[PGO] Move __profc_ and __profvp_ from their own comdat groups to __profd_'s comdat...

D68041 placed `__profc_`,  `__profd_` and (if exists) `__profvp_` in different comdat groups.
There are some issues:

* Cost: one or two additional section headers (`.group` section(s)): 64 or 128 bytes on ELF64.
* `__profc_`,  `__profd_` and (if exists) `__profvp_` should be retained or
  discarded. Placing them into separate comdat groups is conceptually inferior.
* If the prevailing group does not include `__profvp_` (value profiling not
  used) but a non-prevailing group from another translation unit has `__profvp_`
  (the function is inlined into another and triggers value profiling), there
  will be a stray `__profvp_` if --gc-sections is not enabled.
  This has been fixed by 3d6f53018f845e893ad34f64ff2851a2e5c3ba1d.

Actually, we can reuse an existing symbol (we choose `__profd_`) as the group
signature to avoid a string in the string table (the sole reason that D68041
could improve code size is that `__profv_` was an otherwise unused symbol which
wasted string table space). This saves one or two section headers.

For a -DCMAKE_BUILD_TYPE=Release -DLLVM_BUILD_INSTRUMENTED=IR build, `ninja
clang lld`, the patch has saved 10.5MiB (2.2%) for the total .o size.

Reviewed By: davidxl

Differential Revision: https://reviews.llvm.org/D84723

diff --git a/llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp b/llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp
index 7598889..623f463 100644 (file)
--- a/llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp
+++ b/llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp
@@ -882,9 +882,10 @@ InstrProfiling::getOrCreateRegionCounters(InstrProfIncrementInst *Inc) {
       Visibility = GlobalValue::HiddenVisibility;
     }
   }
+  std::string DataVarName = getVarName(Inc, getInstrProfDataVarPrefix());
   auto MaybeSetComdat = [=](GlobalVariable *GV) {
     if (NeedComdat)
-      GV->setComdat(M->getOrInsertComdat(GV->getName()));
+      GV->setComdat(M->getOrInsertComdat(DataVarName));
   };
 
   uint64_t NumCounters = Inc->getNumCounters()->getZExtValue();
@@ -949,9 +950,9 @@ InstrProfiling::getOrCreateRegionCounters(InstrProfIncrementInst *Inc) {
 #define INSTR_PROF_DATA(Type, LLVMType, Name, Init) Init,
 #include "llvm/ProfileData/InstrProfData.inc"
   };
-  auto *Data = new GlobalVariable(*M, DataTy, false, Linkage,
-                                  ConstantStruct::get(DataTy, DataVals),
-                                  getVarName(Inc, getInstrProfDataVarPrefix()));
+  auto *Data =
+      new GlobalVariable(*M, DataTy, false, Linkage,
+                         ConstantStruct::get(DataTy, DataVals), DataVarName);
   Data->setVisibility(Visibility);
   Data->setSection(getInstrProfSectionName(IPSK_data, TT.getObjectFormat()));
   Data->setAlignment(Align(INSTR_PROF_DATA_ALIGNMENT));

diff --git a/llvm/test/Instrumentation/InstrProfiling/PR23499.ll b/llvm/test/Instrumentation/InstrProfiling/PR23499.ll
index 1a4c049..098153f 100644 (file)
--- a/llvm/test/Instrumentation/InstrProfiling/PR23499.ll
+++ b/llvm/test/Instrumentation/InstrProfiling/PR23499.ll
@@ -14,13 +14,13 @@ $_Z3barIvEvv = comdat any
 @__profn__Z3barIvEvv = linkonce_odr hidden constant [11 x i8] c"_Z3barIvEvv", align 1
 
 ; CHECK-NOT: __profn__Z3barIvEvv
-; CHECK: @__profc__Z3barIvEvv = linkonce_odr hidden global [1 x i64] zeroinitializer, section "{{.*}}__llvm_prf_cnts", comdat, align 8
+; CHECK: @__profc__Z3barIvEvv = linkonce_odr hidden global [1 x i64] zeroinitializer, section "{{.*}}__llvm_prf_cnts", comdat($__profd__Z3barIvEvv), align 8
 ; CHECK: @__profd__Z3barIvEvv = linkonce_odr hidden global { i64, i64, i64*, i8*, i8*, i32, [2 x i16] } { i64 4947693190065689389, i64 0, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc__Z3barIvEvv, i32 0, i32 0), i8*{{.*}}, i8* null, i32 1, [2 x i16] zeroinitializer }, section "{{.*}}__llvm_prf_data{{.*}}", comdat, align 8
 ; CHECK: @__llvm_prf_nm = private constant [{{.*}} x i8] c"{{.*}}", section "{{.*}}__llvm_prf_names"
 
 
 ; COFF-NOT: __profn__Z3barIvEvv
-; COFF: @__profc__Z3barIvEvv = linkonce_odr hidden global [1 x i64] zeroinitializer, section "{{.*}}prfc$M", comdat, align 8
+; COFF: @__profc__Z3barIvEvv = linkonce_odr hidden global [1 x i64] zeroinitializer, section "{{.*}}prfc$M", comdat($__profd__Z3barIvEvv), align 8
 ; COFF: @__profd__Z3barIvEvv = linkonce_odr hidden global { i64, i64, i64*, i8*, i8*, i32, [2 x i16] } { i64 4947693190065689389, i64 0, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc__Z3barIvEvv, i32 0, i32 0), i8*{{.*}}, i8* null, i32 1, [2 x i16] zeroinitializer }, section "{{.*}}prfd{{.*}}", comdat, align 8
 
 

diff --git a/llvm/test/Instrumentation/InstrProfiling/comdat.ll b/llvm/test/Instrumentation/InstrProfiling/comdat.ll
index 3f169c4..dfcd71f 100644 (file)
--- a/llvm/test/Instrumentation/InstrProfiling/comdat.ll
+++ b/llvm/test/Instrumentation/InstrProfiling/comdat.ll
@@ -15,9 +15,9 @@ $foo_inline = comdat any
 
 @__profn_foo_inline = linkonce_odr hidden constant [10 x i8] c"foo_inline"
 
-; ELF: @__profc_foo_inline = linkonce_odr hidden global{{.*}}, section "__llvm_prf_cnts", comdat, align 8
+; ELF: @__profc_foo_inline = linkonce_odr hidden global{{.*}}, section "__llvm_prf_cnts", comdat($__profd_foo_inline), align 8
 ; ELF: @__profd_foo_inline = linkonce_odr hidden global{{.*}}, section "__llvm_prf_data", comdat, align 8
-; COFF: @__profc_foo_inline = linkonce_odr hidden global{{.*}}, section ".lprfc$M", comdat, align 8
+; COFF: @__profc_foo_inline = linkonce_odr hidden global{{.*}}, section ".lprfc$M", comdat($__profd_foo_inline), align 8
 ; COFF: @__profd_foo_inline = linkonce_odr hidden global{{.*}}, section ".lprfd$M", comdat, align 8
 define weak_odr void @foo_inline() comdat {
   call void @llvm.instrprof.increment(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @__profn_foo_inline, i32 0, i32 0), i64 0, i32 1, i32 0)
@@ -28,9 +28,9 @@ $foo_extern = comdat any
 
 @__profn_foo_extern = linkonce_odr hidden constant [10 x i8] c"foo_extern"
 
-; ELF: @__profc_foo_extern = linkonce_odr hidden global{{.*}}, section "__llvm_prf_cnts", comdat, align 8
+; ELF: @__profc_foo_extern = linkonce_odr hidden global{{.*}}, section "__llvm_prf_cnts", comdat($__profd_foo_extern), align 8
 ; ELF: @__profd_foo_extern = linkonce_odr hidden global{{.*}}, section "__llvm_prf_data", comdat, align 8
-; COFF: @__profc_foo_extern = linkonce_odr hidden global{{.*}}, section ".lprfc$M", comdat, align 8
+; COFF: @__profc_foo_extern = linkonce_odr hidden global{{.*}}, section ".lprfc$M", comdat($__profd_foo_extern), align 8
 ; COFF: @__profd_foo_extern = linkonce_odr hidden global{{.*}}, section ".lprfd$M", comdat, align 8
 define available_externally void @foo_extern() {
   call void @llvm.instrprof.increment(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @__profn_foo_extern, i32 0, i32 0), i64 0, i32 1, i32 0)

diff --git a/llvm/test/Instrumentation/InstrProfiling/icall.ll b/llvm/test/Instrumentation/InstrProfiling/icall.ll
index d92de47..9d45d7c 100644 (file)
--- a/llvm/test/Instrumentation/InstrProfiling/icall.ll
+++ b/llvm/test/Instrumentation/InstrProfiling/icall.ll
@@ -14,6 +14,7 @@
 
 
 @__profn_foo = private constant [3 x i8] c"foo"
+@__profn_bar = private constant [3 x i8] c"bar"
 
 define i32 @foo(i32 ()* ) {
   call void @llvm.instrprof.increment(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @__profn_foo, i32 0, i32 0), i64 12884901887, i32 1, i32 0)
@@ -23,6 +24,17 @@ define i32 @foo(i32 ()* ) {
   ret i32 %3
 }
 
+$bar = comdat any
+
+define i32 @bar(i32 ()* ) comdat {
+entry:
+  call void @llvm.instrprof.increment(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @__profn_bar, i32 0, i32 0), i64 12884901887, i32 1, i32 0)
+  %1 = ptrtoint i32 ()* %0 to i64
+  call void @llvm.instrprof.value.profile(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @__profn_bar, i32 0, i32 0), i64 12884901887, i64 %1, i32 0, i32 0)
+  %2 = tail call i32 %0()
+  ret i32 %2
+}
+
 ; Function Attrs: nounwind
 declare void @llvm.instrprof.increment(i8*, i64, i32, i32) #0
 
@@ -31,7 +43,8 @@ declare void @llvm.instrprof.value.profile(i8*, i64, i64, i32, i32) #0
 
 attributes #0 = { nounwind }
 
-; STATIC: @__profvp_foo
+; STATIC: @__profvp_foo = private global [1 x i64] zeroinitializer, section "{{[^"]+}}", align 8
+; STATIC: @__profvp_bar = private global [1 x i64] zeroinitializer, section "{{[^"]+}}", comdat($__profd_bar), align 8
 ; STATIC: @__llvm_prf_vnodes
 
 ; DYN-NOT: @__profvp_foo

diff --git a/llvm/test/Instrumentation/InstrProfiling/linkage.ll b/llvm/test/Instrumentation/InstrProfiling/linkage.ll
index be3af8e..5e55ef7 100644 (file)
--- a/llvm/test/Instrumentation/InstrProfiling/linkage.ll
+++ b/llvm/test/Instrumentation/InstrProfiling/linkage.ll
@@ -55,11 +55,11 @@ define linkonce_odr void @foo_inline() {
   ret void
 }
 
-; LINUX: @__profc_foo_extern = linkonce_odr hidden global {{.*}}section "__llvm_prf_cnts", comdat, align 8
+; LINUX: @__profc_foo_extern = linkonce_odr hidden global {{.*}}section "__llvm_prf_cnts", comdat($__profd_foo_extern), align 8
 ; LINUX: @__profd_foo_extern = linkonce_odr hidden global {{.*}}section "__llvm_prf_data", comdat, align 8
 ; MACHO: @__profc_foo_extern = linkonce_odr hidden global
 ; MACHO: @__profd_foo_extern = linkonce_odr hidden global
-; COFF: @__profc_foo_extern = linkonce_odr hidden global {{.*}}section ".lprfc$M", comdat, align 8
+; COFF: @__profc_foo_extern = linkonce_odr hidden global {{.*}}section ".lprfc$M", comdat($__profd_foo_extern), align 8
 ; COFF: @__profd_foo_extern = linkonce_odr hidden global {{.*}}section ".lprfd$M", comdat, align 8
 define available_externally void @foo_extern() {
   call void @llvm.instrprof.increment(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @__profn_foo_extern, i32 0, i32 0), i64 0, i32 1, i32 0)

diff --git a/llvm/test/Transforms/PGOProfile/comdat_internal.ll b/llvm/test/Transforms/PGOProfile/comdat_internal.ll
index f0906bf..e5915d9 100644 (file)
--- a/llvm/test/Transforms/PGOProfile/comdat_internal.ll
+++ b/llvm/test/Transforms/PGOProfile/comdat_internal.ll
@@ -7,12 +7,13 @@ $foo = comdat any
 ; CHECK: $foo = comdat any
 
 ; CHECK: $__llvm_profile_raw_version = comdat any
+; CHECK: $__profd__stdin__foo.[[FOO_HASH:[0-9]+]] = comdat any
 
 @bar = global i32 ()* @foo, align 8
 
 ; CHECK: @__llvm_profile_raw_version = constant i64 {{[0-9]+}}, comdat
 ; CHECK-NOT: __profn__stdin__foo
-; CHECK: @__profc__stdin__foo.[[FOO_HASH:[0-9]+]] = private global [1 x i64] zeroinitializer, section "__llvm_prf_cnts", comdat, align 8
+; CHECK: @__profc__stdin__foo.[[FOO_HASH]] = private global [1 x i64] zeroinitializer, section "__llvm_prf_cnts", comdat($__profd__stdin__foo.[[FOO_HASH]]), align 8
 ; CHECK: @__profd__stdin__foo.[[FOO_HASH]] = private global { i64, i64, i64*, i8*, i8*, i32, [2 x i16] } { i64 -5640069336071256030, i64 [[FOO_HASH]], i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc__stdin__foo.[[FOO_HASH]], i32 0, i32 0), i8* null
 ; CHECK-NOT: bitcast (i32 ()* @foo to i8*)
 ; CHECK-SAME: , i8* null, i32 1, [2 x i16] zeroinitializer }, section "__llvm_prf_data", comdat, align 8