[LoopPred] Robustly handle partially unswitched loops

We may end up with a case where we have a widenable branch above the loop, but not all widenable branches within the loop have been removed.  Since a widenable branch inhibit SCEVs ability to reason about exit counts (by design), we have a tradeoff between effectiveness of this optimization and allowing future widening of the branches within the loop.  LoopPred is thought to be one of the most important optimizations for range check elimination, so let's pay the cost.

1 files changed, 111 insertions, 0 deletions

diff --git a/llvm/test/Transforms/LoopPredication/predicate-exits.ll b/llvm/test/Transforms/LoopPredication/predicate-exits.ll
index 0d6eba9015a..83d85eb74a6 100644
--- a/llvm/test/Transforms/LoopPredication/predicate-exits.ll
+++ b/llvm/test/Transforms/LoopPredication/predicate-exits.ll
@@ -989,6 +989,117 @@ guarded:
 }
 
 
+; If we have a stray widenable branch in the loop, we should still be able to
+; run.  This can happen when unswitching's cost model avoids unswitching some
+; branches.
+define i32 @wb_in_loop(i32* %array, i32 %length, i32 %n, i1 %cond_0) {
+; CHECK-LABEL: @wb_in_loop(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
+; CHECK-NEXT:    [[WC2:%.*]] = call i1 @llvm.experimental.widenable.condition()
+; CHECK-NEXT:    [[TMP0:%.*]] = icmp ugt i32 [[N:%.*]], 1
+; CHECK-NEXT:    [[UMAX:%.*]] = select i1 [[TMP0]], i32 [[N]], i32 1
+; CHECK-NEXT:    [[TMP1:%.*]] = add i32 [[UMAX]], -1
+; CHECK-NEXT:    [[TMP2:%.*]] = icmp ult i32 [[LENGTH:%.*]], [[TMP1]]
+; CHECK-NEXT:    [[UMIN:%.*]] = select i1 [[TMP2]], i32 [[LENGTH]], i32 [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]]
+; CHECK-NEXT:    [[TMP4:%.*]] = freeze i1 [[TMP3]]
+; CHECK-NEXT:    [[TMP5:%.*]] = and i1 [[TMP4]], [[COND_0:%.*]]
+; CHECK-NEXT:    [[TMP6:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]]
+; CHECK-NEXT:    [[TMP7:%.*]] = freeze i1 [[TMP6]]
+; CHECK-NEXT:    [[TMP8:%.*]] = and i1 [[TMP7]], [[TMP5]]
+; CHECK-NEXT:    [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP8]], [[WIDENABLE_COND]]
+; CHECK-NEXT:    br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
+; CHECK:       deopt:
+; CHECK-NEXT:    [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET]]
+; CHECK:       loop.preheader:
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED2:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED2]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]]
+; CHECK-NEXT:    br i1 true, label [[GUARDED:%.*]], label [[DEOPT2:%.*]], !prof !0
+; CHECK:       deopt2:
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET2]]
+; CHECK:       guarded:
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[WITHIN_BOUNDS2:%.*]] = icmp ult i32 [[I]], [[LENGTH]]
+; CHECK-NEXT:    [[WB_COND:%.*]] = and i1 [[WITHIN_BOUNDS2]], true
+; CHECK-NEXT:    br i1 true, label [[GUARDED2]], label [[DEOPT3:%.*]], !prof !0
+; CHECK:       deopt3:
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[DEOPTRET3:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET3]]
+; CHECK:       guarded2:
+; CHECK-NEXT:    [[I_I64:%.*]] = zext i32 [[I]] to i64
+; CHECK-NEXT:    [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
+; CHECK-NEXT:    [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
+; CHECK-NEXT:    store i32 0, i32* [[ARRAY_I_PTR]]
+; CHECK-NEXT:    [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
+; CHECK-NEXT:    [[I_NEXT]] = add nuw i32 [[I]], 1
+; CHECK-NEXT:    [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
+; CHECK:       exit:
+; CHECK-NEXT:    [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED2]] ]
+; CHECK-NEXT:    ret i32 [[RESULT]]
+;
+entry:
+  %widenable_cond = call i1 @llvm.experimental.widenable.condition()
+  %wc2 = call i1 @llvm.experimental.widenable.condition()
+  %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
+  br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
+
+deopt:
+  %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret
+
+loop.preheader:
+  br label %loop
+
+loop:
+  %loop.acc = phi i32 [ %loop.acc.next, %guarded2 ], [ 0, %loop.preheader ]
+  %i = phi i32 [ %i.next, %guarded2 ], [ 0, %loop.preheader ]
+  call void @unknown()
+  %within.bounds = icmp ult i32 %i, %length
+  br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
+
+deopt2:
+  call void @unknown()
+  %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret2
+
+guarded:
+  call void @unknown()
+  %within.bounds2 = icmp ult i32 %i, %length
+  %wb_cond = and i1 %within.bounds2, %wc2
+  br i1 %wb_cond, label %guarded2, label %deopt3, !prof !0
+
+deopt3:
+  call void @unknown()
+  %deoptret3 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret3
+
+guarded2:
+  %i.i64 = zext i32 %i to i64
+  %array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
+  %array.i = load i32, i32* %array.i.ptr, align 4
+  store i32 0, i32* %array.i.ptr
+  %loop.acc.next = add i32 %loop.acc, %array.i
+  %i.next = add nuw i32 %i, 1
+  %continue = icmp ult i32 %i.next, %n
+  br i1 %continue, label %loop, label %exit
+
+exit:
+  %result = phi i32 [ %loop.acc.next, %guarded2 ]
+  ret i32 %result
+}
+
+
+
 declare void @unknown()
 
 declare i1 @llvm.experimental.widenable.condition()