Memory intrinsic value profile optimization: Avoid divide by 0

Summary:
Skip memops if the total value profiled count is 0, we can't correctly
scale up the counts and there is no point anyway.

Reviewers: davidxl

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D32624

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@301645 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp b/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp
index 75fb2d40653fd4aef25ebe78bd283edf140d09ac..493d014586c6a1b4ac440ebf8d5c185140ec9b7a 100644 (file)
--- a/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp
+++ b/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp
@@ -872,6 +872,10 @@ bool MemOPSizeOpt::perform(MemIntrinsic *MI) {
 
   if (ActualCount < MemOPCountThreshold)
     return false;
+  // Skip if the total value profiled count is 0, in which case we can't
+  // scale up the counts properly (and there is no profitable transformation).
+  if (TotalCount == 0)
+    return false;
 
   TotalCount = ActualCount;
   if (MemOPScaleCount)

diff --git a/test/Transforms/PGOProfile/memop_size_opt_zero.ll b/test/Transforms/PGOProfile/memop_size_opt_zero.ll
new file mode 100644 (file)
index 0000000..ede34f0
--- /dev/null
+++ b/test/Transforms/PGOProfile/memop_size_opt_zero.ll
@@ -0,0 +1,19 @@
+; Test to ensure the pgo memop optimization pass doesn't try to scale
+; up a value profile with a 0 count, which would lead to divide by 0.
+; RUN: opt < %s -passes=pgo-memop-opt -pgo-memop-count-threshold=1 -S | FileCheck %s --check-prefix=MEMOP_OPT
+; RUN: opt < %s -pgo-memop-opt -pgo-memop-count-threshold=1 -S | FileCheck %s --check-prefix=MEMOP_OPT
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define void @foo(i8* %dst, i8* %src, i64 %conv) !prof !0 {
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false), !prof !1
+  ret void
+}
+
+; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false), !prof !1
+
+!0 = !{!"function_entry_count", i64 1}
+!1 = !{!"VP", i32 1, i64 0, i64 1, i64 0, i64 2, i64 0, i64 3, i64 0, i64 9, i64 0, i64 4, i64 0, i64 5, i64 0, i64 6, i64 0, i64 7, i64 0, i64 8, i64 0}
+
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1)