16e74fd489
New change on top of [reviewed patch](https://github.com/llvm/llvm-project/pull/81691) are [in commits after this one](d0757f46b3). Previous commits are restored from the remote branch with timestamps. 1. Fix build breakage for non-ELF platforms, by defining the missing functions {`__llvm_profile_begin_vtables`, `__llvm_profile_end_vtables`, `__llvm_profile_begin_vtabnames `, `__llvm_profile_end_vtabnames`} everywhere. * Tested on mac laptop (for darwins) and Windows. Specifically, functions in `InstrProfilingPlatformWindows.c` returns `NULL` to make it more explicit that type prof isn't supported; see comments for the reason. * For the rest (AIX, other), mostly follow existing examples (like this [one](f95b2f1acf)) 2. Rename `__llvm_prf_vtabnames` -> `__llvm_prf_vns` for shorter section name, and make returned pointers [const](a825d2a4ec (diff-4de780ce726d76b7abc9d3353aef95013e7b21e7bda01be8940cc6574fb0b5ffR120-R121)) **Original Description** * Raw profile format - Header: records the byte size of compressed vtable names, and the number of profiled vtable entries (call it `VTableProfData`). Header also records padded bytes of each section. - Payload: adds a section for compressed vtable names, and a section to store `VTableProfData`. Both sections are padded so the size is a multiple of 8. * Indexed profile format - Header: records the byte offset of compressed vtable names. - Payload: adds a section to store compressed vtable names. This section is used by `llvm-profdata` to show the list of vtables profiled for an instrumented site. [The originally reviewed patch](https://github.com/llvm/llvm-project/pull/66825) will have profile reader/write change and llvm-profdata change. - To ensure this PR has all the necessary profile format change along with profile version bump, created a copy of the originally reviewed patch in https://github.com/llvm/llvm-project/pull/80761. The copy doesn't have profile format change, but it has the set of tests which covers type profile generation, profile read and profile merge. Tests pass there. rfc in https://discourse.llvm.org/t/rfc-dynamic-type-profiling-and-optimizations-in-llvm/74600 --------- Co-authored-by: modiking <modiking213@gmail.com>
32 lines
1.7 KiB
LLVM
32 lines
1.7 KiB
LLVM
; RUN: opt < %s -passes=instrprof -S | FileCheck %s
|
|
; RUN: opt < %s -passes=instrprof -profile-correlate=binary -S | FileCheck %s --check-prefix=BINARY
|
|
|
|
target triple = "aarch64-unknown-linux-gnu"
|
|
|
|
@__profn_foo = private constant [3 x i8] c"foo"
|
|
; CHECK: @__profc_foo = private global [1 x i8] c"\FF", section "__llvm_prf_cnts", comdat, align 1
|
|
; CHECK: @__profd_foo = private global { i64, i64, i64, i64, ptr, ptr, i32, [3 x i16], i32 } { i64 {{.*}}, i64 {{.*}}, i64 sub (i64 ptrtoint (ptr @__profc_foo to i64)
|
|
; BINARY: @__profd_foo = private global { i64, i64, i64, i64, ptr, ptr, i32, [3 x i16], i32 } { i64 {{.*}}, i64 {{.*}}, i64 ptrtoint (ptr @__profc_foo to i64),
|
|
@__profn_bar = private constant [3 x i8] c"bar"
|
|
; CHECK: @__profc_bar = private global [1 x i8] c"\FF", section "__llvm_prf_cnts", comdat, align 1
|
|
; CHECK: @__profd_bar = private global { i64, i64, i64, i64, ptr, ptr, i32, [3 x i16], i32 } { i64 {{.*}}, i64 {{.*}}, i64 sub (i64 ptrtoint (ptr @__profc_bar to i64)
|
|
; BINARY: @__profd_bar = private global { i64, i64, i64, i64, ptr, ptr, i32, [3 x i16], i32 } { i64 {{.*}}, i64 {{.*}}, i64 ptrtoint (ptr @__profc_bar to i64),
|
|
|
|
; CHECK: @__llvm_prf_nm = {{.*}} section "__llvm_prf_names"
|
|
; BINARY: @__llvm_prf_nm ={{.*}} section "__llvm_covnames"
|
|
|
|
define void @_Z3foov() {
|
|
call void @llvm.instrprof.cover(ptr @__profn_foo, i64 12345678, i32 1, i32 0)
|
|
; CHECK: store i8 0, ptr @__profc_foo, align 1
|
|
ret void
|
|
}
|
|
|
|
%class.A = type { ptr }
|
|
define dso_local void @_Z3barv(ptr nocapture nonnull align 8 %0) unnamed_addr #0 align 2 {
|
|
call void @llvm.instrprof.cover(ptr @__profn_bar, i64 87654321, i32 1, i32 0)
|
|
; CHECK: store i8 0, ptr @__profc_bar, align 1
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.instrprof.cover(ptr, i64, i32, i32)
|