[SCEV] Limit AddRec "simplifications" to avoid combinatorial explosions

SCEV's transform that turns `{A1,+,A2,+,...,+,An}<L> * {B1,+,B2,+,...,+,Bn}<L>` into
a single AddRec of size `2n+1` with complex combinatorial coefficients can easily
trigger exponential growth of the SCEV (in case if nothing gets folded and simplified).
We tried to restrain this transform using the option `scalar-evolution-max-add-rec-size`,
but its default value seems to be insufficiently small: the test attached to this patch
with default value of this option `16` has a SCEV of >3M symbols (when printed out).

This patch reduces the simplification limit. It is not a cure to combinatorial
explosions, but at least it reduces this corner case to something more or less
reasonable.

Differential Revision: https://reviews.llvm.org/D53282
Reviewed By: sanjoy


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@344584 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 47 insertions, 0 deletions

diff --git a/test/Analysis/ScalarEvolution/binomial-explision.ll b/test/Analysis/ScalarEvolution/binomial-explision.ll
new file mode 100644
index 00000000000..82d0beda6b5
--- /dev/null
+++ b/test/Analysis/ScalarEvolution/binomial-explision.ll
@@ -0,0 +1,47 @@
+; RUN: opt -analyze -scalar-evolution < %s | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128-ni:1"
+
+; Check that we don't have unreasonably huge SCEVs and in particular only a
+; reasonable amount of AddRecs in the notation of %tmp19. If we "simplify" SCEVs
+; too aggressively, we may end up with huge nested expressions.
+define void @test(i32 %x, i64 %y, i1 %cond) {
+
+; CHECK: %tmp19 = mul i32 %tmp17, %tmp18
+; CHECK: ((((
+; CHECK-NOT: (((((
+; CHECK: %tmp20 = add i32 %tmp19, %x
+
+bb:
+  br label %bb1
+
+bb1:                                              ; preds = %bb3, %bb
+  %tmp = phi i64 [ %y, %bb ], [ %tmp22, %bb3 ]
+  %tmp2 = phi i32 [ %x, %bb ], [ %tmp4, %bb3 ]
+  br label %bb5
+
+bb3:                                              ; preds = %bb5
+  %tmp4 = add i32 %tmp2, %x
+  br label %bb1
+
+bb5:                                              ; preds = %bb5, %bb1
+  %tmp6 = phi i32 [ %tmp23, %bb5 ], [ %tmp2, %bb1 ]
+  %tmp7 = sub i32 -119, %tmp6
+  %tmp8 = mul i32 %tmp7, %x
+  %tmp9 = sub i32 -120, %tmp6
+  %tmp10 = mul i32 %tmp8, %tmp9
+  %tmp11 = mul i32 %x, %tmp10
+  %tmp12 = sub i32 -121, %tmp6
+  %tmp13 = mul i32 %tmp10, %tmp12
+  %tmp14 = mul i32 %tmp11, %tmp13
+  %tmp15 = sub i32 -122, %tmp6
+  %tmp16 = mul i32 %tmp13, %tmp15
+  %tmp17 = mul i32 %tmp14, %tmp16
+  %tmp18 = mul i32 %tmp16, %x
+  %tmp19 = mul i32 %tmp17, %tmp18
+  %tmp20 = add i32 %tmp19, %x
+  %tmp21 = sext i32 %tmp20 to i64
+  %tmp22 = add i64 %y, %tmp21
+  %tmp23 = add i32 %tmp6, 7
+  br i1 %cond, label %bb5, label %bb3
+}