llvm-for-llvmta/test/CodeGen/X86/tailcall-64.ll

298 lines
8.4 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=x86_64-apple-macosx -mcpu=core2 < %s | FileCheck %s
declare i64 @testi()
define i64 @test_trivial() {
; CHECK-LABEL: test_trivial:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: jmp _testi ## TAILCALL
entry:
%A = tail call i64 @testi()
ret i64 %A
}
define i64 @test_noop_bitcast() {
; CHECK-LABEL: test_noop_bitcast:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: jmp _testi ## TAILCALL
entry:
%A = tail call i64 @testi()
%B = bitcast i64 %A to i64
ret i64 %B
}
; Tail call shouldn't be blocked by no-op inttoptr.
define i8* @test_inttoptr() {
; CHECK-LABEL: test_inttoptr:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: jmp _testi ## TAILCALL
entry:
%A = tail call i64 @testi()
%B = inttoptr i64 %A to i8*
ret i8* %B
}
declare <4 x float> @testv()
define <4 x i32> @test_vectorbitcast() {
; CHECK-LABEL: test_vectorbitcast:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: jmp _testv ## TAILCALL
entry:
%A = tail call <4 x float> @testv()
%B = bitcast <4 x float> %A to <4 x i32>
ret <4 x i32> %B
}
declare { i64, i64 } @testp()
define {i64, i64} @test_pair_trivial() {
; CHECK-LABEL: test_pair_trivial:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: jmp _testp ## TAILCALL
entry:
%A = tail call { i64, i64} @testp()
ret { i64, i64} %A
}
define {i64, i64} @test_pair_notail() {
; CHECK-LABEL: test_pair_notail:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: pushq %rax
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: callq _testi
; CHECK-NEXT: movq %rax, %rdx
; CHECK-NEXT: popq %rcx
; CHECK-NEXT: retq
entry:
%A = tail call i64 @testi()
%b = insertvalue {i64, i64} undef, i64 %A, 0
%c = insertvalue {i64, i64} %b, i64 %A, 1
ret { i64, i64} %c
}
define {i64, i64} @test_pair_extract_trivial() {
; CHECK-LABEL: test_pair_extract_trivial:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: jmp _testp ## TAILCALL
entry:
%A = tail call { i64, i64} @testp()
%x = extractvalue { i64, i64} %A, 0
%y = extractvalue { i64, i64} %A, 1
%b = insertvalue {i64, i64} undef, i64 %x, 0
%c = insertvalue {i64, i64} %b, i64 %y, 1
ret { i64, i64} %c
}
define {i64, i64} @test_pair_extract_notail() {
; CHECK-LABEL: test_pair_extract_notail:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: pushq %rax
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: callq _testp
; CHECK-NEXT: movq %rax, %rcx
; CHECK-NEXT: movq %rdx, %rax
; CHECK-NEXT: movq %rcx, %rdx
; CHECK-NEXT: popq %rcx
; CHECK-NEXT: retq
entry:
%A = tail call { i64, i64} @testp()
%x = extractvalue { i64, i64} %A, 0
%y = extractvalue { i64, i64} %A, 1
%b = insertvalue {i64, i64} undef, i64 %y, 0
%c = insertvalue {i64, i64} %b, i64 %x, 1
ret { i64, i64} %c
}
define {i8*, i64} @test_pair_extract_conv() {
; CHECK-LABEL: test_pair_extract_conv:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: jmp _testp ## TAILCALL
entry:
%A = tail call { i64, i64} @testp()
%x = extractvalue { i64, i64} %A, 0
%y = extractvalue { i64, i64} %A, 1
%x1 = inttoptr i64 %x to i8*
%b = insertvalue {i8*, i64} undef, i8* %x1, 0
%c = insertvalue {i8*, i64} %b, i64 %y, 1
ret { i8*, i64} %c
}
define {i64, i64} @test_pair_extract_multiple() {
; CHECK-LABEL: test_pair_extract_multiple:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: jmp _testp ## TAILCALL
entry:
%A = tail call { i64, i64} @testp()
%x = extractvalue { i64, i64} %A, 0
%y = extractvalue { i64, i64} %A, 1
%b = insertvalue {i64, i64} undef, i64 %x, 0
%c = insertvalue {i64, i64} %b, i64 %y, 1
%x1 = extractvalue { i64, i64} %b, 0
%y1 = extractvalue { i64, i64} %c, 1
%d = insertvalue {i64, i64} undef, i64 %x1, 0
%e = insertvalue {i64, i64} %b, i64 %y1, 1
ret { i64, i64} %e
}
define {i64, i64} @test_pair_extract_undef() {
; CHECK-LABEL: test_pair_extract_undef:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: jmp _testp ## TAILCALL
entry:
%A = tail call { i64, i64} @testp()
%x = extractvalue { i64, i64} %A, 0
%b = insertvalue {i64, i64} undef, i64 %x, 0
ret { i64, i64} %b
}
declare { i64, { i32, i32 } } @testn()
define {i64, {i32, i32}} @test_nest() {
; CHECK-LABEL: test_nest:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: jmp _testn ## TAILCALL
entry:
%A = tail call { i64, { i32, i32 } } @testn()
%x = extractvalue { i64, { i32, i32}} %A, 0
%y = extractvalue { i64, { i32, i32}} %A, 1
%y1 = extractvalue { i32, i32} %y, 0
%y2 = extractvalue { i32, i32} %y, 1
%b = insertvalue {i64, {i32, i32}} undef, i64 %x, 0
%c1 = insertvalue {i32, i32} undef, i32 %y1, 0
%c2 = insertvalue {i32, i32} %c1, i32 %y2, 1
%c = insertvalue {i64, {i32, i32}} %b, {i32, i32} %c2, 1
ret { i64, { i32, i32}} %c
}
%struct.A = type { i32 }
%struct.B = type { %struct.A, i32 }
declare %struct.B* @testu()
define %struct.A* @test_upcast() {
; CHECK-LABEL: test_upcast:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: jmp _testu ## TAILCALL
entry:
%A = tail call %struct.B* @testu()
%x = getelementptr inbounds %struct.B, %struct.B* %A, i32 0, i32 0
ret %struct.A* %x
}
; PR13006
define { i64, i64 } @crash(i8* %this) {
; CHECK-LABEL: crash:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: jmp _testp ## TAILCALL
entry:
%c = tail call { i64, i64 } @testp()
%mrv7 = insertvalue { i64, i64 } %c, i64 undef, 1
ret { i64, i64 } %mrv7
}
%struct.funcs = type { i32 (i8*, i32*, i32)*, i32 (i8*)*, i32 (i8*)*, i32 (i8*, i32)*, i32 }
@func_table = external global [0 x %struct.funcs]
; Check that we can fold an indexed load into a tail call instruction.
define void @fold_indexed_load(i8* %mbstr, i64 %idxprom) nounwind uwtable ssp {
; CHECK-LABEL: fold_indexed_load:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: leaq (%rsi,%rsi,4), %rax
; CHECK-NEXT: movq _func_table@{{.*}}(%rip), %rcx
; CHECK-NEXT: jmpq *16(%rcx,%rax,8) ## TAILCALL
entry:
%dsplen = getelementptr inbounds [0 x %struct.funcs], [0 x %struct.funcs]* @func_table, i64 0, i64 %idxprom, i32 2
%x1 = load i32 (i8*)*, i32 (i8*)** %dsplen, align 8
%call = tail call i32 %x1(i8* %mbstr) nounwind
ret void
}
@funcs = external constant [0 x i32 (i8*, ...)*]
; <rdar://problem/12282281> Fold an indexed load into the tail call instruction.
; Calling a varargs function with 6 arguments requires 7 registers (%al is the
; vector count for varargs functions). This leaves %r11 as the only available
; scratch register.
;
; It is not possible to fold an indexed load into TCRETURNmi64 in that case.
;
; typedef int (*funcptr)(void*, ...);
; extern const funcptr funcs[];
; int f(int n) {
; return funcs[n](0, 0, 0, 0, 0, 0);
; }
define i32 @rdar12282281(i32 %n) nounwind uwtable ssp {
; CHECK-LABEL: rdar12282281:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: movslq %edi, %rax
; CHECK-NEXT: movq _funcs@{{.*}}(%rip), %rcx
; CHECK-NEXT: movq (%rcx,%rax,8), %r11
; CHECK-NEXT: xorl %edi, %edi
; CHECK-NEXT: xorl %esi, %esi
; CHECK-NEXT: xorl %edx, %edx
; CHECK-NEXT: xorl %ecx, %ecx
; CHECK-NEXT: xorl %r8d, %r8d
; CHECK-NEXT: xorl %r9d, %r9d
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: jmpq *%r11 ## TAILCALL
entry:
%idxprom = sext i32 %n to i64
%arrayidx = getelementptr inbounds [0 x i32 (i8*, ...)*], [0 x i32 (i8*, ...)*]* @funcs, i64 0, i64 %idxprom
%0 = load i32 (i8*, ...)*, i32 (i8*, ...)** %arrayidx, align 8
%call = tail call i32 (i8*, ...) %0(i8* null, i32 0, i32 0, i32 0, i32 0, i32 0) nounwind
ret i32 %call
}
declare x86_fp80 @fp80_callee(x86_fp80)
define x86_fp80 @fp80_call(x86_fp80 %x) nounwind {
; CHECK-LABEL: fp80_call:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: jmp _fp80_callee ## TAILCALL
entry:
%call = tail call x86_fp80 @fp80_callee(x86_fp80 %x) nounwind
ret x86_fp80 %call
}
declare double @trunc(double) nounwind readnone
; rdar://12229511 - Don't tail call trunc here.
define x86_fp80 @trunc_fp80(x86_fp80 %x) nounwind {
; CHECK-LABEL: trunc_fp80:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: subq $24, %rsp
; CHECK-NEXT: fldt {{[0-9]+}}(%rsp)
; CHECK-NEXT: fstpl {{[0-9]+}}(%rsp)
; CHECK-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT: callq _trunc
; CHECK-NEXT: movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT: fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT: addq $24, %rsp
; CHECK-NEXT: retq
entry:
%conv = fptrunc x86_fp80 %x to double
%call = tail call double @trunc(double %conv) nounwind readnone
%conv1 = fpext double %call to x86_fp80
ret x86_fp80 %conv1
}