; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc --mtriple=loongarch64 --target-abi=lp64s < %s | FileCheck %s
; RUN: llc --mtriple=loongarch64 --mattr=+d --target-abi=lp64d < %s | FileCheck %s

;; This file contains tests that should have identical output for all ABIs, i.e.
;; where no arguments are passed via floating point registers.

;; Check that on LA64, i128 is passed in a pair of GPRs.
define i64 @callee_i128_in_regs(i64 %a, i128 %b) nounwind {
; CHECK-LABEL: callee_i128_in_regs:
; CHECK:       # %bb.0:
; CHECK-NEXT:    add.d $a0, $a0, $a1
; CHECK-NEXT:    ret
  %b_trunc = trunc i128 %b to i64
  %1 = add i64 %a, %b_trunc
  ret i64 %1
}

define i64 @caller_i128_in_regs() nounwind {
; CHECK-LABEL: caller_i128_in_regs:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi.d $sp, $sp, -16
; CHECK-NEXT:    st.d $ra, $sp, 8 # 8-byte Folded Spill
; CHECK-NEXT:    ori $a0, $zero, 1
; CHECK-NEXT:    ori $a1, $zero, 2
; CHECK-NEXT:    move $a2, $zero
; CHECK-NEXT:    bl %plt(callee_i128_in_regs)
; CHECK-NEXT:    ld.d $ra, $sp, 8 # 8-byte Folded Reload
; CHECK-NEXT:    addi.d $sp, $sp, 16
; CHECK-NEXT:    ret
  %1 = call i64 @callee_i128_in_regs(i64 1, i128 2)
  ret i64 %1
}

;; Check that the stack is used once the GPRs are exhausted.
define i64 @callee_many_scalars(i8 %a, i16 %b, i32 %c, i64 %d, i128 %e, i64 %f, i128 %g, i64 %h) nounwind {
; CHECK-LABEL: callee_many_scalars:
; CHECK:       # %bb.0:
; CHECK-NEXT:    ld.d $t0, $sp, 0
; CHECK-NEXT:    xor $a5, $a5, $t0
; CHECK-NEXT:    xor $a4, $a4, $a7
; CHECK-NEXT:    or $a4, $a4, $a5
; CHECK-NEXT:    bstrpick.d $a1, $a1, 15, 0
; CHECK-NEXT:    andi $a0, $a0, 255
; CHECK-NEXT:    add.d $a0, $a0, $a1
; CHECK-NEXT:    bstrpick.d $a1, $a2, 31, 0
; CHECK-NEXT:    add.d $a0, $a0, $a1
; CHECK-NEXT:    add.d $a0, $a0, $a3
; CHECK-NEXT:    sltui $a1, $a4, 1
; CHECK-NEXT:    add.d $a0, $a1, $a0
; CHECK-NEXT:    add.d $a0, $a0, $a6
; CHECK-NEXT:    ld.d $a1, $sp, 8
; CHECK-NEXT:    add.d $a0, $a0, $a1
; CHECK-NEXT:    ret
  %a_ext = zext i8 %a to i64
  %b_ext = zext i16 %b to i64
  %c_ext = zext i32 %c to i64
  %1 = add i64 %a_ext, %b_ext
  %2 = add i64 %1, %c_ext
  %3 = add i64 %2, %d
  %4 = icmp eq i128 %e, %g
  %5 = zext i1 %4 to i64
  %6 = add i64 %5, %3
  %7 = add i64 %6, %f
  %8 = add i64 %7, %h
  ret i64 %8
}

define i64 @caller_many_scalars() nounwind {
; CHECK-LABEL: caller_many_scalars:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi.d $sp, $sp, -32
; CHECK-NEXT:    st.d $ra, $sp, 24 # 8-byte Folded Spill
; CHECK-NEXT:    ori $a0, $zero, 8
; CHECK-NEXT:    st.d $a0, $sp, 8
; CHECK-NEXT:    st.d $zero, $sp, 0
; CHECK-NEXT:    ori $a0, $zero, 1
; CHECK-NEXT:    ori $a1, $zero, 2
; CHECK-NEXT:    ori $a2, $zero, 3
; CHECK-NEXT:    ori $a3, $zero, 4
; CHECK-NEXT:    ori $a4, $zero, 5
; CHECK-NEXT:    ori $a6, $zero, 6
; CHECK-NEXT:    ori $a7, $zero, 7
; CHECK-NEXT:    move $a5, $zero
; CHECK-NEXT:    bl %plt(callee_many_scalars)
; CHECK-NEXT:    ld.d $ra, $sp, 24 # 8-byte Folded Reload
; CHECK-NEXT:    addi.d $sp, $sp, 32
; CHECK-NEXT:    ret
  %1 = call i64 @callee_many_scalars(i8 1, i16 2, i32 3, i64 4, i128 5, i64 6, i128 7, i64 8)
  ret i64 %1
}

;; Check that i256 is passed indirectly.

define i64 @callee_large_scalars(i256 %a, i256 %b) nounwind {
; CHECK-LABEL: callee_large_scalars:
; CHECK:       # %bb.0:
; CHECK-NEXT:    ld.d $a2, $a1, 24
; CHECK-NEXT:    ld.d $a3, $a0, 24
; CHECK-NEXT:    xor $a2, $a3, $a2
; CHECK-NEXT:    ld.d $a3, $a1, 8
; CHECK-NEXT:    ld.d $a4, $a0, 8
; CHECK-NEXT:    xor $a3, $a4, $a3
; CHECK-NEXT:    or $a2, $a3, $a2
; CHECK-NEXT:    ld.d $a3, $a1, 16
; CHECK-NEXT:    ld.d $a4, $a0, 16
; CHECK-NEXT:    xor $a3, $a4, $a3
; CHECK-NEXT:    ld.d $a1, $a1, 0
; CHECK-NEXT:    ld.d $a0, $a0, 0
; CHECK-NEXT:    xor $a0, $a0, $a1
; CHECK-NEXT:    or $a0, $a0, $a3
; CHECK-NEXT:    or $a0, $a0, $a2
; CHECK-NEXT:    sltui $a0, $a0, 1
; CHECK-NEXT:    ret
  %1 = icmp eq i256 %a, %b
  %2 = zext i1 %1 to i64
  ret i64 %2
}

define i64 @caller_large_scalars() nounwind {
; CHECK-LABEL: caller_large_scalars:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi.d $sp, $sp, -80
; CHECK-NEXT:    st.d $ra, $sp, 72 # 8-byte Folded Spill
; CHECK-NEXT:    ori $a0, $zero, 2
; CHECK-NEXT:    st.d $a0, $sp, 0
; CHECK-NEXT:    st.d $zero, $sp, 24
; CHECK-NEXT:    st.d $zero, $sp, 16
; CHECK-NEXT:    st.d $zero, $sp, 8
; CHECK-NEXT:    st.d $zero, $sp, 56
; CHECK-NEXT:    st.d $zero, $sp, 48
; CHECK-NEXT:    st.d $zero, $sp, 40
; CHECK-NEXT:    ori $a0, $zero, 1
; CHECK-NEXT:    st.d $a0, $sp, 32
; CHECK-NEXT:    addi.d $a0, $sp, 32
; CHECK-NEXT:    addi.d $a1, $sp, 0
; CHECK-NEXT:    bl %plt(callee_large_scalars)
; CHECK-NEXT:    ld.d $ra, $sp, 72 # 8-byte Folded Reload
; CHECK-NEXT:    addi.d $sp, $sp, 80
; CHECK-NEXT:    ret
  %1 = call i64 @callee_large_scalars(i256 1, i256 2)
  ret i64 %1
}

;; Check that arguments larger than 2*GRLen are handled correctly when their
;; address is passed on the stack rather than in memory.

;; Must keep define on a single line due to an update_llc_test_checks.py limitation
define i64 @callee_large_scalars_exhausted_regs(i64 %a, i64 %b, i64 %c, i64 %d, i64 %e, i64 %f, i64 %g, i256 %h, i64 %i, i256 %j) nounwind {
; CHECK-LABEL: callee_large_scalars_exhausted_regs:
; CHECK:       # %bb.0:
; CHECK-NEXT:    ld.d $a0, $sp, 8
; CHECK-NEXT:    ld.d $a1, $a0, 24
; CHECK-NEXT:    ld.d $a2, $a7, 24
; CHECK-NEXT:    xor $a1, $a2, $a1
; CHECK-NEXT:    ld.d $a2, $a0, 8
; CHECK-NEXT:    ld.d $a3, $a7, 8
; CHECK-NEXT:    xor $a2, $a3, $a2
; CHECK-NEXT:    or $a1, $a2, $a1
; CHECK-NEXT:    ld.d $a2, $a0, 16
; CHECK-NEXT:    ld.d $a3, $a7, 16
; CHECK-NEXT:    xor $a2, $a3, $a2
; CHECK-NEXT:    ld.d $a0, $a0, 0
; CHECK-NEXT:    ld.d $a3, $a7, 0
; CHECK-NEXT:    xor $a0, $a3, $a0
; CHECK-NEXT:    or $a0, $a0, $a2
; CHECK-NEXT:    or $a0, $a0, $a1
; CHECK-NEXT:    sltui $a0, $a0, 1
; CHECK-NEXT:    ret
  %1 = icmp eq i256 %h, %j
  %2 = zext i1 %1 to i64
  ret i64 %2
}

define i64 @caller_large_scalars_exhausted_regs() nounwind {
; CHECK-LABEL: caller_large_scalars_exhausted_regs:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi.d $sp, $sp, -96
; CHECK-NEXT:    st.d $ra, $sp, 88 # 8-byte Folded Spill
; CHECK-NEXT:    addi.d $a0, $sp, 16
; CHECK-NEXT:    st.d $a0, $sp, 8
; CHECK-NEXT:    ori $a0, $zero, 9
; CHECK-NEXT:    st.d $a0, $sp, 0
; CHECK-NEXT:    ori $a0, $zero, 10
; CHECK-NEXT:    st.d $a0, $sp, 16
; CHECK-NEXT:    st.d $zero, $sp, 40
; CHECK-NEXT:    st.d $zero, $sp, 32
; CHECK-NEXT:    st.d $zero, $sp, 24
; CHECK-NEXT:    st.d $zero, $sp, 72
; CHECK-NEXT:    st.d $zero, $sp, 64
; CHECK-NEXT:    st.d $zero, $sp, 56
; CHECK-NEXT:    ori $a0, $zero, 8
; CHECK-NEXT:    st.d $a0, $sp, 48
; CHECK-NEXT:    ori $a0, $zero, 1
; CHECK-NEXT:    ori $a1, $zero, 2
; CHECK-NEXT:    ori $a2, $zero, 3
; CHECK-NEXT:    ori $a3, $zero, 4
; CHECK-NEXT:    ori $a4, $zero, 5
; CHECK-NEXT:    ori $a5, $zero, 6
; CHECK-NEXT:    ori $a6, $zero, 7
; CHECK-NEXT:    addi.d $a7, $sp, 48
; CHECK-NEXT:    bl %plt(callee_large_scalars_exhausted_regs)
; CHECK-NEXT:    ld.d $ra, $sp, 88 # 8-byte Folded Reload
; CHECK-NEXT:    addi.d $sp, $sp, 96
; CHECK-NEXT:    ret
  %1 = call i64 @callee_large_scalars_exhausted_regs(
      i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i256 8, i64 9,
      i256 10)
  ret i64 %1
}

;; Check large struct arguments, which are passed byval

%struct.large = type { i64, i64, i64, i64 }

define i64 @callee_large_struct(ptr byval(%struct.large) align 8 %a) nounwind {
; CHECK-LABEL: callee_large_struct:
; CHECK:       # %bb.0:
; CHECK-NEXT:    ld.d $a1, $a0, 24
; CHECK-NEXT:    ld.d $a0, $a0, 0
; CHECK-NEXT:    add.d $a0, $a0, $a1
; CHECK-NEXT:    ret
  %1 = getelementptr inbounds %struct.large, ptr %a, i64 0, i32 0
  %2 = getelementptr inbounds %struct.large, ptr %a, i64 0, i32 3
  %3 = load i64, ptr %1
  %4 = load i64, ptr %2
  %5 = add i64 %3, %4
  ret i64 %5
}

define i64 @caller_large_struct() nounwind {
; CHECK-LABEL: caller_large_struct:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi.d $sp, $sp, -80
; CHECK-NEXT:    st.d $ra, $sp, 72 # 8-byte Folded Spill
; CHECK-NEXT:    ori $a0, $zero, 1
; CHECK-NEXT:    st.d $a0, $sp, 40
; CHECK-NEXT:    st.d $a0, $sp, 8
; CHECK-NEXT:    ori $a0, $zero, 2
; CHECK-NEXT:    st.d $a0, $sp, 48
; CHECK-NEXT:    st.d $a0, $sp, 16
; CHECK-NEXT:    ori $a0, $zero, 3
; CHECK-NEXT:    st.d $a0, $sp, 56
; CHECK-NEXT:    st.d $a0, $sp, 24
; CHECK-NEXT:    ori $a0, $zero, 4
; CHECK-NEXT:    st.d $a0, $sp, 64
; CHECK-NEXT:    st.d $a0, $sp, 32
; CHECK-NEXT:    addi.d $a0, $sp, 8
; CHECK-NEXT:    bl %plt(callee_large_struct)
; CHECK-NEXT:    ld.d $ra, $sp, 72 # 8-byte Folded Reload
; CHECK-NEXT:    addi.d $sp, $sp, 80
; CHECK-NEXT:    ret
  %ls = alloca %struct.large, align 8
  %a = getelementptr inbounds %struct.large, ptr %ls, i64 0, i32 0
  store i64 1, ptr %a
  %b = getelementptr inbounds %struct.large, ptr %ls, i64 0, i32 1
  store i64 2, ptr %b
  %c = getelementptr inbounds %struct.large, ptr %ls, i64 0, i32 2
  store i64 3, ptr %c
  %d = getelementptr inbounds %struct.large, ptr %ls, i64 0, i32 3
  store i64 4, ptr %d
  %1 = call i64 @callee_large_struct(ptr byval(%struct.large) align 8 %ls)
  ret i64 %1
}

;; Check return scalar which size is 2*GRLen.

define i128 @callee_small_scalar_ret() nounwind {
; CHECK-LABEL: callee_small_scalar_ret:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi.w $a0, $zero, -1
; CHECK-NEXT:    move $a1, $a0
; CHECK-NEXT:    ret
  ret i128 -1
}

define i64 @caller_small_scalar_ret() nounwind {
; CHECK-LABEL: caller_small_scalar_ret:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi.d $sp, $sp, -16
; CHECK-NEXT:    st.d $ra, $sp, 8 # 8-byte Folded Spill
; CHECK-NEXT:    bl %plt(callee_small_scalar_ret)
; CHECK-NEXT:    addi.w $a2, $zero, -2
; CHECK-NEXT:    xor $a0, $a0, $a2
; CHECK-NEXT:    orn $a0, $a0, $a1
; CHECK-NEXT:    sltui $a0, $a0, 1
; CHECK-NEXT:    ld.d $ra, $sp, 8 # 8-byte Folded Reload
; CHECK-NEXT:    addi.d $sp, $sp, 16
; CHECK-NEXT:    ret
  %1 = call i128 @callee_small_scalar_ret()
  %2 = icmp eq i128 -2, %1
  %3 = zext i1 %2 to i64
  ret i64 %3
}

;; Check return struct which size is 2*GRLen.

%struct.small = type { i64, ptr }

define %struct.small @callee_small_struct_ret() nounwind {
; CHECK-LABEL: callee_small_struct_ret:
; CHECK:       # %bb.0:
; CHECK-NEXT:    ori $a0, $zero, 1
; CHECK-NEXT:    move $a1, $zero
; CHECK-NEXT:    ret
  ret %struct.small { i64 1, ptr null }
}

define i64 @caller_small_struct_ret() nounwind {
; CHECK-LABEL: caller_small_struct_ret:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi.d $sp, $sp, -16
; CHECK-NEXT:    st.d $ra, $sp, 8 # 8-byte Folded Spill
; CHECK-NEXT:    bl %plt(callee_small_struct_ret)
; CHECK-NEXT:    add.d $a0, $a0, $a1
; CHECK-NEXT:    ld.d $ra, $sp, 8 # 8-byte Folded Reload
; CHECK-NEXT:    addi.d $sp, $sp, 16
; CHECK-NEXT:    ret
  %1 = call %struct.small @callee_small_struct_ret()
  %2 = extractvalue %struct.small %1, 0
  %3 = extractvalue %struct.small %1, 1
  %4 = ptrtoint ptr %3 to i64
  %5 = add i64 %2, %4
  ret i64 %5
}

;; Check return scalar which size is more than 2*GRLen.

define i256 @callee_large_scalar_ret() nounwind {
; CHECK-LABEL: callee_large_scalar_ret:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi.w $a1, $zero, -1
; CHECK-NEXT:    st.d $a1, $a0, 24
; CHECK-NEXT:    st.d $a1, $a0, 16
; CHECK-NEXT:    st.d $a1, $a0, 8
; CHECK-NEXT:    lu12i.w $a1, -30141
; CHECK-NEXT:    ori $a1, $a1, 747
; CHECK-NEXT:    st.d $a1, $a0, 0
; CHECK-NEXT:    ret
  ret i256 -123456789
}

define void @caller_large_scalar_ret() nounwind {
; CHECK-LABEL: caller_large_scalar_ret:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi.d $sp, $sp, -48
; CHECK-NEXT:    st.d $ra, $sp, 40 # 8-byte Folded Spill
; CHECK-NEXT:    addi.d $a0, $sp, 0
; CHECK-NEXT:    bl %plt(callee_large_scalar_ret)
; CHECK-NEXT:    ld.d $ra, $sp, 40 # 8-byte Folded Reload
; CHECK-NEXT:    addi.d $sp, $sp, 48
; CHECK-NEXT:    ret
  %1 = call i256 @callee_large_scalar_ret()
  ret void
}

;; Check return struct which size is more than 2*GRLen.

define void @callee_large_struct_ret(ptr noalias sret(%struct.large) %agg.result) nounwind {
; CHECK-LABEL: callee_large_struct_ret:
; CHECK:       # %bb.0:
; CHECK-NEXT:    ori $a1, $zero, 4
; CHECK-NEXT:    st.d $a1, $a0, 24
; CHECK-NEXT:    ori $a1, $zero, 3
; CHECK-NEXT:    st.d $a1, $a0, 16
; CHECK-NEXT:    ori $a1, $zero, 2
; CHECK-NEXT:    st.d $a1, $a0, 8
; CHECK-NEXT:    ori $a1, $zero, 1
; CHECK-NEXT:    st.d $a1, $a0, 0
; CHECK-NEXT:    ret
  %a = getelementptr inbounds %struct.large, ptr %agg.result, i64 0, i32 0
  store i64 1, ptr %a, align 4
  %b = getelementptr inbounds %struct.large, ptr %agg.result, i64 0, i32 1
  store i64 2, ptr %b, align 4
  %c = getelementptr inbounds %struct.large, ptr %agg.result, i64 0, i32 2
  store i64 3, ptr %c, align 4
  %d = getelementptr inbounds %struct.large, ptr %agg.result, i64 0, i32 3
  store i64 4, ptr %d, align 4
  ret void
}

define i64 @caller_large_struct_ret() nounwind {
; CHECK-LABEL: caller_large_struct_ret:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi.d $sp, $sp, -48
; CHECK-NEXT:    st.d $ra, $sp, 40 # 8-byte Folded Spill
; CHECK-NEXT:    addi.d $a0, $sp, 8
; CHECK-NEXT:    bl %plt(callee_large_struct_ret)
; CHECK-NEXT:    ld.d $a0, $sp, 32
; CHECK-NEXT:    ld.d $a1, $sp, 8
; CHECK-NEXT:    add.d $a0, $a1, $a0
; CHECK-NEXT:    ld.d $ra, $sp, 40 # 8-byte Folded Reload
; CHECK-NEXT:    addi.d $sp, $sp, 48
; CHECK-NEXT:    ret
  %1 = alloca %struct.large
  call void @callee_large_struct_ret(ptr sret(%struct.large) %1)
  %2 = getelementptr inbounds %struct.large, ptr %1, i64 0, i32 0
  %3 = load i64, ptr %2
  %4 = getelementptr inbounds %struct.large, ptr %1, i64 0, i32 3
  %5 = load i64, ptr %4
  %6 = add i64 %3, %5
  ret i64 %6
}