AMDGPU: Fix handling of constant phi input loop conditions

If the loop condition was an i1 phi with a constantexpr input, this
would add a loop intrinsic fed by a phi dependent on a call to
if.break in the same block. Insert the call in the loop header.

llvm-svn: 298121
This commit is contained in:
Matt Arsenault 2017-03-17 20:52:21 +00:00
parent 8e06e80b87
commit e70d5dcf3e
2 changed files with 266 additions and 5 deletions

View File

@ -220,7 +220,7 @@ Value *SIAnnotateControlFlow::handleLoopCondition(Value *Cond, PHINode *Broken,
if ((Phi = dyn_cast<PHINode>(Cond)) && L->contains(Phi)) {
BasicBlock *Parent = Phi->getParent();
PHINode *NewPhi = PHINode::Create(Int64, 0, "", &Parent->front());
PHINode *NewPhi = PHINode::Create(Int64, 0, "loop.phi", &Parent->front());
Value *Ret = NewPhi;
// Handle all non-constant incoming values first
@ -293,10 +293,13 @@ Value *SIAnnotateControlFlow::handleLoopCondition(Value *Cond, PHINode *Broken,
return CallInst::Create(IfBreak, Args, "", Insert);
}
// Insert IfBreak before TERM for constant COND.
if (isa<ConstantInt>(Cond)) {
// Insert IfBreak in the loop header TERM for constant COND other than true.
if (isa<Constant>(Cond)) {
Instruction *Insert = Cond == BoolTrue ?
Term : L->getHeader()->getTerminator();
Value *Args[] = { Cond, Broken };
return CallInst::Create(IfBreak, Args, "", Term);
return CallInst::Create(IfBreak, Args, "", Insert);
}
llvm_unreachable("Unhandled loop condition!");
@ -313,7 +316,7 @@ void SIAnnotateControlFlow::handleLoop(BranchInst *Term) {
return;
BasicBlock *Target = Term->getSuccessor(1);
PHINode *Broken = PHINode::Create(Int64, 0, "", &Target->front());
PHINode *Broken = PHINode::Create(Int64, 0, "phi.broken", &Target->front());
Value *Cond = Term->getCondition();
Term->setCondition(BoolTrue);

View File

@ -64,6 +64,264 @@ bb9:
ret void
}
; OPT-LABEL: @undef_phi_cond_break_loop(
; OPT: bb1:
; OPT-NEXT: %phi.broken = phi i64 [ %loop.phi, %Flow ], [ 0, %bb ]
; OPT-NEXT: %lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
; OPT: %0 = call i64 @llvm.amdgcn.if.break(i1 undef, i64 %phi.broken)
; OPT-NEXT: br i1 %cmp0, label %bb4, label %Flow
; OPT: bb4:
; OPT-NEXT: %load = load volatile i32, i32 addrspace(1)* undef, align 4
; OPT-NEXT: %cmp1 = icmp sge i32 %tmp, %load
; OPT-NEXT: %1 = call i64 @llvm.amdgcn.if.break(i1 %cmp1, i64 %phi.broken)
; OPT-NEXT: br label %Flow
; OPT: Flow:
; OPT-NEXT: %loop.phi = phi i64 [ %1, %bb4 ], [ %0, %bb1 ]
; OPT-NEXT: %tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
; OPT-NEXT: %2 = call i1 @llvm.amdgcn.loop(i64 %loop.phi)
; OPT-NEXT: br i1 %2, label %bb9, label %bb1
; OPT: bb9: ; preds = %Flow
; OPT-NEXT: call void @llvm.amdgcn.end.cf(i64 %loop.phi)
; OPT-NEXT: store volatile i32 7
; OPT-NEXT: ret void
define void @undef_phi_cond_break_loop(i32 %arg) #0 {
bb:
%id = call i32 @llvm.amdgcn.workitem.id.x()
%tmp = sub i32 %id, %arg
br label %bb1
bb1: ; preds = %Flow, %bb
%lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
%lsr.iv.next = add i32 %lsr.iv, 1
%cmp0 = icmp slt i32 %lsr.iv.next, 0
br i1 %cmp0, label %bb4, label %Flow
bb4: ; preds = %bb1
%load = load volatile i32, i32 addrspace(1)* undef, align 4
%cmp1 = icmp sge i32 %tmp, %load
br label %Flow
Flow: ; preds = %bb4, %bb1
%tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
%tmp3 = phi i1 [ %cmp1, %bb4 ], [ undef, %bb1 ]
br i1 %tmp3, label %bb9, label %bb1
bb9: ; preds = %Flow
store volatile i32 7, i32 addrspace(3)* undef
ret void
}
; FIXME: ConstantExpr compare of address to null folds away
@lds = addrspace(3) global i32 undef
; OPT-LABEL: @constexpr_phi_cond_break_loop(
; OPT: bb1:
; OPT-NEXT: %phi.broken = phi i64 [ %loop.phi, %Flow ], [ 0, %bb ]
; OPT-NEXT: %lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
; OPT: %0 = call i64 @llvm.amdgcn.if.break(i1 icmp ne (i32 addrspace(3)* inttoptr (i32 4 to i32 addrspace(3)*), i32 addrspace(3)* @lds), i64 %phi.broken)
; OPT-NEXT: br i1 %cmp0, label %bb4, label %Flow
; OPT: bb4:
; OPT-NEXT: %load = load volatile i32, i32 addrspace(1)* undef, align 4
; OPT-NEXT: %cmp1 = icmp sge i32 %tmp, %load
; OPT-NEXT: %1 = call i64 @llvm.amdgcn.if.break(i1 %cmp1, i64 %phi.broken)
; OPT-NEXT: br label %Flow
; OPT: Flow:
; OPT-NEXT: %loop.phi = phi i64 [ %1, %bb4 ], [ %0, %bb1 ]
; OPT-NEXT: %tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
; OPT-NEXT: %2 = call i1 @llvm.amdgcn.loop(i64 %loop.phi)
; OPT-NEXT: br i1 %2, label %bb9, label %bb1
; OPT: bb9: ; preds = %Flow
; OPT-NEXT: call void @llvm.amdgcn.end.cf(i64 %loop.phi)
; OPT-NEXT: store volatile i32 7
; OPT-NEXT: ret void
define void @constexpr_phi_cond_break_loop(i32 %arg) #0 {
bb:
%id = call i32 @llvm.amdgcn.workitem.id.x()
%tmp = sub i32 %id, %arg
br label %bb1
bb1: ; preds = %Flow, %bb
%lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
%lsr.iv.next = add i32 %lsr.iv, 1
%cmp0 = icmp slt i32 %lsr.iv.next, 0
br i1 %cmp0, label %bb4, label %Flow
bb4: ; preds = %bb1
%load = load volatile i32, i32 addrspace(1)* undef, align 4
%cmp1 = icmp sge i32 %tmp, %load
br label %Flow
Flow: ; preds = %bb4, %bb1
%tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
%tmp3 = phi i1 [ %cmp1, %bb4 ], [ icmp ne (i32 addrspace(3)* inttoptr (i32 4 to i32 addrspace(3)*), i32 addrspace(3)* @lds), %bb1 ]
br i1 %tmp3, label %bb9, label %bb1
bb9: ; preds = %Flow
store volatile i32 7, i32 addrspace(3)* undef
ret void
}
; OPT-LABEL: @true_phi_cond_break_loop(
; OPT: bb1:
; OPT-NEXT: %phi.broken = phi i64 [ %loop.phi, %Flow ], [ 0, %bb ]
; OPT-NEXT: %lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
; OPT: %0 = call i64 @llvm.amdgcn.break(i64 %phi.broken)
; OPT: br i1 %cmp0, label %bb4, label %Flow
; OPT: bb4:
; OPT-NEXT: %load = load volatile i32, i32 addrspace(1)* undef, align 4
; OPT-NEXT: %cmp1 = icmp sge i32 %tmp, %load
; OPT-NEXT: %1 = call i64 @llvm.amdgcn.if.break(i1 %cmp1, i64 %phi.broken)
; OPT-NEXT: br label %Flow
; OPT: Flow:
; OPT-NEXT: %loop.phi = phi i64 [ %1, %bb4 ], [ %0, %bb1 ]
; OPT-NEXT: %tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
; OPT-NEXT: %2 = call i1 @llvm.amdgcn.loop(i64 %loop.phi)
; OPT-NEXT: br i1 %2, label %bb9, label %bb1
; OPT: bb9: ; preds = %Flow
; OPT-NEXT: call void @llvm.amdgcn.end.cf(i64 %loop.phi)
; OPT-NEXT: store volatile i32 7
; OPT-NEXT: ret void
define void @true_phi_cond_break_loop(i32 %arg) #0 {
bb:
%id = call i32 @llvm.amdgcn.workitem.id.x()
%tmp = sub i32 %id, %arg
br label %bb1
bb1: ; preds = %Flow, %bb
%lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
%lsr.iv.next = add i32 %lsr.iv, 1
%cmp0 = icmp slt i32 %lsr.iv.next, 0
br i1 %cmp0, label %bb4, label %Flow
bb4: ; preds = %bb1
%load = load volatile i32, i32 addrspace(1)* undef, align 4
%cmp1 = icmp sge i32 %tmp, %load
br label %Flow
Flow: ; preds = %bb4, %bb1
%tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
%tmp3 = phi i1 [ %cmp1, %bb4 ], [ true, %bb1 ]
br i1 %tmp3, label %bb9, label %bb1
bb9: ; preds = %Flow
store volatile i32 7, i32 addrspace(3)* undef
ret void
}
; OPT-LABEL: @false_phi_cond_break_loop(
; OPT: bb1:
; OPT-NEXT: %phi.broken = phi i64 [ %loop.phi, %Flow ], [ 0, %bb ]
; OPT-NEXT: %lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
; OPT-NOT: call
; OPT: br i1 %cmp0, label %bb4, label %Flow
; OPT: bb4:
; OPT-NEXT: %load = load volatile i32, i32 addrspace(1)* undef, align 4
; OPT-NEXT: %cmp1 = icmp sge i32 %tmp, %load
; OPT-NEXT: %0 = call i64 @llvm.amdgcn.if.break(i1 %cmp1, i64 %phi.broken)
; OPT-NEXT: br label %Flow
; OPT: Flow:
; OPT-NEXT: %loop.phi = phi i64 [ %0, %bb4 ], [ %phi.broken, %bb1 ]
; OPT-NEXT: %tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
; OPT-NEXT: %1 = call i1 @llvm.amdgcn.loop(i64 %loop.phi)
; OPT-NEXT: br i1 %1, label %bb9, label %bb1
; OPT: bb9: ; preds = %Flow
; OPT-NEXT: call void @llvm.amdgcn.end.cf(i64 %loop.phi)
; OPT-NEXT: store volatile i32 7
; OPT-NEXT: ret void
define void @false_phi_cond_break_loop(i32 %arg) #0 {
bb:
%id = call i32 @llvm.amdgcn.workitem.id.x()
%tmp = sub i32 %id, %arg
br label %bb1
bb1: ; preds = %Flow, %bb
%lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
%lsr.iv.next = add i32 %lsr.iv, 1
%cmp0 = icmp slt i32 %lsr.iv.next, 0
br i1 %cmp0, label %bb4, label %Flow
bb4: ; preds = %bb1
%load = load volatile i32, i32 addrspace(1)* undef, align 4
%cmp1 = icmp sge i32 %tmp, %load
br label %Flow
Flow: ; preds = %bb4, %bb1
%tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
%tmp3 = phi i1 [ %cmp1, %bb4 ], [ false, %bb1 ]
br i1 %tmp3, label %bb9, label %bb1
bb9: ; preds = %Flow
store volatile i32 7, i32 addrspace(3)* undef
ret void
}
; Swap order of branches in flow block so that the true phi is
; continue.
; OPT-LABEL: @invert_true_phi_cond_break_loop(
; OPT: bb1:
; OPT-NEXT: %phi.broken = phi i64 [ %1, %Flow ], [ 0, %bb ]
; OPT-NEXT: %lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
; OPT-NEXT: %lsr.iv.next = add i32 %lsr.iv, 1
; OPT-NEXT: %cmp0 = icmp slt i32 %lsr.iv.next, 0
; OPT-NEXT: br i1 %cmp0, label %bb4, label %Flow
; OPT: bb4:
; OPT-NEXT: %load = load volatile i32, i32 addrspace(1)* undef, align 4
; OPT-NEXT: %cmp1 = icmp sge i32 %tmp, %load
; OPT-NEXT: br label %Flow
; OPT: Flow:
; OPT-NEXT: %tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
; OPT-NEXT: %tmp3 = phi i1 [ %cmp1, %bb4 ], [ true, %bb1 ]
; OPT-NEXT: %0 = xor i1 %tmp3, true
; OPT-NEXT: %1 = call i64 @llvm.amdgcn.if.break(i1 %0, i64 %phi.broken)
; OPT-NEXT: %2 = call i1 @llvm.amdgcn.loop(i64 %1)
; OPT-NEXT: br i1 %2, label %bb9, label %bb1
; OPT: bb9:
; OPT-NEXT: call void @llvm.amdgcn.end.cf(i64 %1)
; OPT-NEXT: store volatile i32 7, i32 addrspace(3)* undef
; OPT-NEXT: ret void
define void @invert_true_phi_cond_break_loop(i32 %arg) #0 {
bb:
%id = call i32 @llvm.amdgcn.workitem.id.x()
%tmp = sub i32 %id, %arg
br label %bb1
bb1: ; preds = %Flow, %bb
%lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
%lsr.iv.next = add i32 %lsr.iv, 1
%cmp0 = icmp slt i32 %lsr.iv.next, 0
br i1 %cmp0, label %bb4, label %Flow
bb4: ; preds = %bb1
%load = load volatile i32, i32 addrspace(1)* undef, align 4
%cmp1 = icmp sge i32 %tmp, %load
br label %Flow
Flow: ; preds = %bb4, %bb1
%tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
%tmp3 = phi i1 [ %cmp1, %bb4 ], [ true, %bb1 ]
br i1 %tmp3, label %bb1, label %bb9
bb9: ; preds = %Flow
store volatile i32 7, i32 addrspace(3)* undef
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x() #1
attributes #0 = { nounwind }