[PGO] Update VP metadata after memory intrinsic optimization

Summary:
Leave an updated VP metadata on the fallback memcpy intrinsic after
specialization. This can be used for later possible expansion based on
the average of the remaining values.

Reviewers: davidxl

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D34164

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@305321 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp b/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp
index 96027bc3d0a91c2d8cea13da30593b5a24562267..39a3ef2a49a5d6c81f08d2bab25e4881e2f59a01 100644 (file)
--- a/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp
+++ b/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp
@@ -884,6 +884,7 @@ bool MemOPSizeOpt::perform(MemIntrinsic *MI) {
 
   // Keeping track of the count of the default case:
   uint64_t RemainCount = TotalCount;
+  uint64_t SavedRemainCount = SavedTotalCount;
   SmallVector<uint64_t, 16> SizeIds;
   SmallVector<uint64_t, 16> CaseCounts;
   uint64_t MaxCount = 0;
@@ -912,6 +913,8 @@ bool MemOPSizeOpt::perform(MemIntrinsic *MI) {
 
     assert(RemainCount >= C);
     RemainCount -= C;
+    assert(SavedRemainCount >= VD.Count);
+    SavedRemainCount -= VD.Count;
 
     if (++Version > MemOPMaxVersion && MemOPMaxVersion != 0)
       break;
@@ -968,6 +971,11 @@ bool MemOPSizeOpt::perform(MemIntrinsic *MI) {
 
   // Clear the value profile data.
   MI->setMetadata(LLVMContext::MD_prof, nullptr);
+  // If all promoted, we don't need the MD.prof metadata.
+  if (SavedRemainCount > 0 || Version != NumVals)
+    // Otherwise we need update with the un-promoted records back.
+    annotateValueSite(*Func.getParent(), *MI, VDs.slice(Version),
+                      SavedRemainCount, IPVK_MemOPSize, NumVals);
 
   DEBUG(dbgs() << "\n\n== Basic Block After==\n");
 

diff --git a/test/Transforms/PGOProfile/memop_size_opt.ll b/test/Transforms/PGOProfile/memop_size_opt.ll
index 19a2b7ed293b2a2e65f002c0d15697fee24b0d9d..e11f235a48e76276c5c9a7596f94efaea20d10b5 100644 (file)
--- a/test/Transforms/PGOProfile/memop_size_opt.ll
+++ b/test/Transforms/PGOProfile/memop_size_opt.ll
@@ -38,7 +38,7 @@ for.body3:
 ; MEMOP_OPT:   call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 1, i32 1, i1 false)
 ; MEMOP_OPT:   br label %[[MERGE_LABEL:.*]]
 ; MEMOP_OPT: [[DEFAULT_LABEL]]:
-; MEMOP_OPT:   call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false){{[[:space:]]}}
+; MEMOP_OPT:   call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false), !prof [[NEWVP:![0-9]+]]
 ; MEMOP_OPT:   br label %[[MERGE_LABEL]]
 ; MEMOP_OPT: [[MERGE_LABEL]]:
 ; MEMOP_OPT:  switch i64 %conv, label %[[DEFAULT_LABEL2:.*]] [
@@ -48,11 +48,16 @@ for.body3:
 ; MEMOP_OPT:   call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src2, i64 1, i32 1, i1 false)
 ; MEMOP_OPT:   br label %[[MERGE_LABEL2:.*]]
 ; MEMOP_OPT: [[DEFAULT_LABEL2]]:
-; MEMOP_OPT:   call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src2, i64 %conv, i32 1, i1 false){{[[:space:]]}}
+; MEMOP_OPT:   call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src2, i64 %conv, i32 1, i1 false), !prof [[NEWVP]]
 ; MEMOP_OPT:   br label %[[MERGE_LABEL2]]
 ; MEMOP_OPT: [[MERGE_LABEL2]]:
 ; MEMOP_OPT:   br label %for.inc
 ; MEMOP_OPT: [[SWITCH_BW]] = !{!"branch_weights", i32 457, i32 99}
+; Should be 457 total left (original total count 556, minus 99 from specialized
+; value 1, which is removed from VP array. Also, we only end up with 5 total
+; values, since the default max number of promotions is 5 and therefore
+; the rest of the values are ignored when extracting the VP metadata.
+; MEMOP_OPT: [[NEWVP]] = !{!"VP", i32 1, i64 457, i64 2, i64 88, i64 3, i64 77, i64 9, i64 72, i64 4, i64 66}
 
 for.inc:
   %inc = add nsw i32 %j.0, 1