw $2, %got(result)($2)
; 16-NEXT: li $3, 1
; 16-NEXT: sw $3, 0($2)
; 16-NEXT: jrc $ra
entry:
%0 = load i32, i32* @i, align 4
%1 = load i32, i32* @j, align 4
%cmp = icmp sgt i32 %0, %1
br i1 %cmp, label %if.end, label %if.then
; 16: slt ${{[0-9]+}}, ${{[0-9]+}}
; 16: btnez $[[LABEL:[0-9A-Ba-b_]+]]
; 16: $[[LABEL]]:
if.then: ; preds = %entry
store i32 1, i32* @result, align 4
br label %if.end

View File

@ -1,3 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=mipsel -mattr=mips16 -relocation-model=pic -O3 < %s | FileCheck %s -check-prefix=16
; RUN: llc -march=mips -mattr=micromips -mcpu=mips32r6 -relocation-model=pic -O3 < %s | FileCheck %s -check-prefix=MM32R6
@ -7,16 +8,52 @@
@result = global i32 0, align 4
define void @test() nounwind {
; 16-LABEL: test:
; 16: # %bb.0: # %entry
; 16-NEXT: lui $2, %hi(_gp_disp)
; 16-NEXT: addiu $2, $2, %lo(_gp_disp)
; 16-NEXT: li $2, %hi(_gp_disp)
; 16-NEXT: addiu $3, $pc, %lo(_gp_disp)
; 16-NEXT: sll $2, $2, 16
; 16-NEXT: addu $2, $3, $2
; 16-NEXT: lw $3, %got(i)($2)
; 16-NEXT: lw $4, %got(j)($2)
; 16-NEXT: lw $3, 0($3)
; 16-NEXT: lw $4, 0($4)
; 16-NEXT: slt $4, $3
; 16-NEXT: bteqz $BB0_2 # 16 bit inst
; 16-NEXT: # %bb.1: # %if.end
; 16-NEXT: jrc $ra
; 16-NEXT: $BB0_2: # %if.then
; 16-NEXT: lw $2, %got(result)($2)
; 16-NEXT: li $3, 1
; 16-NEXT: sw $3, 0($2)
; 16-NEXT: jrc $ra
;
; MM32R6-LABEL: test:
; MM32R6: # %bb.0: # %entry
; MM32R6-NEXT: lui $2, %hi(_gp_disp)
; MM32R6-NEXT: addiu $2, $2, %lo(_gp_disp)
; MM32R6-NEXT: addu $2, $2, $25
; MM32R6-NEXT: lw $3, %got(i)($2)
; MM32R6-NEXT: lw $4, %got(j)($2)
; MM32R6-NEXT: lw16 $3, 0($3)
; MM32R6-NEXT: lw16 $4, 0($4)
; MM32R6-NEXT: slt $1, $4, $3
; MM32R6-NEXT: beqzc $1, $BB0_2
; MM32R6-NEXT: # %bb.1: # %if.end
; MM32R6-NEXT: jrc $ra
; MM32R6-NEXT: $BB0_2: # %if.then
; MM32R6-NEXT: lw $2, %got(result)($2)
; MM32R6-NEXT: li16 $3, 1
; MM32R6-NEXT: sw16 $3, 0($2)
; MM32R6-NEXT: jrc $ra
entry:
%0 = load i32, i32* @j, align 4
%1 = load i32, i32* @i, align 4
%cmp = icmp slt i32 %0, %1
br i1 %cmp, label %if.end, label %if.then
; 16: slt ${{[0-9]+}}, ${{[0-9]+}}
; MM32R6: slt ${{[0-9]+}}, ${{[0-9]+}}
; 16: btnez $[[LABEL:[0-9A-Ba-b_]+]]
; 16: $[[LABEL]]:
if.then: ; preds = %entry
store i32 1, i32* @result, align 4

View File

@ -1,3 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=mipsel -mattr=mips16 -relocation-model=pic -O3 < %s | FileCheck %s -check-prefix=16
@i = global i32 5, align 4
@ -5,15 +6,32 @@
@result = global i32 0, align 4
define void @test() nounwind {
; 16-LABEL: test:
; 16: # %bb.0: # %entry
; 16-NEXT: lui $2, %hi(_gp_disp)
; 16-NEXT: addiu $2, $2, %lo(_gp_disp)
; 16-NEXT: li $2, %hi(_gp_disp)
; 16-NEXT: addiu $3, $pc, %lo(_gp_disp)
; 16-NEXT: sll $2, $2, 16
; 16-NEXT: addu $2, $3, $2
; 16-NEXT: lw $3, %got(i)($2)
; 16-NEXT: lw $4, %got(j)($2)
; 16-NEXT: lw $3, 0($3)
; 16-NEXT: lw $4, 0($4)
; 16-NEXT: cmp $4, $3
; 16-NEXT: bteqz $BB0_2 # 16 bit inst
; 16-NEXT: # %bb.1: # %if.end
; 16-NEXT: jrc $ra
; 16-NEXT: $BB0_2: # %if.then
; 16-NEXT: lw $2, %got(result)($2)
; 16-NEXT: li $3, 1
; 16-NEXT: sw $3, 0($2)
; 16-NEXT: jrc $ra
entry:
%0 = load i32, i32* @j, align 4
%1 = load i32, i32* @i, align 4
%cmp = icmp eq i32 %0, %1
br i1 %cmp, label %if.then, label %if.end
; 16: cmp ${{[0-9]+}}, ${{[0-9]+}}
; 16: btnez $[[LABEL:[0-9A-Ba-b_]+]]
; 16: lw ${{[0-9]+}}, %got(result)(${{[0-9]+}})
; 16: $[[LABEL]]:
if.then: ; preds = %entry
store i32 1, i32* @result, align 4

View File

@ -1,16 +1,57 @@
; RUN: llc -march=mipsel -mcpu=mips32r6 -disable-mips-delay-filler < %s | FileCheck %s
; RUN: llc -march=mips -mcpu=mips32r6 -disable-mips-delay-filler < %s -filetype=obj \
; RUN: -o - | llvm-objdump -d - | FileCheck %s --check-prefix=ENCODING
; RUN: llc -march=mipsel -mcpu=mips64r6 -disable-mips-delay-filler -target-abi=n64 < %s | FileCheck %s
; RUN: llc -march=mips -mcpu=mips64r6 -disable-mips-delay-filler -target-abi=n64 < %s -filetype=obj \
; RUN: -o - | llvm-objdump -d - | FileCheck %s --check-prefix=ENCODING
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=mipsel -mcpu=mips32r6 -disable-mips-delay-filler < %s | FileCheck %s --check-prefixes=ENCODING,MIPSEL32
; RUN: llc -march=mips -mcpu=mips32r6 -disable-mips-delay-filler < %s | FileCheck %s --check-prefixes=ENCODING,MIPS32
; RUN: llc -march=mipsel -mcpu=mips64r6 -disable-mips-delay-filler -target-abi=n64 < %s | FileCheck %s --check-prefixes=ENCODING,MIPSEL64
; RUN: llc -march=mips -mcpu=mips64r6 -disable-mips-delay-filler -target-abi=n64 < %s | FileCheck %s --check-prefixes=ENCODING,MIPS64
; bnezc and beqzc have restriction that $rt != 0
define i32 @f() {
; CHECK-LABEL: f:
; CHECK-NOT: bnezc $0
; MIPSEL32-LABEL: f:
; MIPSEL32: # %bb.0:
; MIPSEL32-NEXT: bnez $zero, $BB0_2
; MIPSEL32-NEXT: nop
; MIPSEL32-NEXT: # %bb.1: # %if.then
; MIPSEL32-NEXT: addiu $2, $zero, 1
; MIPSEL32-NEXT: jrc $ra
; MIPSEL32-NEXT: $BB0_2: # %if.end
; MIPSEL32-NEXT: addiu $2, $zero, 0
; MIPSEL32-NEXT: jrc $ra
;
; MIPS32-LABEL: f:
; MIPS32: # %bb.0:
; MIPS32-NEXT: bnez $zero, $BB0_2
; MIPS32-NEXT: nop
; MIPS32-NEXT: # %bb.1: # %if.then
; MIPS32-NEXT: addiu $2, $zero, 1
; MIPS32-NEXT: jrc $ra
; MIPS32-NEXT: $BB0_2: # %if.end
; MIPS32-NEXT: addiu $2, $zero, 0
; MIPS32-NEXT: jrc $ra
;
; MIPSEL64-LABEL: f:
; MIPSEL64: # %bb.0:
; MIPSEL64-NEXT: bnez $zero, .LBB0_2
; MIPSEL64-NEXT: nop
; MIPSEL64-NEXT: # %bb.1: # %if.then
; MIPSEL64-NEXT: addiu $2, $zero, 1
; MIPSEL64-NEXT: jrc $ra
; MIPSEL64-NEXT: .LBB0_2: # %if.end
; MIPSEL64-NEXT: addiu $2, $zero, 0
; MIPSEL64-NEXT: jrc $ra
;
; MIPS64-LABEL: f:
; MIPS64: # %bb.0:
; MIPS64-NEXT: bnez $zero, .LBB0_2
; MIPS64-NEXT: nop
; MIPS64-NEXT: # %bb.1: # %if.then
; MIPS64-NEXT: addiu $2, $zero, 1
; MIPS64-NEXT: jrc $ra
; MIPS64-NEXT: .LBB0_2: # %if.end
; MIPS64-NEXT: addiu $2, $zero, 0
; MIPS64-NEXT: jrc $ra
%cmp = icmp eq i32 1, 1
br i1 %cmp, label %if.then, label %if.end
@ -24,7 +65,49 @@ define i32 @f() {
define i32 @f1() {
; CHECK-LABEL: f1:
; CHECK-NOT: beqzc $0
; MIPSEL32-LABEL: f1:
; MIPSEL32: # %bb.0:
; MIPSEL32-NEXT: b $BB1_2
; MIPSEL32-NEXT: nop
; MIPSEL32-NEXT: # %bb.1: # %if.end
; MIPSEL32-NEXT: addiu $2, $zero, 0
; MIPSEL32-NEXT: jrc $ra
; MIPSEL32-NEXT: $BB1_2: # %if.then
; MIPSEL32-NEXT: addiu $2, $zero, 1
; MIPSEL32-NEXT: jrc $ra
;
; MIPS32-LABEL: f1:
; MIPS32: # %bb.0:
; MIPS32-NEXT: b $BB1_2
; MIPS32-NEXT: nop
; MIPS32-NEXT: # %bb.1: # %if.end
; MIPS32-NEXT: addiu $2, $zero, 0
; MIPS32-NEXT: jrc $ra
; MIPS32-NEXT: $BB1_2: # %if.then
; MIPS32-NEXT: addiu $2, $zero, 1
; MIPS32-NEXT: jrc $ra
;
; MIPSEL64-LABEL: f1:
; MIPSEL64: # %bb.0:
; MIPSEL64-NEXT: b .LBB1_2
; MIPSEL64-NEXT: nop
; MIPSEL64-NEXT: # %bb.1: # %if.end
; MIPSEL64-NEXT: addiu $2, $zero, 0
; MIPSEL64-NEXT: jrc $ra
; MIPSEL64-NEXT: .LBB1_2: # %if.then
; MIPSEL64-NEXT: addiu $2, $zero, 1
; MIPSEL64-NEXT: jrc $ra
;
; MIPS64-LABEL: f1:
; MIPS64: # %bb.0:
; MIPS64-NEXT: b .LBB1_2
; MIPS64-NEXT: nop
; MIPS64-NEXT: # %bb.1: # %if.end
; MIPS64-NEXT: addiu $2, $zero, 0
; MIPS64-NEXT: jrc $ra
; MIPS64-NEXT: .LBB1_2: # %if.then
; MIPS64-NEXT: addiu $2, $zero, 1
; MIPS64-NEXT: jrc $ra
%cmp = icmp eq i32 0, 0
br i1 %cmp, label %if.then, label %if.end
@ -40,9 +123,49 @@ define i32 @f1() {
; beqc and bnec have the restriction that $rs < $rt.
define i32 @f2(i32 %a, i32 %b) {
; ENCODING-LABEL: <f2>:
; ENCODING-NOT: beqc $5, $4
; ENCODING-NOT: bnec $5, $4
; MIPSEL32-LABEL: f2:
; MIPSEL32: # %bb.0:
; MIPSEL32-NEXT: beqc $5, $4, $BB2_2
; MIPSEL32-NEXT: # %bb.1: # %if.end
; MIPSEL32-NEXT: addiu $2, $zero, 0
; MIPSEL32-NEXT: jrc $ra
; MIPSEL32-NEXT: $BB2_2: # %if.then
; MIPSEL32-NEXT: addiu $2, $zero, 1
; MIPSEL32-NEXT: jrc $ra
;
; MIPS32-LABEL: f2:
; MIPS32: # %bb.0:
; MIPS32-NEXT: beqc $5, $4, $BB2_2
; MIPS32-NEXT: # %bb.1: # %if.end
; MIPS32-NEXT: addiu $2, $zero, 0
; MIPS32-NEXT: jrc $ra
; MIPS32-NEXT: $BB2_2: # %if.then
; MIPS32-NEXT: addiu $2, $zero, 1
; MIPS32-NEXT: jrc $ra
;
; MIPSEL64-LABEL: f2:
; MIPSEL64: # %bb.0:
; MIPSEL64-NEXT: sll $1, $4, 0
; MIPSEL64-NEXT: sll $2, $5, 0
; MIPSEL64-NEXT: beqc $2, $1, .LBB2_2
; MIPSEL64-NEXT: # %bb.1: # %if.end
; MIPSEL64-NEXT: addiu $2, $zero, 0
; MIPSEL64-NEXT: jrc $ra
; MIPSEL64-NEXT: .LBB2_2: # %if.then
; MIPSEL64-NEXT: addiu $2, $zero, 1
; MIPSEL64-NEXT: jrc $ra
;
; MIPS64-LABEL: f2:
; MIPS64: # %bb.0:
; MIPS64-NEXT: sll $1, $4, 0
; MIPS64-NEXT: sll $2, $5, 0
; MIPS64-NEXT: beqc $2, $1, .LBB2_2
; MIPS64-NEXT: # %bb.1: # %if.end
; MIPS64-NEXT: addiu $2, $zero, 0
; MIPS64-NEXT: jrc $ra
; MIPS64-NEXT: .LBB2_2: # %if.then
; MIPS64-NEXT: addiu $2, $zero, 1
; MIPS64-NEXT: jrc $ra
%cmp = icmp eq i32 %b, %a
br i1 %cmp, label %if.then, label %if.end
@ -57,7 +180,53 @@ define i32 @f2(i32 %a, i32 %b) {
define i64 @f3() {
; CHECK-LABEL: f3:
; CHECK-NOT: bnezc $0
; MIPSEL32-LABEL: f3:
; MIPSEL32: # %bb.0:
; MIPSEL32-NEXT: bnez $zero, $BB3_2
; MIPSEL32-NEXT: nop
; MIPSEL32-NEXT: # %bb.1: # %if.then
; MIPSEL32-NEXT: addiu $2, $zero, 1
; MIPSEL32-NEXT: addiu $3, $zero, 0
; MIPSEL32-NEXT: jrc $ra
; MIPSEL32-NEXT: $BB3_2: # %if.end
; MIPSEL32-NEXT: addiu $2, $zero, 0
; MIPSEL32-NEXT: addiu $3, $zero, 0
; MIPSEL32-NEXT: jrc $ra
;
; MIPS32-LABEL: f3:
; MIPS32: # %bb.0:
; MIPS32-NEXT: bnez $zero, $BB3_2
; MIPS32-NEXT: nop
; MIPS32-NEXT: # %bb.1: # %if.then
; MIPS32-NEXT: addiu $2, $zero, 0
; MIPS32-NEXT: addiu $3, $zero, 1
; MIPS32-NEXT: jrc $ra
; MIPS32-NEXT: $BB3_2: # %if.end
; MIPS32-NEXT: addiu $2, $zero, 0
; MIPS32-NEXT: addiu $3, $zero, 0
; MIPS32-NEXT: jrc $ra
;
; MIPSEL64-LABEL: f3:
; MIPSEL64: # %bb.0:
; MIPSEL64-NEXT: bnez $zero, .LBB3_2
; MIPSEL64-NEXT: nop
; MIPSEL64-NEXT: # %bb.1: # %if.then
; MIPSEL64-NEXT: daddiu $2, $zero, 1
; MIPSEL64-NEXT: jrc $ra
; MIPSEL64-NEXT: .LBB3_2: # %if.end
; MIPSEL64-NEXT: daddiu $2, $zero, 0
; MIPSEL64-NEXT: jrc $ra
;
; MIPS64-LABEL: f3:
; MIPS64: # %bb.0:
; MIPS64-NEXT: bnez $zero, .LBB3_2
; MIPS64-NEXT: nop
; MIPS64-NEXT: # %bb.1: # %if.then
; MIPS64-NEXT: daddiu $2, $zero, 1
; MIPS64-NEXT: jrc $ra
; MIPS64-NEXT: .LBB3_2: # %if.end
; MIPS64-NEXT: daddiu $2, $zero, 0
; MIPS64-NEXT: jrc $ra
%cmp = icmp eq i64 1, 1
br i1 %cmp, label %if.then, label %if.end
@ -71,7 +240,53 @@ define i64 @f3() {
define i64 @f4() {
; CHECK-LABEL: f4:
; CHECK-NOT: beqzc $0
; MIPSEL32-LABEL: f4:
; MIPSEL32: # %bb.0:
; MIPSEL32-NEXT: b $BB4_2
; MIPSEL32-NEXT: nop
; MIPSEL32-NEXT: # %bb.1: # %if.end
; MIPSEL32-NEXT: addiu $2, $zero, 0
; MIPSEL32-NEXT: addiu $3, $zero, 0
; MIPSEL32-NEXT: jrc $ra
; MIPSEL32-NEXT: $BB4_2: # %if.then
; MIPSEL32-NEXT: addiu $2, $zero, 1
; MIPSEL32-NEXT: addiu $3, $zero, 0
; MIPSEL32-NEXT: jrc $ra
;
; MIPS32-LABEL: f4:
; MIPS32: # %bb.0:
; MIPS32-NEXT: b $BB4_2
; MIPS32-NEXT: nop
; MIPS32-NEXT: # %bb.1: # %if.end
; MIPS32-NEXT: addiu $2, $zero, 0
; MIPS32-NEXT: addiu $3, $zero, 0
; MIPS32-NEXT: jrc $ra
; MIPS32-NEXT: $BB4_2: # %if.then
; MIPS32-NEXT: addiu $2, $zero, 0
; MIPS32-NEXT: addiu $3, $zero, 1
; MIPS32-NEXT: jrc $ra
;
; MIPSEL64-LABEL: f4:
; MIPSEL64: # %bb.0:
; MIPSEL64-NEXT: b .LBB4_2
; MIPSEL64-NEXT: nop
; MIPSEL64-NEXT: # %bb.1: # %if.end
; MIPSEL64-NEXT: daddiu $2, $zero, 0
; MIPSEL64-NEXT: jrc $ra
; MIPSEL64-NEXT: .LBB4_2: # %if.then
; MIPSEL64-NEXT: daddiu $2, $zero, 1
; MIPSEL64-NEXT: jrc $ra
;
; MIPS64-LABEL: f4:
; MIPS64: # %bb.0:
; MIPS64-NEXT: b .LBB4_2
; MIPS64-NEXT: nop
; MIPS64-NEXT: # %bb.1: # %if.end
; MIPS64-NEXT: daddiu $2, $zero, 0
; MIPS64-NEXT: jrc $ra
; MIPS64-NEXT: .LBB4_2: # %if.then
; MIPS64-NEXT: daddiu $2, $zero, 1
; MIPS64-NEXT: jrc $ra
%cmp = icmp eq i64 0, 0
br i1 %cmp, label %if.then, label %if.end
@ -87,9 +302,55 @@ define i64 @f4() {
; beqc and bnec have the restriction that $rs < $rt.
define i64 @f5(i64 %a, i64 %b) {
; ENCODING-LABEL: <f5>:
; ENCODING-NOT: beqc $5, $4
; ENCODING-NOT: bnec $5, $4
; MIPSEL32-LABEL: f5:
; MIPSEL32: # %bb.0:
; MIPSEL32-NEXT: xor $1, $7, $5
; MIPSEL32-NEXT: xor $2, $6, $4
; MIPSEL32-NEXT: or $1, $2, $1
; MIPSEL32-NEXT: beqzc $1, $BB5_2
; MIPSEL32-NEXT: # %bb.1: # %if.end
; MIPSEL32-NEXT: addiu $2, $zero, 0
; MIPSEL32-NEXT: addiu $3, $zero, 0
; MIPSEL32-NEXT: jrc $ra
; MIPSEL32-NEXT: $BB5_2: # %if.then
; MIPSEL32-NEXT: addiu $2, $zero, 1
; MIPSEL32-NEXT: addiu $3, $zero, 0
; MIPSEL32-NEXT: jrc $ra
;
; MIPS32-LABEL: f5:
; MIPS32: # %bb.0:
; MIPS32-NEXT: xor $1, $6, $4
; MIPS32-NEXT: xor $2, $7, $5
; MIPS32-NEXT: or $1, $2, $1
; MIPS32-NEXT: beqzc $1, $BB5_2
; MIPS32-NEXT: # %bb.1: # %if.end
; MIPS32-NEXT: addiu $2, $zero, 0
; MIPS32-NEXT: addiu $3, $zero, 0
; MIPS32-NEXT: jrc $ra
; MIPS32-NEXT: $BB5_2: # %if.then
; MIPS32-NEXT: addiu $2, $zero, 0
; MIPS32-NEXT: addiu $3, $zero, 1
; MIPS32-NEXT: jrc $ra
;
; MIPSEL64-LABEL: f5:
; MIPSEL64: # %bb.0:
; MIPSEL64-NEXT: beqc $5, $4, .LBB5_2
; MIPSEL64-NEXT: # %bb.1: # %if.end
; MIPSEL64-NEXT: daddiu $2, $zero, 0
; MIPSEL64-NEXT: jrc $ra
; MIPSEL64-NEXT: .LBB5_2: # %if.then
; MIPSEL64-NEXT: daddiu $2, $zero, 1
; MIPSEL64-NEXT: jrc $ra
;
; MIPS64-LABEL: f5:
; MIPS64: # %bb.0:
; MIPS64-NEXT: beqc $5, $4, .LBB5_2
; MIPS64-NEXT: # %bb.1: # %if.end
; MIPS64-NEXT: daddiu $2, $zero, 0
; MIPS64-NEXT: jrc $ra
; MIPS64-NEXT: .LBB5_2: # %if.then
; MIPS64-NEXT: daddiu $2, $zero, 1
; MIPS64-NEXT: jrc $ra
%cmp = icmp eq i64 %b, %a
br i1 %cmp, label %if.then, label %if.end
@ -104,7 +365,47 @@ define i64 @f5(i64 %a, i64 %b) {
define i32 @f6(i32 %a) {
; CHECK-LABEL: f6:
; CHECK: beqzc ${{[0-9]+}}, {{((\$)|(\.L))}}BB
; MIPSEL32-LABEL: f6:
; MIPSEL32: # %bb.0:
; MIPSEL32-NEXT: beqzc $4, $BB6_2
; MIPSEL32-NEXT: # %bb.1: # %if.end
; MIPSEL32-NEXT: addiu $2, $zero, 0
; MIPSEL32-NEXT: jrc $ra
; MIPSEL32-NEXT: $BB6_2: # %if.then
; MIPSEL32-NEXT: addiu $2, $zero, 1
; MIPSEL32-NEXT: jrc $ra
;
; MIPS32-LABEL: f6:
; MIPS32: # %bb.0:
; MIPS32-NEXT: beqzc $4, $BB6_2
; MIPS32-NEXT: # %bb.1: # %if.end
; MIPS32-NEXT: addiu $2, $zero, 0
; MIPS32-NEXT: jrc $ra
; MIPS32-NEXT: $BB6_2: # %if.then
; MIPS32-NEXT: addiu $2, $zero, 1
; MIPS32-NEXT: jrc $ra
;
; MIPSEL64-LABEL: f6:
; MIPSEL64: # %bb.0:
; MIPSEL64-NEXT: sll $1, $4, 0
; MIPSEL64-NEXT: beqzc $1, .LBB6_2
; MIPSEL64-NEXT: # %bb.1: # %if.end
; MIPSEL64-NEXT: addiu $2, $zero, 0
; MIPSEL64-NEXT: jrc $ra
; MIPSEL64-NEXT: .LBB6_2: # %if.then
; MIPSEL64-NEXT: addiu $2, $zero, 1
; MIPSEL64-NEXT: jrc $ra
;
; MIPS64-LABEL: f6:
; MIPS64: # %bb.0:
; MIPS64-NEXT: sll $1, $4, 0
; MIPS64-NEXT: beqzc $1, .LBB6_2
; MIPS64-NEXT: # %bb.1: # %if.end
; MIPS64-NEXT: addiu $2, $zero, 0
; MIPS64-NEXT: jrc $ra
; MIPS64-NEXT: .LBB6_2: # %if.then
; MIPS64-NEXT: addiu $2, $zero, 1
; MIPS64-NEXT: jrc $ra
%cmp = icmp eq i32 %a, 0
br i1 %cmp, label %if.then, label %if.end
@ -118,7 +419,47 @@ define i32 @f6(i32 %a) {
define i32 @f7(i32 %a) {
; CHECK-LABEL: f7:
; CHECK: bnezc ${{[0-9]+}}, {{((\$)|(\.L))}}BB
; MIPSEL32-LABEL: f7:
; MIPSEL32: # %bb.0:
; MIPSEL32-NEXT: beqzc $4, $BB7_2
; MIPSEL32-NEXT: # %bb.1: # %if.end
; MIPSEL32-NEXT: addiu $2, $zero, 0
; MIPSEL32-NEXT: jrc $ra
; MIPSEL32-NEXT: $BB7_2: # %if.then
; MIPSEL32-NEXT: addiu $2, $zero, 1
; MIPSEL32-NEXT: jrc $ra
;
; MIPS32-LABEL: f7:
; MIPS32: # %bb.0:
; MIPS32-NEXT: beqzc $4, $BB7_2
; MIPS32-NEXT: # %bb.1: # %if.end
; MIPS32-NEXT: addiu $2, $zero, 0
; MIPS32-NEXT: jrc $ra
; MIPS32-NEXT: $BB7_2: # %if.then
; MIPS32-NEXT: addiu $2, $zero, 1
; MIPS32-NEXT: jrc $ra
;
; MIPSEL64-LABEL: f7:
; MIPSEL64: # %bb.0:
; MIPSEL64-NEXT: sll $1, $4, 0
; MIPSEL64-NEXT: beqzc $1, .LBB7_2
; MIPSEL64-NEXT: # %bb.1: # %if.end
; MIPSEL64-NEXT: addiu $2, $zero, 0
; MIPSEL64-NEXT: jrc $ra
; MIPSEL64-NEXT: .LBB7_2: # %if.then
; MIPSEL64-NEXT: addiu $2, $zero, 1
; MIPSEL64-NEXT: jrc $ra
;
; MIPS64-LABEL: f7:
; MIPS64: # %bb.0:
; MIPS64-NEXT: sll $1, $4, 0
; MIPS64-NEXT: beqzc $1, .LBB7_2
; MIPS64-NEXT: # %bb.1: # %if.end
; MIPS64-NEXT: addiu $2, $zero, 0
; MIPS64-NEXT: jrc $ra
; MIPS64-NEXT: .LBB7_2: # %if.then
; MIPS64-NEXT: addiu $2, $zero, 1
; MIPS64-NEXT: jrc $ra
%cmp = icmp eq i32 0, %a
br i1 %cmp, label %if.then, label %if.end

View File

@ -1,3 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=mipsel-linux-gnu -march=mipsel -mattr=mips16 -mattr=+soft-float -mips16-hard-float -relocation-model=static -mips16-constant-islands=true < %s | FileCheck %s -check-prefix=lcb
; RUN: llc -mtriple=mipsel-linux-gnu -march=mipsel -mattr=mips16 -mattr=+soft-float -mips16-hard-float -relocation-model=static -mips16-constant-islands=true < %s | FileCheck %s -check-prefix=lcbn
@ -8,6 +9,51 @@
; Function Attrs: nounwind optsize
define i32 @bnez() #0 {
; lcb-LABEL: bnez:
; lcb: # %bb.0: # %entry
; lcb-NEXT: li $2, %hi(i)
; lcb-NEXT: sll $2, $2, 16
; lcb-NEXT: lw $3, %lo(i)($2)
; lcb-NEXT: bnez $3, $BB0_2
; lcb-NEXT: # %bb.1: # %if.then
; lcb-NEXT: li $3, 0
; lcb-NEXT: #APP
; lcb-NEXT: .set push
; lcb-NEXT: .set at
; lcb-NEXT: .set macro
; lcb-NEXT: .set reorder
; lcb-EMPTY:
; lcb-NEXT: .space 10000
; lcb-EMPTY:
; lcb-NEXT: .set pop
; lcb-NEXT: #NO_APP
; lcb-NEXT: sw $3, %lo(i)($2)
; lcb-NEXT: $BB0_2: # %if.end
; lcb-NEXT: li $2, 0
; lcb-NEXT: jrc $ra
;
; lcbn-LABEL: bnez:
; lcbn: # %bb.0: # %entry
; lcbn-NEXT: li $2, %hi(i)
; lcbn-NEXT: sll $2, $2, 16
; lcbn-NEXT: lw $3, %lo(i)($2)
; lcbn-NEXT: bnez $3, $BB0_2
; lcbn-NEXT: # %bb.1: # %if.then
; lcbn-NEXT: li $3, 0
; lcbn-NEXT: #APP
; lcbn-NEXT: .set push
; lcbn-NEXT: .set at
; lcbn-NEXT: .set macro
; lcbn-NEXT: .set reorder
; lcbn-EMPTY:
; lcbn-NEXT: .space 10000
; lcbn-EMPTY:
; lcbn-NEXT: .set pop
; lcbn-NEXT: #NO_APP
; lcbn-NEXT: sw $3, %lo(i)($2)
; lcbn-NEXT: $BB0_2: # %if.end
; lcbn-NEXT: li $2, 0
; lcbn-NEXT: jrc $ra
entry:
%0 = load i32, i32* @i, align 4, !tbaa !1
%cmp = icmp eq i32 %0, 0
@ -21,15 +67,90 @@ if.then: ; preds = %entry
if.end: ; preds = %if.then, %entry
ret i32 0
}
; lcb: .ent bnez
; lcbn: .ent bnez
; lcb: bnez ${{[0-9]+}}, $BB{{[0-9]+}}_{{[0-9]+}}
; lcbn-NOT: bnez ${{[0-9]+}}, $BB{{[0-9]+}}_{{[0-9]+}} # 16 bit inst
; lcb: .end bnez
; lcbn: .end bnez
; Function Attrs: nounwind optsize
define i32 @beqz() #0 {
; lcb-LABEL: beqz:
; lcb: # %bb.0: # %entry
; lcb-NEXT: li $2, %hi(i)
; lcb-NEXT: sll $2, $2, 16
; lcb-NEXT: lw $2, %lo(i)($2)
; lcb-NEXT: beqz $2, $BB1_2
; lcb-NEXT: # %bb.1: # %if.else
; lcb-NEXT: li $2, %hi(j)
; lcb-NEXT: sll $2, $2, 16
; lcb-NEXT: li $3, 55
; lcb-NEXT: sw $3, %lo(j)($2)
; lcb-NEXT: #APP
; lcb-NEXT: .set push
; lcb-NEXT: .set at
; lcb-NEXT: .set macro
; lcb-NEXT: .set reorder
; lcb-EMPTY:
; lcb-NEXT: .space 10000
; lcb-EMPTY:
; lcb-NEXT: .set pop
; lcb-NEXT: #NO_APP
; lcb-NEXT: b $BB1_3
; lcb-NEXT: $BB1_2: # %if.then
; lcb-NEXT: li $2, %hi(j)
; lcb-NEXT: sll $2, $2, 16
; lcb-NEXT: li $3, 10
; lcb-NEXT: sw $3, %lo(j)($2)
; lcb-NEXT: #APP
; lcb-NEXT: .set push
; lcb-NEXT: .set at
; lcb-NEXT: .set macro
; lcb-NEXT: .set reorder
; lcb-EMPTY:
; lcb-NEXT: .space 10000
; lcb-EMPTY:
; lcb-NEXT: .set pop
; lcb-NEXT: #NO_APP
; lcb-NEXT: $BB1_3: # %if.end
; lcb-NEXT: li $2, 0
; lcb-NEXT: jrc $ra
;
; lcbn-LABEL: beqz:
; lcbn: # %bb.0: # %entry
; lcbn-NEXT: li $2, %hi(i)
; lcbn-NEXT: sll $2, $2, 16
; lcbn-NEXT: lw $2, %lo(i)($2)
; lcbn-NEXT: beqz $2, $BB1_2
; lcbn-NEXT: # %bb.1: # %if.else
; lcbn-NEXT: li $2, %hi(j)
; lcbn-NEXT: sll $2, $2, 16
; lcbn-NEXT: li $3, 55
; lcbn-NEXT: sw $3, %lo(j)($2)
; lcbn-NEXT: #APP
; lcbn-NEXT: .set push
; lcbn-NEXT: .set at
; lcbn-NEXT: .set macro
; lcbn-NEXT: .set reorder
; lcbn-EMPTY:
; lcbn-NEXT: .space 10000
; lcbn-EMPTY:
; lcbn-NEXT: .set pop
; lcbn-NEXT: #NO_APP
; lcbn-NEXT: b $BB1_3
; lcbn-NEXT: $BB1_2: # %if.then
; lcbn-NEXT: li $2, %hi(j)
; lcbn-NEXT: sll $2, $2, 16
; lcbn-NEXT: li $3, 10
; lcbn-NEXT: sw $3, %lo(j)($2)
; lcbn-NEXT: #APP
; lcbn-NEXT: .set push
; lcbn-NEXT: .set at
; lcbn-NEXT: .set macro
; lcbn-NEXT: .set reorder
; lcbn-EMPTY:
; lcbn-NEXT: .space 10000
; lcbn-EMPTY:
; lcbn-NEXT: .set pop
; lcbn-NEXT: #NO_APP
; lcbn-NEXT: $BB1_3: # %if.end
; lcbn-NEXT: li $2, 0
; lcbn-NEXT: jrc $ra
entry:
%0 = load i32, i32* @i, align 4, !tbaa !1
%cmp = icmp eq i32 %0, 0
@ -49,16 +170,93 @@ if.end: ; preds = %if.else, %if.then
ret i32 0
}
; lcb: .ent beqz
; lcbn: .ent beqz
; lcb: beqz ${{[0-9]+}}, $BB{{[0-9]+}}_{{[0-9]+}}
; lcbn-NOT: beqz ${{[0-9]+}}, $BB{{[0-9]+}}_{{[0-9]+}} # 16 bit inst
; lcb: .end beqz
; lcbn: .end beqz
; Function Attrs: nounwind optsize
define void @bteqz() #0 {
; lcb-LABEL: bteqz:
; lcb: # %bb.0: # %entry
; lcb-NEXT: li $2, %hi(j)
; lcb-NEXT: sll $2, $2, 16
; lcb-NEXT: lw $2, %lo(j)($2)
; lcb-NEXT: li $3, %hi(i)
; lcb-NEXT: sll $3, $3, 16
; lcb-NEXT: lw $3, %lo(i)($3)
; lcb-NEXT: cmp $3, $2
; lcb-NEXT: bteqz $BB2_2
; lcb-NEXT: # %bb.1: # %if.else
; lcb-NEXT: li $2, %hi(k)
; lcb-NEXT: sll $2, $2, 16
; lcb-NEXT: #APP
; lcb-NEXT: .set push
; lcb-NEXT: .set at
; lcb-NEXT: .set macro
; lcb-NEXT: .set reorder
; lcb-EMPTY:
; lcb-NEXT: .space 1000
; lcb-EMPTY:
; lcb-NEXT: .set pop
; lcb-NEXT: #NO_APP
; lcb-NEXT: li $3, 2
; lcb-NEXT: sw $3, %lo(k)($2)
; lcb-NEXT: jrc $ra
; lcb-NEXT: $BB2_2: # %if.then
; lcb-NEXT: li $2, %hi(k)
; lcb-NEXT: sll $2, $2, 16
; lcb-NEXT: li $3, 1
; lcb-NEXT: sw $3, %lo(k)($2)
; lcb-NEXT: #APP
; lcb-NEXT: .set push
; lcb-NEXT: .set at
; lcb-NEXT: .set macro
; lcb-NEXT: .set reorder
; lcb-EMPTY:
; lcb-NEXT: .space 1000
; lcb-EMPTY:
; lcb-NEXT: .set pop
; lcb-NEXT: #NO_APP
; lcb-NEXT: jrc $ra
;
; lcbn-LABEL: bteqz:
; lcbn: # %bb.0: # %entry
; lcbn-NEXT: li $2, %hi(j)
; lcbn-NEXT: sll $2, $2, 16
; lcbn-NEXT: lw $2, %lo(j)($2)
; lcbn-NEXT: li $3, %hi(i)
; lcbn-NEXT: sll $3, $3, 16
; lcbn-NEXT: lw $3, %lo(i)($3)
; lcbn-NEXT: cmp $3, $2
; lcbn-NEXT: bteqz $BB2_2
; lcbn-NEXT: # %bb.1: # %if.else
; lcbn-NEXT: li $2, %hi(k)
; lcbn-NEXT: sll $2, $2, 16
; lcbn-NEXT: #APP
; lcbn-NEXT: .set push
; lcbn-NEXT: .set at
; lcbn-NEXT: .set macro
; lcbn-NEXT: .set reorder
; lcbn-EMPTY:
; lcbn-NEXT: .space 1000
; lcbn-EMPTY:
; lcbn-NEXT: .set pop
; lcbn-NEXT: #NO_APP
; lcbn-NEXT: li $3, 2
; lcbn-NEXT: sw $3, %lo(k)($2)
; lcbn-NEXT: jrc $ra
; lcbn-NEXT: $BB2_2: # %if.then
; lcbn-NEXT: li $2, %hi(k)
; lcbn-NEXT: sll $2, $2, 16
; lcbn-NEXT: li $3, 1
; lcbn-NEXT: sw $3, %lo(k)($2)
; lcbn-NEXT: #APP
; lcbn-NEXT: .set push
; lcbn-NEXT: .set at
; lcbn-NEXT: .set macro
; lcbn-NEXT: .set reorder
; lcbn-EMPTY:
; lcbn-NEXT: .space 1000
; lcbn-EMPTY:
; lcbn-NEXT: .set pop
; lcbn-NEXT: #NO_APP
; lcbn-NEXT: jrc $ra
entry:
%0 = load i32, i32* @i, align 4, !tbaa !1
%1 = load i32, i32* @j, align 4, !tbaa !1
@ -79,16 +277,65 @@ if.end: ; preds = %if.else, %if.then
ret void
}
; lcb: .ent bteqz
; lcbn: .ent bteqz
; lcb: btnez $BB{{[0-9]+}}_{{[0-9]+}}
; lcbn-NOT: btnez $BB{{[0-9]+}}_{{[0-9]+}} # 16 bit inst
; lcb: .end bteqz
; lcbn: .end bteqz
; Function Attrs: nounwind optsize
define void @btz() #0 {
; lcb-LABEL: btz:
; lcb: # %bb.0: # %entry
; lcb-NEXT: li $2, %hi(i)
; lcb-NEXT: sll $2, $2, 16
; lcb-NEXT: lw $4, %lo(i)($2)
; lcb-NEXT: li $3, %hi(j)
; lcb-NEXT: sll $3, $3, 16
; lcb-NEXT: lw $5, %lo(j)($3)
; lcb-NEXT: slt $5, $4
; lcb-NEXT: bteqz $BB3_2
; lcb-NEXT: $BB3_1: # %if.then
; lcb-NEXT: # =>This Inner Loop Header: Depth=1
; lcb-NEXT: #APP
; lcb-NEXT: .set push
; lcb-NEXT: .set at
; lcb-NEXT: .set macro
; lcb-NEXT: .set reorder
; lcb-EMPTY:
; lcb-NEXT: .space 60000
; lcb-EMPTY:
; lcb-NEXT: .set pop
; lcb-NEXT: #NO_APP
; lcb-NEXT: lw $4, %lo(i)($2)
; lcb-NEXT: lw $5, %lo(j)($3)
; lcb-NEXT: slt $5, $4
; lcb-NEXT: btnez $BB3_1
; lcb-NEXT: $BB3_2: # %if.end
; lcb-NEXT: jrc $ra
;
; lcbn-LABEL: btz:
; lcbn: # %bb.0: # %entry
; lcbn-NEXT: li $2, %hi(i)
; lcbn-NEXT: sll $2, $2, 16
; lcbn-NEXT: lw $4, %lo(i)($2)
; lcbn-NEXT: li $3, %hi(j)
; lcbn-NEXT: sll $3, $3, 16
; lcbn-NEXT: lw $5, %lo(j)($3)
; lcbn-NEXT: slt $5, $4
; lcbn-NEXT: bteqz $BB3_2
; lcbn-NEXT: $BB3_1: # %if.then
; lcbn-NEXT: # =>This Inner Loop Header: Depth=1
; lcbn-NEXT: #APP
; lcbn-NEXT: .set push
; lcbn-NEXT: .set at
; lcbn-NEXT: .set macro
; lcbn-NEXT: .set reorder
; lcbn-EMPTY:
; lcbn-NEXT: .space 60000
; lcbn-EMPTY:
; lcbn-NEXT: .set pop
; lcbn-NEXT: #NO_APP
; lcbn-NEXT: lw $4, %lo(i)($2)
; lcbn-NEXT: lw $5, %lo(j)($3)
; lcbn-NEXT: slt $5, $4
; lcbn-NEXT: btnez $BB3_1
; lcbn-NEXT: $BB3_2: # %if.end
; lcbn-NEXT: jrc $ra
entry:
%0 = load i32, i32* @i, align 4, !tbaa !1
%1 = load i32, i32* @j, align 4, !tbaa !1
@ -106,15 +353,6 @@ if.end: ; preds = %if.then, %entry
ret void
}
; lcb: .ent btz
; lcbn: .ent btz
; lcb: bteqz $BB{{[0-9]+}}_{{[0-9]+}}
; lcbn-NOT: bteqz $BB{{[0-9]+}}_{{[0-9]+}} # 16 bit inst
; lcb: btnez $BB{{[0-9]+}}_{{[0-9]+}}
; lcbn-NOT: btnez $BB{{[0-9]+}}_{{[0-9]+}} # 16 bit inst
; lcb: .end btz
; lcbn: .end btz
attributes #0 = { nounwind optsize "less-precise-fpmad"="false" "frame-pointer"="none" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { nounwind }

View File

@ -1,3 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=mipsel-linux-gnu -march=mipsel -mattr=mips16 -mattr=+soft-float -mips16-hard-float -relocation-model=static < %s | FileCheck %s -check-prefix=ci
@i = global i32 0, align 4
@ -6,6 +7,41 @@
; Function Attrs: nounwind optsize
define i32 @x0() #0 {
; ci-LABEL: x0:
; ci: # %bb.0: # %entry
; ci-NEXT: li $2, %hi(i)
; ci-NEXT: sll $2, $2, 16
; ci-NEXT: lw $3, %lo(i)($2)
; ci-NEXT: beqz $3, $BB0_2
; ci-NEXT: # %bb.1: # %if.else
; ci-NEXT: li $3, 1
; ci-NEXT: #APP
; ci-NEXT: .set push
; ci-NEXT: .set at
; ci-NEXT: .set macro
; ci-NEXT: .set reorder
; ci-EMPTY:
; ci-NEXT: .space 1004
; ci-EMPTY:
; ci-NEXT: .set pop
; ci-NEXT: #NO_APP
; ci-NEXT: b $BB0_3 # 16 bit inst
; ci-NEXT: $BB0_2: # %if.then
; ci-NEXT: li $3, 0
; ci-NEXT: #APP
; ci-NEXT: .set push
; ci-NEXT: .set at
; ci-NEXT: .set macro
; ci-NEXT: .set reorder
; ci-EMPTY:
; ci-NEXT: .space 1000
; ci-EMPTY:
; ci-NEXT: .set pop
; ci-NEXT: #NO_APP
; ci-NEXT: $BB0_3: # %if.end
; ci-NEXT: sw $3, %lo(i)($2)
; ci-NEXT: li $2, 0
; ci-NEXT: jrc $ra
entry:
%0 = load i32, i32* @i, align 4, !tbaa !1
%cmp = icmp eq i32 %0, 0
@ -25,13 +61,48 @@ if.end: ; preds = %if.else, %if.then
ret i32 0
}
; ci: .ent x0
; ci: beqz $3, $BB0_2
; ci: $BB0_2:
; ci: .end x0
; Function Attrs: nounwind optsize
define i32 @x1() #0 {
; ci-LABEL: x1:
; ci: # %bb.0: # %entry
; ci-NEXT: li $2, %hi(i)
; ci-NEXT: sll $2, $2, 16
; ci-NEXT: lw $3, %lo(i)($2)
; ci-NEXT: bnez $3, $BB1_1 # 16 bit inst
; ci-NEXT: jal $BB1_2 # branch
; ci-NEXT: nop
; ci-NEXT: $BB1_1: # %if.else
; ci-NEXT: li $3, 1
; ci-NEXT: #APP
; ci-NEXT: .set push
; ci-NEXT: .set at
; ci-NEXT: .set macro
; ci-NEXT: .set reorder
; ci-EMPTY:
; ci-NEXT: .space 1000004
; ci-EMPTY:
; ci-NEXT: .set pop
; ci-NEXT: #NO_APP
; ci-NEXT: jal $BB1_3 # branch
; ci-NEXT: nop
; ci-NEXT: .p2align 2
; ci-NEXT: $BB1_2: # %if.then
; ci-NEXT: li $3, 0
; ci-NEXT: #APP
; ci-NEXT: .set push
; ci-NEXT: .set at
; ci-NEXT: .set macro
; ci-NEXT: .set reorder
; ci-EMPTY:
; ci-NEXT: .space 1000000
; ci-EMPTY:
; ci-NEXT: .set pop
; ci-NEXT: #NO_APP
; ci-NEXT: .p2align 2
; ci-NEXT: $BB1_3: # %if.end
; ci-NEXT: sw $3, %lo(i)($2)
; ci-NEXT: li $2, 0
; ci-NEXT: jrc $ra
entry:
%0 = load i32, i32* @i, align 4, !tbaa !1
%cmp = icmp eq i32 %0, 0
@ -51,15 +122,49 @@ if.end: ; preds = %if.else, %if.then
ret i32 0
}
; ci: .ent x1
; ci: bnez $3, $BB1_1 # 16 bit inst
; ci: jal $BB1_2 # branch
; ci: nop
; ci: $BB1_1:
; ci: .end x1
; Function Attrs: nounwind optsize
define i32 @y0() #0 {
; ci-LABEL: y0:
; ci: # %bb.0: # %entry
; ci-NEXT: li $2, %hi(i)
; ci-NEXT: sll $2, $2, 16
; ci-NEXT: lw $2, %lo(i)($2)
; ci-NEXT: beqz $2, $BB2_2
; ci-NEXT: # %bb.1: # %if.else
; ci-NEXT: li $2, %hi(j)
; ci-NEXT: sll $2, $2, 16
; ci-NEXT: li $3, 55
; ci-NEXT: sw $3, %lo(j)($2)
; ci-NEXT: #APP
; ci-NEXT: .set push
; ci-NEXT: .set at
; ci-NEXT: .set macro
; ci-NEXT: .set reorder
; ci-EMPTY:
; ci-NEXT: .space 1004
; ci-EMPTY:
; ci-NEXT: .set pop
; ci-NEXT: #NO_APP
; ci-NEXT: b $BB2_3 # 16 bit inst
; ci-NEXT: $BB2_2: # %if.then
; ci-NEXT: li $2, %hi(j)
; ci-NEXT: sll $2, $2, 16
; ci-NEXT: li $3, 10
; ci-NEXT: sw $3, %lo(j)($2)
; ci-NEXT: #APP
; ci-NEXT: .set push
; ci-NEXT: .set at
; ci-NEXT: .set macro
; ci-NEXT: .set reorder
; ci-EMPTY:
; ci-NEXT: .space 1000
; ci-EMPTY:
; ci-NEXT: .set pop
; ci-NEXT: #NO_APP
; ci-NEXT: $BB2_3: # %if.end
; ci-NEXT: li $2, 0
; ci-NEXT: jrc $ra
entry:
%0 = load i32, i32* @i, align 4, !tbaa !1
%cmp = icmp eq i32 %0, 0
@ -79,12 +184,53 @@ if.end: ; preds = %if.else, %if.then
ret i32 0
}
; ci: .ent y0
; ci: beqz $2, $BB2_2
; ci: .end y0
; Function Attrs: nounwind optsize
define i32 @y1() #0 {
; ci-LABEL: y1:
; ci: # %bb.0: # %entry
; ci-NEXT: li $2, %hi(i)
; ci-NEXT: sll $2, $2, 16
; ci-NEXT: lw $2, %lo(i)($2)
; ci-NEXT: bnez $2, $BB3_1 # 16 bit inst
; ci-NEXT: jal $BB3_2 # branch
; ci-NEXT: nop
; ci-NEXT: $BB3_1: # %if.else
; ci-NEXT: li $2, %hi(j)
; ci-NEXT: sll $2, $2, 16
; ci-NEXT: li $3, 55
; ci-NEXT: sw $3, %lo(j)($2)
; ci-NEXT: #APP
; ci-NEXT: .set push
; ci-NEXT: .set at
; ci-NEXT: .set macro
; ci-NEXT: .set reorder
; ci-EMPTY:
; ci-NEXT: .space 1000004
; ci-EMPTY:
; ci-NEXT: .set pop
; ci-NEXT: #NO_APP
; ci-NEXT: jal $BB3_3 # branch
; ci-NEXT: nop
; ci-NEXT: .p2align 2
; ci-NEXT: $BB3_2: # %if.then
; ci-NEXT: li $2, %hi(j)
; ci-NEXT: sll $2, $2, 16
; ci-NEXT: li $3, 10
; ci-NEXT: sw $3, %lo(j)($2)
; ci-NEXT: #APP
; ci-NEXT: .set push
; ci-NEXT: .set at
; ci-NEXT: .set macro
; ci-NEXT: .set reorder
; ci-EMPTY:
; ci-NEXT: .space 1000000
; ci-EMPTY:
; ci-NEXT: .set pop
; ci-NEXT: #NO_APP
; ci-NEXT: .p2align 2
; ci-NEXT: $BB3_3: # %if.end
; ci-NEXT: li $2, 0
; ci-NEXT: jrc $ra
entry:
%0 = load i32, i32* @i, align 4, !tbaa !1
%cmp = icmp eq i32 %0, 0
@ -104,15 +250,51 @@ if.end: ; preds = %if.else, %if.then
ret i32 0
}
; ci: .ent y1
; ci: bnez $2, $BB3_1 # 16 bit inst
; ci: jal $BB3_2 # branch
; ci: nop
; ci: $BB3_1:
; ci: .end y1
; Function Attrs: nounwind optsize
define void @z0() #0 {
; ci-LABEL: z0:
; ci: # %bb.0: # %entry
; ci-NEXT: li $2, %hi(j)
; ci-NEXT: sll $2, $2, 16
; ci-NEXT: lw $2, %lo(j)($2)
; ci-NEXT: li $3, %hi(i)
; ci-NEXT: sll $3, $3, 16
; ci-NEXT: lw $3, %lo(i)($3)
; ci-NEXT: cmp $3, $2
; ci-NEXT: bteqz $BB4_2
; ci-NEXT: # %bb.1: # %if.else
; ci-NEXT: li $2, %hi(k)
; ci-NEXT: sll $2, $2, 16
; ci-NEXT: #APP
; ci-NEXT: .set push
; ci-NEXT: .set at
; ci-NEXT: .set macro
; ci-NEXT: .set reorder
; ci-EMPTY:
; ci-NEXT: .space 10004
; ci-EMPTY:
; ci-NEXT: .set pop
; ci-NEXT: #NO_APP
; ci-NEXT: li $3, 2
; ci-NEXT: sw $3, %lo(k)($2)
; ci-NEXT: jrc $ra
; ci-NEXT: $BB4_2: # %if.then
; ci-NEXT: li $2, %hi(k)
; ci-NEXT: sll $2, $2, 16
; ci-NEXT: li $3, 1
; ci-NEXT: sw $3, %lo(k)($2)
; ci-NEXT: #APP
; ci-NEXT: .set push
; ci-NEXT: .set at
; ci-NEXT: .set macro
; ci-NEXT: .set reorder
; ci-EMPTY:
; ci-NEXT: .space 10000
; ci-EMPTY:
; ci-NEXT: .set pop
; ci-NEXT: #NO_APP
; ci-NEXT: jrc $ra
entry:
%0 = load i32, i32* @i, align 4, !tbaa !1
%1 = load i32, i32* @j, align 4, !tbaa !1
@ -133,12 +315,54 @@ if.end: ; preds = %if.else, %if.then
ret void
}
; ci: .ent z0
; ci: btnez $BB4_2
; ci: .end z0
; Function Attrs: nounwind optsize
define void @z1() #0 {
; ci-LABEL: z1:
; ci: # %bb.0: # %entry
; ci-NEXT: li $2, %hi(j)
; ci-NEXT: sll $2, $2, 16
; ci-NEXT: lw $2, %lo(j)($2)
; ci-NEXT: li $3, %hi(i)
; ci-NEXT: sll $3, $3, 16
; ci-NEXT: lw $3, %lo(i)($3)
; ci-NEXT: cmp $3, $2
; ci-NEXT: btnez $BB5_1 # 16 bit inst
; ci-NEXT: jal $BB5_2 # branch
; ci-NEXT: nop
; ci-NEXT: $BB5_1: # %if.else
; ci-NEXT: li $2, %hi(k)
; ci-NEXT: sll $2, $2, 16
; ci-NEXT: #APP
; ci-NEXT: .set push
; ci-NEXT: .set at
; ci-NEXT: .set macro
; ci-NEXT: .set reorder
; ci-EMPTY:
; ci-NEXT: .space 10000004
; ci-EMPTY:
; ci-NEXT: .set pop
; ci-NEXT: #NO_APP
; ci-NEXT: li $3, 2
; ci-NEXT: sw $3, %lo(k)($2)
; ci-NEXT: jrc $ra
; ci-NEXT: .p2align 2
; ci-NEXT: $BB5_2: # %if.then
; ci-NEXT: li $2, %hi(k)
; ci-NEXT: sll $2, $2, 16
; ci-NEXT: li $3, 1
; ci-NEXT: sw $3, %lo(k)($2)
; ci-NEXT: #APP
; ci-NEXT: .set push
; ci-NEXT: .set at
; ci-NEXT: .set macro
; ci-NEXT: .set reorder
; ci-EMPTY:
; ci-NEXT: .space 10000000
; ci-EMPTY:
; ci-NEXT: .set pop
; ci-NEXT: #NO_APP
; ci-NEXT: jrc $ra
entry:
%0 = load i32, i32* @i, align 4, !tbaa !1
%1 = load i32, i32* @j, align 4, !tbaa !1
@ -159,15 +383,37 @@ if.end: ; preds = %if.else, %if.then
ret void
}
; ci: .ent z1
; ci: bteqz $BB5_1 # 16 bit inst
; ci: jal $BB5_2 # branch
; ci: nop
; ci: $BB5_1:
; ci: .end z1
; Function Attrs: nounwind optsize
define void @z3() #0 {
; ci-LABEL: z3:
; ci: # %bb.0: # %entry
; ci-NEXT: li $2, %hi(i)
; ci-NEXT: sll $2, $2, 16
; ci-NEXT: lw $4, %lo(i)($2)
; ci-NEXT: li $3, %hi(j)
; ci-NEXT: sll $3, $3, 16
; ci-NEXT: lw $5, %lo(j)($3)
; ci-NEXT: slt $5, $4
; ci-NEXT: bteqz $BB6_2
; ci-NEXT: $BB6_1: # %if.then
; ci-NEXT: # =>This Inner Loop Header: Depth=1
; ci-NEXT: #APP
; ci-NEXT: .set push
; ci-NEXT: .set at
; ci-NEXT: .set macro
; ci-NEXT: .set reorder
; ci-EMPTY:
; ci-NEXT: .space 10000
; ci-EMPTY:
; ci-NEXT: .set pop
; ci-NEXT: #NO_APP
; ci-NEXT: lw $4, %lo(i)($2)
; ci-NEXT: lw $5, %lo(j)($3)
; ci-NEXT: slt $5, $4
; ci-NEXT: btnez $BB6_1
; ci-NEXT: $BB6_2: # %if.end
; ci-NEXT: jrc $ra
entry:
%0 = load i32, i32* @i, align 4, !tbaa !1
%1 = load i32, i32* @j, align 4, !tbaa !1
@ -185,12 +431,42 @@ if.end: ; preds = %if.then, %entry
ret void
}
; ci: .ent z3
; ci: bteqz $BB6_2
; ci: .end z3
; Function Attrs: nounwind optsize
define void @z4() #0 {
; ci-LABEL: z4:
; ci: # %bb.0: # %entry
; ci-NEXT: li $2, %hi(i)
; ci-NEXT: sll $2, $2, 16
; ci-NEXT: lw $4, %lo(i)($2)
; ci-NEXT: li $3, %hi(j)
; ci-NEXT: sll $3, $3, 16
; ci-NEXT: lw $5, %lo(j)($3)
; ci-NEXT: slt $5, $4
; ci-NEXT: btnez $BB7_1 # 16 bit inst
; ci-NEXT: jal $BB7_2 # branch
; ci-NEXT: nop
; ci-NEXT: .p2align 2
; ci-NEXT: $BB7_1: # %if.then
; ci-NEXT: # =>This Inner Loop Header: Depth=1
; ci-NEXT: #APP
; ci-NEXT: .set push
; ci-NEXT: .set at
; ci-NEXT: .set macro
; ci-NEXT: .set reorder
; ci-EMPTY:
; ci-NEXT: .space 10000000
; ci-EMPTY:
; ci-NEXT: .set pop
; ci-NEXT: #NO_APP
; ci-NEXT: lw $4, %lo(i)($2)
; ci-NEXT: lw $5, %lo(j)($3)
; ci-NEXT: slt $5, $4
; ci-NEXT: bteqz $BB7_2 # 16 bit inst
; ci-NEXT: jal $BB7_1 # branch
; ci-NEXT: nop
; ci-NEXT: .p2align 2
; ci-NEXT: $BB7_2: # %if.end
; ci-NEXT: jrc $ra
entry:
%0 = load i32, i32* @i, align 4, !tbaa !1
%1 = load i32, i32* @j, align 4, !tbaa !1
@ -208,14 +484,6 @@ if.end: ; preds = %if.then, %entry
ret void
}
; ci: .ent z4
; ci: btnez $BB7_1 # 16 bit inst
; ci: jal $BB7_2 # branch
; ci: nop
; ci: .p2align 2
; ci: $BB7_1:
; ci: .end z4
attributes #0 = { nounwind optsize "less-precise-fpmad"="false" "frame-pointer"="none" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { nounwind }

View File

@ -1,3 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -march=mips -mcpu=mips32r6 -force-mips-long-branch | FileCheck %s
; Check that when MIPS32R6 with the static relocation model with the usage of
@ -9,11 +10,29 @@ declare i32 @f(i32)
declare i32 @g()
; CHECK-LABEL: test1:
; CHECK: bnezc
; CHECK-NEXT: nop
define i32 @test1(i32 %a) {
; CHECK-LABEL: test1:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addiu $sp, $sp, -24
; CHECK-NEXT: .cfi_def_cfa_offset 24
; CHECK-NEXT: sw $ra, 20($sp) # 4-byte Folded Spill
; CHECK-NEXT: .cfi_offset 31, -4
; CHECK-NEXT: bnezc $4, $BB0_2
; CHECK-NEXT: nop
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: bc $BB0_3
; CHECK-NEXT: $BB0_2: # %cond.false
; CHECK-NEXT: jal g
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
; CHECK-NEXT: $BB0_3: # %cond.true
; CHECK-NEXT: jal f
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
entry:
%0 = icmp eq i32 %a, 0
br i1 %0, label %cond.true, label %cond.false
@ -25,11 +44,30 @@ cond.false:
ret i32 %2
}
; CHECK-LABEL: test2:
; CHECK: bgezc
; CHECK-NEXT: nop
define i32 @test2(i32 %a) {
; CHECK-LABEL: test2:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addiu $sp, $sp, -24
; CHECK-NEXT: .cfi_def_cfa_offset 24
; CHECK-NEXT: sw $ra, 20($sp) # 4-byte Folded Spill
; CHECK-NEXT: .cfi_offset 31, -4
; CHECK-NEXT: bgezc $4, $BB1_2
; CHECK-NEXT: nop
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: bc $BB1_3
; CHECK-NEXT: $BB1_2: # %cond.true
; CHECK-NEXT: jal f
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
; CHECK-NEXT: $BB1_3: # %cond.false
; CHECK-NEXT: jal g
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
entry:
%0 = icmp sge i32 %a, 0
br i1 %0, label %cond.true, label %cond.false
@ -41,11 +79,30 @@ cond.false:
ret i32 %2
}
; CHECK-LABEL: test3:
; CHECK: blezc
; CHECK-NEXT: nop
define i32 @test3(i32 %a) {
; CHECK-LABEL: test3:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addiu $sp, $sp, -24
; CHECK-NEXT: .cfi_def_cfa_offset 24
; CHECK-NEXT: sw $ra, 20($sp) # 4-byte Folded Spill
; CHECK-NEXT: .cfi_offset 31, -4
; CHECK-NEXT: blezc $4, $BB2_2
; CHECK-NEXT: nop
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: bc $BB2_3
; CHECK-NEXT: $BB2_2: # %cond.true
; CHECK-NEXT: jal f
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
; CHECK-NEXT: $BB2_3: # %cond.false
; CHECK-NEXT: jal g
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
entry:
%0 = icmp sle i32 %a, 0
br i1 %0, label %cond.true, label %cond.false
@ -57,11 +114,30 @@ cond.false:
ret i32 %2
}
; CHECK-LABEL: test4:
; CHECK: bgtzc
; CHECK-NEXT: nop
define i32 @test4(i32 %a) {
; CHECK-LABEL: test4:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addiu $sp, $sp, -24
; CHECK-NEXT: .cfi_def_cfa_offset 24
; CHECK-NEXT: sw $ra, 20($sp) # 4-byte Folded Spill
; CHECK-NEXT: .cfi_offset 31, -4
; CHECK-NEXT: bgtzc $4, $BB3_2
; CHECK-NEXT: nop
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: bc $BB3_3
; CHECK-NEXT: $BB3_2: # %cond.true
; CHECK-NEXT: jal f
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
; CHECK-NEXT: $BB3_3: # %cond.false
; CHECK-NEXT: jal g
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
entry:
%0 = icmp sgt i32 %a, 0
br i1 %0, label %cond.true, label %cond.false
@ -73,11 +149,29 @@ cond.false:
ret i32 %2
}
; CHECK-LABEL: test5:
; CHECK: bgezc
; CHECK-NEXT: nop
define i32 @test5(i32 %a) {
; CHECK-LABEL: test5:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addiu $sp, $sp, -24
; CHECK-NEXT: .cfi_def_cfa_offset 24
; CHECK-NEXT: sw $ra, 20($sp) # 4-byte Folded Spill
; CHECK-NEXT: .cfi_offset 31, -4
; CHECK-NEXT: bgezc $4, $BB4_2
; CHECK-NEXT: nop
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: bc $BB4_3
; CHECK-NEXT: $BB4_2: # %cond.false
; CHECK-NEXT: jal g
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
; CHECK-NEXT: $BB4_3: # %cond.true
; CHECK-NEXT: jal f
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
entry:
%0 = icmp slt i32 %a, 0
br i1 %0, label %cond.true, label %cond.false
@ -89,11 +183,30 @@ cond.false:
ret i32 %2
}
; CHECK-LABEL: test6:
; CHECK: bnezc
; CHECK-NEXT: nop
define i32 @test6(i32 %a, i32 %b) {
; CHECK-LABEL: test6:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addiu $sp, $sp, -24
; CHECK-NEXT: .cfi_def_cfa_offset 24
; CHECK-NEXT: sw $ra, 20($sp) # 4-byte Folded Spill
; CHECK-NEXT: .cfi_offset 31, -4
; CHECK-NEXT: sltu $1, $5, $4
; CHECK-NEXT: bnezc $1, $BB5_2
; CHECK-NEXT: nop
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: bc $BB5_3
; CHECK-NEXT: $BB5_2: # %cond.true
; CHECK-NEXT: jal f
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
; CHECK-NEXT: $BB5_3: # %cond.false
; CHECK-NEXT: jal g
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
entry:
%0 = icmp ugt i32 %a, %b
br i1 %0, label %cond.true, label %cond.false
@ -105,11 +218,31 @@ cond.false:
ret i32 %2
}
; CHECK-LABEL: test7:
; CHECK: beqzc
; CHECK-NEXT: nop
define i32 @test7(i32 %a, i32 %b) {
; CHECK-LABEL: test7:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addiu $sp, $sp, -24
; CHECK-NEXT: .cfi_def_cfa_offset 24
; CHECK-NEXT: sw $ra, 20($sp) # 4-byte Folded Spill
; CHECK-NEXT: .cfi_offset 31, -4
; CHECK-NEXT: sltu $1, $4, $5
; CHECK-NEXT: bnezc $1, $BB6_2
; CHECK-NEXT: nop
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: bc $BB6_3
; CHECK-NEXT: $BB6_2: # %cond.false
; CHECK-NEXT: jal g
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
; CHECK-NEXT: $BB6_3: # %cond.true
; CHECK-NEXT: jal f
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
entry:
%0 = icmp uge i32 %a, %b
br i1 %0, label %cond.true, label %cond.false
@ -121,11 +254,31 @@ cond.false:
ret i32 %2
}
; CHECK-LABEL: test8:
; CHECK: bnezc
; CHECK-NEXT: nop
define i32 @test8(i32 %a, i32 %b) {
; CHECK-LABEL: test8:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addiu $sp, $sp, -24
; CHECK-NEXT: .cfi_def_cfa_offset 24
; CHECK-NEXT: sw $ra, 20($sp) # 4-byte Folded Spill
; CHECK-NEXT: .cfi_offset 31, -4
; CHECK-NEXT: sltu $1, $4, $5
; CHECK-NEXT: bnezc $1, $BB7_2
; CHECK-NEXT: nop
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: bc $BB7_3
; CHECK-NEXT: $BB7_2: # %cond.true
; CHECK-NEXT: jal f
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
; CHECK-NEXT: $BB7_3: # %cond.false
; CHECK-NEXT: jal g
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
entry:
%0 = icmp ult i32 %a, %b
br i1 %0, label %cond.true, label %cond.false
@ -137,11 +290,31 @@ cond.false:
ret i32 %2
}
; CHECK-LABEL: test9:
; CHECK: beqzc
; CHECK-NEXT: nop
define i32 @test9(i32 %a, i32 %b) {
; CHECK-LABEL: test9:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addiu $sp, $sp, -24
; CHECK-NEXT: .cfi_def_cfa_offset 24
; CHECK-NEXT: sw $ra, 20($sp) # 4-byte Folded Spill
; CHECK-NEXT: .cfi_offset 31, -4
; CHECK-NEXT: sltu $1, $5, $4
; CHECK-NEXT: bnezc $1, $BB8_2
; CHECK-NEXT: nop
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: bc $BB8_3
; CHECK-NEXT: $BB8_2: # %cond.false
; CHECK-NEXT: jal g
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
; CHECK-NEXT: $BB8_3: # %cond.true
; CHECK-NEXT: jal f
; CHECK-NEXT: nop
; CHECK-NEXT: lw $ra, 20($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 24
entry:
%0 = icmp ule i32 %a, %b
br i1 %0, label %cond.true, label %cond.false

View File

@ -1,4 +1,5 @@
; RUN: llc -march=mipsel -mattr=mips16 -relocation-model=pic < %s | FileCheck %s -check-prefix=16
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=mipsel -mattr=mips16 -relocation-model=pic < %s | FileCheck %s -check-prefix=MIPS16
@t = global i32 10, align 4
@f = global i32 199, align 4
@ -11,6 +12,74 @@
@z4 = common global i32 0, align 4
define void @calc_seleq() nounwind {
; MIPS16-LABEL: calc_seleq:
; MIPS16: # %bb.0: # %entry
; MIPS16-NEXT: lui $2, %hi(_gp_disp)
; MIPS16-NEXT: addiu $2, $2, %lo(_gp_disp)
; MIPS16-NEXT: li $2, %hi(_gp_disp)
; MIPS16-NEXT: addiu $3, $pc, %lo(_gp_disp)
; MIPS16-NEXT: sll $2, $2, 16
; MIPS16-NEXT: addu $2, $3, $2
; MIPS16-NEXT: lw $4, %got(b)($2)
; MIPS16-NEXT: lw $5, 0($4)
; MIPS16-NEXT: lw $3, %got(a)($2)
; MIPS16-NEXT: lw $6, 0($3)
; MIPS16-NEXT: cmp $6, $5
; MIPS16-NEXT: bteqz $BB0_2 # 16 bit inst
; MIPS16-NEXT: # %bb.1: # %cond.false
; MIPS16-NEXT: lw $5, %got(t)($2)
; MIPS16-NEXT: lw $5, 0($5)
; MIPS16-NEXT: b $BB0_3 # 16 bit inst
; MIPS16-NEXT: $BB0_2: # %cond.true
; MIPS16-NEXT: lw $5, %got(f)($2)
; MIPS16-NEXT: lw $5, 0($5)
; MIPS16-NEXT: $BB0_3: # %cond.end
; MIPS16-NEXT: lw $6, %got(z1)($2)
; MIPS16-NEXT: sw $5, 0($6)
; MIPS16-NEXT: lw $5, 0($3)
; MIPS16-NEXT: lw $4, 0($4)
; MIPS16-NEXT: cmp $4, $5
; MIPS16-NEXT: bteqz $BB0_5 # 16 bit inst
; MIPS16-NEXT: # %bb.4: # %cond.false3
; MIPS16-NEXT: lw $4, %got(t)($2)
; MIPS16-NEXT: lw $4, 0($4)
; MIPS16-NEXT: b $BB0_6 # 16 bit inst
; MIPS16-NEXT: $BB0_5: # %cond.true2
; MIPS16-NEXT: lw $4, %got(f)($2)
; MIPS16-NEXT: lw $4, 0($4)
; MIPS16-NEXT: $BB0_6: # %cond.end4
; MIPS16-NEXT: lw $5, %got(z2)($2)
; MIPS16-NEXT: sw $4, 0($5)
; MIPS16-NEXT: lw $5, 0($3)
; MIPS16-NEXT: lw $4, %got(c)($2)
; MIPS16-NEXT: lw $6, 0($4)
; MIPS16-NEXT: cmp $6, $5
; MIPS16-NEXT: bteqz $BB0_8 # 16 bit inst
; MIPS16-NEXT: # %bb.7: # %cond.false8
; MIPS16-NEXT: lw $5, %got(f)($2)
; MIPS16-NEXT: lw $5, 0($5)
; MIPS16-NEXT: b $BB0_9 # 16 bit inst
; MIPS16-NEXT: $BB0_8: # %cond.true7
; MIPS16-NEXT: lw $5, %got(t)($2)
; MIPS16-NEXT: lw $5, 0($5)
; MIPS16-NEXT: $BB0_9: # %cond.end9
; MIPS16-NEXT: lw $6, %got(z3)($2)
; MIPS16-NEXT: sw $5, 0($6)
; MIPS16-NEXT: lw $4, 0($4)
; MIPS16-NEXT: lw $3, 0($3)
; MIPS16-NEXT: cmp $3, $4
; MIPS16-NEXT: bteqz $BB0_11 # 16 bit inst
; MIPS16-NEXT: # %bb.10: # %cond.false13
; MIPS16-NEXT: lw $3, %got(f)($2)
; MIPS16-NEXT: lw $3, 0($3)
; MIPS16-NEXT: b $BB0_12 # 16 bit inst
; MIPS16-NEXT: $BB0_11: # %cond.true12
; MIPS16-NEXT: lw $3, %got(t)($2)
; MIPS16-NEXT: lw $3, 0($3)
; MIPS16-NEXT: $BB0_12: # %cond.end14
; MIPS16-NEXT: lw $2, %got(z4)($2)
; MIPS16-NEXT: sw $3, 0($2)
; MIPS16-NEXT: jrc $ra
entry:
%0 = load i32, i32* @a, align 4
%1 = load i32, i32* @b, align 4
@ -80,16 +149,3 @@ cond.end14: ; preds = %cond.false13, %cond
}
attributes #0 = { nounwind "target-cpu"="mips32" "target-features"="+o32,+mips32" }
; 16: cmp ${{[0-9]+}}, ${{[0-9]+}}
; 16: btnez $BB{{[0-9]+}}_{{[0-9]}}
; 16: cmp ${{[0-9]+}}, ${{[0-9]+}}
; 16: btnez $BB{{[0-9]+}}_{{[0-9]}}
; 16: cmp ${{[0-9]+}}, ${{[0-9]+}}
; 16: btnez $BB{{[0-9]+}}_{{[0-9]}}
; 16: cmp ${{[0-9]+}}, ${{[0-9]+}}
; 16: btnez $BB{{[0-9]+}}_{{[0-9]}}

View File

@ -1,4 +1,5 @@
; RUN: llc -march=mipsel -mattr=mips16 -relocation-model=pic < %s | FileCheck %s -check-prefix=16
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=mipsel -mattr=mips16 -relocation-model=pic < %s | FileCheck %s -check-prefix=MIPS16
@t = global i32 10, align 4
@f = global i32 199, align 4
@ -12,6 +13,74 @@
@.str = private unnamed_addr constant [5 x i8] c"%i \0A\00", align 1
define void @calc_z() nounwind "target-cpu"="mips16" "target-features"="+mips16,+o32" {
; MIPS16-LABEL: calc_z:
; MIPS16: # %bb.0: # %entry
; MIPS16-NEXT: lui $2, %hi(_gp_disp)
; MIPS16-NEXT: addiu $2, $2, %lo(_gp_disp)
; MIPS16-NEXT: li $2, %hi(_gp_disp)
; MIPS16-NEXT: addiu $3, $pc, %lo(_gp_disp)
; MIPS16-NEXT: sll $2, $2, 16
; MIPS16-NEXT: addu $2, $3, $2
; MIPS16-NEXT: lw $3, %got(a)($2)
; MIPS16-NEXT: lw $5, 0($3)
; MIPS16-NEXT: lw $4, %got(b)($2)
; MIPS16-NEXT: lw $6, 0($4)
; MIPS16-NEXT: slt $6, $5
; MIPS16-NEXT: bteqz $BB0_2 # 16 bit inst
; MIPS16-NEXT: # %bb.1: # %cond.false
; MIPS16-NEXT: lw $5, %got(f)($2)
; MIPS16-NEXT: lw $5, 0($5)
; MIPS16-NEXT: b $BB0_3 # 16 bit inst
; MIPS16-NEXT: $BB0_2: # %cond.true
; MIPS16-NEXT: lw $5, %got(t)($2)
; MIPS16-NEXT: lw $5, 0($5)
; MIPS16-NEXT: $BB0_3: # %cond.end
; MIPS16-NEXT: lw $6, %got(z1)($2)
; MIPS16-NEXT: sw $5, 0($6)
; MIPS16-NEXT: lw $4, 0($4)
; MIPS16-NEXT: lw $5, 0($3)
; MIPS16-NEXT: slt $5, $4
; MIPS16-NEXT: bteqz $BB0_5 # 16 bit inst
; MIPS16-NEXT: # %bb.4: # %cond.false3
; MIPS16-NEXT: lw $4, %got(t)($2)
; MIPS16-NEXT: lw $4, 0($4)
; MIPS16-NEXT: b $BB0_6 # 16 bit inst
; MIPS16-NEXT: $BB0_5: # %cond.true2
; MIPS16-NEXT: lw $4, %got(f)($2)
; MIPS16-NEXT: lw $4, 0($4)
; MIPS16-NEXT: $BB0_6: # %cond.end4
; MIPS16-NEXT: lw $5, %got(z2)($2)
; MIPS16-NEXT: sw $4, 0($5)
; MIPS16-NEXT: lw $4, %got(c)($2)
; MIPS16-NEXT: lw $5, 0($4)
; MIPS16-NEXT: lw $6, 0($3)
; MIPS16-NEXT: slt $6, $5
; MIPS16-NEXT: bteqz $BB0_8 # 16 bit inst
; MIPS16-NEXT: # %bb.7: # %cond.false8
; MIPS16-NEXT: lw $5, %got(f)($2)
; MIPS16-NEXT: lw $5, 0($5)
; MIPS16-NEXT: b $BB0_9 # 16 bit inst
; MIPS16-NEXT: $BB0_8: # %cond.true7
; MIPS16-NEXT: lw $5, %got(t)($2)
; MIPS16-NEXT: lw $5, 0($5)
; MIPS16-NEXT: $BB0_9: # %cond.end9
; MIPS16-NEXT: lw $6, %got(z3)($2)
; MIPS16-NEXT: sw $5, 0($6)
; MIPS16-NEXT: lw $3, 0($3)
; MIPS16-NEXT: lw $4, 0($4)
; MIPS16-NEXT: slt $4, $3
; MIPS16-NEXT: bteqz $BB0_11 # 16 bit inst
; MIPS16-NEXT: # %bb.10: # %cond.false13
; MIPS16-NEXT: lw $3, %got(f)($2)
; MIPS16-NEXT: lw $3, 0($3)
; MIPS16-NEXT: b $BB0_12 # 16 bit inst
; MIPS16-NEXT: $BB0_11: # %cond.true12
; MIPS16-NEXT: lw $3, %got(t)($2)
; MIPS16-NEXT: lw $3, 0($3)
; MIPS16-NEXT: $BB0_12: # %cond.end14
; MIPS16-NEXT: lw $2, %got(z4)($2)
; MIPS16-NEXT: sw $3, 0($2)
; MIPS16-NEXT: jrc $ra
entry:
%0 = load i32, i32* @a, align 4
%1 = load i32, i32* @b, align 4
@ -80,17 +149,6 @@ cond.end14: ; preds = %cond.false13, %cond
ret void
}
; 16: slt ${{[0-9]+}}, ${{[0-9]+}}
; 16: btnez $BB{{[0-9]+}}_{{[0-9]}}
; 16: slt ${{[0-9]+}}, ${{[0-9]+}}
; 16: btnez $BB{{[0-9]+}}_{{[0-9]}}
; 16: slt ${{[0-9]+}}, ${{[0-9]+}}
; 16: btnez $BB{{[0-9]+}}_{{[0-9]}}
; 16: slt ${{[0-9]+}}, ${{[0-9]+}}
; 16: btnez $BB{{[0-9]+}}_{{[0-9]}}
attributes #0 = { nounwind "target-cpu"="mips16" "target-features"="+mips16,+o32" }
attributes #1 = { "target-cpu"="mips16" "target-features"="+mips16,+o32" }

View File

@ -1,12 +1,22 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-unknown \
; RUN: -ppc-reduce-cr-logicals=false < %s | FileCheck %s
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-unknown \
; RUN: -ppc-reduce-cr-logicals=false < %s | FileCheck %s
define signext i32 @testi32slt(i32 signext %c1, i32 signext %c2, i32 signext %c3, i32 signext %c4, i32 signext %a1, i32 signext %a2) #0 {
; CHECK-LABEL: testi32slt
; CHECK: crorc [[REG:[0-9]+]], 2, 6
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testi32slt:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpw 5, 6
; CHECK-NEXT: cmpw 1, 3, 4
; CHECK-NEXT: crorc 20, 2, 6
; CHECK-NEXT: bc 12, 20, .LBB0_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: extsw 3, 7
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB0_2: # %iffalse
; CHECK-NEXT: extsw 3, 8
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i32 %c3, %c4
%cmp3tmp = icmp eq i32 %c1, %c2
@ -19,9 +29,18 @@ iffalse:
}
define signext i32 @testi32ult(i32 signext %c1, i32 signext %c2, i32 signext %c3, i32 signext %c4, i32 signext %a1, i32 signext %a2) #0 {
; CHECK-LABEL: testi32ult
; CHECK: crorc [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testi32ult:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpw 5, 6
; CHECK-NEXT: cmpw 1, 3, 4
; CHECK-NEXT: crorc 20, 6, 2
; CHECK-NEXT: bc 12, 20, .LBB1_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: extsw 3, 7
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB1_2: # %iffalse
; CHECK-NEXT: extsw 3, 8
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i32 %c3, %c4
%cmp3tmp = icmp eq i32 %c1, %c2
@ -34,9 +53,18 @@ iffalse:
}
define signext i32 @testi32sle(i32 signext %c1, i32 signext %c2, i32 signext %c3, i32 signext %c4, i32 signext %a1, i32 signext %a2) #0 {
; CHECK-LABEL: testi32sle
; CHECK: crandc [[REG:[0-9]+]], 2, 6
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testi32sle:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpw 5, 6
; CHECK-NEXT: cmpw 1, 3, 4
; CHECK-NEXT: crandc 20, 2, 6
; CHECK-NEXT: bc 4, 20, .LBB2_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: extsw 3, 8
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB2_2: # %iftrue
; CHECK-NEXT: extsw 3, 7
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i32 %c3, %c4
%cmp3tmp = icmp eq i32 %c1, %c2
@ -49,9 +77,18 @@ iffalse:
}
define signext i32 @testi32ule(i32 signext %c1, i32 signext %c2, i32 signext %c3, i32 signext %c4, i32 signext %a1, i32 signext %a2) #0 {
; CHECK-LABEL: testi32ule
; CHECK: crandc [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testi32ule:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpw 5, 6
; CHECK-NEXT: cmpw 1, 3, 4
; CHECK-NEXT: crandc 20, 6, 2
; CHECK-NEXT: bc 4, 20, .LBB3_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: extsw 3, 8
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB3_2: # %iftrue
; CHECK-NEXT: extsw 3, 7
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i32 %c3, %c4
%cmp3tmp = icmp eq i32 %c1, %c2
@ -65,8 +102,17 @@ iffalse:
define signext i32 @testi32eq(i32 signext %c1, i32 signext %c2, i32 signext %c3, i32 signext %c4, i32 signext %a1, i32 signext %a2) #0 {
; CHECK-LABEL: testi32eq:
; CHECK: crxor [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpw 5, 6
; CHECK-NEXT: cmpw 1, 3, 4
; CHECK-NEXT: crxor 20, 6, 2
; CHECK-NEXT: bc 4, 20, .LBB4_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: extsw 3, 8
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB4_2: # %iftrue
; CHECK-NEXT: extsw 3, 7
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i32 %c3, %c4
%cmp3tmp = icmp eq i32 %c1, %c2
@ -80,8 +126,17 @@ iffalse:
define signext i32 @testi32sge(i32 signext %c1, i32 signext %c2, i32 signext %c3, i32 signext %c4, i32 signext %a1, i32 signext %a2) #0 {
; CHECK-LABEL: testi32sge:
; CHECK: crandc [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpw 5, 6
; CHECK-NEXT: cmpw 1, 3, 4
; CHECK-NEXT: crandc 20, 6, 2
; CHECK-NEXT: bc 4, 20, .LBB5_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: extsw 3, 8
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB5_2: # %iftrue
; CHECK-NEXT: extsw 3, 7
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i32 %c3, %c4
%cmp3tmp = icmp eq i32 %c1, %c2
@ -95,8 +150,17 @@ iffalse:
define signext i32 @testi32uge(i32 signext %c1, i32 signext %c2, i32 signext %c3, i32 signext %c4, i32 signext %a1, i32 signext %a2) #0 {
; CHECK-LABEL: testi32uge:
; CHECK: crandc [[REG:[0-9]+]], 2, 6
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpw 5, 6
; CHECK-NEXT: cmpw 1, 3, 4
; CHECK-NEXT: crandc 20, 2, 6
; CHECK-NEXT: bc 4, 20, .LBB6_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: extsw 3, 8
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB6_2: # %iftrue
; CHECK-NEXT: extsw 3, 7
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i32 %c3, %c4
%cmp3tmp = icmp eq i32 %c1, %c2
@ -110,8 +174,17 @@ iffalse:
define signext i32 @testi32sgt(i32 signext %c1, i32 signext %c2, i32 signext %c3, i32 signext %c4, i32 signext %a1, i32 signext %a2) #0 {
; CHECK-LABEL: testi32sgt:
; CHECK: crorc [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpw 5, 6
; CHECK-NEXT: cmpw 1, 3, 4
; CHECK-NEXT: crorc 20, 6, 2
; CHECK-NEXT: bc 12, 20, .LBB7_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: extsw 3, 7
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB7_2: # %iffalse
; CHECK-NEXT: extsw 3, 8
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i32 %c3, %c4
%cmp3tmp = icmp eq i32 %c1, %c2
@ -125,8 +198,17 @@ iffalse:
define signext i32 @testi32ugt(i32 signext %c1, i32 signext %c2, i32 signext %c3, i32 signext %c4, i32 signext %a1, i32 signext %a2) #0 {
; CHECK-LABEL: testi32ugt:
; CHECK: crorc [[REG:[0-9]+]], 2, 6
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpw 5, 6
; CHECK-NEXT: cmpw 1, 3, 4
; CHECK-NEXT: crorc 20, 2, 6
; CHECK-NEXT: bc 12, 20, .LBB8_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: extsw 3, 7
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB8_2: # %iffalse
; CHECK-NEXT: extsw 3, 8
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i32 %c3, %c4
%cmp3tmp = icmp eq i32 %c1, %c2
@ -140,8 +222,17 @@ iffalse:
define signext i32 @testi32ne(i32 signext %c1, i32 signext %c2, i32 signext %c3, i32 signext %c4, i32 signext %a1, i32 signext %a2) #0 {
; CHECK-LABEL: testi32ne:
; CHECK: creqv [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpw 5, 6
; CHECK-NEXT: cmpw 1, 3, 4
; CHECK-NEXT: creqv 20, 6, 2
; CHECK-NEXT: bc 12, 20, .LBB9_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: extsw 3, 7
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB9_2: # %iffalse
; CHECK-NEXT: extsw 3, 8
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i32 %c3, %c4
%cmp3tmp = icmp eq i32 %c1, %c2
@ -154,9 +245,18 @@ iffalse:
}
define i64 @testi64slt(i64 %c1, i64 %c2, i64 %c3, i64 %c4, i64 %a1, i64 %a2) #0 {
; CHECK-LABEL: testi64slt
; CHECK: crorc [[REG:[0-9]+]], 2, 6
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testi64slt:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpd 5, 6
; CHECK-NEXT: cmpd 1, 3, 4
; CHECK-NEXT: crorc 20, 2, 6
; CHECK-NEXT: bc 12, 20, .LBB10_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: mr 3, 7
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB10_2: # %iffalse
; CHECK-NEXT: mr 3, 8
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i64 %c3, %c4
%cmp3tmp = icmp eq i64 %c1, %c2
@ -169,9 +269,18 @@ iffalse:
}
define i64 @testi64ult(i64 %c1, i64 %c2, i64 %c3, i64 %c4, i64 %a1, i64 %a2) #0 {
; CHECK-LABEL: testi64ult
; CHECK: crorc [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testi64ult:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpd 5, 6
; CHECK-NEXT: cmpd 1, 3, 4
; CHECK-NEXT: crorc 20, 6, 2
; CHECK-NEXT: bc 12, 20, .LBB11_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: mr 3, 7
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB11_2: # %iffalse
; CHECK-NEXT: mr 3, 8
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i64 %c3, %c4
%cmp3tmp = icmp eq i64 %c1, %c2
@ -184,9 +293,18 @@ iffalse:
}
define i64 @testi64sle(i64 %c1, i64 %c2, i64 %c3, i64 %c4, i64 %a1, i64 %a2) #0 {
; CHECK-LABEL: testi64sle
; CHECK: crandc [[REG:[0-9]+]], 2, 6
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testi64sle:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpd 5, 6
; CHECK-NEXT: cmpd 1, 3, 4
; CHECK-NEXT: crandc 20, 2, 6
; CHECK-NEXT: bc 4, 20, .LBB12_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: mr 3, 8
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB12_2: # %iftrue
; CHECK-NEXT: mr 3, 7
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i64 %c3, %c4
%cmp3tmp = icmp eq i64 %c1, %c2
@ -199,9 +317,18 @@ iffalse:
}
define i64 @testi64ule(i64 %c1, i64 %c2, i64 %c3, i64 %c4, i64 %a1, i64 %a2) #0 {
; CHECK-LABEL: testi64ule
; CHECK: crandc [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testi64ule:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpd 5, 6
; CHECK-NEXT: cmpd 1, 3, 4
; CHECK-NEXT: crandc 20, 6, 2
; CHECK-NEXT: bc 4, 20, .LBB13_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: mr 3, 8
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB13_2: # %iftrue
; CHECK-NEXT: mr 3, 7
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i64 %c3, %c4
%cmp3tmp = icmp eq i64 %c1, %c2
@ -214,9 +341,18 @@ iffalse:
}
define i64 @testi64eq(i64 %c1, i64 %c2, i64 %c3, i64 %c4, i64 %a1, i64 %a2) #0 {
; CHECK-LABEL: testi64eq
; CHECK: crxor [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testi64eq:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpd 5, 6
; CHECK-NEXT: cmpd 1, 3, 4
; CHECK-NEXT: crxor 20, 6, 2
; CHECK-NEXT: bc 4, 20, .LBB14_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: mr 3, 8
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB14_2: # %iftrue
; CHECK-NEXT: mr 3, 7
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i64 %c3, %c4
%cmp3tmp = icmp eq i64 %c1, %c2
@ -229,9 +365,18 @@ iffalse:
}
define i64 @testi64sge(i64 %c1, i64 %c2, i64 %c3, i64 %c4, i64 %a1, i64 %a2) #0 {
; CHECK-LABEL: testi64sge
; CHECK: crandc [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testi64sge:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpd 5, 6
; CHECK-NEXT: cmpd 1, 3, 4
; CHECK-NEXT: crandc 20, 6, 2
; CHECK-NEXT: bc 4, 20, .LBB15_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: mr 3, 8
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB15_2: # %iftrue
; CHECK-NEXT: mr 3, 7
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i64 %c3, %c4
%cmp3tmp = icmp eq i64 %c1, %c2
@ -244,9 +389,18 @@ iffalse:
}
define i64 @testi64uge(i64 %c1, i64 %c2, i64 %c3, i64 %c4, i64 %a1, i64 %a2) #0 {
; CHECK-LABEL: testi64uge
; CHECK: crandc [[REG:[0-9]+]], 2, 6
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testi64uge:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpd 5, 6
; CHECK-NEXT: cmpd 1, 3, 4
; CHECK-NEXT: crandc 20, 2, 6
; CHECK-NEXT: bc 4, 20, .LBB16_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: mr 3, 8
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB16_2: # %iftrue
; CHECK-NEXT: mr 3, 7
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i64 %c3, %c4
%cmp3tmp = icmp eq i64 %c1, %c2
@ -259,9 +413,18 @@ iffalse:
}
define i64 @testi64sgt(i64 %c1, i64 %c2, i64 %c3, i64 %c4, i64 %a1, i64 %a2) #0 {
; CHECK-LABEL: testi64sgt
; CHECK: crorc [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testi64sgt:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpd 5, 6
; CHECK-NEXT: cmpd 1, 3, 4
; CHECK-NEXT: crorc 20, 6, 2
; CHECK-NEXT: bc 12, 20, .LBB17_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: mr 3, 7
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB17_2: # %iffalse
; CHECK-NEXT: mr 3, 8
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i64 %c3, %c4
%cmp3tmp = icmp eq i64 %c1, %c2
@ -274,9 +437,18 @@ iffalse:
}
define i64 @testi64ugt(i64 %c1, i64 %c2, i64 %c3, i64 %c4, i64 %a1, i64 %a2) #0 {
; CHECK-LABEL: testi64ugt
; CHECK: crorc [[REG:[0-9]+]], 2, 6
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testi64ugt:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpd 5, 6
; CHECK-NEXT: cmpd 1, 3, 4
; CHECK-NEXT: crorc 20, 2, 6
; CHECK-NEXT: bc 12, 20, .LBB18_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: mr 3, 7
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB18_2: # %iffalse
; CHECK-NEXT: mr 3, 8
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i64 %c3, %c4
%cmp3tmp = icmp eq i64 %c1, %c2
@ -289,9 +461,18 @@ iffalse:
}
define i64 @testi64ne(i64 %c1, i64 %c2, i64 %c3, i64 %c4, i64 %a1, i64 %a2) #0 {
; CHECK-LABEL: testi64ne
; CHECK: creqv [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testi64ne:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpd 5, 6
; CHECK-NEXT: cmpd 1, 3, 4
; CHECK-NEXT: creqv 20, 6, 2
; CHECK-NEXT: bc 12, 20, .LBB19_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: mr 3, 7
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB19_2: # %iffalse
; CHECK-NEXT: mr 3, 8
; CHECK-NEXT: blr
entry:
%cmp1 = icmp eq i64 %c3, %c4
%cmp3tmp = icmp eq i64 %c1, %c2
@ -304,9 +485,18 @@ iffalse:
}
define float @testfloatslt(float %c1, float %c2, float %c3, float %c4, float %a1, float %a2) #0 {
; CHECK-LABEL: testfloatslt
; CHECK: crorc [[REG:[0-9]+]], 2, 6
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testfloatslt:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crorc 20, 2, 6
; CHECK-NEXT: bc 12, 20, .LBB20_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB20_2: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq float %c3, %c4
%cmp3tmp = fcmp oeq float %c1, %c2
@ -319,9 +509,18 @@ iffalse:
}
define float @testfloatult(float %c1, float %c2, float %c3, float %c4, float %a1, float %a2) #0 {
; CHECK-LABEL: testfloatult
; CHECK: crorc [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testfloatult:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crorc 20, 6, 2
; CHECK-NEXT: bc 12, 20, .LBB21_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB21_2: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq float %c3, %c4
%cmp3tmp = fcmp oeq float %c1, %c2
@ -334,9 +533,18 @@ iffalse:
}
define float @testfloatsle(float %c1, float %c2, float %c3, float %c4, float %a1, float %a2) #0 {
; CHECK-LABEL: testfloatsle
; CHECK: crandc [[REG:[0-9]+]], 2, 6
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testfloatsle:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crandc 20, 2, 6
; CHECK-NEXT: bc 4, 20, .LBB22_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB22_2: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq float %c3, %c4
%cmp3tmp = fcmp oeq float %c1, %c2
@ -349,9 +557,18 @@ iffalse:
}
define float @testfloatule(float %c1, float %c2, float %c3, float %c4, float %a1, float %a2) #0 {
; CHECK-LABEL: testfloatule
; CHECK: crandc [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testfloatule:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crandc 20, 6, 2
; CHECK-NEXT: bc 4, 20, .LBB23_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB23_2: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq float %c3, %c4
%cmp3tmp = fcmp oeq float %c1, %c2
@ -364,9 +581,18 @@ iffalse:
}
define float @testfloateq(float %c1, float %c2, float %c3, float %c4, float %a1, float %a2) #0 {
; CHECK-LABEL: testfloateq
; CHECK: crxor [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testfloateq:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crxor 20, 6, 2
; CHECK-NEXT: bc 4, 20, .LBB24_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB24_2: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq float %c3, %c4
%cmp3tmp = fcmp oeq float %c1, %c2
@ -379,9 +605,18 @@ iffalse:
}
define float @testfloatsge(float %c1, float %c2, float %c3, float %c4, float %a1, float %a2) #0 {
; CHECK-LABEL: testfloatsge
; CHECK: crandc [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testfloatsge:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crandc 20, 6, 2
; CHECK-NEXT: bc 4, 20, .LBB25_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB25_2: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq float %c3, %c4
%cmp3tmp = fcmp oeq float %c1, %c2
@ -394,9 +629,18 @@ iffalse:
}
define float @testfloatuge(float %c1, float %c2, float %c3, float %c4, float %a1, float %a2) #0 {
; CHECK-LABEL: testfloatuge
; CHECK: crandc [[REG:[0-9]+]], 2, 6
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testfloatuge:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crandc 20, 2, 6
; CHECK-NEXT: bc 4, 20, .LBB26_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB26_2: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq float %c3, %c4
%cmp3tmp = fcmp oeq float %c1, %c2
@ -409,9 +653,18 @@ iffalse:
}
define float @testfloatsgt(float %c1, float %c2, float %c3, float %c4, float %a1, float %a2) #0 {
; CHECK-LABEL: testfloatsgt
; CHECK: crorc [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testfloatsgt:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crorc 20, 6, 2
; CHECK-NEXT: bc 12, 20, .LBB27_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB27_2: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq float %c3, %c4
%cmp3tmp = fcmp oeq float %c1, %c2
@ -424,9 +677,18 @@ iffalse:
}
define float @testfloatugt(float %c1, float %c2, float %c3, float %c4, float %a1, float %a2) #0 {
; CHECK-LABEL: testfloatugt
; CHECK: crorc [[REG:[0-9]+]], 2, 6
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testfloatugt:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crorc 20, 2, 6
; CHECK-NEXT: bc 12, 20, .LBB28_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB28_2: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq float %c3, %c4
%cmp3tmp = fcmp oeq float %c1, %c2
@ -439,9 +701,18 @@ iffalse:
}
define float @testfloatne(float %c1, float %c2, float %c3, float %c4, float %a1, float %a2) #0 {
; CHECK-LABEL: testfloatne
; CHECK: creqv [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testfloatne:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: creqv 20, 6, 2
; CHECK-NEXT: bc 12, 20, .LBB29_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB29_2: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq float %c3, %c4
%cmp3tmp = fcmp oeq float %c1, %c2
@ -454,9 +725,18 @@ iffalse:
}
define double @testdoubleslt(double %c1, double %c2, double %c3, double %c4, double %a1, double %a2) #0 {
; CHECK-LABEL: testdoubleslt
; CHECK: crorc [[REG:[0-9]+]], 2, 6
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testdoubleslt:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crorc 20, 2, 6
; CHECK-NEXT: bc 12, 20, .LBB30_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB30_2: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq double %c3, %c4
%cmp3tmp = fcmp oeq double %c1, %c2
@ -470,8 +750,17 @@ iffalse:
define double @testdoubleult(double %c1, double %c2, double %c3, double %c4, double %a1, double %a2) #0 {
; CHECK-LABEL: testdoubleult:
; CHECK: crorc [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crorc 20, 6, 2
; CHECK-NEXT: bc 12, 20, .LBB31_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB31_2: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq double %c3, %c4
%cmp3tmp = fcmp oeq double %c1, %c2
@ -484,9 +773,18 @@ iffalse:
}
define double @testdoublesle(double %c1, double %c2, double %c3, double %c4, double %a1, double %a2) #0 {
; CHECK-LABEL: testdoublesle
; CHECK: crandc [[REG:[0-9]+]], 2, 6
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testdoublesle:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crandc 20, 2, 6
; CHECK-NEXT: bc 4, 20, .LBB32_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB32_2: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq double %c3, %c4
%cmp3tmp = fcmp oeq double %c1, %c2
@ -500,8 +798,17 @@ iffalse:
define double @testdoubleule(double %c1, double %c2, double %c3, double %c4, double %a1, double %a2) #0 {
; CHECK-LABEL: testdoubleule:
; CHECK: crandc [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crandc 20, 6, 2
; CHECK-NEXT: bc 4, 20, .LBB33_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB33_2: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq double %c3, %c4
%cmp3tmp = fcmp oeq double %c1, %c2
@ -514,9 +821,18 @@ iffalse:
}
define double @testdoubleeq(double %c1, double %c2, double %c3, double %c4, double %a1, double %a2) #0 {
; CHECK-LABEL: testdoubleeq
; CHECK: crxor [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testdoubleeq:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crxor 20, 6, 2
; CHECK-NEXT: bc 4, 20, .LBB34_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB34_2: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq double %c3, %c4
%cmp3tmp = fcmp oeq double %c1, %c2
@ -529,9 +845,18 @@ iffalse:
}
define double @testdoublesge(double %c1, double %c2, double %c3, double %c4, double %a1, double %a2) #0 {
; CHECK-LABEL: testdoublesge
; CHECK: crandc [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testdoublesge:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crandc 20, 6, 2
; CHECK-NEXT: bc 4, 20, .LBB35_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB35_2: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq double %c3, %c4
%cmp3tmp = fcmp oeq double %c1, %c2
@ -544,9 +869,18 @@ iffalse:
}
define double @testdoubleuge(double %c1, double %c2, double %c3, double %c4, double %a1, double %a2) #0 {
; CHECK-LABEL: testdoubleuge
; CHECK: crandc [[REG:[0-9]+]], 2, 6
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testdoubleuge:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crandc 20, 2, 6
; CHECK-NEXT: bc 4, 20, .LBB36_2
; CHECK-NEXT: # %bb.1: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB36_2: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq double %c3, %c4
%cmp3tmp = fcmp oeq double %c1, %c2
@ -560,8 +894,17 @@ iffalse:
define double @testdoublesgt(double %c1, double %c2, double %c3, double %c4, double %a1, double %a2) #0 {
; CHECK-LABEL: testdoublesgt:
; CHECK: crorc [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crorc 20, 6, 2
; CHECK-NEXT: bc 12, 20, .LBB37_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB37_2: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq double %c3, %c4
%cmp3tmp = fcmp oeq double %c1, %c2
@ -574,9 +917,18 @@ iffalse:
}
define double @testdoubleugt(double %c1, double %c2, double %c3, double %c4, double %a1, double %a2) #0 {
; CHECK-LABEL: testdoubleugt
; CHECK: crorc [[REG:[0-9]+]], 2, 6
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testdoubleugt:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: crorc 20, 2, 6
; CHECK-NEXT: bc 12, 20, .LBB38_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB38_2: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq double %c3, %c4
%cmp3tmp = fcmp oeq double %c1, %c2
@ -589,9 +941,18 @@ iffalse:
}
define double @testdoublene(double %c1, double %c2, double %c3, double %c4, double %a1, double %a2) #0 {
; CHECK-LABEL: testdoublene
; CHECK: creqv [[REG:[0-9]+]], 6, 2
; CHECK: bc 12, [[REG]], {{\.[a-zA-Z0-9_]+}}
; CHECK-LABEL: testdoublene:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: fcmpu 0, 3, 4
; CHECK-NEXT: fcmpu 1, 1, 2
; CHECK-NEXT: creqv 20, 6, 2
; CHECK-NEXT: bc 12, 20, .LBB39_2
; CHECK-NEXT: # %bb.1: # %iftrue
; CHECK-NEXT: fmr 1, 5
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB39_2: # %iffalse
; CHECK-NEXT: fmr 1, 6
; CHECK-NEXT: blr
entry:
%cmp1 = fcmp oeq double %c3, %c4
%cmp3tmp = fcmp oeq double %c1, %c2

View File

@ -43,12 +43,12 @@ define signext i32 @zeroEqualityTest01(i8* %x, i8* %y) {
; CHECK-NEXT: ld 3, 8(3)
; CHECK-NEXT: ld 4, 8(4)
; CHECK-NEXT: cmpld 3, 4
; CHECK-NEXT: li 3, 0
; CHECK-NEXT: beq 0, .LBB1_3
; CHECK-NEXT: .LBB1_2: # %res_block
; CHECK-NEXT: li 3, 1
; CHECK-NEXT: .LBB1_3: # %endblock
; CHECK-NEXT: clrldi 3, 3, 32
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB1_3:
; CHECK-NEXT: li 3, 0
; CHECK-NEXT: blr
%call = tail call signext i32 @memcmp(i8* %x, i8* %y, i64 16)
%not.tobool = icmp ne i32 %call, 0
@ -73,12 +73,12 @@ define signext i32 @zeroEqualityTest03(i8* %x, i8* %y) {
; CHECK-NEXT: lbz 3, 6(3)
; CHECK-NEXT: lbz 4, 6(4)
; CHECK-NEXT: cmplw 3, 4
; CHECK-NEXT: li 3, 0
; CHECK-NEXT: beq 0, .LBB2_4
; CHECK-NEXT: .LBB2_3: # %res_block
; CHECK-NEXT: li 3, 1
; CHECK-NEXT: .LBB2_4: # %endblock
; CHECK-NEXT: clrldi 3, 3, 32
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB2_4:
; CHECK-NEXT: li 3, 0
; CHECK-NEXT: blr
%call = tail call signext i32 @memcmp(i8* %x, i8* %y, i64 7)
%not.lnot = icmp ne i32 %call, 0
@ -136,14 +136,16 @@ define signext i32 @equalityFoldOneConstant(i8* %X) {
; CHECK-NEXT: sldi 4, 4, 32
; CHECK-NEXT: ori 4, 4, 2
; CHECK-NEXT: cmpld 3, 4
; CHECK-NEXT: li 3, 0
; CHECK-NEXT: beq 0, .LBB6_3
; CHECK-NEXT: beq 0, .LBB6_4
; CHECK-NEXT: .LBB6_2: # %res_block
; CHECK-NEXT: li 3, 1
; CHECK-NEXT: .LBB6_3: # %endblock
; CHECK-NEXT: cntlzw 3, 3
; CHECK-NEXT: srwi 3, 3, 5
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB6_4:
; CHECK-NEXT: li 3, 0
; CHECK-NEXT: b .LBB6_3
%call = tail call signext i32 @memcmp(i8* bitcast ([15 x i32]* @zeroEqualityTest04.buffer1 to i8*), i8* %X, i64 16)
%not.tobool = icmp eq i32 %call, 0
%cond = zext i1 %not.tobool to i32

View File

@ -17,24 +17,28 @@
define dso_local i1 @t(%class.A* %this, i32 %color, i32 %vertex) local_unnamed_addr {
; CHECK-P9-LABEL: t:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: li r5, 1
; CHECK-P9-NEXT: bc 12, 4*cr5+lt, .LBB0_4
; CHECK-P9-NEXT: bc 12, 4*cr5+lt, .LBB0_3
; CHECK-P9-NEXT: # %bb.1: # %land.lhs.true
; CHECK-P9-NEXT: bc 12, 4*cr5+lt, .LBB0_5
; CHECK-P9-NEXT: .LBB0_2: # %for.inc
; CHECK-P9-NEXT: li r4, 1
; CHECK-P9-NEXT: bc 4, 4*cr5+lt, .LBB0_4
; CHECK-P9-NEXT: # %bb.2: # %cleanup16
; CHECK-P9-NEXT: mr r3, r4
; CHECK-P9-NEXT: blr
; CHECK-P9-NEXT: .LBB0_3: # %lor.lhs.false
; CHECK-P9-NEXT: cmplwi r4, 0
; CHECK-P9-NEXT: beq cr0, .LBB0_6
; CHECK-P9-NEXT: .LBB0_4: # %for.inc
; CHECK-P9-NEXT: lhz r3, 5308(r3)
; CHECK-P9-NEXT: cmplwi r3, 2
; CHECK-P9-NEXT: bge- cr0, .LBB0_6
; CHECK-P9-NEXT: # %bb.3: # %land.lhs.true.1
; CHECK-P9-NEXT: bge- cr0, .LBB0_7
; CHECK-P9-NEXT: # %bb.5: # %land.lhs.true.1
; CHECK-P9-NEXT: li r3, 0
; CHECK-P9-NEXT: blr
; CHECK-P9-NEXT: .LBB0_4: # %lor.lhs.false
; CHECK-P9-NEXT: cmplwi r4, 0
; CHECK-P9-NEXT: bne cr0, .LBB0_2
; CHECK-P9-NEXT: .LBB0_5: # %cleanup16
; CHECK-P9-NEXT: mr r3, r5
; CHECK-P9-NEXT: .LBB0_6:
; CHECK-P9-NEXT: li r4, 1
; CHECK-P9-NEXT: mr r3, r4
; CHECK-P9-NEXT: blr
; CHECK-P9-NEXT: .LBB0_6: # %lor.lhs.false.1
; CHECK-P9-NEXT: .LBB0_7: # %lor.lhs.false.1
entry:
br i1 undef, label %land.lhs.true, label %lor.lhs.false

View File

@ -6,41 +6,42 @@ define void @foo(i32 %a, i32 *%b, i1 %c) nounwind {
; RV32I-LABEL: foo:
; RV32I: # %bb.0:
; RV32I-NEXT: lw a3, 0(a1)
; RV32I-NEXT: beq a3, a0, .LBB0_12
; RV32I-NEXT: beq a3, a0, .LBB0_2
; RV32I-NEXT: # %bb.1: # %test2
; RV32I-NEXT: lw a3, 0(a1)
; RV32I-NEXT: bne a3, a0, .LBB0_12
; RV32I-NEXT: # %bb.2: # %test3
; RV32I-NEXT: beq a3, a0, .LBB0_3
; RV32I-NEXT: .LBB0_2: # %end
; RV32I-NEXT: ret
; RV32I-NEXT: .LBB0_3: # %test3
; RV32I-NEXT: lw a3, 0(a1)
; RV32I-NEXT: blt a3, a0, .LBB0_12
; RV32I-NEXT: # %bb.3: # %test4
; RV32I-NEXT: blt a3, a0, .LBB0_2
; RV32I-NEXT: # %bb.4: # %test4
; RV32I-NEXT: lw a3, 0(a1)
; RV32I-NEXT: bge a3, a0, .LBB0_12
; RV32I-NEXT: # %bb.4: # %test5
; RV32I-NEXT: bge a3, a0, .LBB0_2
; RV32I-NEXT: # %bb.5: # %test5
; RV32I-NEXT: lw a3, 0(a1)
; RV32I-NEXT: bltu a3, a0, .LBB0_12
; RV32I-NEXT: # %bb.5: # %test6
; RV32I-NEXT: bltu a3, a0, .LBB0_2
; RV32I-NEXT: # %bb.6: # %test6
; RV32I-NEXT: lw a3, 0(a1)
; RV32I-NEXT: bgeu a3, a0, .LBB0_12
; RV32I-NEXT: # %bb.6: # %test7
; RV32I-NEXT: bgeu a3, a0, .LBB0_2
; RV32I-NEXT: # %bb.7: # %test7
; RV32I-NEXT: lw a3, 0(a1)
; RV32I-NEXT: blt a0, a3, .LBB0_12
; RV32I-NEXT: # %bb.7: # %test8
; RV32I-NEXT: blt a0, a3, .LBB0_2
; RV32I-NEXT: # %bb.8: # %test8
; RV32I-NEXT: lw a3, 0(a1)
; RV32I-NEXT: bge a0, a3, .LBB0_12
; RV32I-NEXT: # %bb.8: # %test9
; RV32I-NEXT: bge a0, a3, .LBB0_2
; RV32I-NEXT: # %bb.9: # %test9
; RV32I-NEXT: lw a3, 0(a1)
; RV32I-NEXT: bltu a0, a3, .LBB0_12
; RV32I-NEXT: # %bb.9: # %test10
; RV32I-NEXT: bltu a0, a3, .LBB0_2
; RV32I-NEXT: # %bb.10: # %test10
; RV32I-NEXT: lw a3, 0(a1)
; RV32I-NEXT: bgeu a0, a3, .LBB0_12
; RV32I-NEXT: # %bb.10: # %test11
; RV32I-NEXT: bgeu a0, a3, .LBB0_2
; RV32I-NEXT: # %bb.11: # %test11
; RV32I-NEXT: lw a0, 0(a1)
; RV32I-NEXT: andi a0, a2, 1
; RV32I-NEXT: bnez a0, .LBB0_12
; RV32I-NEXT: # %bb.11: # %test12
; RV32I-NEXT: bnez a0, .LBB0_2
; RV32I-NEXT: # %bb.12: # %test12
; RV32I-NEXT: lw a0, 0(a1)
; RV32I-NEXT: .LBB0_12: # %end
; RV32I-NEXT: ret
%val1 = load volatile i32, i32* %b
%tst1 = icmp eq i32 %val1, %a

View File

@ -5,15 +5,13 @@ define signext i32 @mulw(i32 signext %s, i32 signext %n, i32 signext %k) nounwin
; CHECK-LABEL: mulw:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi a2, zero, 1
; CHECK-NEXT: bge a0, a1, .LBB0_3
; CHECK-NEXT: # %bb.1: # %for.body.preheader
; CHECK-NEXT: addi a2, zero, 1
; CHECK-NEXT: .LBB0_2: # %for.body
; CHECK-NEXT: bge a0, a1, .LBB0_2
; CHECK-NEXT: .LBB0_1: # %for.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: mulw a2, a0, a2
; CHECK-NEXT: addiw a0, a0, 1
; CHECK-NEXT: blt a0, a1, .LBB0_2
; CHECK-NEXT: .LBB0_3: # %for.cond.cleanup
; CHECK-NEXT: blt a0, a1, .LBB0_1
; CHECK-NEXT: .LBB0_2: # %for.cond.cleanup
; CHECK-NEXT: mv a0, a2
; CHECK-NEXT: ret
entry:

View File

@ -1,3 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; Test 32-bit comparisons in which the second operand is zero-extended
; from a PC-relative i16.
;
@ -9,9 +10,16 @@
; Check unsigned comparison.
define i32 @f1(i32 %src1) {
; CHECK-LABEL: f1:
; CHECK: clhrl %r2, g
; CHECK-NEXT: jl
; CHECK: br %r14
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: clhrl %r2, g
; CHECK-NEXT: jhe .LBB0_2
; CHECK-NEXT: # %bb.1: # %exit
; CHECK-NEXT: ahi %r2, 1
; CHECK-NEXT: br %r14
; CHECK-NEXT: .LBB0_2: # %mulb
; CHECK-NEXT: msr %r2, %r2
; CHECK-NEXT: ahi %r2, 1
; CHECK-NEXT: br %r14
entry:
%val = load i16, i16 *@g
%src2 = zext i16 %val to i32
@ -29,8 +37,16 @@ exit:
; Check signed comparison.
define i32 @f2(i32 %src1) {
; CHECK-LABEL: f2:
; CHECK-NOT: clhrl
; CHECK: br %r14
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: llhrl %r0, g
; CHECK-NEXT: crjhe %r2, %r0, .LBB1_2
; CHECK-NEXT: # %bb.1: # %exit
; CHECK-NEXT: ahi %r2, 1
; CHECK-NEXT: br %r14
; CHECK-NEXT: .LBB1_2: # %mulb
; CHECK-NEXT: msr %r2, %r2
; CHECK-NEXT: ahi %r2, 1
; CHECK-NEXT: br %r14
entry:
%val = load i16, i16 *@g
%src2 = zext i16 %val to i32
@ -48,9 +64,14 @@ exit:
; Check equality.
define i32 @f3(i32 %src1) {
; CHECK-LABEL: f3:
; CHECK: clhrl %r2, g
; CHECK-NEXT: je
; CHECK: br %r14
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: clhrl %r2, g
; CHECK-NEXT: je .LBB2_2
; CHECK-NEXT: # %bb.1: # %mulb
; CHECK-NEXT: msr %r2, %r2
; CHECK-NEXT: .LBB2_2: # %exit
; CHECK-NEXT: ahi %r2, 1
; CHECK-NEXT: br %r14
entry:
%val = load i16, i16 *@g
%src2 = zext i16 %val to i32
@ -68,9 +89,16 @@ exit:
; Check inequality.
define i32 @f4(i32 %src1) {
; CHECK-LABEL: f4:
; CHECK: clhrl %r2, g
; CHECK-NEXT: jlh
; CHECK: br %r14
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: clhrl %r2, g
; CHECK-NEXT: je .LBB3_2
; CHECK-NEXT: # %bb.1: # %exit
; CHECK-NEXT: ahi %r2, 1
; CHECK-NEXT: br %r14
; CHECK-NEXT: .LBB3_2: # %mulb
; CHECK-NEXT: msr %r2, %r2
; CHECK-NEXT: ahi %r2, 1
; CHECK-NEXT: br %r14
entry:
%val = load i16, i16 *@g
%src2 = zext i16 %val to i32
@ -88,10 +116,17 @@ exit:
; Repeat f1 with an unaligned address.
define i32 @f5(i32 %src1) {
; CHECK-LABEL: f5:
; CHECK: lgrl [[REG:%r[0-5]]], h@GOT
; CHECK: llh [[VAL:%r[0-5]]], 0([[REG]])
; CHECK: clrjl %r2, [[VAL]],
; CHECK: br %r14
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lgrl %r1, h@GOT
; CHECK-NEXT: llh %r0, 0(%r1)
; CHECK-NEXT: clrjhe %r2, %r0, .LBB4_2
; CHECK-NEXT: # %bb.1: # %exit
; CHECK-NEXT: ahi %r2, 1
; CHECK-NEXT: br %r14
; CHECK-NEXT: .LBB4_2: # %mulb
; CHECK-NEXT: msr %r2, %r2
; CHECK-NEXT: ahi %r2, 1
; CHECK-NEXT: br %r14
entry:
%val = load i16, i16 *@h, align 1
%src2 = zext i16 %val to i32
@ -109,9 +144,16 @@ exit:
; Check the comparison can be reversed if that allows CLHRL to be used.
define i32 @f6(i32 %src2) {
; CHECK-LABEL: f6:
; CHECK: clhrl %r2, g
; CHECK-NEXT: jh {{\.L.*}}
; CHECK: br %r14
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: clhrl %r2, g
; CHECK-NEXT: jle .LBB5_2
; CHECK-NEXT: # %bb.1: # %exit
; CHECK-NEXT: ahi %r2, 1
; CHECK-NEXT: br %r14
; CHECK-NEXT: .LBB5_2: # %mulb
; CHECK-NEXT: msr %r2, %r2
; CHECK-NEXT: ahi %r2, 1
; CHECK-NEXT: br %r14
entry:
%val = load i16, i16 *@g
%src1 = zext i16 %val to i32

View File

@ -1,3 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; Test 64-bit comparisons in which the second operand is zero-extended
; from a PC-relative i16.
;
@ -9,9 +10,16 @@
; Check unsigned comparison.
define i64 @f1(i64 %src1) {
; CHECK-LABEL: f1:
; CHECK: clghrl %r2, g
; CHECK-NEXT: jl
; CHECK: br %r14
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: clghrl %r2, g
; CHECK-NEXT: jhe .LBB0_2
; CHECK-NEXT: # %bb.1: # %exit
; CHECK-NEXT: la %r2, 1(%r2)
; CHECK-NEXT: br %r14
; CHECK-NEXT: .LBB0_2: # %mulb
; CHECK-NEXT: msgr %r2, %r2
; CHECK-NEXT: la %r2, 1(%r2)
; CHECK-NEXT: br %r14
entry:
%val = load i16, i16 *@g
%src2 = zext i16 %val to i64
@ -29,8 +37,16 @@ exit:
; Check signed comparison.
define i64 @f2(i64 %src1) {
; CHECK-LABEL: f2:
; CHECK-NOT: clghrl
; CHECK: br %r14
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: llghrl %r0, g
; CHECK-NEXT: cgrjhe %r2, %r0, .LBB1_2
; CHECK-NEXT: # %bb.1: # %exit
; CHECK-NEXT: la %r2, 1(%r2)
; CHECK-NEXT: br %r14
; CHECK-NEXT: .LBB1_2: # %mulb
; CHECK-NEXT: msgr %r2, %r2
; CHECK-NEXT: la %r2, 1(%r2)
; CHECK-NEXT: br %r14
entry:
%val = load i16, i16 *@g
%src2 = zext i16 %val to i64
@ -48,9 +64,14 @@ exit:
; Check equality.
define i64 @f3(i64 %src1) {
; CHECK-LABEL: f3:
; CHECK: clghrl %r2, g
; CHECK-NEXT: je
; CHECK: br %r14
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: clghrl %r2, g
; CHECK-NEXT: je .LBB2_2
; CHECK-NEXT: # %bb.1: # %mulb
; CHECK-NEXT: msgr %r2, %r2
; CHECK-NEXT: .LBB2_2: # %exit
; CHECK-NEXT: la %r2, 1(%r2)
; CHECK-NEXT: br %r14
entry:
%val = load i16, i16 *@g
%src2 = zext i16 %val to i64
@ -68,9 +89,16 @@ exit:
; Check inequality.
define i64 @f4(i64 %src1) {
; CHECK-LABEL: f4:
; CHECK: clghrl %r2, g
; CHECK-NEXT: jlh
; CHECK: br %r14
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: clghrl %r2, g
; CHECK-NEXT: je .LBB3_2
; CHECK-NEXT: # %bb.1: # %exit
; CHECK-NEXT: la %r2, 1(%r2)
; CHECK-NEXT: br %r14
; CHECK-NEXT: .LBB3_2: # %mulb
; CHECK-NEXT: msgr %r2, %r2
; CHECK-NEXT: la %r2, 1(%r2)
; CHECK-NEXT: br %r14
entry:
%val = load i16, i16 *@g
%src2 = zext i16 %val to i64
@ -88,10 +116,17 @@ exit:
; Repeat f1 with an unaligned address.
define i64 @f5(i64 %src1) {
; CHECK-LABEL: f5:
; CHECK: lgrl [[REG:%r[0-5]]], h@GOT
; CHECK: llgh [[VAL:%r[0-5]]], 0([[REG]])
; CHECK: clgrjl %r2, [[VAL]],
; CHECK: br %r14
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lgrl %r1, h@GOT
; CHECK-NEXT: llgh %r0, 0(%r1)
; CHECK-NEXT: clgrjhe %r2, %r0, .LBB4_2
; CHECK-NEXT: # %bb.1: # %exit
; CHECK-NEXT: la %r2, 1(%r2)
; CHECK-NEXT: br %r14
; CHECK-NEXT: .LBB4_2: # %mulb
; CHECK-NEXT: msgr %r2, %r2
; CHECK-NEXT: la %r2, 1(%r2)
; CHECK-NEXT: br %r14
entry:
%val = load i16, i16 *@h, align 1
%src2 = zext i16 %val to i64
@ -109,9 +144,16 @@ exit:
; Check the comparison can be reversed if that allows CLGHRL to be used.
define i64 @f6(i64 %src2) {
; CHECK-LABEL: f6:
; CHECK: clghrl %r2, g
; CHECK-NEXT: jh {{\.L.*}}
; CHECK: br %r14
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: clghrl %r2, g
; CHECK-NEXT: jle .LBB5_2
; CHECK-NEXT: # %bb.1: # %exit
; CHECK-NEXT: la %r2, 1(%r2)
; CHECK-NEXT: br %r14
; CHECK-NEXT: .LBB5_2: # %mulb
; CHECK-NEXT: msgr %r2, %r2
; CHECK-NEXT: la %r2, 1(%r2)
; CHECK-NEXT: br %r14
entry:
%val = load i16, i16 *@g
%src1 = zext i16 %val to i64

View File

@ -903,8 +903,7 @@ define arm_aapcs_vfpcc void @float_int_int_mul(i32* nocapture readonly %a, i32*
; CHECK-NEXT: le lr, .LBB4_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: cmp r12, r3
; CHECK-NEXT: it eq
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: beq .LBB4_8
; CHECK-NEXT: .LBB4_6: @ %for.body.preheader11
; CHECK-NEXT: sub.w lr, r3, r12
; CHECK-NEXT: add.w r0, r0, r12, lsl #2

View File

@ -17,7 +17,7 @@
define dso_local void @varying_outer_2d_reduction(i16* nocapture readonly %Input, i16* nocapture %Output, i16 signext %Size, i16 signext %N, i16 signext %Scale) local_unnamed_addr {
; ENABLED-LABEL: varying_outer_2d_reduction:
; ENABLED: @ %bb.0: @ %entry
; ENABLED-NEXT: push.w {r4, r5, r6, r7, r8, r9, r10, lr}
; ENABLED-NEXT: push.w {r4, r5, r6, r7, r9, r10, r11, lr}
; ENABLED-NEXT: sub sp, #4
; ENABLED-NEXT: cmp r3, #1
; ENABLED-NEXT: str r0, [sp] @ 4-byte Spill
@ -54,7 +54,7 @@ define dso_local void @varying_outer_2d_reduction(i16* nocapture readonly %Input
; ENABLED-NEXT: subs r0, #4
; ENABLED-NEXT: subs r4, r2, r6
; ENABLED-NEXT: vmov.i32 q0, #0x0
; ENABLED-NEXT: add.w r8, r7, r0, lsr #2
; ENABLED-NEXT: add.w r11, r7, r0, lsr #2
; ENABLED-NEXT: mov r7, r10
; ENABLED-NEXT: dlstp.32 lr, r4
; ENABLED-NEXT: ldr r0, [sp] @ 4-byte Reload
@ -63,9 +63,9 @@ define dso_local void @varying_outer_2d_reduction(i16* nocapture readonly %Input
; ENABLED-NEXT: @ => This Inner Loop Header: Depth=2
; ENABLED-NEXT: vldrh.s32 q1, [r0], #8
; ENABLED-NEXT: vldrh.s32 q2, [r7], #8
; ENABLED-NEXT: mov lr, r8
; ENABLED-NEXT: mov lr, r11
; ENABLED-NEXT: vmul.i32 q1, q2, q1
; ENABLED-NEXT: sub.w r8, r8, #1
; ENABLED-NEXT: sub.w r11, r11, #1
; ENABLED-NEXT: vshl.s32 q1, r5
; ENABLED-NEXT: vadd.i32 q0, q1, q0
; ENABLED-NEXT: letp lr, .LBB0_6
@ -75,11 +75,11 @@ define dso_local void @varying_outer_2d_reduction(i16* nocapture readonly %Input
; ENABLED-NEXT: b .LBB0_3
; ENABLED-NEXT: .LBB0_8: @ %for.end17
; ENABLED-NEXT: add sp, #4
; ENABLED-NEXT: pop.w {r4, r5, r6, r7, r8, r9, r10, pc}
; ENABLED-NEXT: pop.w {r4, r5, r6, r7, r9, r10, r11, pc}
;
; NOREDUCTIONS-LABEL: varying_outer_2d_reduction:
; NOREDUCTIONS: @ %bb.0: @ %entry
; NOREDUCTIONS-NEXT: push.w {r4, r5, r6, r7, r8, r9, r10, lr}
; NOREDUCTIONS-NEXT: push.w {r4, r5, r6, r7, r9, r10, r11, lr}
; NOREDUCTIONS-NEXT: sub sp, #4
; NOREDUCTIONS-NEXT: cmp r3, #1
; NOREDUCTIONS-NEXT: str r0, [sp] @ 4-byte Spill
@ -116,7 +116,7 @@ define dso_local void @varying_outer_2d_reduction(i16* nocapture readonly %Input
; NOREDUCTIONS-NEXT: subs r0, #4
; NOREDUCTIONS-NEXT: subs r4, r2, r6
; NOREDUCTIONS-NEXT: vmov.i32 q0, #0x0
; NOREDUCTIONS-NEXT: add.w r8, r7, r0, lsr #2
; NOREDUCTIONS-NEXT: add.w r11, r7, r0, lsr #2
; NOREDUCTIONS-NEXT: mov r7, r10
; NOREDUCTIONS-NEXT: dlstp.32 lr, r4
; NOREDUCTIONS-NEXT: ldr r0, [sp] @ 4-byte Reload
@ -125,9 +125,9 @@ define dso_local void @varying_outer_2d_reduction(i16* nocapture readonly %Input
; NOREDUCTIONS-NEXT: @ => This Inner Loop Header: Depth=2
; NOREDUCTIONS-NEXT: vldrh.s32 q1, [r0], #8
; NOREDUCTIONS-NEXT: vldrh.s32 q2, [r7], #8
; NOREDUCTIONS-NEXT: mov lr, r8
; NOREDUCTIONS-NEXT: mov lr, r11
; NOREDUCTIONS-NEXT: vmul.i32 q1, q2, q1
; NOREDUCTIONS-NEXT: sub.w r8, r8, #1
; NOREDUCTIONS-NEXT: sub.w r11, r11, #1
; NOREDUCTIONS-NEXT: vshl.s32 q1, r5
; NOREDUCTIONS-NEXT: vadd.i32 q0, q1, q0
; NOREDUCTIONS-NEXT: letp lr, .LBB0_6
@ -137,8 +137,7 @@ define dso_local void @varying_outer_2d_reduction(i16* nocapture readonly %Input
; NOREDUCTIONS-NEXT: b .LBB0_3
; NOREDUCTIONS-NEXT: .LBB0_8: @ %for.end17
; NOREDUCTIONS-NEXT: add sp, #4
; NOREDUCTIONS-NEXT: pop.w {r4, r5, r6, r7, r8, r9, r10, pc}
;
; NOREDUCTIONS-NEXT: pop.w {r4, r5, r6, r7, r9, r10, r11, pc}
entry:
%conv = sext i16 %N to i32
%cmp36 = icmp sgt i16 %N, 0

View File

@ -302,8 +302,7 @@ define void @fma8(float* noalias nocapture readonly %A, float* noalias nocapture
; CHECK-NEXT: le lr, .LBB2_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: cmp r12, r3
; CHECK-NEXT: it eq
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: beq .LBB2_8
; CHECK-NEXT: .LBB2_6: @ %for.body.preheader12
; CHECK-NEXT: sub.w lr, r3, r12
; CHECK-NEXT: add.w r0, r0, r12, lsl #2

View File

@ -36,8 +36,7 @@ define void @fma(float* noalias nocapture readonly %A, float* noalias nocapture
; CHECK-NEXT: le lr, .LBB0_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: cmp r12, r3
; CHECK-NEXT: it eq
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: beq .LBB0_8
; CHECK-NEXT: .LBB0_6: @ %for.body.preheader12
; CHECK-NEXT: sub.w lr, r3, r12
; CHECK-NEXT: add.w r0, r0, r12, lsl #2
@ -220,7 +219,7 @@ define i8* @test(i8* nocapture readonly %input_row, i8* nocapture readonly %inpu
; CHECK-NEXT: ldr r3, [sp, #64]
; CHECK-NEXT: mov.w r11, #0
; CHECK-NEXT: ldr r1, [sp, #16] @ 4-byte Reload
; CHECK-NEXT: ldr.w r9, [sp, #56]
; CHECK-NEXT: ldr r4, [sp, #56]
; CHECK-NEXT: add.w r0, r1, r3, lsl #1
; CHECK-NEXT: str r0, [sp, #8] @ 4-byte Spill
; CHECK-NEXT: adds r0, r1, r3
@ -229,56 +228,56 @@ define i8* @test(i8* nocapture readonly %input_row, i8* nocapture readonly %inpu
; CHECK-NEXT: add r0, r1
; CHECK-NEXT: str r0, [sp] @ 4-byte Spill
; CHECK-NEXT: adds r0, r3, #7
; CHECK-NEXT: lsrs r0, r0, #3
; CHECK-NEXT: lsr.w r9, r0, #3
; CHECK-NEXT: b .LBB2_5
; CHECK-NEXT: .LBB2_3: @ in Loop: Header=BB2_5 Depth=1
; CHECK-NEXT: mov r8, r12
; CHECK-NEXT: mov r10, r12
; CHECK-NEXT: mov r6, r12
; CHECK-NEXT: mov r8, r10
; CHECK-NEXT: mov r12, r10
; CHECK-NEXT: mov r6, r10
; CHECK-NEXT: .LBB2_4: @ %for.cond.cleanup23
; CHECK-NEXT: @ in Loop: Header=BB2_5 Depth=1
; CHECK-NEXT: ldr r3, [sp, #72]
; CHECK-NEXT: add.w r1, r10, r8
; CHECK-NEXT: add r1, r6
; CHECK-NEXT: add r1, r12
; CHECK-NEXT: strb.w r1, [r3, r11]
; CHECK-NEXT: ldr r1, [sp, #72]
; CHECK-NEXT: add.w r0, r12, r8
; CHECK-NEXT: add r0, r6
; CHECK-NEXT: add r0, r10
; CHECK-NEXT: strb.w r0, [r1, r11]
; CHECK-NEXT: add.w r11, r11, #1
; CHECK-NEXT: cmp r11, r2
; CHECK-NEXT: beq .LBB2_8
; CHECK-NEXT: .LBB2_5: @ %for.body
; CHECK-NEXT: @ =>This Loop Header: Depth=1
; CHECK-NEXT: @ Child Loop BB2_7 Depth 2
; CHECK-NEXT: ldr r1, [sp, #68]
; CHECK-NEXT: subs.w lr, r0, r0
; CHECK-NEXT: ldr.w r12, [r1, r11, lsl #2]
; CHECK-NEXT: ldr r0, [sp, #68]
; CHECK-NEXT: subs.w lr, r9, r9
; CHECK-NEXT: ldr.w r10, [r0, r11, lsl #2]
; CHECK-NEXT: ble .LBB2_3
; CHECK-NEXT: @ %bb.6: @ %for.body24.preheader
; CHECK-NEXT: @ in Loop: Header=BB2_5 Depth=1
; CHECK-NEXT: ldr r3, [sp, #64]
; CHECK-NEXT: mov r6, r12
; CHECK-NEXT: ldr r1, [sp, #12] @ 4-byte Reload
; CHECK-NEXT: ldr r1, [sp, #64]
; CHECK-NEXT: mov r6, r10
; CHECK-NEXT: ldr r0, [sp, #12] @ 4-byte Reload
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: ldr r5, [sp, #8] @ 4-byte Reload
; CHECK-NEXT: mov r10, r12
; CHECK-NEXT: mla r7, r11, r3, r1
; CHECK-NEXT: ldr r3, [sp, #8] @ 4-byte Reload
; CHECK-NEXT: mov r12, r10
; CHECK-NEXT: mla r7, r11, r1, r0
; CHECK-NEXT: ldr r1, [sp, #16] @ 4-byte Reload
; CHECK-NEXT: ldrd r4, r3, [sp] @ 8-byte Folded Reload
; CHECK-NEXT: mov r8, r12
; CHECK-NEXT: ldrd r5, r0, [sp] @ 8-byte Folded Reload
; CHECK-NEXT: mov r8, r10
; CHECK-NEXT: .LBB2_7: @ %for.body24
; CHECK-NEXT: @ Parent Loop BB2_5 Depth=1
; CHECK-NEXT: @ => This Inner Loop Header: Depth=2
; CHECK-NEXT: vldrb.s16 q0, [r4], #8
; CHECK-NEXT: vadd.i16 q1, q0, r9
; CHECK-NEXT: vldrb.s16 q0, [r5], #8
; CHECK-NEXT: vadd.i16 q1, q0, r4
; CHECK-NEXT: vldrb.s16 q0, [r7], #8
; CHECK-NEXT: vmlava.s16 r12, q0, q1
; CHECK-NEXT: vldrb.s16 q1, [r5], #8
; CHECK-NEXT: vadd.i16 q1, q1, r9
; CHECK-NEXT: vmlava.s16 r6, q0, q1
; CHECK-NEXT: vldrb.s16 q1, [r3], #8
; CHECK-NEXT: vadd.i16 q1, q1, r9
; CHECK-NEXT: vmlava.s16 r10, q0, q1
; CHECK-NEXT: vldrb.s16 q1, [r3], #8
; CHECK-NEXT: vadd.i16 q1, q1, r4
; CHECK-NEXT: vmlava.s16 r6, q0, q1
; CHECK-NEXT: vldrb.s16 q1, [r0], #8
; CHECK-NEXT: vadd.i16 q1, q1, r4
; CHECK-NEXT: vmlava.s16 r12, q0, q1
; CHECK-NEXT: vldrb.s16 q1, [r1], #8
; CHECK-NEXT: vadd.i16 q1, q1, r9
; CHECK-NEXT: vadd.i16 q1, q1, r4
; CHECK-NEXT: vmlava.s16 r8, q0, q1
; CHECK-NEXT: le lr, .LBB2_7
; CHECK-NEXT: b .LBB2_4
@ -403,7 +402,7 @@ define i8* @test_optsize(i8* nocapture readonly %input_row, i8* nocapture readon
; CHECK-NEXT: ldr r3, [sp, #64]
; CHECK-NEXT: mov.w r11, #0
; CHECK-NEXT: ldr r1, [sp, #16] @ 4-byte Reload
; CHECK-NEXT: ldr.w r9, [sp, #56]
; CHECK-NEXT: ldr r4, [sp, #56]
; CHECK-NEXT: add.w r0, r1, r3, lsl #1
; CHECK-NEXT: str r0, [sp, #8] @ 4-byte Spill
; CHECK-NEXT: adds r0, r1, r3
@ -412,55 +411,55 @@ define i8* @test_optsize(i8* nocapture readonly %input_row, i8* nocapture readon
; CHECK-NEXT: add r0, r1
; CHECK-NEXT: str r0, [sp] @ 4-byte Spill
; CHECK-NEXT: adds r0, r3, #7
; CHECK-NEXT: lsrs r0, r0, #3
; CHECK-NEXT: lsr.w r9, r0, #3
; CHECK-NEXT: .LBB3_3: @ %for.body
; CHECK-NEXT: @ =>This Loop Header: Depth=1
; CHECK-NEXT: @ Child Loop BB3_5 Depth 2
; CHECK-NEXT: ldr r1, [sp, #68]
; CHECK-NEXT: subs.w lr, r0, r0
; CHECK-NEXT: ldr.w r12, [r1, r11, lsl #2]
; CHECK-NEXT: ldr r0, [sp, #68]
; CHECK-NEXT: subs.w lr, r9, r9
; CHECK-NEXT: ldr.w r10, [r0, r11, lsl #2]
; CHECK-NEXT: ble .LBB3_6
; CHECK-NEXT: @ %bb.4: @ %for.body24.preheader
; CHECK-NEXT: @ in Loop: Header=BB3_3 Depth=1
; CHECK-NEXT: ldr r3, [sp, #64]
; CHECK-NEXT: mov r6, r12
; CHECK-NEXT: ldr r1, [sp, #12] @ 4-byte Reload
; CHECK-NEXT: ldr r1, [sp, #64]
; CHECK-NEXT: mov r6, r10
; CHECK-NEXT: ldr r0, [sp, #12] @ 4-byte Reload
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: ldr r5, [sp, #8] @ 4-byte Reload
; CHECK-NEXT: mov r10, r12
; CHECK-NEXT: mla r7, r11, r3, r1
; CHECK-NEXT: ldr r3, [sp, #8] @ 4-byte Reload
; CHECK-NEXT: mov r12, r10
; CHECK-NEXT: mla r7, r11, r1, r0
; CHECK-NEXT: ldr r1, [sp, #16] @ 4-byte Reload
; CHECK-NEXT: ldrd r4, r3, [sp] @ 8-byte Folded Reload
; CHECK-NEXT: mov r8, r12
; CHECK-NEXT: ldrd r5, r0, [sp] @ 8-byte Folded Reload
; CHECK-NEXT: mov r8, r10
; CHECK-NEXT: .LBB3_5: @ %for.body24
; CHECK-NEXT: @ Parent Loop BB3_3 Depth=1
; CHECK-NEXT: @ => This Inner Loop Header: Depth=2
; CHECK-NEXT: vldrb.s16 q0, [r4], #8
; CHECK-NEXT: vadd.i16 q1, q0, r9
; CHECK-NEXT: vldrb.s16 q0, [r5], #8
; CHECK-NEXT: vadd.i16 q1, q0, r4
; CHECK-NEXT: vldrb.s16 q0, [r7], #8
; CHECK-NEXT: vmlava.s16 r12, q0, q1
; CHECK-NEXT: vldrb.s16 q1, [r5], #8
; CHECK-NEXT: vadd.i16 q1, q1, r9
; CHECK-NEXT: vmlava.s16 r6, q0, q1
; CHECK-NEXT: vldrb.s16 q1, [r3], #8
; CHECK-NEXT: vadd.i16 q1, q1, r9
; CHECK-NEXT: vmlava.s16 r10, q0, q1
; CHECK-NEXT: vldrb.s16 q1, [r3], #8
; CHECK-NEXT: vadd.i16 q1, q1, r4
; CHECK-NEXT: vmlava.s16 r6, q0, q1
; CHECK-NEXT: vldrb.s16 q1, [r0], #8
; CHECK-NEXT: vadd.i16 q1, q1, r4
; CHECK-NEXT: vmlava.s16 r12, q0, q1
; CHECK-NEXT: vldrb.s16 q1, [r1], #8
; CHECK-NEXT: vadd.i16 q1, q1, r9
; CHECK-NEXT: vadd.i16 q1, q1, r4
; CHECK-NEXT: vmlava.s16 r8, q0, q1
; CHECK-NEXT: le lr, .LBB3_5
; CHECK-NEXT: b .LBB3_7
; CHECK-NEXT: .LBB3_6: @ in Loop: Header=BB3_3 Depth=1
; CHECK-NEXT: mov r8, r12
; CHECK-NEXT: mov r10, r12
; CHECK-NEXT: mov r6, r12
; CHECK-NEXT: mov r8, r10
; CHECK-NEXT: mov r12, r10
; CHECK-NEXT: mov r6, r10
; CHECK-NEXT: .LBB3_7: @ %for.cond.cleanup23
; CHECK-NEXT: @ in Loop: Header=BB3_3 Depth=1
; CHECK-NEXT: ldr r3, [sp, #72]
; CHECK-NEXT: add.w r1, r10, r8
; CHECK-NEXT: add r1, r6
; CHECK-NEXT: add r1, r12
; CHECK-NEXT: strb.w r1, [r3, r11]
; CHECK-NEXT: ldr r1, [sp, #72]
; CHECK-NEXT: add.w r0, r12, r8
; CHECK-NEXT: add r0, r6
; CHECK-NEXT: add r0, r10
; CHECK-NEXT: strb.w r0, [r1, r11]
; CHECK-NEXT: add.w r11, r11, #1
; CHECK-NEXT: cmp r11, r2
; CHECK-NEXT: bne .LBB3_3
@ -737,8 +736,8 @@ define i8* @signext(i8* %input_row, i8* %input_col, i16 zeroext %output_ch, i16
; CHECK-NEXT: ldr r1, [sp, #16] @ 4-byte Reload
; CHECK-NEXT: mov r8, r12
; CHECK-NEXT: mla r5, r11, r3, r0
; CHECK-NEXT: ldr r0, [sp, #8] @ 4-byte Reload
; CHECK-NEXT: ldrd r4, r7, [sp] @ 8-byte Folded Reload
; CHECK-NEXT: ldr r7, [sp, #8] @ 4-byte Reload
; CHECK-NEXT: ldrd r4, r0, [sp] @ 8-byte Folded Reload
; CHECK-NEXT: mov r10, r12
; CHECK-NEXT: .LBB5_7: @ %for.body24
; CHECK-NEXT: @ Parent Loop BB5_5 Depth=1
@ -747,10 +746,10 @@ define i8* @signext(i8* %input_row, i8* %input_col, i16 zeroext %output_ch, i16
; CHECK-NEXT: vadd.i16 q2, q1, q0
; CHECK-NEXT: vldrb.s16 q1, [r5], #8
; CHECK-NEXT: vmlava.s16 r12, q1, q2
; CHECK-NEXT: vldrb.s16 q2, [r0], #8
; CHECK-NEXT: vldrb.s16 q2, [r7], #8
; CHECK-NEXT: vadd.i16 q2, q2, q0
; CHECK-NEXT: vmlava.s16 r6, q1, q2
; CHECK-NEXT: vldrb.s16 q2, [r7], #8
; CHECK-NEXT: vldrb.s16 q2, [r0], #8
; CHECK-NEXT: vadd.i16 q2, q2, q0
; CHECK-NEXT: vmlava.s16 r8, q1, q2
; CHECK-NEXT: vldrb.s16 q2, [r1], #8
@ -908,8 +907,8 @@ define i8* @signext_optsize(i8* %input_row, i8* %input_col, i16 zeroext %output_
; CHECK-NEXT: ldr r1, [sp, #16] @ 4-byte Reload
; CHECK-NEXT: mov r8, r12
; CHECK-NEXT: mla r5, r11, r3, r0
; CHECK-NEXT: ldr r0, [sp, #8] @ 4-byte Reload
; CHECK-NEXT: ldrd r4, r7, [sp] @ 8-byte Folded Reload
; CHECK-NEXT: ldr r7, [sp, #8] @ 4-byte Reload
; CHECK-NEXT: ldrd r4, r0, [sp] @ 8-byte Folded Reload
; CHECK-NEXT: mov r10, r12
; CHECK-NEXT: .LBB6_5: @ %for.body24
; CHECK-NEXT: @ Parent Loop BB6_3 Depth=1
@ -918,10 +917,10 @@ define i8* @signext_optsize(i8* %input_row, i8* %input_col, i16 zeroext %output_
; CHECK-NEXT: vadd.i16 q2, q1, q0
; CHECK-NEXT: vldrb.s16 q1, [r5], #8
; CHECK-NEXT: vmlava.s16 r12, q1, q2
; CHECK-NEXT: vldrb.s16 q2, [r0], #8
; CHECK-NEXT: vldrb.s16 q2, [r7], #8
; CHECK-NEXT: vadd.i16 q2, q2, q0
; CHECK-NEXT: vmlava.s16 r6, q1, q2
; CHECK-NEXT: vldrb.s16 q2, [r7], #8
; CHECK-NEXT: vldrb.s16 q2, [r0], #8
; CHECK-NEXT: vadd.i16 q2, q2, q0
; CHECK-NEXT: vmlava.s16 r8, q1, q2
; CHECK-NEXT: vldrb.s16 q2, [r1], #8

View File

@ -20,50 +20,50 @@ define arm_aapcs_vfpcc void @ssatmul_s_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: @ %bb.2:
; CHECK-NEXT: movs r7, #0
; CHECK-NEXT: mov r12, r0
; CHECK-NEXT: mov r9, r1
; CHECK-NEXT: mov r6, r1
; CHECK-NEXT: mov r11, r2
; CHECK-NEXT: b .LBB0_6
; CHECK-NEXT: .LBB0_3: @ %vector.ph
; CHECK-NEXT: str r3, [sp, #4] @ 4-byte Spill
; CHECK-NEXT: bic r3, r3, #1
; CHECK-NEXT: subs r7, r3, #2
; CHECK-NEXT: adr r4, .LCPI0_0
; CHECK-NEXT: movs r6, #1
; CHECK-NEXT: adr r4, .LCPI0_0
; CHECK-NEXT: add.w r11, r2, r3, lsl #2
; CHECK-NEXT: add.w lr, r6, r7, lsr #1
; CHECK-NEXT: add.w r9, r1, r3, lsl #2
; CHECK-NEXT: add.w r6, r1, r3, lsl #2
; CHECK-NEXT: add.w r12, r0, r3, lsl #2
; CHECK-NEXT: vldrw.u32 q0, [r4]
; CHECK-NEXT: mvn r10, #-2147483648
; CHECK-NEXT: vmvn.i32 q1, #0x80000000
; CHECK-NEXT: mov.w r10, #-1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: str r3, [sp] @ 4-byte Spill
; CHECK-NEXT: .LBB0_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldrd r4, r5, [r0]
; CHECK-NEXT: ldrd r4, r8, [r0]
; CHECK-NEXT: adds r0, #8
; CHECK-NEXT: ldrd r7, r6, [r1]
; CHECK-NEXT: ldrd r7, r5, [r1]
; CHECK-NEXT: adds r1, #8
; CHECK-NEXT: smull r8, r5, r6, r5
; CHECK-NEXT: smull r8, r5, r5, r8
; CHECK-NEXT: smull r4, r7, r7, r4
; CHECK-NEXT: asrl r8, r5, #31
; CHECK-NEXT: asrl r4, r7, #31
; CHECK-NEXT: rsbs.w r3, r4, #-2147483648
; CHECK-NEXT: rsbs.w r9, r4, #-2147483648
; CHECK-NEXT: vmov.32 q4[0], r4
; CHECK-NEXT: sbcs.w r3, r10, r7
; CHECK-NEXT: vmov.32 q4[1], r7
; CHECK-NEXT: mov.w r9, #-1
; CHECK-NEXT: sbcs.w r3, r9, r7
; CHECK-NEXT: mov.w r3, #0
; CHECK-NEXT: vmov.32 q4[2], r8
; CHECK-NEXT: vmov.32 q4[1], r7
; CHECK-NEXT: it lt
; CHECK-NEXT: movlt r3, #1
; CHECK-NEXT: cmp r3, #0
; CHECK-NEXT: csetm r3, ne
; CHECK-NEXT: vmov.32 q4[3], r5
; CHECK-NEXT: vmov.32 q4[2], r8
; CHECK-NEXT: vmov.32 q2[0], r3
; CHECK-NEXT: vmov.32 q4[3], r5
; CHECK-NEXT: vmov.32 q2[1], r3
; CHECK-NEXT: rsbs.w r3, r8, #-2147483648
; CHECK-NEXT: sbcs.w r3, r10, r5
; CHECK-NEXT: mvn r5, #-2147483648
; CHECK-NEXT: sbcs.w r3, r9, r5
; CHECK-NEXT: mov.w r3, #0
; CHECK-NEXT: it lt
; CHECK-NEXT: movlt r3, #1
@ -76,7 +76,7 @@ define arm_aapcs_vfpcc void @ssatmul_s_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: vorr q2, q2, q3
; CHECK-NEXT: vmov r4, s8
; CHECK-NEXT: vmov r3, s9
; CHECK-NEXT: subs r4, r4, r5
; CHECK-NEXT: subs.w r4, r4, r10
; CHECK-NEXT: sbcs r3, r3, #0
; CHECK-NEXT: vmov r4, s10
; CHECK-NEXT: mov.w r3, #0
@ -87,7 +87,7 @@ define arm_aapcs_vfpcc void @ssatmul_s_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: vmov.32 q3[0], r3
; CHECK-NEXT: vmov.32 q3[1], r3
; CHECK-NEXT: vmov r3, s11
; CHECK-NEXT: subs r4, r4, r5
; CHECK-NEXT: subs.w r4, r4, r10
; CHECK-NEXT: sbcs r3, r3, #0
; CHECK-NEXT: mov.w r3, #0
; CHECK-NEXT: it lt
@ -116,7 +116,7 @@ define arm_aapcs_vfpcc void @ssatmul_s_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: .LBB0_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r3, [r12], #4
; CHECK-NEXT: ldr r4, [r9], #4
; CHECK-NEXT: ldr r4, [r6], #4
; CHECK-NEXT: smull r4, r3, r4, r3
; CHECK-NEXT: asrl r4, r3, #31
; CHECK-NEXT: subs r5, r1, r4
@ -908,36 +908,41 @@ for.body: ; preds = %for.body.preheader,
define arm_aapcs_vfpcc void @usatmul_4_q31(i32* nocapture readonly %pSrcA, i32* nocapture readonly %pSrcB, i32* noalias nocapture %pDst, i32 %N) {
; CHECK-LABEL: usatmul_4_q31:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: .save {r4, r5, r6, r7, r8, r9, r10, lr}
; CHECK-NEXT: push.w {r4, r5, r6, r7, r8, r9, r10, lr}
; CHECK-NEXT: .save {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT: push.w {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT: .pad #4
; CHECK-NEXT: sub sp, #4
; CHECK-NEXT: .vsave {d8, d9}
; CHECK-NEXT: vpush {d8, d9}
; CHECK-NEXT: cmp r3, #0
; CHECK-NEXT: beq.w .LBB4_8
; CHECK-NEXT: @ %bb.1: @ %for.body.preheader
; CHECK-NEXT: mov.w r8, #0
; CHECK-NEXT: mov.w r11, #0
; CHECK-NEXT: cmp r3, #3
; CHECK-NEXT: bhi .LBB4_3
; CHECK-NEXT: @ %bb.2:
; CHECK-NEXT: mov r12, r0
; CHECK-NEXT: mov r9, r1
; CHECK-NEXT: mov r10, r2
; CHECK-NEXT: mov r8, r1
; CHECK-NEXT: mov r9, r2
; CHECK-NEXT: b .LBB4_6
; CHECK-NEXT: .LBB4_3: @ %vector.ph
; CHECK-NEXT: bic r8, r3, #3
; CHECK-NEXT: bic r11, r3, #3
; CHECK-NEXT: movs r6, #1
; CHECK-NEXT: sub.w r7, r8, #4
; CHECK-NEXT: add.w r10, r2, r8, lsl #2
; CHECK-NEXT: add.w r9, r1, r8, lsl #2
; CHECK-NEXT: add.w lr, r6, r7, lsr #2
; CHECK-NEXT: add.w r12, r0, r8, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: sub.w r7, r11, #4
; CHECK-NEXT: add.w r9, r2, r11, lsl #2
; CHECK-NEXT: add.w r8, r1, r11, lsl #2
; CHECK-NEXT: add.w r7, r6, r7, lsr #2
; CHECK-NEXT: add.w r12, r0, r11, lsl #2
; CHECK-NEXT: mov r10, r7
; CHECK-NEXT: .LBB4_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #16
; CHECK-NEXT: vldrw.u32 q2, [r1], #16
; CHECK-NEXT: mov lr, r10
; CHECK-NEXT: vmov.f32 s4, s2
; CHECK-NEXT: sub.w lr, lr, #1
; CHECK-NEXT: vmov.f32 s12, s10
; CHECK-NEXT: mov r10, lr
; CHECK-NEXT: vmov.f32 s6, s3
; CHECK-NEXT: vmov.f32 s14, s11
; CHECK-NEXT: vmullb.u32 q4, q3, q1
@ -1002,28 +1007,31 @@ define arm_aapcs_vfpcc void @usatmul_4_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: vmov.f32 s2, s4
; CHECK-NEXT: vmov.f32 s3, s6
; CHECK-NEXT: vstrb.8 q0, [r2], #16
; CHECK-NEXT: le lr, .LBB4_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: cmp r8, r3
; CHECK-NEXT: cmp.w lr, #0
; CHECK-NEXT: bne.w .LBB4_4
; CHECK-NEXT: b .LBB4_5
; CHECK-NEXT: .LBB4_5: @ %middle.block
; CHECK-NEXT: cmp r11, r3
; CHECK-NEXT: beq .LBB4_8
; CHECK-NEXT: .LBB4_6: @ %for.body.preheader21
; CHECK-NEXT: sub.w lr, r3, r8
; CHECK-NEXT: sub.w lr, r3, r11
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB4_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r0, [r12], #4
; CHECK-NEXT: ldr r1, [r9], #4
; CHECK-NEXT: ldr r1, [r8], #4
; CHECK-NEXT: umull r0, r1, r1, r0
; CHECK-NEXT: lsrl r0, r1, #31
; CHECK-NEXT: subs.w r2, r0, #-1
; CHECK-NEXT: sbcs r1, r1, #0
; CHECK-NEXT: it hs
; CHECK-NEXT: movhs.w r0, #-1
; CHECK-NEXT: str r0, [r10], #4
; CHECK-NEXT: str r0, [r9], #4
; CHECK-NEXT: le lr, .LBB4_7
; CHECK-NEXT: .LBB4_8: @ %for.cond.cleanup
; CHECK-NEXT: vpop {d8, d9}
; CHECK-NEXT: pop.w {r4, r5, r6, r7, r8, r9, r10, pc}
; CHECK-NEXT: add sp, #4
; CHECK-NEXT: pop.w {r4, r5, r6, r7, r8, r9, r10, r11, pc}
entry:
%cmp8 = icmp eq i32 %N, 0
br i1 %cmp8, label %for.cond.cleanup, label %for.body.preheader
@ -1136,8 +1144,7 @@ define arm_aapcs_vfpcc void @ssatmul_4_q15(i16* nocapture readonly %pSrcA, i16*
; CHECK-NEXT: le lr, .LBB5_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: cmp r5, r3
; CHECK-NEXT: it eq
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: beq .LBB5_8
; CHECK-NEXT: .LBB5_6: @ %for.body.preheader21
; CHECK-NEXT: movw r0, #32768
; CHECK-NEXT: sub.w lr, r3, r5
@ -1277,8 +1284,7 @@ define arm_aapcs_vfpcc void @ssatmul_8_q15(i16* nocapture readonly %pSrcA, i16*
; CHECK-NEXT: le lr, .LBB6_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: cmp r5, r3
; CHECK-NEXT: it eq
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: beq .LBB6_8
; CHECK-NEXT: .LBB6_6: @ %for.body.preheader21
; CHECK-NEXT: movw r0, #32768
; CHECK-NEXT: sub.w lr, r3, r5
@ -1415,8 +1421,7 @@ define arm_aapcs_vfpcc void @ssatmul_8i_q15(i16* nocapture readonly %pSrcA, i16*
; CHECK-NEXT: le lr, .LBB7_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: cmp r5, r3
; CHECK-NEXT: it eq
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: beq .LBB7_8
; CHECK-NEXT: .LBB7_6: @ %for.body.preheader21
; CHECK-NEXT: movw r0, #32768
; CHECK-NEXT: sub.w lr, r3, r5
@ -1959,8 +1964,7 @@ define arm_aapcs_vfpcc void @usatmul_4_q15(i16* nocapture readonly %pSrcA, i16*
; CHECK-NEXT: le lr, .LBB11_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: cmp r5, r3
; CHECK-NEXT: it eq
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: beq .LBB11_8
; CHECK-NEXT: .LBB11_6: @ %for.body.preheader21
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: movw r0, #65535
@ -2093,8 +2097,7 @@ define arm_aapcs_vfpcc void @usatmul_8_q15(i16* nocapture readonly %pSrcA, i16*
; CHECK-NEXT: le lr, .LBB12_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: cmp r5, r3
; CHECK-NEXT: it eq
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: beq .LBB12_8
; CHECK-NEXT: .LBB12_6: @ %for.body.preheader21
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: movw r0, #65535
@ -2229,8 +2232,7 @@ define arm_aapcs_vfpcc void @ssatmul_4_q7(i8* nocapture readonly %pSrcA, i8* noc
; CHECK-NEXT: le lr, .LBB13_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: cmp r5, r3
; CHECK-NEXT: it eq
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: beq .LBB13_8
; CHECK-NEXT: .LBB13_6: @ %for.body.preheader21
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: dls lr, lr
@ -2364,8 +2366,7 @@ define arm_aapcs_vfpcc void @ssatmul_8_q7(i8* nocapture readonly %pSrcA, i8* noc
; CHECK-NEXT: le lr, .LBB14_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: cmp r5, r3
; CHECK-NEXT: it eq
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: beq .LBB14_8
; CHECK-NEXT: .LBB14_6: @ %for.body.preheader23
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: mvn r0, #127
@ -2504,8 +2505,7 @@ define arm_aapcs_vfpcc void @ssatmul_16_q7(i8* nocapture readonly %pSrcA, i8* no
; CHECK-NEXT: le lr, .LBB15_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: cmp r5, r3
; CHECK-NEXT: it eq
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: beq .LBB15_8
; CHECK-NEXT: .LBB15_6: @ %for.body.preheader23
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: mvn r0, #127
@ -2641,8 +2641,7 @@ define arm_aapcs_vfpcc void @ssatmul_16i_q7(i8* nocapture readonly %pSrcA, i8* n
; CHECK-NEXT: le lr, .LBB16_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: cmp r5, r3
; CHECK-NEXT: it eq
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: beq .LBB16_8
; CHECK-NEXT: .LBB16_6: @ %for.body.preheader23
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: mvn r0, #127
@ -3422,8 +3421,7 @@ define arm_aapcs_vfpcc void @usatmul_8_q7(i8* nocapture readonly %pSrcA, i8* noc
; CHECK-NEXT: le lr, .LBB20_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: cmp r5, r3
; CHECK-NEXT: it eq
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: beq .LBB20_8
; CHECK-NEXT: .LBB20_6: @ %for.body.preheader23
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: dls lr, lr
@ -3557,8 +3555,7 @@ define arm_aapcs_vfpcc void @usatmul_16_q7(i8* nocapture readonly %pSrcA, i8* no
; CHECK-NEXT: le lr, .LBB21_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: cmp r5, r3
; CHECK-NEXT: it eq
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: beq .LBB21_8
; CHECK-NEXT: .LBB21_6: @ %for.body.preheader23
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: dls lr, lr

View File

@ -8,7 +8,7 @@ declare void @foo()
define i32 @f1(i32 %a, i32 %b, i32* %v) {
entry:
; CHECK-LABEL: f1:
; CHECK: bne LBB
; CHECK: beq LBB
%tmp = icmp eq i32 %a, %b ; <i1> [#uses=1]
br i1 %tmp, label %cond_true, label %return
@ -59,7 +59,7 @@ return: ; preds = %entry
define i32 @f4(i32 %a, i32 %b, i32* %v) {
entry:
; CHECK-LABEL: f4:
; CHECK: blo LBB
; CHECK: bhs LBB
%tmp = icmp uge i32 %a, %b ; <i1> [#uses=1]
br i1 %tmp, label %cond_true, label %return

View File

@ -12,8 +12,11 @@ define zeroext i16 @test1(i16 zeroext %c, i16 zeroext %k) nounwind ssp {
; X64-NEXT: movl %esi, %eax
; X64-NEXT: incl %eax
; X64-NEXT: cmpw %di, %si
; X64-NEXT: jne LBB0_2
; X64-NEXT: ## %bb.1: ## %bb
; X64-NEXT: je LBB0_1
; X64-NEXT: ## %bb.2: ## %bb1
; X64-NEXT: movzwl %ax, %eax
; X64-NEXT: retq
; X64-NEXT: LBB0_1: ## %bb
; X64-NEXT: pushq %rbx
; X64-NEXT: movzwl %ax, %ebx
; X64-NEXT: movl %ebx, %edi
@ -21,9 +24,6 @@ define zeroext i16 @test1(i16 zeroext %c, i16 zeroext %k) nounwind ssp {
; X64-NEXT: movl %ebx, %eax
; X64-NEXT: popq %rbx
; X64-NEXT: retq
; X64-NEXT: LBB0_2: ## %bb1
; X64-NEXT: movzwl %ax, %eax
; X64-NEXT: retq
;
; X32-LABEL: test1:
; X32: ## %bb.0: ## %entry
@ -33,15 +33,15 @@ define zeroext i16 @test1(i16 zeroext %c, i16 zeroext %k) nounwind ssp {
; X32-NEXT: movl %ecx, %eax
; X32-NEXT: incl %eax
; X32-NEXT: cmpw {{[0-9]+}}(%esp), %cx
; X32-NEXT: jne LBB0_2
; X32-NEXT: ## %bb.1: ## %bb
; X32-NEXT: je LBB0_1
; X32-NEXT: ## %bb.2: ## %bb1
; X32-NEXT: movzwl %ax, %eax
; X32-NEXT: jmp LBB0_3
; X32-NEXT: LBB0_1: ## %bb
; X32-NEXT: movzwl %ax, %esi
; X32-NEXT: movl %esi, (%esp)
; X32-NEXT: calll _foo
; X32-NEXT: movl %esi, %eax
; X32-NEXT: jmp LBB0_3
; X32-NEXT: LBB0_2: ## %bb1
; X32-NEXT: movzwl %ax, %eax
; X32-NEXT: LBB0_3: ## %bb1
; X32-NEXT: addl $8, %esp
; X32-NEXT: popl %esi
@ -65,8 +65,11 @@ define zeroext i16 @test2(i16 zeroext %c, i16 zeroext %k) nounwind ssp {
; X64-NEXT: movl %esi, %eax
; X64-NEXT: decl %eax
; X64-NEXT: cmpw %di, %si
; X64-NEXT: jne LBB1_2
; X64-NEXT: ## %bb.1: ## %bb
; X64-NEXT: je LBB1_1
; X64-NEXT: ## %bb.2: ## %bb1
; X64-NEXT: movzwl %ax, %eax
; X64-NEXT: retq
; X64-NEXT: LBB1_1: ## %bb
; X64-NEXT: pushq %rbx
; X64-NEXT: movzwl %ax, %ebx
; X64-NEXT: movl %ebx, %edi
@ -74,9 +77,6 @@ define zeroext i16 @test2(i16 zeroext %c, i16 zeroext %k) nounwind ssp {
; X64-NEXT: movl %ebx, %eax
; X64-NEXT: popq %rbx
; X64-NEXT: retq
; X64-NEXT: LBB1_2: ## %bb1
; X64-NEXT: movzwl %ax, %eax
; X64-NEXT: retq
;
; X32-LABEL: test2:
; X32: ## %bb.0: ## %entry
@ -86,15 +86,15 @@ define zeroext i16 @test2(i16 zeroext %c, i16 zeroext %k) nounwind ssp {
; X32-NEXT: movl %ecx, %eax
; X32-NEXT: decl %eax
; X32-NEXT: cmpw {{[0-9]+}}(%esp), %cx
; X32-NEXT: jne LBB1_2
; X32-NEXT: ## %bb.1: ## %bb
; X32-NEXT: je LBB1_1
; X32-NEXT: ## %bb.2: ## %bb1
; X32-NEXT: movzwl %ax, %eax
; X32-NEXT: jmp LBB1_3
; X32-NEXT: LBB1_1: ## %bb
; X32-NEXT: movzwl %ax, %esi
; X32-NEXT: movl %esi, (%esp)
; X32-NEXT: calll _foo
; X32-NEXT: movl %esi, %eax
; X32-NEXT: jmp LBB1_3
; X32-NEXT: LBB1_2: ## %bb1
; X32-NEXT: movzwl %ax, %eax
; X32-NEXT: LBB1_3: ## %bb1
; X32-NEXT: addl $8, %esp
; X32-NEXT: popl %esi
@ -120,8 +120,11 @@ define zeroext i16 @test3(i16 zeroext %c, i16 zeroext %k) nounwind ssp {
; X64-NEXT: movl %esi, %eax
; X64-NEXT: addl $2, %eax
; X64-NEXT: cmpw %di, %si
; X64-NEXT: jne LBB2_2
; X64-NEXT: ## %bb.1: ## %bb
; X64-NEXT: je LBB2_1
; X64-NEXT: ## %bb.2: ## %bb1
; X64-NEXT: movzwl %ax, %eax
; X64-NEXT: retq
; X64-NEXT: LBB2_1: ## %bb
; X64-NEXT: pushq %rbx
; X64-NEXT: movzwl %ax, %ebx
; X64-NEXT: movl %ebx, %edi
@ -129,9 +132,6 @@ define zeroext i16 @test3(i16 zeroext %c, i16 zeroext %k) nounwind ssp {
; X64-NEXT: movl %ebx, %eax
; X64-NEXT: popq %rbx
; X64-NEXT: retq
; X64-NEXT: LBB2_2: ## %bb1
; X64-NEXT: movzwl %ax, %eax
; X64-NEXT: retq
;
; X32-LABEL: test3:
; X32: ## %bb.0: ## %entry
@ -141,15 +141,15 @@ define zeroext i16 @test3(i16 zeroext %c, i16 zeroext %k) nounwind ssp {
; X32-NEXT: movl %ecx, %eax
; X32-NEXT: addl $2, %eax
; X32-NEXT: cmpw {{[0-9]+}}(%esp), %cx
; X32-NEXT: jne LBB2_2
; X32-NEXT: ## %bb.1: ## %bb
; X32-NEXT: je LBB2_1
; X32-NEXT: ## %bb.2: ## %bb1
; X32-NEXT: movzwl %ax, %eax
; X32-NEXT: jmp LBB2_3
; X32-NEXT: LBB2_1: ## %bb
; X32-NEXT: movzwl %ax, %esi
; X32-NEXT: movl %esi, (%esp)
; X32-NEXT: calll _foo
; X32-NEXT: movl %esi, %eax
; X32-NEXT: jmp LBB2_3
; X32-NEXT: LBB2_2: ## %bb1
; X32-NEXT: movzwl %ax, %eax
; X32-NEXT: LBB2_3: ## %bb1
; X32-NEXT: addl $8, %esp
; X32-NEXT: popl %esi
@ -173,8 +173,11 @@ define zeroext i16 @test4(i16 zeroext %c, i16 zeroext %k) nounwind ssp {
; X64-NEXT: movl %esi, %eax
; X64-NEXT: addl %edi, %eax
; X64-NEXT: cmpw %di, %si
; X64-NEXT: jne LBB3_2
; X64-NEXT: ## %bb.1: ## %bb
; X64-NEXT: je LBB3_1
; X64-NEXT: ## %bb.2: ## %bb1
; X64-NEXT: movzwl %ax, %eax
; X64-NEXT: retq
; X64-NEXT: LBB3_1: ## %bb
; X64-NEXT: pushq %rbx
; X64-NEXT: movzwl %ax, %ebx
; X64-NEXT: movl %ebx, %edi
@ -182,9 +185,6 @@ define zeroext i16 @test4(i16 zeroext %c, i16 zeroext %k) nounwind ssp {
; X64-NEXT: movl %ebx, %eax
; X64-NEXT: popq %rbx
; X64-NEXT: retq
; X64-NEXT: LBB3_2: ## %bb1
; X64-NEXT: movzwl %ax, %eax
; X64-NEXT: retq
;
; X32-LABEL: test4:
; X32: ## %bb.0: ## %entry
@ -195,15 +195,15 @@ define zeroext i16 @test4(i16 zeroext %c, i16 zeroext %k) nounwind ssp {
; X32-NEXT: movl %edx, %eax
; X32-NEXT: addl %ecx, %eax
; X32-NEXT: cmpw %cx, %dx
; X32-NEXT: jne LBB3_2
; X32-NEXT: ## %bb.1: ## %bb
; X32-NEXT: je LBB3_1
; X32-NEXT: ## %bb.2: ## %bb1
; X32-NEXT: movzwl %ax, %eax
; X32-NEXT: jmp LBB3_3
; X32-NEXT: LBB3_1: ## %bb
; X32-NEXT: movzwl %ax, %esi
; X32-NEXT: movl %esi, (%esp)
; X32-NEXT: calll _foo
; X32-NEXT: movl %esi, %eax
; X32-NEXT: jmp LBB3_3
; X32-NEXT: LBB3_2: ## %bb1
; X32-NEXT: movzwl %ax, %eax
; X32-NEXT: LBB3_3: ## %bb1
; X32-NEXT: addl $8, %esp
; X32-NEXT: popl %esi

View File

@ -17,12 +17,16 @@ define void @foo8(i64 %val) {
; NOPIC-NEXT: .cfi_def_cfa_offset 16
; NOPIC-NEXT: cmpq $cmp8@ABS8, %rdi # encoding: [0x48,0x83,0xff,A]
; NOPIC-NEXT: # fixup A - offset: 3, value: cmp8@ABS8, kind: FK_Data_1
; NOPIC-NEXT: ja .LBB0_2 # encoding: [0x77,A]
; NOPIC-NEXT: # fixup A - offset: 1, value: .LBB0_2-1, kind: FK_PCRel_1
; NOPIC-NEXT: # %bb.1: # %t
; NOPIC-NEXT: jbe .LBB0_1 # encoding: [0x76,A]
; NOPIC-NEXT: # fixup A - offset: 1, value: .LBB0_1-1, kind: FK_PCRel_1
; NOPIC-NEXT: # %bb.2: # %f
; NOPIC-NEXT: popq %rax # encoding: [0x58]
; NOPIC-NEXT: .cfi_def_cfa_offset 8
; NOPIC-NEXT: retq # encoding: [0xc3]
; NOPIC-NEXT: .LBB0_1: # %t
; NOPIC-NEXT: .cfi_def_cfa_offset 16
; NOPIC-NEXT: callq f # encoding: [0xe8,A,A,A,A]
; NOPIC-NEXT: # fixup A - offset: 1, value: f-4, kind: reloc_branch_4byte_pcrel
; NOPIC-NEXT: .LBB0_2: # %f
; NOPIC-NEXT: popq %rax # encoding: [0x58]
; NOPIC-NEXT: .cfi_def_cfa_offset 8
; NOPIC-NEXT: retq # encoding: [0xc3]
@ -33,12 +37,16 @@ define void @foo8(i64 %val) {
; PIC-NEXT: .cfi_def_cfa_offset 16
; PIC-NEXT: cmpq $cmp8@ABS8, %rdi # encoding: [0x48,0x83,0xff,A]
; PIC-NEXT: # fixup A - offset: 3, value: cmp8@ABS8, kind: FK_Data_1
; PIC-NEXT: ja .LBB0_2 # encoding: [0x77,A]
; PIC-NEXT: # fixup A - offset: 1, value: .LBB0_2-1, kind: FK_PCRel_1
; PIC-NEXT: # %bb.1: # %t
; PIC-NEXT: jbe .LBB0_1 # encoding: [0x76,A]
; PIC-NEXT: # fixup A - offset: 1, value: .LBB0_1-1, kind: FK_PCRel_1
; PIC-NEXT: # %bb.2: # %f
; PIC-NEXT: popq %rax # encoding: [0x58]
; PIC-NEXT: .cfi_def_cfa_offset 8
; PIC-NEXT: retq # encoding: [0xc3]
; PIC-NEXT: .LBB0_1: # %t
; PIC-NEXT: .cfi_def_cfa_offset 16
; PIC-NEXT: callq f@PLT # encoding: [0xe8,A,A,A,A]
; PIC-NEXT: # fixup A - offset: 1, value: f@PLT-4, kind: FK_PCRel_4
; PIC-NEXT: .LBB0_2: # %f
; PIC-NEXT: popq %rax # encoding: [0x58]
; PIC-NEXT: .cfi_def_cfa_offset 8
; PIC-NEXT: retq # encoding: [0xc3]
@ -60,12 +68,16 @@ define void @foo32(i64 %val) {
; NOPIC-NEXT: .cfi_def_cfa_offset 16
; NOPIC-NEXT: cmpq $cmp32, %rdi # encoding: [0x48,0x81,0xff,A,A,A,A]
; NOPIC-NEXT: # fixup A - offset: 3, value: cmp32, kind: reloc_signed_4byte
; NOPIC-NEXT: ja .LBB1_2 # encoding: [0x77,A]
; NOPIC-NEXT: # fixup A - offset: 1, value: .LBB1_2-1, kind: FK_PCRel_1
; NOPIC-NEXT: # %bb.1: # %t
; NOPIC-NEXT: jbe .LBB1_1 # encoding: [0x76,A]
; NOPIC-NEXT: # fixup A - offset: 1, value: .LBB1_1-1, kind: FK_PCRel_1
; NOPIC-NEXT: # %bb.2: # %f
; NOPIC-NEXT: popq %rax # encoding: [0x58]
; NOPIC-NEXT: .cfi_def_cfa_offset 8
; NOPIC-NEXT: retq # encoding: [0xc3]
; NOPIC-NEXT: .LBB1_1: # %t
; NOPIC-NEXT: .cfi_def_cfa_offset 16
; NOPIC-NEXT: callq f # encoding: [0xe8,A,A,A,A]
; NOPIC-NEXT: # fixup A - offset: 1, value: f-4, kind: reloc_branch_4byte_pcrel
; NOPIC-NEXT: .LBB1_2: # %f
; NOPIC-NEXT: popq %rax # encoding: [0x58]
; NOPIC-NEXT: .cfi_def_cfa_offset 8
; NOPIC-NEXT: retq # encoding: [0xc3]
@ -76,12 +88,16 @@ define void @foo32(i64 %val) {
; PIC-NEXT: .cfi_def_cfa_offset 16
; PIC-NEXT: cmpq $cmp32, %rdi # encoding: [0x48,0x81,0xff,A,A,A,A]
; PIC-NEXT: # fixup A - offset: 3, value: cmp32, kind: reloc_signed_4byte
; PIC-NEXT: ja .LBB1_2 # encoding: [0x77,A]
; PIC-NEXT: # fixup A - offset: 1, value: .LBB1_2-1, kind: FK_PCRel_1
; PIC-NEXT: # %bb.1: # %t
; PIC-NEXT: jbe .LBB1_1 # encoding: [0x76,A]
; PIC-NEXT: # fixup A - offset: 1, value: .LBB1_1-1, kind: FK_PCRel_1
; PIC-NEXT: # %bb.2: # %f
; PIC-NEXT: popq %rax # encoding: [0x58]
; PIC-NEXT: .cfi_def_cfa_offset 8
; PIC-NEXT: retq # encoding: [0xc3]
; PIC-NEXT: .LBB1_1: # %t
; PIC-NEXT: .cfi_def_cfa_offset 16
; PIC-NEXT: callq f@PLT # encoding: [0xe8,A,A,A,A]
; PIC-NEXT: # fixup A - offset: 1, value: f@PLT-4, kind: FK_PCRel_4
; PIC-NEXT: .LBB1_2: # %f
; PIC-NEXT: popq %rax # encoding: [0x58]
; PIC-NEXT: .cfi_def_cfa_offset 8
; PIC-NEXT: retq # encoding: [0xc3]

View File

@ -1,20 +1,55 @@
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -verify-machineinstrs | FileCheck %s
; RUN: llc < %s -mtriple=i686-unknown-unknown -verify-machineinstrs | FileCheck %s
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,X86-64
; RUN: llc < %s -mtriple=i686-unknown-unknown -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,X86-32
; Make sure that flags are properly preserved despite atomic optimizations.
define i32 @atomic_and_flags_1(i8* %p, i32 %a, i32 %b) {
; CHECK-LABEL: atomic_and_flags_1:
; Generate flags value, and use it.
; CHECK: cmpl
; CHECK-NEXT: jne
; X86-64-LABEL: atomic_and_flags_1:
; X86-64: # %bb.0:
; X86-64-NEXT: cmpl %edx, %esi
; X86-64-NEXT: je .LBB0_1
; X86-64-NEXT: # %bb.3: # %L2
; X86-64-NEXT: movl $2, %eax
; X86-64-NEXT: retq
; X86-64-NEXT: .LBB0_1: # %L1
; X86-64-NEXT: incb (%rdi)
; X86-64-NEXT: cmpl %edx, %esi
; X86-64-NEXT: je .LBB0_4
; X86-64-NEXT: # %bb.2: # %L4
; X86-64-NEXT: movl $4, %eax
; X86-64-NEXT: retq
; X86-64-NEXT: .LBB0_4: # %L3
; X86-64-NEXT: movl $3, %eax
; X86-64-NEXT: retq
;
; X86-32-LABEL: atomic_and_flags_1:
; X86-32: # %bb.0:
; X86-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-32-NEXT: cmpl %eax, %ecx
; X86-32-NEXT: je .LBB0_1
; X86-32-NEXT: # %bb.3: # %L2
; X86-32-NEXT: movl $2, %eax
; X86-32-NEXT: retl
; X86-32-NEXT: .LBB0_1: # %L1
; X86-32-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-32-NEXT: incb (%edx)
; X86-32-NEXT: cmpl %eax, %ecx
; X86-32-NEXT: je .LBB0_4
; X86-32-NEXT: # %bb.2: # %L4
; X86-32-NEXT: movl $4, %eax
; X86-32-NEXT: retl
; X86-32-NEXT: .LBB0_4: # %L3
; X86-32-NEXT: movl $3, %eax
; X86-32-NEXT: retl
%cmp = icmp eq i32 %a, %b
br i1 %cmp, label %L1, label %L2
L1:
; The following pattern will get folded.
; CHECK: incb
%1 = load atomic i8, i8* %p seq_cst, align 1
%2 = add i8 %1, 1 ; This forces the INC instruction to be generated.
store atomic i8 %2, i8* %p release, align 1
@ -23,8 +58,7 @@ L1:
; somehow. This test checks that cmpl gets emitted again, but any
; rematerialization would work (the optimizer used to clobber the flags with
; the add).
; CHECK-NEXT: cmpl
; CHECK-NEXT: jne
br i1 %cmp, label %L3, label %L4
L2:
@ -39,18 +73,51 @@ L4:
; Same as above, but using 2 as immediate to avoid the INC instruction.
define i32 @atomic_and_flags_2(i8* %p, i32 %a, i32 %b) {
; CHECK-LABEL: atomic_and_flags_2:
; CHECK: cmpl
; CHECK-NEXT: jne
; X86-64-LABEL: atomic_and_flags_2:
; X86-64: # %bb.0:
; X86-64-NEXT: cmpl %edx, %esi
; X86-64-NEXT: je .LBB1_1
; X86-64-NEXT: # %bb.3: # %L2
; X86-64-NEXT: movl $2, %eax
; X86-64-NEXT: retq
; X86-64-NEXT: .LBB1_1: # %L1
; X86-64-NEXT: addb $2, (%rdi)
; X86-64-NEXT: cmpl %edx, %esi
; X86-64-NEXT: je .LBB1_4
; X86-64-NEXT: # %bb.2: # %L4
; X86-64-NEXT: movl $4, %eax
; X86-64-NEXT: retq
; X86-64-NEXT: .LBB1_4: # %L3
; X86-64-NEXT: movl $3, %eax
; X86-64-NEXT: retq
;
; X86-32-LABEL: atomic_and_flags_2:
; X86-32: # %bb.0:
; X86-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-32-NEXT: cmpl %eax, %ecx
; X86-32-NEXT: je .LBB1_1
; X86-32-NEXT: # %bb.3: # %L2
; X86-32-NEXT: movl $2, %eax
; X86-32-NEXT: retl
; X86-32-NEXT: .LBB1_1: # %L1
; X86-32-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-32-NEXT: addb $2, (%edx)
; X86-32-NEXT: cmpl %eax, %ecx
; X86-32-NEXT: je .LBB1_4
; X86-32-NEXT: # %bb.2: # %L4
; X86-32-NEXT: movl $4, %eax
; X86-32-NEXT: retl
; X86-32-NEXT: .LBB1_4: # %L3
; X86-32-NEXT: movl $3, %eax
; X86-32-NEXT: retl
%cmp = icmp eq i32 %a, %b
br i1 %cmp, label %L1, label %L2
L1:
; CHECK: addb
%1 = load atomic i8, i8* %p seq_cst, align 1
%2 = add i8 %1, 2
store atomic i8 %2, i8* %p release, align 1
; CHECK-NEXT: cmpl
; CHECK-NEXT: jne
br i1 %cmp, label %L3, label %L4
L2:
ret i32 2

View File

@ -2716,24 +2716,24 @@ define i1 @fold_cmp_over_fence(i32* %p, i32 %v1) {
; CHECK-O3-CUR-NEXT: movl (%rdi), %eax
; CHECK-O3-CUR-NEXT: mfence
; CHECK-O3-CUR-NEXT: cmpl %eax, %esi
; CHECK-O3-CUR-NEXT: jne .LBB116_2
; CHECK-O3-CUR-NEXT: # %bb.1: # %taken
; CHECK-O3-CUR-NEXT: movb $1, %al
; CHECK-O3-CUR-NEXT: retq
; CHECK-O3-CUR-NEXT: .LBB116_2: # %untaken
; CHECK-O3-CUR-NEXT: je .LBB116_1
; CHECK-O3-CUR-NEXT: # %bb.2: # %untaken
; CHECK-O3-CUR-NEXT: xorl %eax, %eax
; CHECK-O3-CUR-NEXT: retq
; CHECK-O3-CUR-NEXT: .LBB116_1: # %taken
; CHECK-O3-CUR-NEXT: movb $1, %al
; CHECK-O3-CUR-NEXT: retq
;
; CHECK-O3-EX-LABEL: fold_cmp_over_fence:
; CHECK-O3-EX: # %bb.0:
; CHECK-O3-EX-NEXT: cmpl (%rdi), %esi
; CHECK-O3-EX-NEXT: mfence
; CHECK-O3-EX-NEXT: jne .LBB116_2
; CHECK-O3-EX-NEXT: # %bb.1: # %taken
; CHECK-O3-EX-NEXT: movb $1, %al
; CHECK-O3-EX-NEXT: retq
; CHECK-O3-EX-NEXT: .LBB116_2: # %untaken
; CHECK-O3-EX-NEXT: je .LBB116_1
; CHECK-O3-EX-NEXT: # %bb.2: # %untaken
; CHECK-O3-EX-NEXT: xorl %eax, %eax
; CHECK-O3-EX-NEXT: retq
; CHECK-O3-EX-NEXT: .LBB116_1: # %taken
; CHECK-O3-EX-NEXT: movb $1, %al
; CHECK-O3-EX-NEXT: retq
%v2 = load atomic i32, i32* %p unordered, align 4
fence seq_cst

View File

@ -1249,20 +1249,20 @@ define void @pr42118_i32(i32 %x) {
; X86-LABEL: pr42118_i32:
; X86: # %bb.0:
; X86-NEXT: blsrl {{[0-9]+}}(%esp), %eax
; X86-NEXT: jne .LBB50_1
; X86-NEXT: # %bb.2:
; X86-NEXT: jmp bar # TAILCALL
; X86-NEXT: .LBB50_1:
; X86-NEXT: je .LBB50_2
; X86-NEXT: # %bb.1:
; X86-NEXT: retl
; X86-NEXT: .LBB50_2:
; X86-NEXT: jmp bar # TAILCALL
;
; X64-LABEL: pr42118_i32:
; X64: # %bb.0:
; X64-NEXT: blsrl %edi, %eax
; X64-NEXT: jne .LBB50_1
; X64-NEXT: # %bb.2:
; X64-NEXT: jmp bar # TAILCALL
; X64-NEXT: .LBB50_1:
; X64-NEXT: je .LBB50_2
; X64-NEXT: # %bb.1:
; X64-NEXT: retq
; X64-NEXT: .LBB50_2:
; X64-NEXT: jmp bar # TAILCALL
%tmp = sub i32 0, %x
%tmp1 = and i32 %tmp, %x
%cmp = icmp eq i32 %tmp1, %x
@ -1289,25 +1289,25 @@ define void @pr42118_i64(i64 %x) {
; X86-NEXT: andl %eax, %edx
; X86-NEXT: andl %ecx, %esi
; X86-NEXT: orl %edx, %esi
; X86-NEXT: jne .LBB51_1
; X86-NEXT: # %bb.2:
; X86-NEXT: popl %esi
; X86-NEXT: .cfi_def_cfa_offset 4
; X86-NEXT: jmp bar # TAILCALL
; X86-NEXT: .LBB51_1:
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: je .LBB51_2
; X86-NEXT: # %bb.1:
; X86-NEXT: popl %esi
; X86-NEXT: .cfi_def_cfa_offset 4
; X86-NEXT: retl
; X86-NEXT: .LBB51_2:
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: popl %esi
; X86-NEXT: .cfi_def_cfa_offset 4
; X86-NEXT: jmp bar # TAILCALL
;
; X64-LABEL: pr42118_i64:
; X64: # %bb.0:
; X64-NEXT: blsrq %rdi, %rax
; X64-NEXT: jne .LBB51_1
; X64-NEXT: # %bb.2:
; X64-NEXT: jmp bar # TAILCALL
; X64-NEXT: .LBB51_1:
; X64-NEXT: je .LBB51_2
; X64-NEXT: # %bb.1:
; X64-NEXT: retq
; X64-NEXT: .LBB51_2:
; X64-NEXT: jmp bar # TAILCALL
%tmp = sub i64 0, %x
%tmp1 = and i64 %tmp, %x
%cmp = icmp eq i64 %tmp1, %x

View File

@ -611,21 +611,23 @@ define void @query3(i32 %x, i32 %n) nounwind {
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: btl %ecx, %eax
; X86-NEXT: jae .LBB16_2
; X86-NEXT: # %bb.1: # %bb
; X86-NEXT: jb .LBB16_1
; X86-NEXT: # %bb.2: # %UnifiedReturnBlock
; X86-NEXT: retl
; X86-NEXT: .LBB16_1: # %bb
; X86-NEXT: calll foo
; X86-NEXT: .LBB16_2: # %UnifiedReturnBlock
; X86-NEXT: retl
;
; X64-LABEL: query3:
; X64: # %bb.0: # %entry
; X64-NEXT: btl %esi, %edi
; X64-NEXT: jae .LBB16_2
; X64-NEXT: # %bb.1: # %bb
; X64-NEXT: jb .LBB16_1
; X64-NEXT: # %bb.2: # %UnifiedReturnBlock
; X64-NEXT: retq
; X64-NEXT: .LBB16_1: # %bb
; X64-NEXT: pushq %rax
; X64-NEXT: callq foo
; X64-NEXT: popq %rax
; X64-NEXT: .LBB16_2: # %UnifiedReturnBlock
; X64-NEXT: retq
entry:
%tmp29 = shl i32 1, %n
@ -647,21 +649,23 @@ define void @query3b(i32 %x, i32 %n) nounwind {
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: btl %ecx, %eax
; X86-NEXT: jae .LBB17_2
; X86-NEXT: # %bb.1: # %bb
; X86-NEXT: jb .LBB17_1
; X86-NEXT: # %bb.2: # %UnifiedReturnBlock
; X86-NEXT: retl
; X86-NEXT: .LBB17_1: # %bb
; X86-NEXT: calll foo
; X86-NEXT: .LBB17_2: # %UnifiedReturnBlock
; X86-NEXT: retl
;
; X64-LABEL: query3b:
; X64: # %bb.0: # %entry
; X64-NEXT: btl %esi, %edi
; X64-NEXT: jae .LBB17_2
; X64-NEXT: # %bb.1: # %bb
; X64-NEXT: jb .LBB17_1
; X64-NEXT: # %bb.2: # %UnifiedReturnBlock
; X64-NEXT: retq
; X64-NEXT: .LBB17_1: # %bb
; X64-NEXT: pushq %rax
; X64-NEXT: callq foo
; X64-NEXT: popq %rax
; X64-NEXT: .LBB17_2: # %UnifiedReturnBlock
; X64-NEXT: retq
entry:
%tmp29 = shl i32 1, %n
@ -683,21 +687,23 @@ define void @query3x(i32 %x, i32 %n) nounwind {
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: btl %ecx, %eax
; X86-NEXT: jae .LBB18_2
; X86-NEXT: # %bb.1: # %bb
; X86-NEXT: jb .LBB18_1
; X86-NEXT: # %bb.2: # %UnifiedReturnBlock
; X86-NEXT: retl
; X86-NEXT: .LBB18_1: # %bb
; X86-NEXT: calll foo
; X86-NEXT: .LBB18_2: # %UnifiedReturnBlock
; X86-NEXT: retl
;
; X64-LABEL: query3x:
; X64: # %bb.0: # %entry
; X64-NEXT: btl %esi, %edi
; X64-NEXT: jae .LBB18_2
; X64-NEXT: # %bb.1: # %bb
; X64-NEXT: jb .LBB18_1
; X64-NEXT: # %bb.2: # %UnifiedReturnBlock
; X64-NEXT: retq
; X64-NEXT: .LBB18_1: # %bb
; X64-NEXT: pushq %rax
; X64-NEXT: callq foo
; X64-NEXT: popq %rax
; X64-NEXT: .LBB18_2: # %UnifiedReturnBlock
; X64-NEXT: retq
entry:
%tmp29 = shl i32 1, %n
@ -719,21 +725,23 @@ define void @query3bx(i32 %x, i32 %n) nounwind {
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: btl %ecx, %eax
; X86-NEXT: jae .LBB19_2
; X86-NEXT: # %bb.1: # %bb
; X86-NEXT: jb .LBB19_1
; X86-NEXT: # %bb.2: # %UnifiedReturnBlock
; X86-NEXT: retl
; X86-NEXT: .LBB19_1: # %bb
; X86-NEXT: calll foo
; X86-NEXT: .LBB19_2: # %UnifiedReturnBlock
; X86-NEXT: retl
;
; X64-LABEL: query3bx:
; X64: # %bb.0: # %entry
; X64-NEXT: btl %esi, %edi
; X64-NEXT: jae .LBB19_2
; X64-NEXT: # %bb.1: # %bb
; X64-NEXT: jb .LBB19_1
; X64-NEXT: # %bb.2: # %UnifiedReturnBlock
; X64-NEXT: retq
; X64-NEXT: .LBB19_1: # %bb
; X64-NEXT: pushq %rax
; X64-NEXT: callq foo
; X64-NEXT: popq %rax
; X64-NEXT: .LBB19_2: # %UnifiedReturnBlock
; X64-NEXT: retq
entry:
%tmp29 = shl i32 1, %n

View File

@ -63,21 +63,21 @@ define void @f_non_leaf(i32 %x, i32 %y) !prof !14 {
; CHECK32-NEXT: #APP
; CHECK32-NEXT: #NO_APP
; CHECK32-NEXT: cmpl {{[0-9]+}}(%esp), %eax # encoding: [0x3b,0x44,0x24,0x0c]
; CHECK32-NEXT: jne .LBB1_2 # encoding: [0x75,A]
; CHECK32-NEXT: # fixup A - offset: 1, value: .LBB1_2-1, kind: FK_PCRel_1
; CHECK32-NEXT: # %bb.1: # %bb1
; CHECK32-NEXT: popl %ebx # encoding: [0x5b]
; CHECK32-NEXT: .cfi_def_cfa_offset 4
; CHECK32-NEXT: jmp foo # TAILCALL
; CHECK32-NEXT: # encoding: [0xeb,A]
; CHECK32-NEXT: # fixup A - offset: 1, value: foo-1, kind: FK_PCRel_1
; CHECK32-NEXT: .LBB1_2: # %bb2
; CHECK32-NEXT: .cfi_def_cfa_offset 8
; CHECK32-NEXT: je .LBB1_1 # encoding: [0x74,A]
; CHECK32-NEXT: # fixup A - offset: 1, value: .LBB1_1-1, kind: FK_PCRel_1
; CHECK32-NEXT: # %bb.2: # %bb2
; CHECK32-NEXT: popl %ebx # encoding: [0x5b]
; CHECK32-NEXT: .cfi_def_cfa_offset 4
; CHECK32-NEXT: jmp bar # TAILCALL
; CHECK32-NEXT: # encoding: [0xeb,A]
; CHECK32-NEXT: # fixup A - offset: 1, value: bar-1, kind: FK_PCRel_1
; CHECK32-NEXT: .LBB1_1: # %bb1
; CHECK32-NEXT: .cfi_def_cfa_offset 8
; CHECK32-NEXT: popl %ebx # encoding: [0x5b]
; CHECK32-NEXT: .cfi_def_cfa_offset 4
; CHECK32-NEXT: jmp foo # TAILCALL
; CHECK32-NEXT: # encoding: [0xeb,A]
; CHECK32-NEXT: # fixup A - offset: 1, value: foo-1, kind: FK_PCRel_1
;
; CHECK64-LABEL: f_non_leaf:
; CHECK64: # %bb.0: # %entry
@ -87,21 +87,21 @@ define void @f_non_leaf(i32 %x, i32 %y) !prof !14 {
; CHECK64-NEXT: #APP
; CHECK64-NEXT: #NO_APP
; CHECK64-NEXT: cmpl %esi, %edi # encoding: [0x39,0xf7]
; CHECK64-NEXT: jne .LBB1_2 # encoding: [0x75,A]
; CHECK64-NEXT: # fixup A - offset: 1, value: .LBB1_2-1, kind: FK_PCRel_1
; CHECK64-NEXT: # %bb.1: # %bb1
; CHECK64-NEXT: popq %rbx # encoding: [0x5b]
; CHECK64-NEXT: .cfi_def_cfa_offset 8
; CHECK64-NEXT: jmp foo # TAILCALL
; CHECK64-NEXT: # encoding: [0xeb,A]
; CHECK64-NEXT: # fixup A - offset: 1, value: foo-1, kind: FK_PCRel_1
; CHECK64-NEXT: .LBB1_2: # %bb2
; CHECK64-NEXT: .cfi_def_cfa_offset 16
; CHECK64-NEXT: je .LBB1_1 # encoding: [0x74,A]
; CHECK64-NEXT: # fixup A - offset: 1, value: .LBB1_1-1, kind: FK_PCRel_1
; CHECK64-NEXT: # %bb.2: # %bb2
; CHECK64-NEXT: popq %rbx # encoding: [0x5b]
; CHECK64-NEXT: .cfi_def_cfa_offset 8
; CHECK64-NEXT: jmp bar # TAILCALL
; CHECK64-NEXT: # encoding: [0xeb,A]
; CHECK64-NEXT: # fixup A - offset: 1, value: bar-1, kind: FK_PCRel_1
; CHECK64-NEXT: .LBB1_1: # %bb1
; CHECK64-NEXT: .cfi_def_cfa_offset 16
; CHECK64-NEXT: popq %rbx # encoding: [0x5b]
; CHECK64-NEXT: .cfi_def_cfa_offset 8
; CHECK64-NEXT: jmp foo # TAILCALL
; CHECK64-NEXT: # encoding: [0xeb,A]
; CHECK64-NEXT: # fixup A - offset: 1, value: foo-1, kind: FK_PCRel_1
;
; WIN64-LABEL: f_non_leaf:
; WIN64: # %bb.0: # %entry
@ -111,19 +111,19 @@ define void @f_non_leaf(i32 %x, i32 %y) !prof !14 {
; WIN64-NEXT: #APP
; WIN64-NEXT: #NO_APP
; WIN64-NEXT: cmpl %edx, %ecx # encoding: [0x39,0xd1]
; WIN64-NEXT: jne .LBB1_2 # encoding: [0x75,A]
; WIN64-NEXT: # fixup A - offset: 1, value: .LBB1_2-1, kind: FK_PCRel_1
; WIN64-NEXT: # %bb.1: # %bb1
; WIN64-NEXT: popq %rbx # encoding: [0x5b]
; WIN64-NEXT: jmp foo # TAILCALL
; WIN64-NEXT: # encoding: [0xeb,A]
; WIN64-NEXT: # fixup A - offset: 1, value: foo-1, kind: FK_PCRel_1
; WIN64-NEXT: .LBB1_2: # %bb2
; WIN64-NEXT: nop # encoding: [0x90]
; WIN64-NEXT: je .LBB1_1 # encoding: [0x74,A]
; WIN64-NEXT: # fixup A - offset: 1, value: .LBB1_1-1, kind: FK_PCRel_1
; WIN64-NEXT: # %bb.2: # %bb2
; WIN64-NEXT: popq %rbx # encoding: [0x5b]
; WIN64-NEXT: jmp bar # TAILCALL
; WIN64-NEXT: # encoding: [0xeb,A]
; WIN64-NEXT: # fixup A - offset: 1, value: bar-1, kind: FK_PCRel_1
; WIN64-NEXT: .LBB1_1: # %bb1
; WIN64-NEXT: nop # encoding: [0x90]
; WIN64-NEXT: popq %rbx # encoding: [0x5b]
; WIN64-NEXT: jmp foo # TAILCALL
; WIN64-NEXT: # encoding: [0xeb,A]
; WIN64-NEXT: # fixup A - offset: 1, value: foo-1, kind: FK_PCRel_1
; WIN64-NEXT: .seh_handlerdata
; WIN64-NEXT: .text
; WIN64-NEXT: .seh_endproc

View File

@ -63,21 +63,21 @@ define void @f_non_leaf(i32 %x, i32 %y) optsize {
; CHECK32-NEXT: #APP
; CHECK32-NEXT: #NO_APP
; CHECK32-NEXT: cmpl {{[0-9]+}}(%esp), %eax # encoding: [0x3b,0x44,0x24,0x0c]
; CHECK32-NEXT: jne .LBB1_2 # encoding: [0x75,A]
; CHECK32-NEXT: # fixup A - offset: 1, value: .LBB1_2-1, kind: FK_PCRel_1
; CHECK32-NEXT: # %bb.1: # %bb1
; CHECK32-NEXT: popl %ebx # encoding: [0x5b]
; CHECK32-NEXT: .cfi_def_cfa_offset 4
; CHECK32-NEXT: jmp foo # TAILCALL
; CHECK32-NEXT: # encoding: [0xeb,A]
; CHECK32-NEXT: # fixup A - offset: 1, value: foo-1, kind: FK_PCRel_1
; CHECK32-NEXT: .LBB1_2: # %bb2
; CHECK32-NEXT: .cfi_def_cfa_offset 8
; CHECK32-NEXT: je .LBB1_1 # encoding: [0x74,A]
; CHECK32-NEXT: # fixup A - offset: 1, value: .LBB1_1-1, kind: FK_PCRel_1
; CHECK32-NEXT: # %bb.2: # %bb2
; CHECK32-NEXT: popl %ebx # encoding: [0x5b]
; CHECK32-NEXT: .cfi_def_cfa_offset 4
; CHECK32-NEXT: jmp bar # TAILCALL
; CHECK32-NEXT: # encoding: [0xeb,A]
; CHECK32-NEXT: # fixup A - offset: 1, value: bar-1, kind: FK_PCRel_1
; CHECK32-NEXT: .LBB1_1: # %bb1
; CHECK32-NEXT: .cfi_def_cfa_offset 8
; CHECK32-NEXT: popl %ebx # encoding: [0x5b]
; CHECK32-NEXT: .cfi_def_cfa_offset 4
; CHECK32-NEXT: jmp foo # TAILCALL
; CHECK32-NEXT: # encoding: [0xeb,A]
; CHECK32-NEXT: # fixup A - offset: 1, value: foo-1, kind: FK_PCRel_1
;
; CHECK64-LABEL: f_non_leaf:
; CHECK64: # %bb.0: # %entry
@ -87,21 +87,21 @@ define void @f_non_leaf(i32 %x, i32 %y) optsize {
; CHECK64-NEXT: #APP
; CHECK64-NEXT: #NO_APP
; CHECK64-NEXT: cmpl %esi, %edi # encoding: [0x39,0xf7]
; CHECK64-NEXT: jne .LBB1_2 # encoding: [0x75,A]
; CHECK64-NEXT: # fixup A - offset: 1, value: .LBB1_2-1, kind: FK_PCRel_1
; CHECK64-NEXT: # %bb.1: # %bb1
; CHECK64-NEXT: popq %rbx # encoding: [0x5b]
; CHECK64-NEXT: .cfi_def_cfa_offset 8
; CHECK64-NEXT: jmp foo # TAILCALL
; CHECK64-NEXT: # encoding: [0xeb,A]
; CHECK64-NEXT: # fixup A - offset: 1, value: foo-1, kind: FK_PCRel_1
; CHECK64-NEXT: .LBB1_2: # %bb2
; CHECK64-NEXT: .cfi_def_cfa_offset 16
; CHECK64-NEXT: je .LBB1_1 # encoding: [0x74,A]
; CHECK64-NEXT: # fixup A - offset: 1, value: .LBB1_1-1, kind: FK_PCRel_1
; CHECK64-NEXT: # %bb.2: # %bb2
; CHECK64-NEXT: popq %rbx # encoding: [0x5b]
; CHECK64-NEXT: .cfi_def_cfa_offset 8
; CHECK64-NEXT: jmp bar # TAILCALL
; CHECK64-NEXT: # encoding: [0xeb,A]
; CHECK64-NEXT: # fixup A - offset: 1, value: bar-1, kind: FK_PCRel_1
; CHECK64-NEXT: .LBB1_1: # %bb1
; CHECK64-NEXT: .cfi_def_cfa_offset 16
; CHECK64-NEXT: popq %rbx # encoding: [0x5b]
; CHECK64-NEXT: .cfi_def_cfa_offset 8
; CHECK64-NEXT: jmp foo # TAILCALL
; CHECK64-NEXT: # encoding: [0xeb,A]
; CHECK64-NEXT: # fixup A - offset: 1, value: foo-1, kind: FK_PCRel_1
;
; WIN64-LABEL: f_non_leaf:
; WIN64: # %bb.0: # %entry
@ -111,19 +111,19 @@ define void @f_non_leaf(i32 %x, i32 %y) optsize {
; WIN64-NEXT: #APP
; WIN64-NEXT: #NO_APP
; WIN64-NEXT: cmpl %edx, %ecx # encoding: [0x39,0xd1]
; WIN64-NEXT: jne .LBB1_2 # encoding: [0x75,A]
; WIN64-NEXT: # fixup A - offset: 1, value: .LBB1_2-1, kind: FK_PCRel_1
; WIN64-NEXT: # %bb.1: # %bb1
; WIN64-NEXT: popq %rbx # encoding: [0x5b]
; WIN64-NEXT: jmp foo # TAILCALL
; WIN64-NEXT: # encoding: [0xeb,A]
; WIN64-NEXT: # fixup A - offset: 1, value: foo-1, kind: FK_PCRel_1
; WIN64-NEXT: .LBB1_2: # %bb2
; WIN64-NEXT: nop # encoding: [0x90]
; WIN64-NEXT: je .LBB1_1 # encoding: [0x74,A]
; WIN64-NEXT: # fixup A - offset: 1, value: .LBB1_1-1, kind: FK_PCRel_1
; WIN64-NEXT: # %bb.2: # %bb2
; WIN64-NEXT: popq %rbx # encoding: [0x5b]
; WIN64-NEXT: jmp bar # TAILCALL
; WIN64-NEXT: # encoding: [0xeb,A]
; WIN64-NEXT: # fixup A - offset: 1, value: bar-1, kind: FK_PCRel_1
; WIN64-NEXT: .LBB1_1: # %bb1
; WIN64-NEXT: nop # encoding: [0x90]
; WIN64-NEXT: popq %rbx # encoding: [0x5b]
; WIN64-NEXT: jmp foo # TAILCALL
; WIN64-NEXT: # encoding: [0xeb,A]
; WIN64-NEXT: # fixup A - offset: 1, value: foo-1, kind: FK_PCRel_1
; WIN64-NEXT: .seh_handlerdata
; WIN64-NEXT: .text
; WIN64-NEXT: .seh_endproc

View File

@ -1,11 +1,19 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin10 | FileCheck %s
; RUN: llc < %s -fast-isel -fast-isel-abort=1 -mtriple=x86_64-apple-darwin10 | FileCheck %s
define i32 @fcmp_oeq(float %x, float %y) {
; CHECK-LABEL: fcmp_oeq
; CHECK: ucomiss %xmm1, %xmm0
; CHECK-NEXT: jne {{LBB.+_1}}
; CHECK-NEXT: jp {{LBB.+_1}}
; CHECK-LABEL: fcmp_oeq:
; CHECK: ## %bb.0:
; CHECK-NEXT: ucomiss %xmm1, %xmm0
; CHECK-NEXT: jne LBB0_1
; CHECK-NEXT: jp LBB0_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB0_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = fcmp oeq float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -15,9 +23,16 @@ bb1:
}
define i32 @fcmp_ogt(float %x, float %y) {
; CHECK-LABEL: fcmp_ogt
; CHECK: ucomiss %xmm1, %xmm0
; CHECK-NEXT: jbe {{LBB.+_1}}
; CHECK-LABEL: fcmp_ogt:
; CHECK: ## %bb.0:
; CHECK-NEXT: ucomiss %xmm1, %xmm0
; CHECK-NEXT: jbe LBB1_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB1_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = fcmp ogt float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -27,9 +42,16 @@ bb1:
}
define i32 @fcmp_oge(float %x, float %y) {
; CHECK-LABEL: fcmp_oge
; CHECK: ucomiss %xmm1, %xmm0
; CHECK-NEXT: jb {{LBB.+_1}}
; CHECK-LABEL: fcmp_oge:
; CHECK: ## %bb.0:
; CHECK-NEXT: ucomiss %xmm1, %xmm0
; CHECK-NEXT: jb LBB2_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB2_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = fcmp oge float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -39,9 +61,16 @@ bb1:
}
define i32 @fcmp_olt(float %x, float %y) {
; CHECK-LABEL: fcmp_olt
; CHECK: ucomiss %xmm0, %xmm1
; CHECK-NEXT: jbe {{LBB.+_1}}
; CHECK-LABEL: fcmp_olt:
; CHECK: ## %bb.0:
; CHECK-NEXT: ucomiss %xmm0, %xmm1
; CHECK-NEXT: jbe LBB3_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB3_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = fcmp olt float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -51,9 +80,16 @@ bb1:
}
define i32 @fcmp_ole(float %x, float %y) {
; CHECK-LABEL: fcmp_ole
; CHECK: ucomiss %xmm0, %xmm1
; CHECK-NEXT: jb {{LBB.+_1}}
; CHECK-LABEL: fcmp_ole:
; CHECK: ## %bb.0:
; CHECK-NEXT: ucomiss %xmm0, %xmm1
; CHECK-NEXT: jb LBB4_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB4_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = fcmp ole float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -63,9 +99,16 @@ bb1:
}
define i32 @fcmp_one(float %x, float %y) {
; CHECK-LABEL: fcmp_one
; CHECK: ucomiss %xmm1, %xmm0
; CHECK-NEXT: je {{LBB.+_1}}
; CHECK-LABEL: fcmp_one:
; CHECK: ## %bb.0:
; CHECK-NEXT: ucomiss %xmm1, %xmm0
; CHECK-NEXT: je LBB5_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB5_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = fcmp one float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -75,9 +118,16 @@ bb1:
}
define i32 @fcmp_ord(float %x, float %y) {
; CHECK-LABEL: fcmp_ord
; CHECK: ucomiss %xmm1, %xmm0
; CHECK-NEXT: jp {{LBB.+_1}}
; CHECK-LABEL: fcmp_ord:
; CHECK: ## %bb.0:
; CHECK-NEXT: ucomiss %xmm1, %xmm0
; CHECK-NEXT: jp LBB6_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB6_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = fcmp ord float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -87,9 +137,16 @@ bb1:
}
define i32 @fcmp_uno(float %x, float %y) {
; CHECK-LABEL: fcmp_uno
; CHECK: ucomiss %xmm1, %xmm0
; CHECK-NEXT: jp {{LBB.+_2}}
; CHECK-LABEL: fcmp_uno:
; CHECK: ## %bb.0:
; CHECK-NEXT: ucomiss %xmm1, %xmm0
; CHECK-NEXT: jp LBB7_2
; CHECK-NEXT: ## %bb.1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB7_2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
%1 = fcmp uno float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -99,9 +156,16 @@ bb1:
}
define i32 @fcmp_ueq(float %x, float %y) {
; CHECK-LABEL: fcmp_ueq
; CHECK: ucomiss %xmm1, %xmm0
; CHECK-NEXT: je {{LBB.+_2}}
; CHECK-LABEL: fcmp_ueq:
; CHECK: ## %bb.0:
; CHECK-NEXT: ucomiss %xmm1, %xmm0
; CHECK-NEXT: je LBB8_2
; CHECK-NEXT: ## %bb.1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB8_2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
%1 = fcmp ueq float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -111,9 +175,16 @@ bb1:
}
define i32 @fcmp_ugt(float %x, float %y) {
; CHECK-LABEL: fcmp_ugt
; CHECK: ucomiss %xmm0, %xmm1
; CHECK-NEXT: jae {{LBB.+_1}}
; CHECK-LABEL: fcmp_ugt:
; CHECK: ## %bb.0:
; CHECK-NEXT: ucomiss %xmm0, %xmm1
; CHECK-NEXT: jae LBB9_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB9_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = fcmp ugt float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -123,9 +194,16 @@ bb1:
}
define i32 @fcmp_uge(float %x, float %y) {
; CHECK-LABEL: fcmp_uge
; CHECK: ucomiss %xmm0, %xmm1
; CHECK-NEXT: ja {{LBB.+_1}}
; CHECK-LABEL: fcmp_uge:
; CHECK: ## %bb.0:
; CHECK-NEXT: ucomiss %xmm0, %xmm1
; CHECK-NEXT: ja LBB10_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB10_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = fcmp uge float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -135,9 +213,16 @@ bb1:
}
define i32 @fcmp_ult(float %x, float %y) {
; CHECK-LABEL: fcmp_ult
; CHECK: ucomiss %xmm1, %xmm0
; CHECK-NEXT: jae {{LBB.+_1}}
; CHECK-LABEL: fcmp_ult:
; CHECK: ## %bb.0:
; CHECK-NEXT: ucomiss %xmm1, %xmm0
; CHECK-NEXT: jae LBB11_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB11_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = fcmp ult float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -147,9 +232,16 @@ bb1:
}
define i32 @fcmp_ule(float %x, float %y) {
; CHECK-LABEL: fcmp_ule
; CHECK: ucomiss %xmm1, %xmm0
; CHECK-NEXT: ja {{LBB.+_1}}
; CHECK-LABEL: fcmp_ule:
; CHECK: ## %bb.0:
; CHECK-NEXT: ucomiss %xmm1, %xmm0
; CHECK-NEXT: ja LBB12_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB12_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = fcmp ule float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -159,10 +251,17 @@ bb1:
}
define i32 @fcmp_une(float %x, float %y) {
; CHECK-LABEL: fcmp_une
; CHECK: ucomiss %xmm1, %xmm0
; CHECK-NEXT: jne {{LBB.+_2}}
; CHECK-NEXT: jnp {{LBB.+_1}}
; CHECK-LABEL: fcmp_une:
; CHECK: ## %bb.0:
; CHECK-NEXT: ucomiss %xmm1, %xmm0
; CHECK-NEXT: jne LBB13_2
; CHECK-NEXT: jnp LBB13_1
; CHECK-NEXT: LBB13_2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB13_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = fcmp une float %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -172,9 +271,16 @@ bb1:
}
define i32 @icmp_eq(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_eq
; CHECK: cmpl %esi, %edi
; CHECK-NEXT: jne {{LBB.+_1}}
; CHECK-LABEL: icmp_eq:
; CHECK: ## %bb.0:
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: je LBB14_2
; CHECK-NEXT: ## %bb.1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB14_2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
%1 = icmp eq i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -184,9 +290,16 @@ bb1:
}
define i32 @icmp_ne(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_ne
; CHECK: cmpl %esi, %edi
; CHECK-NEXT: je {{LBB.+_1}}
; CHECK-LABEL: icmp_ne:
; CHECK: ## %bb.0:
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: je LBB15_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB15_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = icmp ne i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -196,9 +309,16 @@ bb1:
}
define i32 @icmp_ugt(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_ugt
; CHECK: cmpl %esi, %edi
; CHECK-NEXT: jbe {{LBB.+_1}}
; CHECK-LABEL: icmp_ugt:
; CHECK: ## %bb.0:
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: jbe LBB16_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB16_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = icmp ugt i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -208,9 +328,16 @@ bb1:
}
define i32 @icmp_uge(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_uge
; CHECK: cmpl %esi, %edi
; CHECK-NEXT: jb {{LBB.+_1}}
; CHECK-LABEL: icmp_uge:
; CHECK: ## %bb.0:
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: jae LBB17_2
; CHECK-NEXT: ## %bb.1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB17_2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
%1 = icmp uge i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -220,9 +347,16 @@ bb1:
}
define i32 @icmp_ult(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_ult
; CHECK: cmpl %esi, %edi
; CHECK-NEXT: jae {{LBB.+_1}}
; CHECK-LABEL: icmp_ult:
; CHECK: ## %bb.0:
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: jae LBB18_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB18_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = icmp ult i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -232,9 +366,16 @@ bb1:
}
define i32 @icmp_ule(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_ule
; CHECK: cmpl %esi, %edi
; CHECK-NEXT: ja {{LBB.+_1}}
; CHECK-LABEL: icmp_ule:
; CHECK: ## %bb.0:
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: jbe LBB19_2
; CHECK-NEXT: ## %bb.1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB19_2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
%1 = icmp ule i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -244,9 +385,16 @@ bb1:
}
define i32 @icmp_sgt(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_sgt
; CHECK: cmpl %esi, %edi
; CHECK-NEXT: jle {{LBB.+_1}}
; CHECK-LABEL: icmp_sgt:
; CHECK: ## %bb.0:
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: jle LBB20_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB20_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = icmp sgt i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -256,9 +404,16 @@ bb1:
}
define i32 @icmp_sge(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_sge
; CHECK: cmpl %esi, %edi
; CHECK-NEXT: jl {{LBB.+_1}}
; CHECK-LABEL: icmp_sge:
; CHECK: ## %bb.0:
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: jge LBB21_2
; CHECK-NEXT: ## %bb.1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB21_2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
%1 = icmp sge i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -268,9 +423,16 @@ bb1:
}
define i32 @icmp_slt(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_slt
; CHECK: cmpl %esi, %edi
; CHECK-NEXT: jge {{LBB.+_1}}
; CHECK-LABEL: icmp_slt:
; CHECK: ## %bb.0:
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: jge LBB22_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB22_1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
%1 = icmp slt i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:
@ -280,9 +442,16 @@ bb1:
}
define i32 @icmp_sle(i32 %x, i32 %y) {
; CHECK-LABEL: icmp_sle
; CHECK: cmpl %esi, %edi
; CHECK-NEXT: jg {{LBB.+_1}}
; CHECK-LABEL: icmp_sle:
; CHECK: ## %bb.0:
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: jle LBB23_2
; CHECK-NEXT: ## %bb.1: ## %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retq
; CHECK-NEXT: LBB23_2: ## %bb1
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retq
%1 = icmp sle i32 %x, %y
br i1 %1, label %bb1, label %bb2
bb2:

View File

@ -941,17 +941,17 @@ define void @PR45265(i32 %0, %struct.S* nocapture readonly %1) nounwind {
; X32-SSE2-NEXT: shldl $24, %ebx, %edi
; X32-SSE2-NEXT: xorl %eax, %edi
; X32-SSE2-NEXT: orl %edi, %ecx
; X32-SSE2-NEXT: jne .LBB44_1
; X32-SSE2-NEXT: # %bb.2:
; X32-SSE2-NEXT: popl %esi
; X32-SSE2-NEXT: popl %edi
; X32-SSE2-NEXT: popl %ebx
; X32-SSE2-NEXT: jmp _Z3foov # TAILCALL
; X32-SSE2-NEXT: .LBB44_1:
; X32-SSE2-NEXT: je .LBB44_2
; X32-SSE2-NEXT: # %bb.1:
; X32-SSE2-NEXT: popl %esi
; X32-SSE2-NEXT: popl %edi
; X32-SSE2-NEXT: popl %ebx
; X32-SSE2-NEXT: retl
; X32-SSE2-NEXT: .LBB44_2:
; X32-SSE2-NEXT: popl %esi
; X32-SSE2-NEXT: popl %edi
; X32-SSE2-NEXT: popl %ebx
; X32-SSE2-NEXT: jmp _Z3foov # TAILCALL
;
; X64-AVX2-LABEL: PR45265:
; X64-AVX2: # %bb.0:
@ -964,11 +964,11 @@ define void @PR45265(i32 %0, %struct.S* nocapture readonly %1) nounwind {
; X64-AVX2-NEXT: movq (%rsi,%rcx,4), %rcx
; X64-AVX2-NEXT: shrdq $40, %rdi, %rcx
; X64-AVX2-NEXT: cmpq %rax, %rcx
; X64-AVX2-NEXT: jne .LBB44_1
; X64-AVX2-NEXT: # %bb.2:
; X64-AVX2-NEXT: jmp _Z3foov # TAILCALL
; X64-AVX2-NEXT: .LBB44_1:
; X64-AVX2-NEXT: je .LBB44_2
; X64-AVX2-NEXT: # %bb.1:
; X64-AVX2-NEXT: retq
; X64-AVX2-NEXT: .LBB44_2:
; X64-AVX2-NEXT: jmp _Z3foov # TAILCALL
%3 = sext i32 %0 to i64
%4 = getelementptr inbounds %struct.S, %struct.S* %1, i64 %3
%5 = bitcast %struct.S* %4 to i88*

View File

@ -1,59 +1,183 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple x86_64-unknown-unknown -exception-model sjlj -verify-machineinstrs=0 < %s | FileCheck %s --check-prefix=NUM
; RUN: llc -mtriple x86_64-unknown-unknown -exception-model sjlj -verify-machineinstrs=0 < %s | FileCheck %s --check-prefix=SJLJ
; NUM-COUNT-3: endbr64
;SJLJ: main: # @main
;SJLJ-NEXT: .Lfunc_begin0:
;SJLJ-NEXT: # %bb.0: # %entry
;SJLJ-NEXT: endbr64
;SJLJ-NEXT: pushq %rbp
;SJLJ: callq _Unwind_SjLj_Register
;SJLJ-NEXT: .Ltmp0:
;SJLJ-NEXT: callq _Z3foov
;SJLJ-NEXT: .Ltmp1:
;SJLJ-NEXT: # %bb.1: # %invoke.cont
;SJLJ-NEXT: movl
;SJLJ-NEXT: .LBB0_7: # %return
;SJLJ: callq _Unwind_SjLj_Unregister
;SJLJ: retq
;SJLJ-NEXT: .LBB0_9:
;SJLJ-NEXT: endbr64
;SJLJ-NEXT: movl
;SJLJ-NEXT: cmpl
;SJLJ-NEXT: jb .LBB0_10
;SJLJ-NEXT: # %bb.11:
;SJLJ-NEXT: ud2
;SJLJ-NEXT: .LBB0_10:
;SJLJ-NEXT: leaq .LJTI0_0(%rip), %rcx
;SJLJ-NEXT: jmpq *(%rcx,%rax,8)
;SJLJ-NEXT: .LBB0_2: # %lpad
;SJLJ-NEXT: .Ltmp2:
;SJLJ-NEXT: endbr64
;SJLJ: jne .LBB0_4
;SJLJ-NEXT: # %bb.3: # %catch3
;SJLJ: callq __cxa_begin_catch
;SJLJ: jmp .LBB0_6
;SJLJ-NEXT: .LBB0_4: # %catch.fallthrough
;SJLJ-NEXT: cmpl
;SJLJ-NEXT: jne .LBB0_8
;SJLJ-NEXT: # %bb.5: # %catch
;SJLJ: callq __cxa_begin_catch
;SJLJ: cmpb
;SJLJ-NEXT: .LBB0_6: # %return
;SJLJ: callq __cxa_end_catch
;SJLJ-NEXT: jmp .LBB0_7
;SJLJ-NEXT: .LBB0_8: # %eh.resume
;SJLJ-NEXT: movl
;SJLJ-NEXT: .Lfunc_end0:
;SJLJ: .LJTI0_0:
;SJLJ-NEXT: .quad .LBB0_2
@_ZTIi = external dso_local constant i8*
@_ZTIc = external dso_local constant i8*
; Function Attrs: noinline norecurse optnone uwtable
define dso_local i32 @main() #0 personality i8* bitcast (i32 (...)* @__gxx_personality_sj0 to i8*) {
; NUM-LABEL: main:
; NUM: # %bb.0: # %entry
; NUM-NEXT: endbr64
; NUM-NEXT: pushq %rbp
; NUM-NEXT: movq %rsp, %rbp
; NUM-NEXT: pushq %r15
; NUM-NEXT: pushq %r14
; NUM-NEXT: pushq %r13
; NUM-NEXT: pushq %r12
; NUM-NEXT: pushq %rbx
; NUM-NEXT: subq $120, %rsp
; NUM-NEXT: movl $0, -44(%rbp)
; NUM-NEXT: movq $__gxx_personality_sj0, -120(%rbp)
; NUM-NEXT: movq $GCC_except_table0, -112(%rbp)
; NUM-NEXT: movq %rbp, -104(%rbp)
; NUM-NEXT: movq %rsp, -88(%rbp)
; NUM-NEXT: movq $.LBB0_9, -96(%rbp)
; NUM-NEXT: movl $1, -144(%rbp)
; NUM-NEXT: leaq -152(%rbp), %rdi
; NUM-NEXT: callq _Unwind_SjLj_Register
; NUM-NEXT: .Ltmp0:
; NUM-NEXT: callq _Z3foov
; NUM-NEXT: .Ltmp1:
; NUM-NEXT: # %bb.1: # %invoke.cont
; NUM-NEXT: movl $1, -44(%rbp)
; NUM-NEXT: .LBB0_7: # %return
; NUM-NEXT: movl -44(%rbp), %ebx
; NUM-NEXT: leaq -152(%rbp), %rdi
; NUM-NEXT: callq _Unwind_SjLj_Unregister
; NUM-NEXT: movl %ebx, %eax
; NUM-NEXT: addq $120, %rsp
; NUM-NEXT: popq %rbx
; NUM-NEXT: popq %r12
; NUM-NEXT: popq %r13
; NUM-NEXT: popq %r14
; NUM-NEXT: popq %r15
; NUM-NEXT: popq %rbp
; NUM-NEXT: retq
; NUM-NEXT: .LBB0_9:
; NUM-NEXT: endbr64
; NUM-NEXT: movl -144(%rbp), %eax
; NUM-NEXT: cmpl $1, %eax
; NUM-NEXT: jb .LBB0_10
; NUM-NEXT: # %bb.11:
; NUM-NEXT: ud2
; NUM-NEXT: .LBB0_10:
; NUM-NEXT: leaq {{.*}}(%rip), %rcx
; NUM-NEXT: jmpq *(%rcx,%rax,8)
; NUM-NEXT: .LBB0_2: # %lpad
; NUM-NEXT: .Ltmp2:
; NUM-NEXT: endbr64
; NUM-NEXT: movl -140(%rbp), %ecx
; NUM-NEXT: movl -136(%rbp), %eax
; NUM-NEXT: movq %rcx, -56(%rbp)
; NUM-NEXT: movl %eax, -64(%rbp)
; NUM-NEXT: cmpl $2, %eax
; NUM-NEXT: je .LBB0_3
; NUM-NEXT: # %bb.4: # %catch.fallthrough
; NUM-NEXT: cmpl $1, %eax
; NUM-NEXT: jne .LBB0_8
; NUM-NEXT: # %bb.5: # %catch
; NUM-NEXT: movq -56(%rbp), %rdi
; NUM-NEXT: movl $-1, -144(%rbp)
; NUM-NEXT: callq __cxa_begin_catch
; NUM-NEXT: movb (%rax), %al
; NUM-NEXT: movb %al, -45(%rbp)
; NUM-NEXT: xorl %ecx, %ecx
; NUM-NEXT: cmpb $3, %al
; NUM-NEXT: jmp .LBB0_6
; NUM-NEXT: .LBB0_3: # %catch3
; NUM-NEXT: movq -56(%rbp), %rdi
; NUM-NEXT: movl $-1, -144(%rbp)
; NUM-NEXT: callq __cxa_begin_catch
; NUM-NEXT: movl (%rax), %eax
; NUM-NEXT: movl %eax, -60(%rbp)
; NUM-NEXT: xorl %ecx, %ecx
; NUM-NEXT: cmpl $5, %eax
; NUM-NEXT: .LBB0_6: # %return
; NUM-NEXT: setne %cl
; NUM-NEXT: movl %ecx, -44(%rbp)
; NUM-NEXT: movl $-1, -144(%rbp)
; NUM-NEXT: callq __cxa_end_catch
; NUM-NEXT: jmp .LBB0_7
; NUM-NEXT: .LBB0_8: # %eh.resume
; NUM-NEXT: movl $-1, -144(%rbp)
;
; SJLJ-LABEL: main:
; SJLJ: # %bb.0: # %entry
; SJLJ-NEXT: endbr64
; SJLJ-NEXT: pushq %rbp
; SJLJ-NEXT: movq %rsp, %rbp
; SJLJ-NEXT: pushq %r15
; SJLJ-NEXT: pushq %r14
; SJLJ-NEXT: pushq %r13
; SJLJ-NEXT: pushq %r12
; SJLJ-NEXT: pushq %rbx
; SJLJ-NEXT: subq $120, %rsp
; SJLJ-NEXT: movl $0, -44(%rbp)
; SJLJ-NEXT: movq $__gxx_personality_sj0, -120(%rbp)
; SJLJ-NEXT: movq $GCC_except_table0, -112(%rbp)
; SJLJ-NEXT: movq %rbp, -104(%rbp)
; SJLJ-NEXT: movq %rsp, -88(%rbp)
; SJLJ-NEXT: movq $.LBB0_9, -96(%rbp)
; SJLJ-NEXT: movl $1, -144(%rbp)
; SJLJ-NEXT: leaq -152(%rbp), %rdi
; SJLJ-NEXT: callq _Unwind_SjLj_Register
; SJLJ-NEXT: .Ltmp0:
; SJLJ-NEXT: callq _Z3foov
; SJLJ-NEXT: .Ltmp1:
; SJLJ-NEXT: # %bb.1: # %invoke.cont
; SJLJ-NEXT: movl $1, -44(%rbp)
; SJLJ-NEXT: .LBB0_7: # %return
; SJLJ-NEXT: movl -44(%rbp), %ebx
; SJLJ-NEXT: leaq -152(%rbp), %rdi
; SJLJ-NEXT: callq _Unwind_SjLj_Unregister
; SJLJ-NEXT: movl %ebx, %eax
; SJLJ-NEXT: addq $120, %rsp
; SJLJ-NEXT: popq %rbx
; SJLJ-NEXT: popq %r12
; SJLJ-NEXT: popq %r13
; SJLJ-NEXT: popq %r14
; SJLJ-NEXT: popq %r15
; SJLJ-NEXT: popq %rbp
; SJLJ-NEXT: retq
; SJLJ-NEXT: .LBB0_9:
; SJLJ-NEXT: endbr64
; SJLJ-NEXT: movl -144(%rbp), %eax
; SJLJ-NEXT: cmpl $1, %eax
; SJLJ-NEXT: jb .LBB0_10
; SJLJ-NEXT: # %bb.11:
; SJLJ-NEXT: ud2
; SJLJ-NEXT: .LBB0_10:
; SJLJ-NEXT: leaq {{.*}}(%rip), %rcx
; SJLJ-NEXT: jmpq *(%rcx,%rax,8)
; SJLJ-NEXT: .LBB0_2: # %lpad
; SJLJ-NEXT: .Ltmp2:
; SJLJ-NEXT: endbr64
; SJLJ-NEXT: movl -140(%rbp), %ecx
; SJLJ-NEXT: movl -136(%rbp), %eax
; SJLJ-NEXT: movq %rcx, -56(%rbp)
; SJLJ-NEXT: movl %eax, -64(%rbp)
; SJLJ-NEXT: cmpl $2, %eax
; SJLJ-NEXT: je .LBB0_3
; SJLJ-NEXT: # %bb.4: # %catch.fallthrough
; SJLJ-NEXT: cmpl $1, %eax
; SJLJ-NEXT: jne .LBB0_8
; SJLJ-NEXT: # %bb.5: # %catch
; SJLJ-NEXT: movq -56(%rbp), %rdi
; SJLJ-NEXT: movl $-1, -144(%rbp)
; SJLJ-NEXT: callq __cxa_begin_catch
; SJLJ-NEXT: movb (%rax), %al
; SJLJ-NEXT: movb %al, -45(%rbp)
; SJLJ-NEXT: xorl %ecx, %ecx
; SJLJ-NEXT: cmpb $3, %al
; SJLJ-NEXT: jmp .LBB0_6
; SJLJ-NEXT: .LBB0_3: # %catch3
; SJLJ-NEXT: movq -56(%rbp), %rdi
; SJLJ-NEXT: movl $-1, -144(%rbp)
; SJLJ-NEXT: callq __cxa_begin_catch
; SJLJ-NEXT: movl (%rax), %eax
; SJLJ-NEXT: movl %eax, -60(%rbp)
; SJLJ-NEXT: xorl %ecx, %ecx
; SJLJ-NEXT: cmpl $5, %eax
; SJLJ-NEXT: .LBB0_6: # %return
; SJLJ-NEXT: setne %cl
; SJLJ-NEXT: movl %ecx, -44(%rbp)
; SJLJ-NEXT: movl $-1, -144(%rbp)
; SJLJ-NEXT: callq __cxa_end_catch
; SJLJ-NEXT: jmp .LBB0_7
; SJLJ-NEXT: .LBB0_8: # %eh.resume
; SJLJ-NEXT: movl $-1, -144(%rbp)
entry:
%retval = alloca i32, align 4
%exn.slot = alloca i8*

View File

@ -139,11 +139,12 @@ define i32 @func_l2(i32 %a, i32 %b) nounwind {
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %ecx
; CHECK-NEXT: movl %ecx, %eax
; CHECK-NEXT: subl %edx, %eax
; CHECK-NEXT: jne .LBB8_2
; CHECK-NEXT: # %bb.1: # %if.then
; CHECK-NEXT: je .LBB8_1
; CHECK-NEXT: # %bb.2: # %if.else
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB8_1: # %if.then
; CHECK-NEXT: cmpl %ecx, %edx
; CHECK-NEXT: cmovlel %ecx, %eax
; CHECK-NEXT: .LBB8_2: # %if.else
; CHECK-NEXT: retl
%cmp = icmp eq i32 %b, %a
%sub = sub nsw i32 %a, %b
@ -329,12 +330,13 @@ define i8* @func_r(i8* %base, i32* nocapture %offset, i32 %size) nounwind {
; CHECK-NEXT: movl (%edx), %ecx
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: subl {{[0-9]+}}(%esp), %ecx
; CHECK-NEXT: jl .LBB15_2
; CHECK-NEXT: # %bb.1: # %if.end
; CHECK-NEXT: jge .LBB15_1
; CHECK-NEXT: # %bb.2: # %return
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB15_1: # %if.end
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: movl %ecx, (%edx)
; CHECK-NEXT: addl %ecx, %eax
; CHECK-NEXT: .LBB15_2: # %return
; CHECK-NEXT: retl
entry:
%0 = load i32, i32* %offset, align 8

View File

@ -19,11 +19,7 @@ define i32 @t(i32 %a, i32 %b) nounwind {
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %ecx
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %edx
; CHECK-NEXT: cmpl %ecx, %edx
; CHECK-NEXT: jne .LBB0_2
; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: movl %edx, %eax
; CHECK-NEXT: retl
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: je .LBB0_1
; CHECK-NEXT: .LBB0_2: # %bb.outer
; CHECK-NEXT: # =>This Loop Header: Depth=1
; CHECK-NEXT: # Child Loop BB0_3 Depth 2
@ -49,6 +45,9 @@ define i32 @t(i32 %a, i32 %b) nounwind {
; CHECK-NEXT: jne .LBB0_2
; CHECK-NEXT: .LBB0_6: # %bb17
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB0_1:
; CHECK-NEXT: movl %edx, %eax
; CHECK-NEXT: retl
entry:
%tmp1434 = icmp eq i32 %a, %b ; <i1> [#uses=1]
br i1 %tmp1434, label %bb17, label %bb.outer

View File

@ -110,10 +110,11 @@ define i32 @cross_mbb_phys_cse(i32 %a, i32 %b) nounwind ssp {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: ja .LBB2_2
; CHECK-NEXT: # %bb.1: # %if.end
; CHECK-NEXT: jbe .LBB2_1
; CHECK-NEXT: # %bb.2: # %return
; CHECK-NEXT: retq
; CHECK-NEXT: .LBB2_1: # %if.end
; CHECK-NEXT: sbbl %eax, %eax
; CHECK-NEXT: .LBB2_2: # %return
; CHECK-NEXT: retq
entry:
%cmp = icmp ugt i32 %a, %b

File diff suppressed because it is too large Load Diff

View File

@ -120,16 +120,16 @@ define i32 @length3(i8* %X, i8* %Y) nounwind optsize {
; X86-NEXT: rolw $8, %dx
; X86-NEXT: rolw $8, %si
; X86-NEXT: cmpw %si, %dx
; X86-NEXT: jne .LBB4_3
; X86-NEXT: # %bb.1: # %loadbb1
; X86-NEXT: movzbl 2(%eax), %eax
; X86-NEXT: movzbl 2(%ecx), %ecx
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: jmp .LBB4_2
; X86-NEXT: .LBB4_3: # %res_block
; X86-NEXT: je .LBB4_1
; X86-NEXT: # %bb.3: # %res_block
; X86-NEXT: setae %al
; X86-NEXT: movzbl %al, %eax
; X86-NEXT: leal -1(%eax,%eax), %eax
; X86-NEXT: jmp .LBB4_2
; X86-NEXT: .LBB4_1: # %loadbb1
; X86-NEXT: movzbl 2(%eax), %eax
; X86-NEXT: movzbl 2(%ecx), %ecx
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: .LBB4_2: # %endblock
; X86-NEXT: popl %esi
; X86-NEXT: retl
@ -141,16 +141,16 @@ define i32 @length3(i8* %X, i8* %Y) nounwind optsize {
; X64-NEXT: rolw $8, %ax
; X64-NEXT: rolw $8, %cx
; X64-NEXT: cmpw %cx, %ax
; X64-NEXT: jne .LBB4_3
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movzbl 2(%rdi), %eax
; X64-NEXT: movzbl 2(%rsi), %ecx
; X64-NEXT: subl %ecx, %eax
; X64-NEXT: retq
; X64-NEXT: .LBB4_3: # %res_block
; X64-NEXT: je .LBB4_1
; X64-NEXT: # %bb.3: # %res_block
; X64-NEXT: setae %al
; X64-NEXT: movzbl %al, %eax
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: retq
; X64-NEXT: .LBB4_1: # %loadbb1
; X64-NEXT: movzbl 2(%rdi), %eax
; X64-NEXT: movzbl 2(%rsi), %ecx
; X64-NEXT: subl %ecx, %eax
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 3) nounwind
ret i32 %m
@ -265,16 +265,16 @@ define i32 @length5(i8* %X, i8* %Y) nounwind optsize {
; X86-NEXT: bswapl %edx
; X86-NEXT: bswapl %esi
; X86-NEXT: cmpl %esi, %edx
; X86-NEXT: jne .LBB9_3
; X86-NEXT: # %bb.1: # %loadbb1
; X86-NEXT: movzbl 4(%eax), %eax
; X86-NEXT: movzbl 4(%ecx), %ecx
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: jmp .LBB9_2
; X86-NEXT: .LBB9_3: # %res_block
; X86-NEXT: je .LBB9_1
; X86-NEXT: # %bb.3: # %res_block
; X86-NEXT: setae %al
; X86-NEXT: movzbl %al, %eax
; X86-NEXT: leal -1(%eax,%eax), %eax
; X86-NEXT: jmp .LBB9_2
; X86-NEXT: .LBB9_1: # %loadbb1
; X86-NEXT: movzbl 4(%eax), %eax
; X86-NEXT: movzbl 4(%ecx), %ecx
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: .LBB9_2: # %endblock
; X86-NEXT: popl %esi
; X86-NEXT: retl
@ -286,16 +286,16 @@ define i32 @length5(i8* %X, i8* %Y) nounwind optsize {
; X64-NEXT: bswapl %eax
; X64-NEXT: bswapl %ecx
; X64-NEXT: cmpl %ecx, %eax
; X64-NEXT: jne .LBB9_3
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movzbl 4(%rdi), %eax
; X64-NEXT: movzbl 4(%rsi), %ecx
; X64-NEXT: subl %ecx, %eax
; X64-NEXT: retq
; X64-NEXT: .LBB9_3: # %res_block
; X64-NEXT: je .LBB9_1
; X64-NEXT: # %bb.3: # %res_block
; X64-NEXT: setae %al
; X64-NEXT: movzbl %al, %eax
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: retq
; X64-NEXT: .LBB9_1: # %loadbb1
; X64-NEXT: movzbl 4(%rdi), %eax
; X64-NEXT: movzbl 4(%rsi), %ecx
; X64-NEXT: subl %ecx, %eax
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 5) nounwind
ret i32 %m
@ -334,30 +334,32 @@ define i32 @length8(i8* %X, i8* %Y) nounwind optsize {
; X86-LABEL: length8:
; X86: # %bb.0:
; X86-NEXT: pushl %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: movl (%esi), %ecx
; X86-NEXT: movl (%eax), %edx
; X86-NEXT: movl (%esi), %eax
; X86-NEXT: movl (%edx), %ecx
; X86-NEXT: bswapl %eax
; X86-NEXT: bswapl %ecx
; X86-NEXT: bswapl %edx
; X86-NEXT: cmpl %edx, %ecx
; X86-NEXT: jne .LBB11_2
; X86-NEXT: cmpl %ecx, %eax
; X86-NEXT: jne .LBB11_4
; X86-NEXT: # %bb.1: # %loadbb1
; X86-NEXT: movl 4(%esi), %ecx
; X86-NEXT: movl 4(%eax), %edx
; X86-NEXT: movl 4(%esi), %eax
; X86-NEXT: movl 4(%edx), %ecx
; X86-NEXT: bswapl %eax
; X86-NEXT: bswapl %ecx
; X86-NEXT: bswapl %edx
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: cmpl %edx, %ecx
; X86-NEXT: je .LBB11_3
; X86-NEXT: .LBB11_2: # %res_block
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: cmpl %edx, %ecx
; X86-NEXT: setae %al
; X86-NEXT: leal -1(%eax,%eax), %eax
; X86-NEXT: cmpl %ecx, %eax
; X86-NEXT: je .LBB11_2
; X86-NEXT: .LBB11_4: # %res_block
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: cmpl %ecx, %eax
; X86-NEXT: setae %dl
; X86-NEXT: leal -1(%edx,%edx), %eax
; X86-NEXT: .LBB11_3: # %endblock
; X86-NEXT: popl %esi
; X86-NEXT: retl
; X86-NEXT: .LBB11_2:
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: jmp .LBB11_3
;
; X64-LABEL: length8:
; X64: # %bb.0:
@ -461,26 +463,27 @@ define i32 @length12(i8* %X, i8* %Y) nounwind optsize {
;
; X64-LABEL: length12:
; X64: # %bb.0:
; X64-NEXT: movq (%rdi), %rcx
; X64-NEXT: movq (%rsi), %rdx
; X64-NEXT: movq (%rdi), %rax
; X64-NEXT: movq (%rsi), %rcx
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: bswapq %rdx
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: jne .LBB15_2
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: jne .LBB15_4
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movl 8(%rdi), %ecx
; X64-NEXT: movl 8(%rsi), %edx
; X64-NEXT: movl 8(%rdi), %eax
; X64-NEXT: movl 8(%rsi), %ecx
; X64-NEXT: bswapl %eax
; X64-NEXT: bswapl %ecx
; X64-NEXT: bswapl %edx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: je .LBB15_2
; X64-NEXT: .LBB15_4: # %res_block
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: setae %dl
; X64-NEXT: leal -1(%rdx,%rdx), %eax
; X64-NEXT: retq
; X64-NEXT: .LBB15_2:
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: je .LBB15_3
; X64-NEXT: .LBB15_2: # %res_block
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: setae %al
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: .LBB15_3: # %endblock
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 12) nounwind
ret i32 %m
@ -501,26 +504,27 @@ define i32 @length16(i8* %X, i8* %Y) nounwind optsize {
;
; X64-LABEL: length16:
; X64: # %bb.0:
; X64-NEXT: movq (%rdi), %rcx
; X64-NEXT: movq (%rsi), %rdx
; X64-NEXT: movq (%rdi), %rax
; X64-NEXT: movq (%rsi), %rcx
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: bswapq %rdx
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: jne .LBB16_2
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: jne .LBB16_4
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movq 8(%rdi), %rcx
; X64-NEXT: movq 8(%rsi), %rdx
; X64-NEXT: movq 8(%rdi), %rax
; X64-NEXT: movq 8(%rsi), %rcx
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: bswapq %rdx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: je .LBB16_2
; X64-NEXT: .LBB16_4: # %res_block
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: setae %dl
; X64-NEXT: leal -1(%rdx,%rdx), %eax
; X64-NEXT: retq
; X64-NEXT: .LBB16_2:
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: je .LBB16_3
; X64-NEXT: .LBB16_2: # %res_block
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: setae %al
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: .LBB16_3: # %endblock
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 16) nounwind
ret i32 %m

View File

@ -120,19 +120,19 @@ define i32 @length3(i8* %X, i8* %Y) nounwind !prof !14 {
; X86-NEXT: rolw $8, %dx
; X86-NEXT: rolw $8, %si
; X86-NEXT: cmpw %si, %dx
; X86-NEXT: jne .LBB4_3
; X86-NEXT: # %bb.1: # %loadbb1
; X86-NEXT: movzbl 2(%eax), %eax
; X86-NEXT: movzbl 2(%ecx), %ecx
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: jmp .LBB4_2
; X86-NEXT: .LBB4_3: # %res_block
; X86-NEXT: je .LBB4_1
; X86-NEXT: # %bb.3: # %res_block
; X86-NEXT: setae %al
; X86-NEXT: movzbl %al, %eax
; X86-NEXT: leal -1(%eax,%eax), %eax
; X86-NEXT: .LBB4_2: # %endblock
; X86-NEXT: popl %esi
; X86-NEXT: retl
; X86-NEXT: .LBB4_1: # %loadbb1
; X86-NEXT: movzbl 2(%eax), %eax
; X86-NEXT: movzbl 2(%ecx), %ecx
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: jmp .LBB4_2
;
; X64-LABEL: length3:
; X64: # %bb.0:
@ -141,16 +141,16 @@ define i32 @length3(i8* %X, i8* %Y) nounwind !prof !14 {
; X64-NEXT: rolw $8, %ax
; X64-NEXT: rolw $8, %cx
; X64-NEXT: cmpw %cx, %ax
; X64-NEXT: jne .LBB4_3
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movzbl 2(%rdi), %eax
; X64-NEXT: movzbl 2(%rsi), %ecx
; X64-NEXT: subl %ecx, %eax
; X64-NEXT: retq
; X64-NEXT: .LBB4_3: # %res_block
; X64-NEXT: je .LBB4_1
; X64-NEXT: # %bb.3: # %res_block
; X64-NEXT: setae %al
; X64-NEXT: movzbl %al, %eax
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: retq
; X64-NEXT: .LBB4_1: # %loadbb1
; X64-NEXT: movzbl 2(%rdi), %eax
; X64-NEXT: movzbl 2(%rsi), %ecx
; X64-NEXT: subl %ecx, %eax
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 3) nounwind
ret i32 %m
@ -265,19 +265,19 @@ define i32 @length5(i8* %X, i8* %Y) nounwind !prof !14 {
; X86-NEXT: bswapl %edx
; X86-NEXT: bswapl %esi
; X86-NEXT: cmpl %esi, %edx
; X86-NEXT: jne .LBB9_3
; X86-NEXT: # %bb.1: # %loadbb1
; X86-NEXT: movzbl 4(%eax), %eax
; X86-NEXT: movzbl 4(%ecx), %ecx
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: jmp .LBB9_2
; X86-NEXT: .LBB9_3: # %res_block
; X86-NEXT: je .LBB9_1
; X86-NEXT: # %bb.3: # %res_block
; X86-NEXT: setae %al
; X86-NEXT: movzbl %al, %eax
; X86-NEXT: leal -1(%eax,%eax), %eax
; X86-NEXT: .LBB9_2: # %endblock
; X86-NEXT: popl %esi
; X86-NEXT: retl
; X86-NEXT: .LBB9_1: # %loadbb1
; X86-NEXT: movzbl 4(%eax), %eax
; X86-NEXT: movzbl 4(%ecx), %ecx
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: jmp .LBB9_2
;
; X64-LABEL: length5:
; X64: # %bb.0:
@ -286,16 +286,16 @@ define i32 @length5(i8* %X, i8* %Y) nounwind !prof !14 {
; X64-NEXT: bswapl %eax
; X64-NEXT: bswapl %ecx
; X64-NEXT: cmpl %ecx, %eax
; X64-NEXT: jne .LBB9_3
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movzbl 4(%rdi), %eax
; X64-NEXT: movzbl 4(%rsi), %ecx
; X64-NEXT: subl %ecx, %eax
; X64-NEXT: retq
; X64-NEXT: .LBB9_3: # %res_block
; X64-NEXT: je .LBB9_1
; X64-NEXT: # %bb.3: # %res_block
; X64-NEXT: setae %al
; X64-NEXT: movzbl %al, %eax
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: retq
; X64-NEXT: .LBB9_1: # %loadbb1
; X64-NEXT: movzbl 4(%rdi), %eax
; X64-NEXT: movzbl 4(%rsi), %ecx
; X64-NEXT: subl %ecx, %eax
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 5) nounwind
ret i32 %m
@ -334,30 +334,32 @@ define i32 @length8(i8* %X, i8* %Y) nounwind !prof !14 {
; X86-LABEL: length8:
; X86: # %bb.0:
; X86-NEXT: pushl %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: movl (%esi), %ecx
; X86-NEXT: movl (%eax), %edx
; X86-NEXT: movl (%esi), %eax
; X86-NEXT: movl (%edx), %ecx
; X86-NEXT: bswapl %eax
; X86-NEXT: bswapl %ecx
; X86-NEXT: bswapl %edx
; X86-NEXT: cmpl %edx, %ecx
; X86-NEXT: jne .LBB11_2
; X86-NEXT: # %bb.1: # %loadbb1
; X86-NEXT: movl 4(%esi), %ecx
; X86-NEXT: movl 4(%eax), %edx
; X86-NEXT: bswapl %ecx
; X86-NEXT: bswapl %edx
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: cmpl %edx, %ecx
; X86-NEXT: je .LBB11_3
; X86-NEXT: .LBB11_2: # %res_block
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: cmpl %edx, %ecx
; X86-NEXT: setae %al
; X86-NEXT: leal -1(%eax,%eax), %eax
; X86-NEXT: cmpl %ecx, %eax
; X86-NEXT: je .LBB11_1
; X86-NEXT: .LBB11_4: # %res_block
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: cmpl %ecx, %eax
; X86-NEXT: setae %dl
; X86-NEXT: leal -1(%edx,%edx), %eax
; X86-NEXT: .LBB11_3: # %endblock
; X86-NEXT: popl %esi
; X86-NEXT: retl
; X86-NEXT: .LBB11_1: # %loadbb1
; X86-NEXT: movl 4(%esi), %eax
; X86-NEXT: movl 4(%edx), %ecx
; X86-NEXT: bswapl %eax
; X86-NEXT: bswapl %ecx
; X86-NEXT: cmpl %ecx, %eax
; X86-NEXT: jne .LBB11_4
; X86-NEXT: # %bb.2:
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: jmp .LBB11_3
;
; X64-LABEL: length8:
; X64: # %bb.0:
@ -461,26 +463,27 @@ define i32 @length12(i8* %X, i8* %Y) nounwind !prof !14 {
;
; X64-LABEL: length12:
; X64: # %bb.0:
; X64-NEXT: movq (%rdi), %rcx
; X64-NEXT: movq (%rsi), %rdx
; X64-NEXT: movq (%rdi), %rax
; X64-NEXT: movq (%rsi), %rcx
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: bswapq %rdx
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: jne .LBB15_2
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movl 8(%rdi), %ecx
; X64-NEXT: movl 8(%rsi), %edx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: je .LBB15_1
; X64-NEXT: .LBB15_4: # %res_block
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: setae %dl
; X64-NEXT: leal -1(%rdx,%rdx), %eax
; X64-NEXT: retq
; X64-NEXT: .LBB15_1: # %loadbb1
; X64-NEXT: movl 8(%rdi), %eax
; X64-NEXT: movl 8(%rsi), %ecx
; X64-NEXT: bswapl %eax
; X64-NEXT: bswapl %ecx
; X64-NEXT: bswapl %edx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: jne .LBB15_4
; X64-NEXT: # %bb.2:
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: je .LBB15_3
; X64-NEXT: .LBB15_2: # %res_block
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: setae %al
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: .LBB15_3: # %endblock
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 12) nounwind
ret i32 %m
@ -501,26 +504,27 @@ define i32 @length16(i8* %X, i8* %Y) nounwind !prof !14 {
;
; X64-LABEL: length16:
; X64: # %bb.0:
; X64-NEXT: movq (%rdi), %rcx
; X64-NEXT: movq (%rsi), %rdx
; X64-NEXT: movq (%rdi), %rax
; X64-NEXT: movq (%rsi), %rcx
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: bswapq %rdx
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: jne .LBB16_2
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movq 8(%rdi), %rcx
; X64-NEXT: movq 8(%rsi), %rdx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: je .LBB16_1
; X64-NEXT: .LBB16_4: # %res_block
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: setae %dl
; X64-NEXT: leal -1(%rdx,%rdx), %eax
; X64-NEXT: retq
; X64-NEXT: .LBB16_1: # %loadbb1
; X64-NEXT: movq 8(%rdi), %rax
; X64-NEXT: movq 8(%rsi), %rcx
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: bswapq %rdx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: jne .LBB16_4
; X64-NEXT: # %bb.2:
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: je .LBB16_3
; X64-NEXT: .LBB16_2: # %res_block
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: setae %al
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: .LBB16_3: # %endblock
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 16) nounwind
ret i32 %m

View File

@ -285,19 +285,19 @@ define i32 @length3(i8* %X, i8* %Y) nounwind {
; X86-NEXT: rolw $8, %dx
; X86-NEXT: rolw $8, %si
; X86-NEXT: cmpw %si, %dx
; X86-NEXT: jne .LBB11_3
; X86-NEXT: # %bb.1: # %loadbb1
; X86-NEXT: movzbl 2(%eax), %eax
; X86-NEXT: movzbl 2(%ecx), %ecx
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: popl %esi
; X86-NEXT: retl
; X86-NEXT: .LBB11_3: # %res_block
; X86-NEXT: je .LBB11_1
; X86-NEXT: # %bb.3: # %res_block
; X86-NEXT: setae %al
; X86-NEXT: movzbl %al, %eax
; X86-NEXT: leal -1(%eax,%eax), %eax
; X86-NEXT: popl %esi
; X86-NEXT: retl
; X86-NEXT: .LBB11_1: # %loadbb1
; X86-NEXT: movzbl 2(%eax), %eax
; X86-NEXT: movzbl 2(%ecx), %ecx
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: length3:
; X64: # %bb.0:
@ -306,16 +306,16 @@ define i32 @length3(i8* %X, i8* %Y) nounwind {
; X64-NEXT: rolw $8, %ax
; X64-NEXT: rolw $8, %cx
; X64-NEXT: cmpw %cx, %ax
; X64-NEXT: jne .LBB11_3
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movzbl 2(%rdi), %eax
; X64-NEXT: movzbl 2(%rsi), %ecx
; X64-NEXT: subl %ecx, %eax
; X64-NEXT: retq
; X64-NEXT: .LBB11_3: # %res_block
; X64-NEXT: je .LBB11_1
; X64-NEXT: # %bb.3: # %res_block
; X64-NEXT: setae %al
; X64-NEXT: movzbl %al, %eax
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: retq
; X64-NEXT: .LBB11_1: # %loadbb1
; X64-NEXT: movzbl 2(%rdi), %eax
; X64-NEXT: movzbl 2(%rsi), %ecx
; X64-NEXT: subl %ecx, %eax
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 3) nounwind
ret i32 %m
@ -500,19 +500,19 @@ define i32 @length5(i8* %X, i8* %Y) nounwind {
; X86-NEXT: bswapl %edx
; X86-NEXT: bswapl %esi
; X86-NEXT: cmpl %esi, %edx
; X86-NEXT: jne .LBB18_3
; X86-NEXT: # %bb.1: # %loadbb1
; X86-NEXT: movzbl 4(%eax), %eax
; X86-NEXT: movzbl 4(%ecx), %ecx
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: popl %esi
; X86-NEXT: retl
; X86-NEXT: .LBB18_3: # %res_block
; X86-NEXT: je .LBB18_1
; X86-NEXT: # %bb.3: # %res_block
; X86-NEXT: setae %al
; X86-NEXT: movzbl %al, %eax
; X86-NEXT: leal -1(%eax,%eax), %eax
; X86-NEXT: popl %esi
; X86-NEXT: retl
; X86-NEXT: .LBB18_1: # %loadbb1
; X86-NEXT: movzbl 4(%eax), %eax
; X86-NEXT: movzbl 4(%ecx), %ecx
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: length5:
; X64: # %bb.0:
@ -521,16 +521,16 @@ define i32 @length5(i8* %X, i8* %Y) nounwind {
; X64-NEXT: bswapl %eax
; X64-NEXT: bswapl %ecx
; X64-NEXT: cmpl %ecx, %eax
; X64-NEXT: jne .LBB18_3
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movzbl 4(%rdi), %eax
; X64-NEXT: movzbl 4(%rsi), %ecx
; X64-NEXT: subl %ecx, %eax
; X64-NEXT: retq
; X64-NEXT: .LBB18_3: # %res_block
; X64-NEXT: je .LBB18_1
; X64-NEXT: # %bb.3: # %res_block
; X64-NEXT: setae %al
; X64-NEXT: movzbl %al, %eax
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: retq
; X64-NEXT: .LBB18_1: # %loadbb1
; X64-NEXT: movzbl 4(%rdi), %eax
; X64-NEXT: movzbl 4(%rsi), %ecx
; X64-NEXT: subl %ecx, %eax
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 5) nounwind
ret i32 %m
@ -576,16 +576,16 @@ define i1 @length5_lt(i8* %X, i8* %Y) nounwind {
; X86-NEXT: bswapl %edx
; X86-NEXT: bswapl %esi
; X86-NEXT: cmpl %esi, %edx
; X86-NEXT: jne .LBB20_3
; X86-NEXT: # %bb.1: # %loadbb1
; X86-NEXT: movzbl 4(%eax), %eax
; X86-NEXT: movzbl 4(%ecx), %ecx
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: jmp .LBB20_2
; X86-NEXT: .LBB20_3: # %res_block
; X86-NEXT: je .LBB20_1
; X86-NEXT: # %bb.3: # %res_block
; X86-NEXT: setae %al
; X86-NEXT: movzbl %al, %eax
; X86-NEXT: leal -1(%eax,%eax), %eax
; X86-NEXT: jmp .LBB20_2
; X86-NEXT: .LBB20_1: # %loadbb1
; X86-NEXT: movzbl 4(%eax), %eax
; X86-NEXT: movzbl 4(%ecx), %ecx
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: .LBB20_2: # %endblock
; X86-NEXT: shrl $31, %eax
; X86-NEXT: # kill: def $al killed $al killed $eax
@ -599,20 +599,20 @@ define i1 @length5_lt(i8* %X, i8* %Y) nounwind {
; X64-NEXT: bswapl %eax
; X64-NEXT: bswapl %ecx
; X64-NEXT: cmpl %ecx, %eax
; X64-NEXT: jne .LBB20_3
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movzbl 4(%rdi), %eax
; X64-NEXT: movzbl 4(%rsi), %ecx
; X64-NEXT: subl %ecx, %eax
; X64-NEXT: shrl $31, %eax
; X64-NEXT: # kill: def $al killed $al killed $eax
; X64-NEXT: retq
; X64-NEXT: .LBB20_3: # %res_block
; X64-NEXT: je .LBB20_1
; X64-NEXT: # %bb.3: # %res_block
; X64-NEXT: setae %al
; X64-NEXT: movzbl %al, %eax
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: shrl $31, %eax
; X64-NEXT: # kill: def $al killed $al killed $eax
; X64-NEXT: retq
; X64-NEXT: .LBB20_1: # %loadbb1
; X64-NEXT: movzbl 4(%rdi), %eax
; X64-NEXT: movzbl 4(%rsi), %ecx
; X64-NEXT: subl %ecx, %eax
; X64-NEXT: shrl $31, %eax
; X64-NEXT: # kill: def $al killed $al killed $eax
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 5) nounwind
%c = icmp slt i32 %m, 0
@ -623,53 +623,56 @@ define i32 @length7(i8* %X, i8* %Y) nounwind {
; X86-LABEL: length7:
; X86: # %bb.0:
; X86-NEXT: pushl %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: movl (%esi), %ecx
; X86-NEXT: movl (%eax), %edx
; X86-NEXT: movl (%esi), %eax
; X86-NEXT: movl (%edx), %ecx
; X86-NEXT: bswapl %eax
; X86-NEXT: bswapl %ecx
; X86-NEXT: bswapl %edx
; X86-NEXT: cmpl %edx, %ecx
; X86-NEXT: jne .LBB21_2
; X86-NEXT: cmpl %ecx, %eax
; X86-NEXT: jne .LBB21_4
; X86-NEXT: # %bb.1: # %loadbb1
; X86-NEXT: movl 3(%esi), %ecx
; X86-NEXT: movl 3(%eax), %edx
; X86-NEXT: movl 3(%esi), %eax
; X86-NEXT: movl 3(%edx), %ecx
; X86-NEXT: bswapl %eax
; X86-NEXT: bswapl %ecx
; X86-NEXT: bswapl %edx
; X86-NEXT: cmpl %ecx, %eax
; X86-NEXT: je .LBB21_2
; X86-NEXT: .LBB21_4: # %res_block
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: cmpl %ecx, %eax
; X86-NEXT: setae %dl
; X86-NEXT: leal -1(%edx,%edx), %eax
; X86-NEXT: popl %esi
; X86-NEXT: retl
; X86-NEXT: .LBB21_2:
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: cmpl %edx, %ecx
; X86-NEXT: je .LBB21_3
; X86-NEXT: .LBB21_2: # %res_block
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: cmpl %edx, %ecx
; X86-NEXT: setae %al
; X86-NEXT: leal -1(%eax,%eax), %eax
; X86-NEXT: .LBB21_3: # %endblock
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: length7:
; X64: # %bb.0:
; X64-NEXT: movl (%rdi), %ecx
; X64-NEXT: movl (%rsi), %edx
; X64-NEXT: movl (%rdi), %eax
; X64-NEXT: movl (%rsi), %ecx
; X64-NEXT: bswapl %eax
; X64-NEXT: bswapl %ecx
; X64-NEXT: bswapl %edx
; X64-NEXT: cmpl %edx, %ecx
; X64-NEXT: jne .LBB21_2
; X64-NEXT: cmpl %ecx, %eax
; X64-NEXT: jne .LBB21_4
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movl 3(%rdi), %ecx
; X64-NEXT: movl 3(%rsi), %edx
; X64-NEXT: movl 3(%rdi), %eax
; X64-NEXT: movl 3(%rsi), %ecx
; X64-NEXT: bswapl %eax
; X64-NEXT: bswapl %ecx
; X64-NEXT: bswapl %edx
; X64-NEXT: cmpl %ecx, %eax
; X64-NEXT: je .LBB21_2
; X64-NEXT: .LBB21_4: # %res_block
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: cmpl %ecx, %eax
; X64-NEXT: setae %dl
; X64-NEXT: leal -1(%rdx,%rdx), %eax
; X64-NEXT: retq
; X64-NEXT: .LBB21_2:
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpl %edx, %ecx
; X64-NEXT: je .LBB21_3
; X64-NEXT: .LBB21_2: # %res_block
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpl %edx, %ecx
; X64-NEXT: setae %al
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: .LBB21_3: # %endblock
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 7) nounwind
ret i32 %m
@ -679,55 +682,60 @@ define i1 @length7_lt(i8* %X, i8* %Y) nounwind {
; X86-LABEL: length7_lt:
; X86: # %bb.0:
; X86-NEXT: pushl %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: movl (%esi), %ecx
; X86-NEXT: movl (%eax), %edx
; X86-NEXT: movl (%esi), %eax
; X86-NEXT: movl (%edx), %ecx
; X86-NEXT: bswapl %eax
; X86-NEXT: bswapl %ecx
; X86-NEXT: bswapl %edx
; X86-NEXT: cmpl %edx, %ecx
; X86-NEXT: jne .LBB22_2
; X86-NEXT: cmpl %ecx, %eax
; X86-NEXT: jne .LBB22_4
; X86-NEXT: # %bb.1: # %loadbb1
; X86-NEXT: movl 3(%esi), %ecx
; X86-NEXT: movl 3(%eax), %edx
; X86-NEXT: movl 3(%esi), %eax
; X86-NEXT: movl 3(%edx), %ecx
; X86-NEXT: bswapl %eax
; X86-NEXT: bswapl %ecx
; X86-NEXT: bswapl %edx
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: cmpl %edx, %ecx
; X86-NEXT: je .LBB22_3
; X86-NEXT: .LBB22_2: # %res_block
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: cmpl %edx, %ecx
; X86-NEXT: setae %al
; X86-NEXT: leal -1(%eax,%eax), %eax
; X86-NEXT: cmpl %ecx, %eax
; X86-NEXT: je .LBB22_2
; X86-NEXT: .LBB22_4: # %res_block
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: cmpl %ecx, %eax
; X86-NEXT: setae %dl
; X86-NEXT: leal -1(%edx,%edx), %eax
; X86-NEXT: .LBB22_3: # %endblock
; X86-NEXT: shrl $31, %eax
; X86-NEXT: # kill: def $al killed $al killed $eax
; X86-NEXT: popl %esi
; X86-NEXT: retl
; X86-NEXT: .LBB22_2:
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: jmp .LBB22_3
;
; X64-LABEL: length7_lt:
; X64: # %bb.0:
; X64-NEXT: movl (%rdi), %ecx
; X64-NEXT: movl (%rsi), %edx
; X64-NEXT: movl (%rdi), %eax
; X64-NEXT: movl (%rsi), %ecx
; X64-NEXT: bswapl %eax
; X64-NEXT: bswapl %ecx
; X64-NEXT: bswapl %edx
; X64-NEXT: cmpl %edx, %ecx
; X64-NEXT: cmpl %ecx, %eax
; X64-NEXT: jne .LBB22_2
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movl 3(%rdi), %ecx
; X64-NEXT: movl 3(%rsi), %edx
; X64-NEXT: movl 3(%rdi), %eax
; X64-NEXT: movl 3(%rsi), %ecx
; X64-NEXT: bswapl %eax
; X64-NEXT: bswapl %ecx
; X64-NEXT: bswapl %edx
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpl %edx, %ecx
; X64-NEXT: cmpl %ecx, %eax
; X64-NEXT: je .LBB22_3
; X64-NEXT: .LBB22_2: # %res_block
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: cmpl %ecx, %eax
; X64-NEXT: setae %dl
; X64-NEXT: leal -1(%rdx,%rdx), %eax
; X64-NEXT: shrl $31, %eax
; X64-NEXT: # kill: def $al killed $al killed $eax
; X64-NEXT: retq
; X64-NEXT: .LBB22_3:
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpl %edx, %ecx
; X64-NEXT: setae %al
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: .LBB22_3: # %endblock
; X64-NEXT: shrl $31, %eax
; X64-NEXT: # kill: def $al killed $al killed $eax
; X64-NEXT: retq
@ -767,28 +775,30 @@ define i32 @length8(i8* %X, i8* %Y) nounwind {
; X86-LABEL: length8:
; X86: # %bb.0:
; X86-NEXT: pushl %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: movl (%esi), %ecx
; X86-NEXT: movl (%eax), %edx
; X86-NEXT: movl (%esi), %eax
; X86-NEXT: movl (%edx), %ecx
; X86-NEXT: bswapl %eax
; X86-NEXT: bswapl %ecx
; X86-NEXT: bswapl %edx
; X86-NEXT: cmpl %edx, %ecx
; X86-NEXT: jne .LBB24_2
; X86-NEXT: cmpl %ecx, %eax
; X86-NEXT: jne .LBB24_4
; X86-NEXT: # %bb.1: # %loadbb1
; X86-NEXT: movl 4(%esi), %ecx
; X86-NEXT: movl 4(%eax), %edx
; X86-NEXT: movl 4(%esi), %eax
; X86-NEXT: movl 4(%edx), %ecx
; X86-NEXT: bswapl %eax
; X86-NEXT: bswapl %ecx
; X86-NEXT: bswapl %edx
; X86-NEXT: cmpl %ecx, %eax
; X86-NEXT: je .LBB24_2
; X86-NEXT: .LBB24_4: # %res_block
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: cmpl %ecx, %eax
; X86-NEXT: setae %dl
; X86-NEXT: leal -1(%edx,%edx), %eax
; X86-NEXT: popl %esi
; X86-NEXT: retl
; X86-NEXT: .LBB24_2:
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: cmpl %edx, %ecx
; X86-NEXT: je .LBB24_3
; X86-NEXT: .LBB24_2: # %res_block
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: cmpl %edx, %ecx
; X86-NEXT: setae %al
; X86-NEXT: leal -1(%eax,%eax), %eax
; X86-NEXT: .LBB24_3: # %endblock
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
@ -977,26 +987,27 @@ define i32 @length12(i8* %X, i8* %Y) nounwind {
;
; X64-LABEL: length12:
; X64: # %bb.0:
; X64-NEXT: movq (%rdi), %rcx
; X64-NEXT: movq (%rsi), %rdx
; X64-NEXT: movq (%rdi), %rax
; X64-NEXT: movq (%rsi), %rcx
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: bswapq %rdx
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: jne .LBB31_2
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: jne .LBB31_4
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movl 8(%rdi), %ecx
; X64-NEXT: movl 8(%rsi), %edx
; X64-NEXT: movl 8(%rdi), %eax
; X64-NEXT: movl 8(%rsi), %ecx
; X64-NEXT: bswapl %eax
; X64-NEXT: bswapl %ecx
; X64-NEXT: bswapl %edx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: je .LBB31_2
; X64-NEXT: .LBB31_4: # %res_block
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: setae %dl
; X64-NEXT: leal -1(%rdx,%rdx), %eax
; X64-NEXT: retq
; X64-NEXT: .LBB31_2:
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: je .LBB31_3
; X64-NEXT: .LBB31_2: # %res_block
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: setae %al
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: .LBB31_3: # %endblock
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 12) nounwind
ret i32 %m
@ -1069,26 +1080,27 @@ define i32 @length15(i8* %X, i8* %Y) nounwind {
;
; X64-LABEL: length15:
; X64: # %bb.0:
; X64-NEXT: movq (%rdi), %rcx
; X64-NEXT: movq (%rsi), %rdx
; X64-NEXT: movq (%rdi), %rax
; X64-NEXT: movq (%rsi), %rcx
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: bswapq %rdx
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: jne .LBB34_2
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: jne .LBB34_4
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movq 7(%rdi), %rcx
; X64-NEXT: movq 7(%rsi), %rdx
; X64-NEXT: movq 7(%rdi), %rax
; X64-NEXT: movq 7(%rsi), %rcx
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: bswapq %rdx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: je .LBB34_2
; X64-NEXT: .LBB34_4: # %res_block
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: setae %dl
; X64-NEXT: leal -1(%rdx,%rdx), %eax
; X64-NEXT: retq
; X64-NEXT: .LBB34_2:
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: je .LBB34_3
; X64-NEXT: .LBB34_2: # %res_block
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: setae %al
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: .LBB34_3: # %endblock
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 15) nounwind
ret i32 %m
@ -1109,26 +1121,29 @@ define i1 @length15_lt(i8* %X, i8* %Y) nounwind {
;
; X64-LABEL: length15_lt:
; X64: # %bb.0:
; X64-NEXT: movq (%rdi), %rcx
; X64-NEXT: movq (%rsi), %rdx
; X64-NEXT: movq (%rdi), %rax
; X64-NEXT: movq (%rsi), %rcx
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: bswapq %rdx
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: jne .LBB35_2
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movq 7(%rdi), %rcx
; X64-NEXT: movq 7(%rsi), %rdx
; X64-NEXT: movq 7(%rdi), %rax
; X64-NEXT: movq 7(%rsi), %rcx
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: bswapq %rdx
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: je .LBB35_3
; X64-NEXT: .LBB35_2: # %res_block
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: setae %dl
; X64-NEXT: leal -1(%rdx,%rdx), %eax
; X64-NEXT: shrl $31, %eax
; X64-NEXT: # kill: def $al killed $al killed $eax
; X64-NEXT: retq
; X64-NEXT: .LBB35_3:
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: setae %al
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: .LBB35_3: # %endblock
; X64-NEXT: shrl $31, %eax
; X64-NEXT: # kill: def $al killed $al killed $eax
; X64-NEXT: retq
@ -1256,26 +1271,27 @@ define i32 @length16(i8* %X, i8* %Y) nounwind {
;
; X64-LABEL: length16:
; X64: # %bb.0:
; X64-NEXT: movq (%rdi), %rcx
; X64-NEXT: movq (%rsi), %rdx
; X64-NEXT: movq (%rdi), %rax
; X64-NEXT: movq (%rsi), %rcx
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: bswapq %rdx
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: jne .LBB39_2
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: jne .LBB39_4
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movq 8(%rdi), %rcx
; X64-NEXT: movq 8(%rsi), %rdx
; X64-NEXT: movq 8(%rdi), %rax
; X64-NEXT: movq 8(%rsi), %rcx
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: bswapq %rdx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: je .LBB39_2
; X64-NEXT: .LBB39_4: # %res_block
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: setae %dl
; X64-NEXT: leal -1(%rdx,%rdx), %eax
; X64-NEXT: retq
; X64-NEXT: .LBB39_2:
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: je .LBB39_3
; X64-NEXT: .LBB39_2: # %res_block
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: setae %al
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: .LBB39_3: # %endblock
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 16) nounwind
ret i32 %m
@ -1385,26 +1401,29 @@ define i1 @length16_lt(i8* %x, i8* %y) nounwind {
;
; X64-LABEL: length16_lt:
; X64: # %bb.0:
; X64-NEXT: movq (%rdi), %rcx
; X64-NEXT: movq (%rsi), %rdx
; X64-NEXT: movq (%rdi), %rax
; X64-NEXT: movq (%rsi), %rcx
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: bswapq %rdx
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: jne .LBB41_2
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movq 8(%rdi), %rcx
; X64-NEXT: movq 8(%rsi), %rdx
; X64-NEXT: movq 8(%rdi), %rax
; X64-NEXT: movq 8(%rsi), %rcx
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: bswapq %rdx
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: je .LBB41_3
; X64-NEXT: .LBB41_2: # %res_block
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: setae %dl
; X64-NEXT: leal -1(%rdx,%rdx), %eax
; X64-NEXT: shrl $31, %eax
; X64-NEXT: # kill: def $al killed $al killed $eax
; X64-NEXT: retq
; X64-NEXT: .LBB41_3:
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpq %rdx, %rcx
; X64-NEXT: setae %al
; X64-NEXT: leal -1(%rax,%rax), %eax
; X64-NEXT: .LBB41_3: # %endblock
; X64-NEXT: shrl $31, %eax
; X64-NEXT: # kill: def $al killed $al killed $eax
; X64-NEXT: retq
@ -1433,24 +1452,26 @@ define i1 @length16_gt(i8* %x, i8* %y) nounwind {
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: jne .LBB42_2
; X64-NEXT: jne .LBB42_4
; X64-NEXT: # %bb.1: # %loadbb1
; X64-NEXT: movq 8(%rdi), %rax
; X64-NEXT: movq 8(%rsi), %rcx
; X64-NEXT: bswapq %rax
; X64-NEXT: bswapq %rcx
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: je .LBB42_3
; X64-NEXT: .LBB42_2: # %res_block
; X64-NEXT: je .LBB42_2
; X64-NEXT: .LBB42_4: # %res_block
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: cmpq %rcx, %rax
; X64-NEXT: setae %dl
; X64-NEXT: leal -1(%rdx,%rdx), %edx
; X64-NEXT: leal -1(%rdx,%rdx), %eax
; X64-NEXT: .LBB42_3: # %endblock
; X64-NEXT: testl %edx, %edx
; X64-NEXT: testl %eax, %eax
; X64-NEXT: setg %al
; X64-NEXT: retq
; X64-NEXT: .LBB42_2:
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: jmp .LBB42_3
%call = tail call i32 @memcmp(i8* %x, i8* %y, i64 16) nounwind
%cmp = icmp sgt i32 %call, 0
ret i1 %cmp

View File

@ -10,11 +10,11 @@ define void @neg_cmp(i32 %x, i32 %y) nounwind {
; CHECK-LABEL: neg_cmp:
; CHECK: # %bb.0:
; CHECK-NEXT: addl %esi, %edi
; CHECK-NEXT: jne .LBB0_1
; CHECK-NEXT: # %bb.2: # %if.then
; CHECK-NEXT: jmp g # TAILCALL
; CHECK-NEXT: .LBB0_1: # %if.end
; CHECK-NEXT: je .LBB0_2
; CHECK-NEXT: # %bb.1: # %if.end
; CHECK-NEXT: retq
; CHECK-NEXT: .LBB0_2: # %if.then
; CHECK-NEXT: jmp g # TAILCALL
%sub = sub i32 0, %y
%cmp = icmp eq i32 %x, %sub
br i1 %cmp, label %if.then, label %if.end
@ -31,11 +31,11 @@ define void @neg_cmp_commuted(i32 %x, i32 %y) nounwind {
; CHECK-LABEL: neg_cmp_commuted:
; CHECK: # %bb.0:
; CHECK-NEXT: addl %esi, %edi
; CHECK-NEXT: jne .LBB1_1
; CHECK-NEXT: # %bb.2: # %if.then
; CHECK-NEXT: jmp g # TAILCALL
; CHECK-NEXT: .LBB1_1: # %if.end
; CHECK-NEXT: je .LBB1_2
; CHECK-NEXT: # %bb.1: # %if.end
; CHECK-NEXT: retq
; CHECK-NEXT: .LBB1_2: # %if.then
; CHECK-NEXT: jmp g # TAILCALL
%sub = sub i32 0, %y
%cmp = icmp eq i32 %sub, %x
br i1 %cmp, label %if.then, label %if.end

View File

@ -9,10 +9,11 @@ define void @test2(i32 %x, i32 %n) nounwind {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testb %al, %al
; CHECK-NEXT: jne .LBB0_2
; CHECK-NEXT: # %bb.1: # %bb
; CHECK-NEXT: je .LBB0_1
; CHECK-NEXT: # %bb.2: # %UnifiedReturnBlock
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB0_1: # %bb
; CHECK-NEXT: calll foo
; CHECK-NEXT: .LBB0_2: # %UnifiedReturnBlock
; CHECK-NEXT: retl
entry:
%tmp1 = and i32 %x, 1
@ -34,10 +35,11 @@ define void @test3(i32 %x, i32 %n) nounwind {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testb %al, %al
; CHECK-NEXT: jne .LBB1_2
; CHECK-NEXT: # %bb.1: # %bb
; CHECK-NEXT: je .LBB1_1
; CHECK-NEXT: # %bb.2: # %UnifiedReturnBlock
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB1_1: # %bb
; CHECK-NEXT: calll foo
; CHECK-NEXT: .LBB1_2: # %UnifiedReturnBlock
; CHECK-NEXT: retl
entry:
%tmp1 = and i32 %x, 1

View File

@ -11,8 +11,11 @@ define i32 @main() {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testb %al, %al
; CHECK-NEXT: jne .LBB0_3
; CHECK-NEXT: # %bb.1: # %go
; CHECK-NEXT: je .LBB0_1
; CHECK-NEXT: .LBB0_3: # %if.else
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB0_1: # %go
; CHECK-NEXT: movl $-1, %ecx
; CHECK-NEXT: movsbl b, %edx
; CHECK-NEXT: notl %ecx
@ -23,9 +26,6 @@ define i32 @main() {
; CHECK-NEXT: # %bb.2: # %if.then
; CHECK-NEXT: movl $42, %eax
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB0_3: # %if.else
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retl
entry:
%true = icmp eq i32 0, 0
%const = bitcast i64 -4294967296 to i64

View File

@ -9,13 +9,13 @@ define i32 @branch_eq(i64 %a, i64 %b) {
; CHECK-NEXT: xorl {{[0-9]+}}(%esp), %ecx
; CHECK-NEXT: xorl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: orl %ecx, %eax
; CHECK-NEXT: jne .LBB0_2
; CHECK-NEXT: # %bb.1: # %bb1
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB0_2: # %bb2
; CHECK-NEXT: je .LBB0_1
; CHECK-NEXT: # %bb.2: # %bb2
; CHECK-NEXT: movl $2, %eax
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB0_1: # %bb1
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retl
entry:
%cmp = icmp eq i64 %a, %b
br i1 %cmp, label %bb1, label %bb2
@ -55,13 +55,13 @@ define i32 @branch_ule(i64 %a, i64 %b) {
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %ecx
; CHECK-NEXT: cmpl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: sbbl {{[0-9]+}}(%esp), %ecx
; CHECK-NEXT: jb .LBB2_2
; CHECK-NEXT: # %bb.1: # %bb1
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB2_2: # %bb2
; CHECK-NEXT: jae .LBB2_1
; CHECK-NEXT: # %bb.2: # %bb2
; CHECK-NEXT: movl $2, %eax
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB2_1: # %bb1
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retl
entry:
%cmp = icmp ule i64 %a, %b
br i1 %cmp, label %bb1, label %bb2

View File

@ -16,8 +16,11 @@
; ASM: .cv_loc 0 1 3 9 # t.c:3:9
; ASM: movl %ecx, %eax
; ASM: cmpl %edx, %ecx
; ASM: jl [[EPILOGUE:LBB0_[0-9]+]]
; ASM: jge LBB0_1
; ASM: retl $8
; ASM: LBB0_1:
; ASM: pushl %ebx
; ASM: .cv_fpo_pushreg %ebx
; ASM: pushl %edi
@ -31,9 +34,7 @@
; ASM: popl %esi
; ASM: popl %edi
; ASM: popl %ebx
; ASM: [[EPILOGUE]]: # %return
; ASM: retl $8
; ASM: Ltmp10:
; ASM: Ltmp11:
; ASM: .cv_fpo_endproc
; Note how RvaStart advances 7 bytes to skip the shrink-wrapped portion.
@ -41,7 +42,7 @@
; OBJ: FrameData {
; OBJ: RvaStart: 0x0
; OBJ: CodeSize: 0x36
; OBJ: PrologSize: 0x9
; OBJ: PrologSize: 0xC
; OBJ: FrameFunc [
; OBJ-NEXT: $T0 .raSearch =
; OBJ-NEXT: $eip $T0 ^ =
@ -49,8 +50,8 @@
; OBJ-NEXT: ]
; OBJ: }
; OBJ: FrameData {
; OBJ: RvaStart: 0x7
; OBJ: CodeSize: 0x2F
; OBJ: RvaStart: 0xA
; OBJ: CodeSize: 0x2C
; OBJ: PrologSize: 0x2
; OBJ: FrameFunc [
; OBJ-NEXT: $T0 .raSearch =
@ -60,8 +61,8 @@
; OBJ-NEXT: ]
; OBJ: }
; OBJ: FrameData {
; OBJ: RvaStart: 0x8
; OBJ: CodeSize: 0x2E
; OBJ: RvaStart: 0xB
; OBJ: CodeSize: 0x2B
; OBJ: PrologSize: 0x1
; OBJ: FrameFunc [
; OBJ-NEXT: $T0 .raSearch =
@ -72,8 +73,8 @@
; OBJ-NEXT: ]
; OBJ: }
; OBJ: FrameData {
; OBJ: RvaStart: 0x9
; OBJ: CodeSize: 0x2D
; OBJ: RvaStart: 0xC
; OBJ: CodeSize: 0x2A
; OBJ: PrologSize: 0x0
; OBJ: FrameFunc [
; OBJ-NEXT: $T0 .raSearch =

View File

@ -1,27 +1,95 @@
; RUN: opt < %s -pgo-instr-gen -instrprof -do-counter-promotion=true -speculative-counter-promotion-max-exiting=3 -S | FileCheck --check-prefix=PROMO %s
; RUN: opt < %s --passes=pgo-instr-gen,instrprof -do-counter-promotion=true -speculative-counter-promotion-max-exiting=3 -S | FileCheck --check-prefix=PROMO %s
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -pgo-instr-gen -instrprof -do-counter-promotion=true -speculative-counter-promotion-max-exiting=3 -S | FileCheck %s --check-prefix=PROMO
; RUN: opt < %s --passes=pgo-instr-gen,instrprof -do-counter-promotion=true -speculative-counter-promotion-max-exiting=3 -S | FileCheck %s --check-prefix=PROMO
@g = common local_unnamed_addr global i32 0, align 4
define void @foo(i32 %arg) local_unnamed_addr {
; PROMO-LABEL: @foo
; PROMO-LABEL: @foo(
; PROMO-NEXT: bb:
; PROMO-NEXT: [[T:%.*]] = add nsw i32 [[ARG:%.*]], -1
; PROMO-NEXT: br label [[BB1:%.*]]
; PROMO: bb1:
; PROMO-NEXT: [[PGOCOUNT213:%.*]] = phi i64 [ 0, [[BB:%.*]] ], [ [[PGOCOUNT212:%.*]], [[BB11:%.*]] ]
; PROMO-NEXT: [[PGOCOUNT19:%.*]] = phi i64 [ 0, [[BB]] ], [ [[PGOCOUNT18:%.*]], [[BB11]] ]
; PROMO-NEXT: [[PGOCOUNT6:%.*]] = phi i64 [ 0, [[BB]] ], [ [[PGOCOUNT5:%.*]], [[BB11]] ]
; PROMO-NEXT: [[T2:%.*]] = phi i32 [ 0, [[BB]] ], [ [[T12:%.*]], [[BB11]] ]
; PROMO-NEXT: [[T3:%.*]] = icmp sgt i32 [[T2]], [[ARG]]
; PROMO-NEXT: br i1 [[T3]], label [[BB7:%.*]], label [[BB4:%.*]]
; PROMO: bb4:
; PROMO-NEXT: [[TMP0:%.*]] = add i64 [[PGOCOUNT6]], 1
; PROMO-NEXT: tail call void @bar(i32 1)
; PROMO-NEXT: [[T5:%.*]] = load i32, i32* @g, align 4
; PROMO-NEXT: [[T6:%.*]] = icmp sgt i32 [[T5]], 100
; PROMO-NEXT: br i1 [[T6]], label [[BB15_0:%.*]], label [[BB11]]
; PROMO: bb7:
; PROMO-NEXT: [[T8:%.*]] = icmp slt i32 [[T2]], [[T]]
; PROMO-NEXT: br i1 [[T8]], label [[BB9:%.*]], label [[BB10:%.*]]
; PROMO: bb9:
; PROMO-NEXT: [[TMP1:%.*]] = add i64 [[PGOCOUNT19]], 1
; PROMO-NEXT: tail call void @bar(i32 2)
; PROMO-NEXT: br label [[BB11]]
; PROMO: bb10:
; PROMO-NEXT: [[TMP2:%.*]] = add i64 [[PGOCOUNT213]], 1
; PROMO-NEXT: tail call void @bar(i32 3)
; PROMO-NEXT: br label [[BB11]]
; PROMO: bb11:
; PROMO-NEXT: [[PGOCOUNT212]] = phi i64 [ [[TMP2]], [[BB10]] ], [ [[PGOCOUNT213]], [[BB9]] ], [ [[PGOCOUNT213]], [[BB4]] ]
; PROMO-NEXT: [[PGOCOUNT18]] = phi i64 [ [[PGOCOUNT19]], [[BB10]] ], [ [[TMP1]], [[BB9]] ], [ [[PGOCOUNT19]], [[BB4]] ]
; PROMO-NEXT: [[PGOCOUNT5]] = phi i64 [ [[PGOCOUNT6]], [[BB10]] ], [ [[PGOCOUNT6]], [[BB9]] ], [ [[TMP0]], [[BB4]] ]
; PROMO-NEXT: [[T12]] = add nuw nsw i32 [[T2]], 1
; PROMO-NEXT: [[T13:%.*]] = icmp slt i32 [[T2]], 99
; PROMO-NEXT: br i1 [[T13]], label [[BB1]], label [[BB14:%.*]]
; PROMO: bb14:
; PROMO-NEXT: [[PGOCOUNT_PROMOTED7:%.*]] = load i64, i64* getelementptr inbounds ([5 x i64], [5 x i64]* @__profc_foo, i64 0, i64 1), align 4
; PROMO-NEXT: [[TMP3:%.*]] = add i64 [[PGOCOUNT_PROMOTED7]], [[PGOCOUNT5]]
; PROMO-NEXT: store i64 [[TMP3]], i64* getelementptr inbounds ([5 x i64], [5 x i64]* @__profc_foo, i64 0, i64 1), align 4
; PROMO-NEXT: [[PGOCOUNT_PROMOTED11:%.*]] = load i64, i64* getelementptr inbounds ([5 x i64], [5 x i64]* @__profc_foo, i64 0, i64 0), align 4
; PROMO-NEXT: [[TMP4:%.*]] = add i64 [[PGOCOUNT_PROMOTED11]], [[PGOCOUNT18]]
; PROMO-NEXT: store i64 [[TMP4]], i64* getelementptr inbounds ([5 x i64], [5 x i64]* @__profc_foo, i64 0, i64 0), align 4
; PROMO-NEXT: [[PGOCOUNT_PROMOTED15:%.*]] = load i64, i64* getelementptr inbounds ([5 x i64], [5 x i64]* @__profc_foo, i64 0, i64 2), align 4
; PROMO-NEXT: [[TMP5:%.*]] = add i64 [[PGOCOUNT_PROMOTED15]], [[PGOCOUNT212]]
; PROMO-NEXT: store i64 [[TMP5]], i64* getelementptr inbounds ([5 x i64], [5 x i64]* @__profc_foo, i64 0, i64 2), align 4
; PROMO-NEXT: [[PGOCOUNT3:%.*]] = load i64, i64* getelementptr inbounds ([5 x i64], [5 x i64]* @__profc_foo, i64 0, i64 3), align 4
; PROMO-NEXT: [[TMP6:%.*]] = add i64 [[PGOCOUNT3]], 1
; PROMO-NEXT: store i64 [[TMP6]], i64* getelementptr inbounds ([5 x i64], [5 x i64]* @__profc_foo, i64 0, i64 3), align 4
; PROMO-NEXT: tail call void @bar(i32 0)
; PROMO-NEXT: br label [[BB15:%.*]]
; PROMO: bb15_0:
; PROMO-NEXT: [[PGOCOUNT_PROMOTED:%.*]] = load i64, i64* getelementptr inbounds ([5 x i64], [5 x i64]* @__profc_foo, i64 0, i64 1), align 4
; PROMO-NEXT: [[TMP7:%.*]] = add i64 [[PGOCOUNT_PROMOTED]], [[TMP0]]
; PROMO-NEXT: store i64 [[TMP7]], i64* getelementptr inbounds ([5 x i64], [5 x i64]* @__profc_foo, i64 0, i64 1), align 4
; PROMO-NEXT: [[PGOCOUNT_PROMOTED10:%.*]] = load i64, i64* getelementptr inbounds ([5 x i64], [5 x i64]* @__profc_foo, i64 0, i64 0), align 4
; PROMO-NEXT: [[TMP8:%.*]] = add i64 [[PGOCOUNT_PROMOTED10]], [[PGOCOUNT19]]
; PROMO-NEXT: store i64 [[TMP8]], i64* getelementptr inbounds ([5 x i64], [5 x i64]* @__profc_foo, i64 0, i64 0), align 4
; PROMO-NEXT: [[PGOCOUNT_PROMOTED14:%.*]] = load i64, i64* getelementptr inbounds ([5 x i64], [5 x i64]* @__profc_foo, i64 0, i64 2), align 4
; PROMO-NEXT: [[TMP9:%.*]] = add i64 [[PGOCOUNT_PROMOTED14]], [[PGOCOUNT213]]
; PROMO-NEXT: store i64 [[TMP9]], i64* getelementptr inbounds ([5 x i64], [5 x i64]* @__profc_foo, i64 0, i64 2), align 4
; PROMO-NEXT: [[PGOCOUNT4:%.*]] = load i64, i64* getelementptr inbounds ([5 x i64], [5 x i64]* @__profc_foo, i64 0, i64 4), align 4
; PROMO-NEXT: [[TMP10:%.*]] = add i64 [[PGOCOUNT4]], 1
; PROMO-NEXT: store i64 [[TMP10]], i64* getelementptr inbounds ([5 x i64], [5 x i64]* @__profc_foo, i64 0, i64 4), align 4
; PROMO-NEXT: br label [[BB15]]
; PROMO: bb15:
; PROMO-NEXT: tail call void @bar(i32 1)
; PROMO-NEXT: ret void
;
bb:
%tmp = add nsw i32 %arg, -1
%t = add nsw i32 %arg, -1
br label %bb1
bb1: ; preds = %bb11, %bb
%tmp2 = phi i32 [ 0, %bb ], [ %tmp12, %bb11 ]
%tmp3 = icmp sgt i32 %tmp2, %arg
br i1 %tmp3, label %bb7, label %bb4
%t2 = phi i32 [ 0, %bb ], [ %t12, %bb11 ]
%t3 = icmp sgt i32 %t2, %arg
br i1 %t3, label %bb7, label %bb4
bb4: ; preds = %bb1
tail call void @bar(i32 1)
%tmp5 = load i32, i32* @g, align 4
%tmp6 = icmp sgt i32 %tmp5, 100
br i1 %tmp6, label %bb15_0, label %bb11
%t5 = load i32, i32* @g, align 4
%t6 = icmp sgt i32 %t5, 100
br i1 %t6, label %bb15_0, label %bb11
bb7: ; preds = %bb1
%tmp8 = icmp slt i32 %tmp2, %tmp
br i1 %tmp8, label %bb9, label %bb10
%t8 = icmp slt i32 %t2, %t
br i1 %t8, label %bb9, label %bb10
bb9: ; preds = %bb7
tail call void @bar(i32 2)
@ -32,45 +100,18 @@ bb10: ; preds = %bb7
br label %bb11
bb11: ; preds = %bb10, %bb9, %bb4
%tmp12 = add nuw nsw i32 %tmp2, 1
%tmp13 = icmp slt i32 %tmp2, 99
br i1 %tmp13, label %bb1, label %bb14
%t12 = add nuw nsw i32 %t2, 1
%t13 = icmp slt i32 %t2, 99
br i1 %t13, label %bb1, label %bb14
bb14: ; preds = %bb11
; PROMO-LABEL: bb14:
tail call void @bar(i32 0)
br label %bb15
; PROMO: %pgocount.promoted{{.*}} = load {{.*}} @__profc_foo{{.*}} 0)
; PROMO-NEXT: add
; PROMO-NEXT: store {{.*}}@__profc_foo{{.*}}0)
; PROMO-NEXT: %pgocount.promoted{{.*}} = load {{.*}} @__profc_foo{{.*}} 1)
; PROMO-NEXT: add
; PROMO-NEXT: store {{.*}}@__profc_foo{{.*}}1)
; PROMO-NEXT: %pgocount.promoted{{.*}} = load {{.*}} @__profc_foo{{.*}} 2)
; PROMO-NEXT: add
; PROMO-NEXT: store {{.*}}@__profc_foo{{.*}}2)
; PROMO-NEXT: %pgocount{{.*}} = load {{.*}} @__profc_foo{{.*}} 3)
; PROMO-NEXT: add
; PROMO-NEXT: store {{.*}}@__profc_foo{{.*}}3)
bb15_0: ; preds = %bb11
; PROMO-LABEL: bb15_0:
br label %bb15
; PROMO: %pgocount.promoted{{.*}} = load {{.*}} @__profc_foo{{.*}} 0)
; PROMO-NEXT: add
; PROMO-NEXT: store {{.*}}@__profc_foo{{.*}}0)
; PROMO-NEXT: %pgocount.promoted{{.*}} = load {{.*}} @__profc_foo{{.*}} 1)
; PROMO-NEXT: add
; PROMO-NEXT: store {{.*}}@__profc_foo{{.*}}1)
; PROMO-NEXT: %pgocount.promoted{{.*}} = load {{.*}} @__profc_foo{{.*}} 2)
; PROMO-NEXT: add
; PROMO-NEXT: store {{.*}}@__profc_foo{{.*}}2)
; PROMO-NEXT: %pgocount{{.*}} = load {{.*}} @__profc_foo{{.*}} 4)
; PROMO-NEXT: add
; PROMO-NEXT: store {{.*}}@__profc_foo{{.*}}4)
; PROMO-NOT: @__profc_foo
bb15: ; preds = %bb14, %bb4
tail call void @bar(i32 1)

View File

@ -85,7 +85,8 @@ catch.dispatch:
; GEN: catch.dispatch:
; GEN-NOT: call void @llvm.instrprof.increment
%tmp3 = call i32 @llvm.eh.typeid.for(i8* bitcast (i8** @_ZTIi to i8*))
%matches = icmp eq i32 %tmp2, %tmp3
%c = icmp ne i32 %tmp2, %tmp3
%matches = xor i1 %c, -1
br i1 %matches, label %catch, label %eh.resume
; USE: br i1 %matches, label %catch, label %eh.resume
; USE-SAME: !prof ![[BW_CATCH_DISPATCH:[0-9]+]]