Rewrite #3 of machine block placement. This is based somewhat on the

[oota-llvm.git] / test / CodeGen / X86 / block-placement.ll

diff --git a/test/CodeGen/X86/block-placement.ll b/test/CodeGen/X86/block-placement.ll
index 887a62eabd23950d36ac7a020ac03847585e83dc..4f0b6714b8486371bd77e91a1ea89fa8ff1cd706 100644 (file)
--- a/test/CodeGen/X86/block-placement.ll
+++ b/test/CodeGen/X86/block-placement.ll
@@ -72,14 +72,109 @@ exit:
   ret i32 %b
 }
 
+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: %entry
+; CHECK: %body1
+; CHECK: %body2
+; CHECK: %body3
+; CHECK: %unlikely1
+; CHECK: %unlikely2
+; CHECK: %exit
+
+entry:
+  br label %body1
+
+body1:
+  %iv = phi i32 [ 0, %entry ], [ %next, %body3 ]
+  %base = phi i32 [ 0, %entry ], [ %sum, %body3 ]
+  %unlikelycond1 = icmp slt i32 %base, 42
+  br i1 %unlikelycond1, label %unlikely1, label %body2, !prof !0
+
+unlikely1:
+  call void @error(i32 %i, i32 1, i32 %base)
+  br label %body2
+
+body2:
+  %unlikelycond2 = icmp sgt i32 %base, 21
+  br i1 %unlikelycond2, label %unlikely2, label %body3, !prof !0
+
+unlikely2:
+  call void @error(i32 %i, i32 2, i32 %base)
+  br label %body3
+
+body3:
+  %arrayidx = getelementptr inbounds i32* %a, i32 %iv
+  %0 = load i32* %arrayidx
+  %sum = add nsw i32 %0, %base
+  %next = add i32 %iv, 1
+  %exitcond = icmp eq i32 %next, %i
+  br i1 %exitcond, label %exit, label %body1
+
+exit:
+  ret i32 %sum
+}
+
 !0 = metadata !{metadata !"branch_weights", i32 4, i32 64}
 
+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: %entry
+; CHECK: %body1
+; CHECK: %body2
+; CHECK: %body3
+; CHECK: %body4
+; CHECK: %exit
+; CHECK: %bail1
+; CHECK: %bail2
+; CHECK: %bail3
+
+entry:
+  br label %body1
+
+body1:
+  %iv = phi i32 [ 0, %entry ], [ %next, %body4 ]
+  %base = phi i32 [ 0, %entry ], [ %sum, %body4 ]
+  %bailcond1 = icmp eq i32 %base, 42
+  br i1 %bailcond1, label %bail1, label %body2
+
+bail1:
+  ret i32 -1
+
+body2:
+  %bailcond2 = icmp eq i32 %base, 43
+  br i1 %bailcond2, label %bail2, label %body3
+
+bail2:
+  ret i32 -2
+
+body3:
+  %bailcond3 = icmp eq i32 %base, 44
+  br i1 %bailcond3, label %bail3, label %body4
+
+bail3:
+  ret i32 -3
+
+body4:
+  %arrayidx = getelementptr inbounds i32* %a, i32 %iv
+  %0 = load i32* %arrayidx
+  %sum = add nsw i32 %0, %base
+  %next = add i32 %iv, 1
+  %exitcond = icmp eq i32 %next, %i
+  br i1 %exitcond, label %exit, label %body1
+
+exit:
+  ret i32 %sum
+}
+
 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: %entry
-; CHECK: .align 16,
+; CHECK: .align [[ALIGN:[0-9]+]],
 ; CHECK-NEXT: %body
 ; CHECK: %exit
 
@@ -104,12 +199,11 @@ 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: %entry
-; CHECK: .align 16,
+; CHECK: .align [[ALIGN]],
 ; CHECK-NEXT: %loop.body.1
-; CHECK: .align 16,
+; CHECK: .align [[ALIGN]],
 ; CHECK-NEXT: %inner.loop.body
 ; CHECK-NOT: .align
-; CHECK: %loop.body.2
 ; CHECK: %exit
 
 entry: