-; RUN: llc -mtriple=i686-linux -enable-block-placement < %s | FileCheck %s
+; RUN: llc -mtriple=i686-linux -pre-RA-sched=source < %s | FileCheck %s
declare void @error(i32 %i, i32 %a, i32 %b)
define i32 @test_ifchains(i32 %i, i32* %a, i32 %b) {
; Test a chain of ifs, where the block guarded by the if is error handling code
; that is not expected to run.
-; CHECK: test_ifchains:
+; CHECK-LABEL: test_ifchains:
; CHECK: %entry
+; CHECK-NOT: .align
; CHECK: %else1
+; CHECK-NOT: .align
; CHECK: %else2
+; CHECK-NOT: .align
; CHECK: %else3
+; CHECK-NOT: .align
; CHECK: %else4
+; CHECK-NOT: .align
; CHECK: %exit
; CHECK: %then1
; CHECK: %then2
define i32 @test_loop_cold_blocks(i32 %i, i32* %a) {
; Check that we sink cold loop blocks after the hot loop body.
-; CHECK: test_loop_cold_blocks:
+; CHECK-LABEL: test_loop_cold_blocks:
; CHECK: %entry
+; CHECK-NOT: .align
; CHECK: %unlikely1
+; CHECK-NOT: .align
; CHECK: %unlikely2
+; CHECK: .align
; CHECK: %body1
; CHECK: %body2
; CHECK: %body3
define i32 @test_loop_early_exits(i32 %i, i32* %a) {
; Check that we sink early exit blocks out of loop bodies.
-; CHECK: test_loop_early_exits:
+; CHECK-LABEL: test_loop_early_exits:
; CHECK: %entry
+; CHECK: %body1
; CHECK: %body2
; CHECK: %body3
; CHECK: %body4
-; CHECK: %body1
+; CHECK: %exit
; CHECK: %bail1
; CHECK: %bail2
; CHECK: %bail3
-; CHECK: %exit
entry:
br label %body1
define i32 @test_loop_rotate(i32 %i, i32* %a) {
; Check that we rotate conditional exits from the loop to the bottom of the
; loop, eliminating unconditional branches to the top.
-; CHECK: test_loop_rotate:
+; CHECK-LABEL: test_loop_rotate:
; CHECK: %entry
; CHECK: %body1
; CHECK: %body0
ret i32 %base
}
+define i32 @test_no_loop_rotate(i32 %i, i32* %a) {
+; Check that we don't try to rotate a loop which is already laid out with
+; fallthrough opportunities into the top and out of the bottom.
+; CHECK-LABEL: test_no_loop_rotate:
+; CHECK: %entry
+; CHECK: %body0
+; CHECK: %body1
+; CHECK: %exit
+
+entry:
+ br label %body0
+
+body0:
+ %iv = phi i32 [ 0, %entry ], [ %next, %body1 ]
+ %base = phi i32 [ 0, %entry ], [ %sum, %body1 ]
+ %arrayidx = getelementptr inbounds i32* %a, i32 %iv
+ %0 = load i32* %arrayidx
+ %sum = add nsw i32 %0, %base
+ %bailcond1 = icmp eq i32 %sum, 42
+ br i1 %bailcond1, label %exit, label %body1
+
+body1:
+ %next = add i32 %iv, 1
+ %exitcond = icmp eq i32 %next, %i
+ br i1 %exitcond, label %exit, label %body0
+
+exit:
+ ret i32 %base
+}
+
define void @test_loop_rotate_reversed_blocks() {
; This test case (greatly reduced from an Olden bencmark) ensures that the loop
; rotate implementation doesn't assume that loops are laid out in a particular
define i32 @test_loop_align(i32 %i, i32* %a) {
; Check that we provide basic loop body alignment with the block placement
; pass.
-; CHECK: test_loop_align:
+; CHECK-LABEL: test_loop_align:
; CHECK: %entry
; CHECK: .align [[ALIGN:[0-9]+]],
; CHECK-NEXT: %body
define i32 @test_nested_loop_align(i32 %i, i32* %a, i32* %b) {
; Check that we provide nested loop body alignment.
-; CHECK: test_nested_loop_align:
+; CHECK-LABEL: test_nested_loop_align:
; CHECK: %entry
; CHECK: .align [[ALIGN]],
; CHECK-NEXT: %loop.body.1
br i1 %cond, label %entry.if.then_crit_edge, label %lor.lhs.false, !prof !1
entry.if.then_crit_edge:
- %.pre14 = load i8* undef, align 1, !tbaa !0
+ %.pre14 = load i8* undef, align 1
br label %if.then
lor.lhs.false:
if.then:
%0 = phi i8 [ %.pre14, %entry.if.then_crit_edge ], [ undef, %exit ]
%1 = and i8 %0, 1
- store i8 %1, i8* undef, align 4, !tbaa !0
+ store i8 %1, i8* undef, align 4
br label %if.end
if.end:
;
; CHECK: test_unnatural_cfg_backwards_inner_loop
; CHECK: %entry
-; CHECK: %body
+; CHECK: [[BODY:# BB#[0-9]+]]:
; CHECK: %loop2b
; CHECK: %loop1
; CHECK: %loop2a
define void @unanalyzable_branch_to_best_succ(i1 %cond) {
; Ensure that we can handle unanalyzable branches where the destination block
-; gets selected as the optimal sucessor to merge.
+; gets selected as the optimal successor to merge.
;
; CHECK: unanalyzable_branch_to_best_succ
; CHECK: %entry
; CHECK: %entry
; First rotated loop top.
; CHECK: .align
+; CHECK: %while.end
+; CHECK: %for.cond
+; CHECK: %if.then
+; CHECK: %if.else
; CHECK: %if.end10
; Second rotated loop top
; CHECK: .align
+; CHECK: %if.then24
; CHECK: %while.cond.outer
; Third rotated loop top
; CHECK: .align
; CHECK: %while.body
; CHECK: %land.lhs.true
; CHECK: %if.then19
-; CHECK: %if.then19
-; CHECK: %if.then24
-; CHECK: %while.end
-; CHECK: %for.cond
-; CHECK: %if.then
-; CHECK: %if.else
+; CHECK: %if.end20
; CHECK: %if.then8
; CHECK: ret
store double %rra.0, double* %arrayidx34, align 8
br label %for.cond
}
+
+declare void @cold_function() cold
+
+define i32 @test_cold_calls(i32* %a) {
+; Test that edges to blocks post-dominated by cold calls are
+; marked as not expected to be taken. They should be laid out
+; at the bottom.
+; CHECK-LABEL: test_cold_calls:
+; CHECK: %entry
+; CHECK: %else
+; CHECK: %exit
+; CHECK: %then
+
+entry:
+ %gep1 = getelementptr i32* %a, i32 1
+ %val1 = load i32* %gep1
+ %cond1 = icmp ugt i32 %val1, 1
+ br i1 %cond1, label %then, label %else
+
+then:
+ call void @cold_function()
+ br label %exit
+
+else:
+ %gep2 = getelementptr i32* %a, i32 2
+ %val2 = load i32* %gep2
+ br label %exit
+
+exit:
+ %ret = phi i32 [ %val1, %then ], [ %val2, %else ]
+ ret i32 %ret
+}