CodeGen: If Convert blocks that would form a diamond when tail-merged.

The following function currently relies on tail-merging for if
conversion to succeed. The common tail of cond_true and cond_false is
extracted, and this then forms a diamond pattern that can be
successfully if converted.

If this block does not get extracted, either because tail-merging is
disabled or the threshold is higher, we should still recognize this
pattern and if-convert it.

Fixed a regression in the original commit. Need to un-reverse branches after
reversing them, or other conversions go awry.

define i32 @t2(i32 %a, i32 %b) nounwind {
entry:
        %tmp1434 = icmp eq i32 %a, %b           ; <i1> [#uses=1]
        br i1 %tmp1434, label %bb17, label %bb.outer

bb.outer:               ; preds = %cond_false, %entry
        %b_addr.021.0.ph = phi i32 [ %b, %entry ], [ %tmp10, %cond_false ]
        %a_addr.026.0.ph = phi i32 [ %a, %entry ], [ %a_addr.026.0, %cond_false ]
        br label %bb

bb:             ; preds = %cond_true, %bb.outer
        %indvar = phi i32 [ 0, %bb.outer ], [ %indvar.next, %cond_true ]
        %tmp. = sub i32 0, %b_addr.021.0.ph
        %tmp.40 = mul i32 %indvar, %tmp.
        %a_addr.026.0 = add i32 %tmp.40, %a_addr.026.0.ph
        %tmp3 = icmp sgt i32 %a_addr.026.0, %b_addr.021.0.ph
        br i1 %tmp3, label %cond_true, label %cond_false

cond_true:              ; preds = %bb
        %tmp7 = sub i32 %a_addr.026.0, %b_addr.021.0.ph
        %tmp1437 = icmp eq i32 %tmp7, %b_addr.021.0.ph
        %indvar.next = add i32 %indvar, 1
        br i1 %tmp1437, label %bb17, label %bb

cond_false:             ; preds = %bb
        %tmp10 = sub i32 %b_addr.021.0.ph, %a_addr.026.0
        %tmp14 = icmp eq i32 %a_addr.026.0, %tmp10
        br i1 %tmp14, label %bb17, label %bb.outer

bb17:           ; preds = %cond_false, %cond_true, %entry
        %a_addr.026.1 = phi i32 [ %a, %entry ], [ %tmp7, %cond_true ], [ %a_addr.026.0, %cond_false ]
        ret i32 %a_addr.026.1
}

Without tail-merging or diamond-tail if conversion:
LBB1_1:                                 @ %bb
                                        @ =>This Inner Loop Header: Depth=1
        cmp     r0, r1
        ble     LBB1_3
@ BB#2:                                 @ %cond_true
                                        @   in Loop: Header=BB1_1 Depth=1
        subs    r0, r0, r1
        cmp     r1, r0
        it      ne
        cmpne   r0, r1
        bgt     LBB1_4
LBB1_3:                                 @ %cond_false
                                        @   in Loop: Header=BB1_1 Depth=1
        subs    r1, r1, r0
        cmp     r1, r0
        bne     LBB1_1
LBB1_4:                                 @ %bb17
        bx      lr

With diamond-tail if conversion, but without tail-merging:
@ BB#0:                                 @ %entry
        cmp     r0, r1
        it      eq
        bxeq    lr
LBB1_1:                                 @ %bb
                                        @ =>This Inner Loop Header: Depth=1
        cmp     r0, r1
        ite     le
        suble   r1, r1, r0
        subgt   r0, r0, r1
        cmp     r1, r0
        bne     LBB1_1
@ BB#2:                                 @ %bb17
        bx      lr

llvm-svn: 279671

1 files changed, 36 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/PowerPC/ifcvt-forked-bug-2016-08-08.ll b/llvm/test/CodeGen/PowerPC/ifcvt-forked-bug-2016-08-08.ll
new file mode 100644
index 00000000000..baa8d87562c
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/ifcvt-forked-bug-2016-08-08.ll
@@ -0,0 +1,36 @@
+; ModuleID = 'bugpoint-reduced-instructions.bc'
+; RUN: llc -O2 -o - %s | FileCheck %s
+source_filename = "bugpoint-output-9ad75f8.bc"
+target datalayout = "e-m:e-i64:64-n32:64"
+target triple = "powerpc64le-unknown-linux-gnu"
+
+; Function Attrs: nounwind uwtable
+define hidden void @_ZN11__sanitizer25MaybeStartBackgroudThreadEv() local_unnamed_addr #0 {
+entry:
+  br i1 undef, label %land.lhs.true, label %if.end
+
+; CHECK: # %land.lhs.true
+; CHECK-NEXT: bclr
+; CHECK-NEXT: # %if.end4
+land.lhs.true:                                    ; preds = %entry
+  br i1 undef, label %return, label %if.end4
+
+if.end:                                           ; preds = %entry
+  br i1 icmp ne (i32 (i8*, i8*, i8* (i8*)*, i8*)* @_ZN11__sanitizer19real_pthread_createEPvS0_PFS0_S0_ES0_, i32 (i8*, i8*, i8* (i8*)*, i8*)* null), label %if.end4, label %return
+
+if.end4:                                          ; preds = %if.end, %land.lhs.true
+  %call5 = tail call i8* @_ZN11__sanitizer21internal_start_threadEPFvPvES0_(void (i8*)* nonnull @_ZN11__sanitizer16BackgroundThreadEPv, i8* null) #7
+  unreachable
+
+return:                                           ; preds = %if.end, %land.lhs.true
+  ret void
+}
+
+declare extern_weak signext i32 @_ZN11__sanitizer19real_pthread_createEPvS0_PFS0_S0_ES0_(i8*, i8*, i8* (i8*)*, i8*) #2
+
+declare i8* @_ZN11__sanitizer21internal_start_threadEPFvPvES0_(void (i8*)*, i8*) local_unnamed_addr #2
+
+declare hidden void @_ZN11__sanitizer16BackgroundThreadEPv(i8* nocapture readnone) #5
+
+attributes #0 = { nounwind uwtable "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="ppc64le" "target-features"="+altivec,+bpermd,+crypto,+direct-move,+extdiv,+power8-vector,+vsx,-qpx" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #7 = { nobuiltin nounwind }