[LTT] Add unknown branch weights when lowering type tests with conditional

Author: mtrofin

llvm/lib/Transforms/IPO/LowerTypeTests.cpp

@@ -54,6 +54,7 @@
 #include "llvm/IR/ModuleSummaryIndexYAML.h"
 #include "llvm/IR/Operator.h"
 #include "llvm/IR/PassManager.h"
+#include "llvm/IR/ProfDataUtils.h"
 #include "llvm/IR/ReplaceConstant.h"
 #include "llvm/IR/Type.h"
 #include "llvm/IR/Use.h"
@@ -803,6 +804,8 @@ Value *LowerTypeTestsModule::lowerTypeTestCall(Metadata *TypeId, CallInst *CI,
       }
 
   IRBuilder<> ThenB(SplitBlockAndInsertIfThen(OffsetInRange, CI, false));
+  setExplicitlyUnknownBranchWeightsIfProfiled(*InitialBB->getTerminator(),
+                                              DEBUG_TYPE);
 
   // Now that we know that the offset is in range and aligned, load the
   // appropriate bit from the bitset.

llvm/test/Transforms/LowerTypeTests/import.ll

@@ -85,14 +85,14 @@ define i1 @allones32(ptr %p) {
   ret i1 %x
 }
 
-define i1 @bytearray7(ptr %p) {
+define i1 @bytearray7(ptr %p) !prof !0 {
 ; X86-LABEL: define i1 @bytearray7(
-; X86-SAME: ptr [[P:%.*]]) {
+; X86-SAME: ptr [[P:%.*]]) !prof [[PROF6:![0-9]+]] {
 ; X86-NEXT:    [[TMP1:%.*]] = ptrtoint ptr [[P]] to i64
 ; X86-NEXT:    [[TMP2:%.*]] = sub i64 ptrtoint (ptr @__typeid_bytearray7_global_addr to i64), [[TMP1]]
-; X86-NEXT:    [[TMP3:%.*]] = call i64 @llvm.fshr.i64(i64 [[TMP2]], i64 [[TMP2]], i64 ptrtoint (ptr @__typeid_bytearray7_align to i64))
-; X86-NEXT:    [[TMP4:%.*]] = icmp ule i64 [[TMP3]], ptrtoint (ptr @__typeid_bytearray7_size_m1 to i64)
-; X86-NEXT:    br i1 [[TMP4]], label [[TMP5:%.*]], label [[TMP10:%.*]]
+; X86-NEXT:    [[TMP7:%.*]] = call i64 @llvm.fshr.i64(i64 [[TMP2]], i64 [[TMP2]], i64 ptrtoint (ptr @__typeid_bytearray7_align to i64))
+; X86-NEXT:    [[TMP8:%.*]] = icmp ule i64 [[TMP7]], ptrtoint (ptr @__typeid_bytearray7_size_m1 to i64)
+; X86-NEXT:    br i1 [[TMP8]], label [[TMP5:%.*]], label [[TMP14:%.*]], !prof [[PROF7:![0-9]+]]
 ; X86:       5:
 ; X86-NEXT:    [[TMP6:%.*]] = getelementptr i8, ptr @__typeid_bytearray7_byte_array, i64 [[TMP3]]
 ; X86-NEXT:    [[TMP7:%.*]] = load i8, ptr [[TMP6]], align 1
@@ -104,12 +104,12 @@ define i1 @bytearray7(ptr %p) {
 ; X86-NEXT:    ret i1 [[TMP11]]
 ;
 ; ARM-LABEL: define i1 @bytearray7(
-; ARM-SAME: ptr [[P:%.*]]) {
+; ARM-SAME: ptr [[P:%.*]]) !prof [[PROF0:![0-9]+]] {
 ; ARM-NEXT:    [[TMP1:%.*]] = ptrtoint ptr [[P]] to i64
 ; ARM-NEXT:    [[TMP2:%.*]] = sub i64 ptrtoint (ptr @__typeid_bytearray7_global_addr to i64), [[TMP1]]
-; ARM-NEXT:    [[TMP3:%.*]] = call i64 @llvm.fshr.i64(i64 [[TMP2]], i64 [[TMP2]], i64 3)
-; ARM-NEXT:    [[TMP4:%.*]] = icmp ule i64 [[TMP3]], 43
-; ARM-NEXT:    br i1 [[TMP4]], label [[TMP5:%.*]], label [[TMP10:%.*]]
+; ARM-NEXT:    [[TMP5:%.*]] = call i64 @llvm.fshr.i64(i64 [[TMP2]], i64 [[TMP2]], i64 3)
+; ARM-NEXT:    [[TMP6:%.*]] = icmp ule i64 [[TMP5]], 43
+; ARM-NEXT:    br i1 [[TMP6]], label [[TMP7:%.*]], label [[TMP12:%.*]], !prof [[PROF1:![0-9]+]]
 ; ARM:       5:
 ; ARM-NEXT:    [[TMP6:%.*]] = getelementptr i8, ptr @__typeid_bytearray7_byte_array, i64 [[TMP3]]
 ; ARM-NEXT:    [[TMP7:%.*]] = load i8, ptr [[TMP6]], align 1
@@ -253,17 +253,31 @@ define i1 @single(ptr %p) {
   %x = call i1 @llvm.type.test(ptr %p, metadata !"single")
   ret i1 %x
 }
+
+!0 = !{!"function_entry_count", i32 10}
+
+; X86: !0 = !{i64 0, i64 256}
+; X86: !1 = !{i64 0, i64 64}
+; X86: !2 = !{i64 -1, i64 -1}
+; X86: !3 = !{i64 0, i64 32}
+; X86: !4 = !{i64 0, i64 4294967296}
+; X86: !5 = !{i64 0, i64 128}
 ;.
 ; X86: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
 ; X86: attributes #[[ATTR1:[0-9]+]] = { nocallback nocreateundeforpoison nofree nosync nounwind speculatable willreturn memory(none) }
 ;.
+; ARM: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
+; ARM: attributes #[[ATTR1:[0-9]+]] = { nocallback nocreateundeforpoison nofree nosync nounwind speculatable willreturn memory(none) }
+;.
 ; X86: [[META0]] = !{i64 0, i64 256}
 ; X86: [[META1]] = !{i64 0, i64 64}
 ; X86: [[META2]] = !{i64 -1, i64 -1}
 ; X86: [[META3]] = !{i64 0, i64 32}
 ; X86: [[META4]] = !{i64 0, i64 4294967296}
 ; X86: [[META5]] = !{i64 0, i64 128}
+; X86: [[PROF6]] = !{!"function_entry_count", i32 10}
+; X86: [[PROF7]] = !{!"unknown", !"lowertypetests"}
 ;.
-; ARM: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
-; ARM: attributes #[[ATTR1:[0-9]+]] = { nocallback nocreateundeforpoison nofree nosync nounwind speculatable willreturn memory(none) }
+; ARM: [[PROF0]] = !{!"function_entry_count", i32 10}
+; ARM: [[PROF1]] = !{!"unknown", !"lowertypetests"}
 ;.

llvm/utils/profcheck-xfail.txt

@@ -493,8 +493,6 @@ Transforms/LowerSwitch/do-not-handle-impossible-values.ll
 Transforms/LowerSwitch/feature.ll
 Transforms/LowerSwitch/fold-popular-case-to-unreachable-default.ll
 Transforms/LowerSwitch/pr59316.ll
-Transforms/LowerTypeTests/import.ll
-Transforms/LowerTypeTests/simple.ll
 Transforms/MergeFunc/2011-02-08-RemoveEqual.ll
 Transforms/MergeFunc/apply_function_attributes.ll
 Transforms/MergeFunc/call-and-invoke-with-ranges-attr.ll