[CodeGenPrepare] limit overflow intrinsic matching to a single basic block

Using/updating a dominator tree to match math overflow patterns may be very
expensive in compile-time (because of the way CGP uses a DT), so just handle
the single-block case.

Also, we were restarting the iterator loops when doing the overflow intrinsic
transforms by marking the dominator tree for update. That was done to prevent
iterating over a removed instruction. But we can postpone the deletion using
the existing "RemovedInsts" structure, and that means we don't need to update
the DT.

See post-commit thread for rL354298 for more details:
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20190422/646276.html

Differential Revision: https://reviews.llvm.org/D61075

llvm-svn: 359879

1 files changed, 4 insertions, 5 deletions

diff --git a/llvm/test/Transforms/CodeGenPrepare/X86/optimizeSelect-DT.ll b/llvm/test/Transforms/CodeGenPrepare/X86/optimizeSelect-DT.ll
index dc638425355..05389bfe8d0 100644
--- a/llvm/test/Transforms/CodeGenPrepare/X86/optimizeSelect-DT.ll
+++ b/llvm/test/Transforms/CodeGenPrepare/X86/optimizeSelect-DT.ll
@@ -14,11 +14,10 @@ define i1 @PR41004(i32 %x, i32 %y, i32 %t1) {
 ; CHECK-NEXT:    br label [[SELECT_END]]
 ; CHECK:       select.end:
 ; CHECK-NEXT:    [[MUL:%.*]] = phi i32 [ [[REM]], [[SELECT_TRUE_SINK]] ], [ 0, [[ENTRY:%.*]] ]
-; CHECK-NEXT:    [[TMP0:%.*]] = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 [[T1:%.*]], i32 1)
-; CHECK-NEXT:    [[MATH:%.*]] = extractvalue { i32, i1 } [[TMP0]], 0
-; CHECK-NEXT:    [[OV:%.*]] = extractvalue { i32, i1 } [[TMP0]], 1
-; CHECK-NEXT:    [[ADD:%.*]] = add i32 [[MATH]], [[MUL]]
-; CHECK-NEXT:    ret i1 [[OV]]
+; CHECK-NEXT:    [[NEG:%.*]] = add i32 [[T1:%.*]], -1
+; CHECK-NEXT:    [[ADD:%.*]] = add i32 [[NEG]], [[MUL]]
+; CHECK-NEXT:    [[TOBOOL:%.*]] = icmp eq i32 [[T1]], 0
+; CHECK-NEXT:    ret i1 [[TOBOOL]]
 ;
 entry:
   %rem = srem i32 %x, 2