call-abi-compatibility.ll | Explore in Territory

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature
; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -S -passes=inline | FileCheck %s

; Test for PR52660.

; This call should not get inlined, because it would make the callee_not_avx
; call ABI incompatible.
define void @caller_avx() "target-features"="+avx" {
; CHECK-LABEL: define {{[^@]+}}@caller_avx
; CHECK-SAME: () #[[ATTR0:[0-9]+]] {
; CHECK-NEXT:    call void @caller_not_avx()
; CHECK-NEXT:    ret void
;
  call void @caller_not_avx()
  ret void
}

define internal void @caller_not_avx() {
; CHECK-LABEL: define {{[^@]+}}@caller_not_avx() {
; CHECK-NEXT:    [[TMP1:%.*]] = call i64 @callee_not_avx(<4 x i64> <i64 0, i64 1, i64 2, i64 3>)
; CHECK-NEXT:    ret void
;
  call i64 @callee_not_avx(<4 x i64> <i64 0, i64 1, i64 2, i64 3>)
  ret void
}

define i64 @callee_not_avx(<4 x i64> %arg) noinline {
; CHECK-LABEL: define {{[^@]+}}@callee_not_avx
; CHECK-SAME: (<4 x i64> [[ARG:%.*]]) #[[ATTR1:[0-9]+]] {
; CHECK-NEXT:    [[V:%.*]] = extractelement <4 x i64> [[ARG]], i64 2
; CHECK-NEXT:    ret i64 [[V]]
;
  %v = extractelement <4 x i64> %arg, i64 2
  ret i64 %v
}

; This call also shouldn't be inlined, as we don't know whether callee_unknown
; is ABI compatible or not.
define void @caller_avx2() "target-features"="+avx" {
; CHECK-LABEL: define {{[^@]+}}@caller_avx2
; CHECK-SAME: () #[[ATTR0]] {
; CHECK-NEXT:    call void @caller_not_avx2()
; CHECK-NEXT:    ret void
;
  call void @caller_not_avx2()
  ret void
}

define internal void @caller_not_avx2() {
; CHECK-LABEL: define {{[^@]+}}@caller_not_avx2() {
; CHECK-NEXT:    [[TMP1:%.*]] = call i64 @callee_unknown(<4 x i64> <i64 0, i64 1, i64 2, i64 3>)
; CHECK-NEXT:    ret void
;
  call i64 @callee_unknown(<4 x i64> <i64 0, i64 1, i64 2, i64 3>)
  ret void
}

declare i64 @callee_unknown(<4 x i64>)

; This call should get inlined, because we assume that intrinsics are always
; ABI compatible.
define void @caller_avx3() "target-features"="+avx" {
; CHECK-LABEL: define {{[^@]+}}@caller_avx3
; CHECK-SAME: () #[[ATTR0]] {
; CHECK-NEXT:    [[TMP1:%.*]] = call i64 @llvm.some_intrinsic(<4 x i64> <i64 0, i64 1, i64 2, i64 3>)
; CHECK-NEXT:    ret void
;
  call void @caller_not_avx3()
  ret void
}

define internal void @caller_not_avx3() {
  call i64 @llvm.some_intrinsic(<4 x i64> <i64 0, i64 1, i64 2, i64 3>)
  ret void
}

declare i64 @llvm.some_intrinsic(<4 x i64>)

; This call should get inlined, because only simple types are involved.
define void @caller_avx4() "target-features"="+avx" {
; CHECK-LABEL: define {{[^@]+}}@caller_avx4
; CHECK-SAME: () #[[ATTR0]] {
; CHECK-NEXT:    [[TMP1:%.*]] = call i64 @caller_unknown_simple(i64 0)
; CHECK-NEXT:    ret void
;
  call void @caller_not_avx4()
  ret void
}

define internal void @caller_not_avx4() {
  call i64 @caller_unknown_simple(i64 0)
  ret void
}

declare i64 @caller_unknown_simple(i64)

; This call should get inlined, because the callee only contains
; inline ASM, not real calls.
define <8 x i64> @caller_inline_asm(ptr %p0, i64 %k, ptr %p1, ptr %p2) #0 {
; CHECK-LABEL: define {{[^@]+}}@caller_inline_asm
; CHECK-SAME: (ptr [[P0:%.*]], i64 [[K:%.*]], ptr [[P1:%.*]], ptr [[P2:%.*]]) #[[ATTR2:[0-9]+]] {
; CHECK-NEXT:    [[SRC_I:%.*]] = load <8 x i64>, ptr [[P0]], align 64
; CHECK-NEXT:    [[A_I:%.*]] = load <8 x i64>, ptr [[P1]], align 64
; CHECK-NEXT:    [[B_I:%.*]] = load <8 x i64>, ptr [[P2]], align 64
; CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i64> asm "vpaddb\09$($3, $2, $0 {$1}", "=v,^Yk,v,v,0,~{dirflag},~{fpsr},~{flags}"(i64 [[K]], <8 x i64> [[A_I]], <8 x i64> [[B_I]], <8 x i64> [[SRC_I]])
; CHECK-NEXT:    ret <8 x i64> [[TMP1]]
;
  %call = call <8 x i64> @callee_inline_asm(ptr %p0, i64 %k, ptr %p1, ptr %p2)
  ret <8 x i64> %call
}

define internal <8 x i64> @callee_inline_asm(ptr %p0, i64 %k, ptr %p1, ptr %p2) #1 {
  %src = load <8 x i64>, ptr %p0, align 64
  %a = load <8 x i64>, ptr %p1, align 64
  %b = load <8 x i64>, ptr %p2, align 64
  %3 = tail call <8 x i64> asm "vpaddb\09$($3, $2, $0 {$1}", "=v,^Yk,v,v,0,~{dirflag},~{fpsr},~{flags}"(i64 %k, <8 x i64> %a, <8 x i64> %b, <8 x i64> %src) #2
  ret <8 x i64> %3
}

attributes #0 = { "min-legal-vector-width"="512" "target-features"="+avx,+avx2,+avx512bw,+avx512dq,+avx512f,+cmov,+crc32,+cx8,+evex512,+f16c,+fma,+fxsr,+mmx,+popcnt,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave" "tune-cpu"="generic" }
attributes #1 = { "min-legal-vector-width"="512" "target-features"="+avx,+avx2,+avx512bw,+avx512f,+cmov,+crc32,+cx8,+evex512,+f16c,+fma,+fxsr,+mmx,+popcnt,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave" "tune-cpu"="generic" }
llvm/llvm/test/Transforms/Inline/X86/call-abi-compatibility.ll
