e56626e438
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 3d6f53018f.
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
60 lines
3.5 KiB
LLVM
60 lines
3.5 KiB
LLVM
;; Check that static counters are allocated for value profiler
|
|
|
|
; RUN: opt < %s -mtriple=x86_64-apple-macosx10.10.0 -vp-static-alloc=true -instrprof -S | FileCheck %s --check-prefix=STATIC
|
|
; RUN: opt < %s -mtriple=x86_64-unknown-linux -instrprof -vp-static-alloc=true -S | FileCheck %s --check-prefix=STATIC
|
|
; RUN: opt < %s -mtriple=powerpc-unknown-linux -instrprof -vp-static-alloc=true -S | FileCheck %s --check-prefix=STATIC
|
|
; RUN: opt < %s -mtriple=sparc-unknown-linux -instrprof -vp-static-alloc=true -S | FileCheck %s --check-prefix=STATIC
|
|
; RUN: opt < %s -mtriple=s390x-unknown-linux -instrprof -vp-static-alloc=true -S | FileCheck %s --check-prefix=STATIC-EXT
|
|
; RUN: opt < %s -mtriple=powerpc64-unknown-linux -instrprof -vp-static-alloc=true -S | FileCheck %s --check-prefix=STATIC-EXT
|
|
; RUN: opt < %s -mtriple=sparc64-unknown-linux -instrprof -vp-static-alloc=true -S | FileCheck %s --check-prefix=STATIC-EXT
|
|
; RUN: opt < %s -mtriple=mips-unknown-linux -instrprof -vp-static-alloc=true -S | FileCheck %s --check-prefix=STATIC-SEXT
|
|
; RUN: opt < %s -mtriple=mips64-unknown-linux -instrprof -vp-static-alloc=true -S | FileCheck %s --check-prefix=STATIC-SEXT
|
|
; RUN: opt < %s -mtriple=x86_64-apple-macosx10.10.0 -vp-static-alloc=false -instrprof -S | FileCheck %s --check-prefix=DYN
|
|
; RUN: opt < %s -mtriple=x86_64-unknown-linux -instrprof -vp-static-alloc=false -S | FileCheck %s --check-prefix=DYN
|
|
|
|
|
|
@__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)
|
|
%2 = ptrtoint i32 ()* %0 to i64
|
|
call void @llvm.instrprof.value.profile(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @__profn_foo, i32 0, i32 0), i64 12884901887, i64 %2, i32 0, i32 0)
|
|
%3 = tail call i32 %0()
|
|
ret i32 %3
|
|
}
|
|
|
|
$bar = comdat any
|
|
|
|
define i32 @bar(i32 ()* ) comdat {
|
|
entry:
|
|
call void @llvm.instrprof.increment(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @__profn_bar, i32 0, i32 0), i64 12884901887, i32 1, i32 0)
|
|
%1 = ptrtoint i32 ()* %0 to i64
|
|
call void @llvm.instrprof.value.profile(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @__profn_bar, i32 0, i32 0), i64 12884901887, i64 %1, i32 0, i32 0)
|
|
%2 = tail call i32 %0()
|
|
ret i32 %2
|
|
}
|
|
|
|
; Function Attrs: nounwind
|
|
declare void @llvm.instrprof.increment(i8*, i64, i32, i32) #0
|
|
|
|
; Function Attrs: nounwind
|
|
declare void @llvm.instrprof.value.profile(i8*, i64, i64, i32, i32) #0
|
|
|
|
attributes #0 = { nounwind }
|
|
|
|
; STATIC: @__profvp_foo = private global [1 x i64] zeroinitializer, section "{{[^"]+}}", align 8
|
|
; STATIC: @__profvp_bar = private global [1 x i64] zeroinitializer, section "{{[^"]+}}", comdat($__profd_bar), align 8
|
|
; STATIC: @__llvm_prf_vnodes
|
|
|
|
; DYN-NOT: @__profvp_foo
|
|
; DYN-NOT: @__llvm_prf_vnodes
|
|
|
|
; STATIC: call void @__llvm_profile_instrument_target(i64 %3, i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 0)
|
|
; STATIC-EXT: call void @__llvm_profile_instrument_target(i64 %3, i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 zeroext 0)
|
|
; STATIC-SEXT: call void @__llvm_profile_instrument_target(i64 %3, i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 signext 0)
|
|
|
|
; STATIC: declare void @__llvm_profile_instrument_target(i64, i8*, i32)
|
|
; STATIC-EXT: declare void @__llvm_profile_instrument_target(i64, i8*, i32 zeroext)
|
|
; STATIC-SEXT: declare void @__llvm_profile_instrument_target(i64, i8*, i32 signext)
|