mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-22 10:42:39 +01:00
76489f90a5
`__profd_*` variables are referenced by code only when value profiling is enabled. If disabled (e.g. default -fprofile-instr-generate), the symbols just waste space on ELF/Mach-O. We change the comdat symbol from `__profd_*` to `__profc_*` because an internal symbol does not provide deduplication features on COFF. The choice doesn't matter on ELF. (In -DLLVM_BUILD_INSTRUMENTED_COVERAGE=on build, there is now no `__profd_*` symbols.) On Windows this enables further optimization. We are no longer affected by the link.exe limitation: an external symbol in IMAGE_COMDAT_SELECT_ASSOCIATIVE can cause duplicate definition error. https://lists.llvm.org/pipermail/llvm-dev/2021-May/150758.html We can thus use llvm.compiler.used instead of llvm.used like ELF (D97585). This avoids many `/INCLUDE:` directives in `.drectve`. Here is rnk's measurement for Chrome: ``` This reduced object file size of base_unittests.exe, compiled with coverage, optimizations, and gmlt debug info by 10%: #BEFORE $ find . -iname '*.obj' | xargs du -b | awk '{ sum += $1 } END { print sum}' 1047758867 $ du -cksh base_unittests.exe 82M base_unittests.exe 82M total # AFTER $ find . -iname '*.obj' | xargs du -b | awk '{ sum += $1 } END { print sum}' 937886499 $ du -cksh base_unittests.exe 78M base_unittests.exe 78M total ``` The change is NFC for Mach-O. Reviewed By: davidxl, rnk Differential Revision: https://reviews.llvm.org/D103372
66 lines
3.7 KiB
LLVM
66 lines
3.7 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
|
|
}
|
|
|
|
$bar = comdat any
|
|
|
|
define i32 @bar(i32 ()* ) comdat {
|
|
entry:
|
|
call void @llvm.instrprof.increment(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @__profn_bar, i32 0, i32 0), i64 12884901887, i32 1, i32 0)
|
|
%1 = ptrtoint i32 ()* %0 to i64
|
|
call void @llvm.instrprof.value.profile(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @__profn_bar, i32 0, i32 0), i64 12884901887, i64 %1, i32 0, i32 0)
|
|
%2 = tail call i32 %0()
|
|
ret i32 %2
|
|
}
|
|
|
|
; Function Attrs: nounwind
|
|
declare void @llvm.instrprof.increment(i8*, i64, i32, i32) #0
|
|
|
|
; Function Attrs: nounwind
|
|
declare void @llvm.instrprof.value.profile(i8*, i64, i64, i32, i32) #0
|
|
|
|
attributes #0 = { nounwind }
|
|
|
|
; STATIC: @__profvp_foo = private global [1 x i64] zeroinitializer, section "{{[^"]+}}"
|
|
; STATIC: @__profvp_bar = private global [1 x i64] zeroinitializer, section "{{[^"]+}}", comdat($__profc_bar)
|
|
; STATIC: @__llvm_prf_vnodes
|
|
|
|
; DYN-NOT: @__profvp_foo
|
|
; DYN-NOT: @__llvm_prf_vnodes
|
|
|
|
;; __llvm_prf_vnodes and __llvm_prf_nm are not referenced by other metadata sections.
|
|
;; We have to conservatively place them in llvm.used.
|
|
; STATIC: @llvm.used = appending global
|
|
; STATIC-SAME: @__llvm_prf_vnodes
|
|
; STATIC-SAME: @__llvm_prf_nm
|
|
|
|
; 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)
|