; BranchFolding should tail-merge the stores since they all precede
; direct branches to the same place.
-; CHECK: tail_merge_me:
+; CHECK-LABEL: tail_merge_me:
; CHECK-NOT: GHJK
; CHECK: movl $0, GHJK(%rip)
; CHECK-NEXT: movl $1, HABC(%rip)
ret void
}
-declare i8* @choose(i8*, i8*);
+declare i8* @choose(i8*, i8*)
; BranchFolding should tail-duplicate the indirect jump to avoid
; redundant branching.
-; CHECK: tail_duplicate_me:
+; CHECK-LABEL: tail_duplicate_me:
; CHECK: movl $0, GHJK(%rip)
-; CHECK-NEXT: jmpq *%rbx
+; CHECK-NEXT: jmpq *%r
; CHECK: movl $0, GHJK(%rip)
-; CHECK-NEXT: jmpq *%rbx
+; CHECK-NEXT: jmpq *%r
; CHECK: movl $0, GHJK(%rip)
-; CHECK-NEXT: jmpq *%rbx
+; CHECK-NEXT: jmpq *%r
define void @tail_duplicate_me() nounwind {
entry:
; BranchFolding shouldn't try to merge the tails of two blocks
; with only a branch in common, regardless of the fallthrough situation.
-; CHECK: dont_merge_oddly:
+; CHECK-LABEL: dont_merge_oddly:
; CHECK-NOT: ret
-; CHECK: ucomiss %xmm0, %xmm1
-; CHECK-NEXT: jbe .LBB3_3
-; CHECK-NEXT: ucomiss %xmm2, %xmm0
-; CHECK-NEXT: ja .LBB3_4
-; CHECK-NEXT: .LBB3_2:
-; CHECK-NEXT: movb $1, %al
+; CHECK: ucomiss %xmm{{[0-2]}}, %xmm{{[0-2]}}
+; CHECK-NEXT: jbe .LBB2_3
+; CHECK-NEXT: ucomiss %xmm{{[0-2]}}, %xmm{{[0-2]}}
+; CHECK-NEXT: ja .LBB2_4
+; CHECK-NEXT: jmp .LBB2_2
+; CHECK-NEXT: .LBB2_3:
+; CHECK-NEXT: ucomiss %xmm{{[0-2]}}, %xmm{{[0-2]}}
+; CHECK-NEXT: jbe .LBB2_2
+; CHECK-NEXT: .LBB2_4:
+; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: ret
-; CHECK-NEXT: .LBB3_3:
-; CHECK-NEXT: ucomiss %xmm2, %xmm1
-; CHECK-NEXT: jbe .LBB3_2
-; CHECK-NEXT: .LBB3_4:
-; CHECK-NEXT: xorb %al, %al
+; CHECK-NEXT: .LBB2_2:
+; CHECK-NEXT: movb $1, %al
; CHECK-NEXT: ret
define i1 @dont_merge_oddly(float* %result) nounwind {
entry:
- %tmp4 = getelementptr float* %result, i32 2
- %tmp5 = load float* %tmp4, align 4
- %tmp7 = getelementptr float* %result, i32 4
- %tmp8 = load float* %tmp7, align 4
- %tmp10 = getelementptr float* %result, i32 6
- %tmp11 = load float* %tmp10, align 4
+ %tmp4 = getelementptr float, float* %result, i32 2
+ %tmp5 = load float, float* %tmp4, align 4
+ %tmp7 = getelementptr float, float* %result, i32 4
+ %tmp8 = load float, float* %tmp7, align 4
+ %tmp10 = getelementptr float, float* %result, i32 6
+ %tmp11 = load float, float* %tmp10, align 4
%tmp12 = fcmp olt float %tmp8, %tmp11
br i1 %tmp12, label %bb, label %bb21
; Do any-size tail-merging when two candidate blocks will both require
; an unconditional jump to complete a two-way conditional branch.
-; CHECK: c_expand_expr_stmt:
-; CHECK: jmp .LBB4_7
-; CHECK-NEXT: .LBB4_12:
-; CHECK-NEXT: movq 8(%rax), %rax
-; CHECK-NEXT: movb 16(%rax), %al
-; CHECK-NEXT: cmpb $16, %al
-; CHECK-NEXT: je .LBB4_6
-; CHECK-NEXT: cmpb $23, %al
-; CHECK-NEXT: je .LBB4_6
-; CHECK-NEXT: jmp .LBB4_15
-; CHECK-NEXT: .LBB4_14:
-; CHECK-NEXT: cmpb $23, %bl
-; CHECK-NEXT: jne .LBB4_15
-; CHECK-NEXT: .LBB4_15:
+; CHECK-LABEL: c_expand_expr_stmt:
+;
+; This test only works when register allocation happens to use %rax for both
+; load addresses.
+;
+; CHE: jmp .LBB3_11
+; CHE-NEXT: .LBB3_9:
+; CHE-NEXT: movq 8(%rax), %rax
+; CHE-NEXT: xorl %edx, %edx
+; CHE-NEXT: movb 16(%rax), %al
+; CHE-NEXT: cmpb $16, %al
+; CHE-NEXT: je .LBB3_11
+; CHE-NEXT: cmpb $23, %al
+; CHE-NEXT: jne .LBB3_14
+; CHE-NEXT: .LBB3_11:
%0 = type { %struct.rtx_def* }
%struct.lang_decl = type opaque
define fastcc void @c_expand_expr_stmt(%union.tree_node* %expr) nounwind {
entry:
- %tmp4 = load i8* null, align 8 ; <i8> [#uses=3]
+ %tmp4 = load i8, i8* null, align 8 ; <i8> [#uses=3]
switch i8 %tmp4, label %bb3 [
i8 18, label %bb
]
br label %bb3
lvalue_p.exit: ; preds = %bb.i
- %tmp21 = load %union.tree_node** null, align 8 ; <%union.tree_node*> [#uses=3]
- %tmp22 = getelementptr inbounds %union.tree_node* %tmp21, i64 0, i32 0, i32 0, i64 0 ; <i8*> [#uses=1]
- %tmp23 = load i8* %tmp22, align 8 ; <i8> [#uses=1]
+ %tmp21 = load %union.tree_node*, %union.tree_node** null, align 8 ; <%union.tree_node*> [#uses=3]
+ %tmp22 = getelementptr inbounds %union.tree_node, %union.tree_node* %tmp21, i64 0, i32 0, i32 0, i64 0 ; <i8*> [#uses=1]
+ %tmp23 = load i8, i8* %tmp22, align 8 ; <i8> [#uses=1]
%tmp24 = zext i8 %tmp23 to i32 ; <i32> [#uses=1]
switch i32 %tmp24, label %lvalue_p.exit4 [
i32 0, label %bb2.i3
]
bb.i1: ; preds = %lvalue_p.exit
- %tmp25 = getelementptr inbounds %union.tree_node* %tmp21, i64 0, i32 0, i32 2 ; <i32*> [#uses=1]
+ %tmp25 = getelementptr inbounds %union.tree_node, %union.tree_node* %tmp21, i64 0, i32 0, i32 2 ; <i32*> [#uses=1]
%tmp26 = bitcast i32* %tmp25 to %union.tree_node** ; <%union.tree_node**> [#uses=1]
- %tmp27 = load %union.tree_node** %tmp26, align 8 ; <%union.tree_node*> [#uses=2]
- %tmp28 = getelementptr inbounds %union.tree_node* %tmp27, i64 0, i32 0, i32 0, i64 16 ; <i8*> [#uses=1]
- %tmp29 = load i8* %tmp28, align 8 ; <i8> [#uses=1]
+ %tmp27 = load %union.tree_node*, %union.tree_node** %tmp26, align 8 ; <%union.tree_node*> [#uses=2]
+ %tmp28 = getelementptr inbounds %union.tree_node, %union.tree_node* %tmp27, i64 0, i32 0, i32 0, i64 16 ; <i8*> [#uses=1]
+ %tmp29 = load i8, i8* %tmp28, align 8 ; <i8> [#uses=1]
%tmp30 = zext i8 %tmp29 to i32 ; <i32> [#uses=1]
switch i32 %tmp30, label %lvalue_p.exit4 [
i32 0, label %bb2.i.i2
br label %lvalue_p.exit4
bb2.i.i2: ; preds = %bb.i1
- %tmp35 = getelementptr inbounds %union.tree_node* %tmp27, i64 0, i32 0, i32 0, i64 8 ; <i8*> [#uses=1]
+ %tmp35 = getelementptr inbounds %union.tree_node, %union.tree_node* %tmp27, i64 0, i32 0, i32 0, i64 8 ; <i8*> [#uses=1]
%tmp36 = bitcast i8* %tmp35 to %union.tree_node** ; <%union.tree_node**> [#uses=1]
- %tmp37 = load %union.tree_node** %tmp36, align 8 ; <%union.tree_node*> [#uses=1]
- %tmp38 = getelementptr inbounds %union.tree_node* %tmp37, i64 0, i32 0, i32 0, i64 16 ; <i8*> [#uses=1]
- %tmp39 = load i8* %tmp38, align 8 ; <i8> [#uses=1]
+ %tmp37 = load %union.tree_node*, %union.tree_node** %tmp36, align 8 ; <%union.tree_node*> [#uses=1]
+ %tmp38 = getelementptr inbounds %union.tree_node, %union.tree_node* %tmp37, i64 0, i32 0, i32 0, i64 16 ; <i8*> [#uses=1]
+ %tmp39 = load i8, i8* %tmp38, align 8 ; <i8> [#uses=1]
switch i8 %tmp39, label %bb2 [
i8 16, label %lvalue_p.exit4
i8 23, label %lvalue_p.exit4
]
bb2.i3: ; preds = %lvalue_p.exit
- %tmp40 = getelementptr inbounds %union.tree_node* %tmp21, i64 0, i32 0, i32 0, i64 8 ; <i8*> [#uses=1]
+ %tmp40 = getelementptr inbounds %union.tree_node, %union.tree_node* %tmp21, i64 0, i32 0, i32 0, i64 8 ; <i8*> [#uses=1]
%tmp41 = bitcast i8* %tmp40 to %union.tree_node** ; <%union.tree_node**> [#uses=1]
- %tmp42 = load %union.tree_node** %tmp41, align 8 ; <%union.tree_node*> [#uses=1]
- %tmp43 = getelementptr inbounds %union.tree_node* %tmp42, i64 0, i32 0, i32 0, i64 16 ; <i8*> [#uses=1]
- %tmp44 = load i8* %tmp43, align 8 ; <i8> [#uses=1]
+ %tmp42 = load %union.tree_node*, %union.tree_node** %tmp41, align 8 ; <%union.tree_node*> [#uses=1]
+ %tmp43 = getelementptr inbounds %union.tree_node, %union.tree_node* %tmp42, i64 0, i32 0, i32 0, i64 16 ; <i8*> [#uses=1]
+ %tmp44 = load i8, i8* %tmp43, align 8 ; <i8> [#uses=1]
switch i8 %tmp44, label %bb2 [
i8 16, label %lvalue_p.exit4
i8 23, label %lvalue_p.exit4
; instructions are involved. This function should have only
; one ret instruction.
-; CHECK: foo:
+; CHECK-LABEL: foo:
; CHECK: callq func
-; CHECK-NEXT: .LBB5_2:
-; CHECK-NEXT: addq $8, %rsp
+; CHECK-NEXT: .LBB4_2:
+; CHECK-NEXT: popq
; CHECK-NEXT: ret
define void @foo(i1* %V) nounwind {
; one - One instruction may be tail-duplicated even with optsize.
-; CHECK: one:
+; CHECK-LABEL: one:
; CHECK: movl $0, XYZ(%rip)
; CHECK: movl $0, XYZ(%rip)
]
bb7:
- volatile store i32 0, i32* @XYZ
+ store volatile i32 0, i32* @XYZ
unreachable
bbx:
]
bb12:
- volatile store i32 0, i32* @XYZ
+ store volatile i32 0, i32* @XYZ
unreachable
return:
; tail instead of one. This is too much to be merged, given
; the optsize attribute.
-; CHECK: two:
+; CHECK-LABEL: two:
; CHECK-NOT: XYZ
+; CHECK: ret
; CHECK: movl $0, XYZ(%rip)
; CHECK: movl $1, XYZ(%rip)
; CHECK-NOT: XYZ
-; CHECK: ret
define void @two() nounwind optsize {
entry:
]
bb7:
- volatile store i32 0, i32* @XYZ
- volatile store i32 1, i32* @XYZ
+ store volatile i32 0, i32* @XYZ
+ store volatile i32 1, i32* @XYZ
unreachable
bbx:
]
bb12:
- volatile store i32 0, i32* @XYZ
- volatile store i32 1, i32* @XYZ
+ store volatile i32 0, i32* @XYZ
+ store volatile i32 1, i32* @XYZ
+ unreachable
+
+return:
+ ret void
+}
+
+; two_minsize - Same as two, but with minsize instead of optsize.
+
+; CHECK-LABEL: two_minsize:
+; CHECK-NOT: XYZ
+; CHECK: ret
+; CHECK: movl $0, XYZ(%rip)
+; CHECK: movl $1, XYZ(%rip)
+; CHECK-NOT: XYZ
+
+define void @two_minsize() nounwind minsize {
+entry:
+ %0 = icmp eq i32 undef, 0
+ br i1 %0, label %bbx, label %bby
+
+bby:
+ switch i32 undef, label %bb7 [
+ i32 16, label %return
+ ]
+
+bb7:
+ store volatile i32 0, i32* @XYZ
+ store volatile i32 1, i32* @XYZ
+ unreachable
+
+bbx:
+ switch i32 undef, label %bb12 [
+ i32 128, label %return
+ ]
+
+bb12:
+ store volatile i32 0, i32* @XYZ
+ store volatile i32 1, i32* @XYZ
unreachable
return:
; two_nosize - Same as two, but without the optsize attribute.
; Now two instructions are enough to be tail-duplicated.
-; CHECK: two_nosize:
+; CHECK-LABEL: two_nosize:
; CHECK: movl $0, XYZ(%rip)
; CHECK: movl $1, XYZ(%rip)
; CHECK: movl $0, XYZ(%rip)
]
bb7:
- volatile store i32 0, i32* @XYZ
- volatile store i32 1, i32* @XYZ
+ store volatile i32 0, i32* @XYZ
+ store volatile i32 1, i32* @XYZ
unreachable
bbx:
]
bb12:
- volatile store i32 0, i32* @XYZ
- volatile store i32 1, i32* @XYZ
+ store volatile i32 0, i32* @XYZ
+ store volatile i32 1, i32* @XYZ
unreachable
return:
ret void
}
+
+; Tail-merging should merge the two ret instructions since one side
+; can fall-through into the ret and the other side has to branch anyway.
+
+; CHECK-LABEL: TESTE:
+; CHECK: ret
+; CHECK-NOT: ret
+; CHECK: size TESTE
+
+define i64 @TESTE(i64 %parami, i64 %paraml) nounwind readnone {
+entry:
+ %cmp = icmp slt i64 %parami, 1 ; <i1> [#uses=1]
+ %varx.0 = select i1 %cmp, i64 1, i64 %parami ; <i64> [#uses=1]
+ %cmp410 = icmp slt i64 %paraml, 1 ; <i1> [#uses=1]
+ br i1 %cmp410, label %for.end, label %bb.nph
+
+bb.nph: ; preds = %entry
+ %tmp15 = mul i64 %paraml, %parami ; <i64> [#uses=1]
+ ret i64 %tmp15
+
+for.end: ; preds = %entry
+ ret i64 %varx.0
+}