11d3074267
Use the llvm flag `-pgo-function-entry-coverage` to create single byte "counters" to track functions coverage. This mode has significantly less size overhead in both code and data because * We mark a function as "covered" with a store instead of an increment which generally requires fewer assembly instructions * We use a single byte per function rather than 8 bytes per block The trade off of course is that this mode only tells you if a function has been covered. This is useful, for example, to detect dead code. When combined with debug info correlation [0] we are able to create an instrumented Clang binary that is only 150M (the vanilla Clang binary is 143M). That is an overhead of 7M (4.9%) compared to the default instrumentation (without value profiling) which has an overhead of 31M (21.7%). [0] https://groups.google.com/g/llvm-dev/c/r03Z6JoN7d4 Reviewed By: kyulee Differential Revision: https://reviews.llvm.org/D116180
24 lines
1.1 KiB
LLVM
24 lines
1.1 KiB
LLVM
; RUN: opt < %s -instrprof -S | FileCheck %s
|
|
|
|
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
|
|
@__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
|
|
|
|
define void @_Z3foov() {
|
|
call void @llvm.instrprof.cover(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @__profn_foo, i32 0, i32 0), i64 12345678, i32 1, i32 0)
|
|
; CHECK: store i8 0, i8* getelementptr inbounds ([1 x i8], [1 x i8]* @__profc_foo, i32 0, i32 0), align 1
|
|
ret void
|
|
}
|
|
|
|
%class.A = type { i32 (...)** }
|
|
define dso_local void @_Z3barv(%class.A* nocapture nonnull align 8 %0) unnamed_addr #0 align 2 {
|
|
call void @llvm.instrprof.cover(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @__profn_bar, i32 0, i32 0), i64 87654321, i32 1, i32 0)
|
|
; CHECK: store i8 0, i8* getelementptr inbounds ([1 x i8], [1 x i8]* @__profc_bar, i32 0, i32 0), align 1
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.instrprof.cover(i8*, i64, i32, i32)
|