959448fbd6
…ntElimination ArgumentPromotion and DeadArgumentElimination passes could change function signatures but the function name remains the same as before the transformation. This makes it hard for tracing with bpf programs where user tends to use function signature in the source. See discussion [1] for details. This patch added suffix to functions whose signatures are changed. The suffix lets users know that function signature has changed and they need to impact the IR or binary to find modified signature before tracing those functions. The suffix for ArgumentPromotion is ".argprom" and the suffixes for DeadArgumentElimination are ".argelim" and ".retelim". The suffix also gives user hints about what kind of transformation has been done. With this patch, I built a recent linux kernel with full LTO enabled. I got 4 functions with only argpromotion like ``` set_track_update.argelim.argprom pmd_trans_huge_lock.argprom ... ``` I got 1058 functions with only deadargelim like ``` process_bit0.argelim pci_io_ecs_init.argelim ... ``` I got 3 functions with both argpromotion and deadargelim ``` set_track_update.argelim.argprom zero_pud_populate.argelim.argprom zero_pmd_populate.argelim.argprom ``` [1] https://github.com/llvm/llvm-project/issues/104678
67 lines
2.1 KiB
LLVM
67 lines
2.1 KiB
LLVM
; RUN: opt -S --passes=ipsccp,deadargelim -funcspec-for-literal-constant --force-specialization < %s | FileCheck %s
|
|
|
|
; Test that all of `f0`, `f1`, and `f2` are specialised, even though `f0` has its address taken
|
|
; and `f1` is with external linkage (`f2` was specialised anyway).
|
|
|
|
@p = global ptr @f0
|
|
|
|
; `f0` is kept even though all apparent calls are specialized
|
|
; CHECK-LABEL: define internal i32 @f0(
|
|
define internal i32 @f0(i32 %i) {
|
|
%v = add i32 %i, 1
|
|
ret i32 %v
|
|
}
|
|
|
|
; Likewise, `f1` is kept, because of the external linkage
|
|
; CHECK-LABEL: define i32 @f1(
|
|
define i32 @f1(i32 %i) {
|
|
%v = add i32 %i, 1
|
|
ret i32 %v
|
|
}
|
|
|
|
; `f2` is fully specialised.
|
|
; CHECK-NOT: defined internal i32 @f2()
|
|
define internal i32 @f2(i32 %i) {
|
|
%v = add i32 %i, 1
|
|
ret i32 %v
|
|
}
|
|
|
|
;; All calls are to specilisation instances.
|
|
|
|
; CHECK-LABEL: define i32 @g0
|
|
; CHECK: call void @f0.specialized.[[#A:]].argelim()
|
|
; CHECK-NEXT: call void @f1.specialized.[[#B:]].argelim()
|
|
; CHECK-NEXT: call void @f2.specialized.[[#C:]].argelim()
|
|
; CHECK-NEXT: ret i32 9
|
|
define i32 @g0(i32 %i) {
|
|
%u0 = call i32 @f0(i32 1)
|
|
%u1 = call i32 @f1(i32 2)
|
|
%u2 = call i32 @f2(i32 3)
|
|
%v0 = add i32 %u0, %u1
|
|
%v = add i32 %v0, %u2
|
|
ret i32 %v
|
|
}
|
|
|
|
; CHECK-LABEL: define i32 @g1
|
|
; CHECK: call void @f0.specialized.[[#D:]].argelim()
|
|
; CHECK-NEXT: call void @f1.specialized.[[#E:]].argelim()
|
|
; CHECK-NEXT: call void @f2.specialized.[[#F:]].argelim()
|
|
; CHECK-NEXT: ret i32 12
|
|
define i32 @g1(i32 %i) {
|
|
%u0 = call i32 @f0(i32 2)
|
|
%u1 = call i32 @f1(i32 3)
|
|
%u2 = call i32 @f2(i32 4)
|
|
%v0 = add i32 %u0, %u1
|
|
%v = add i32 %v0, %u2
|
|
ret i32 %v
|
|
}
|
|
|
|
; All of the function are specialized and all clones are with internal linkage.
|
|
|
|
; CHECK-DAG: define internal void @f0.specialized.[[#A]].argelim() {
|
|
; CHECK-DAG: define internal void @f1.specialized.[[#B]].argelim() {
|
|
; CHECK-DAG: define internal void @f2.specialized.[[#C]].argelim() {
|
|
; CHECK-DAG: define internal void @f0.specialized.[[#D]].argelim() {
|
|
; CHECK-DAG: define internal void @f1.specialized.[[#E]].argelim() {
|
|
; CHECK-DAG: define internal void @f2.specialized.[[#F]].argelim() {
|