// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 2
// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -target-feature +fullbf16 -emit-llvm %s -o - | FileCheck %s
// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -emit-llvm %s -o - | FileCheck -check-prefix=CHECK-NBF16 %s

// CHECK-LABEL: define dso_local void @_Z11test_scalarDF16bDF16b
// CHECK-SAME: (bfloat noundef [[A:%.*]], bfloat noundef [[B:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK:         [[A_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-NEXT:    [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-NEXT:    [[C:%.*]] = alloca bfloat, align 2
// CHECK-NEXT:    store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-NEXT:    store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-NEXT:    [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NEXT:    [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NEXT:    [[ADD:%.*]] = fadd bfloat [[TMP0]], [[TMP1]]
// CHECK-NEXT:    store bfloat [[ADD]], ptr [[C]], align 2
// CHECK-NEXT:    [[TMP2:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NEXT:    [[TMP3:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NEXT:    [[SUB:%.*]] = fsub bfloat [[TMP2]], [[TMP3]]
// CHECK-NEXT:    store bfloat [[SUB]], ptr [[C]], align 2
// CHECK-NEXT:    [[TMP4:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NEXT:    [[TMP5:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NEXT:    [[MUL:%.*]] = fmul bfloat [[TMP4]], [[TMP5]]
// CHECK-NEXT:    store bfloat [[MUL]], ptr [[C]], align 2
// CHECK-NEXT:    [[TMP6:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NEXT:    [[TMP7:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NEXT:    [[DIV:%.*]] = fdiv bfloat [[TMP6]], [[TMP7]]
// CHECK-NEXT:    store bfloat [[DIV]], ptr [[C]], align 2
// CHECK-NEXT:    ret void
//
// CHECK-NBF16-LABEL: define dso_local void @_Z11test_scalarDF16bDF16b
// CHECK-NBF16-SAME: (bfloat noundef [[A:%.*]], bfloat noundef [[B:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NBF16:         [[A_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-NBF16-NEXT:    [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-NBF16-NEXT:    [[C:%.*]] = alloca bfloat, align 2
// CHECK-NBF16-NEXT:    store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-NBF16-NEXT:    store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-NBF16-NEXT:    [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NBF16-NEXT:    [[EXT:%.*]] = fpext bfloat [[TMP0]] to float
// CHECK-NBF16-NEXT:    [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NBF16-NEXT:    [[EXT1:%.*]] = fpext bfloat [[TMP1]] to float
// CHECK-NBF16-NEXT:    [[ADD:%.*]] = fadd float [[EXT]], [[EXT1]]
// CHECK-NBF16-NEXT:    [[UNPROMOTION:%.*]] = fptrunc float [[ADD]] to bfloat
// CHECK-NBF16-NEXT:    store bfloat [[UNPROMOTION]], ptr [[C]], align 2
// CHECK-NBF16-NEXT:    [[TMP2:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NBF16-NEXT:    [[EXT2:%.*]] = fpext bfloat [[TMP2]] to float
// CHECK-NBF16-NEXT:    [[TMP3:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NBF16-NEXT:    [[EXT3:%.*]] = fpext bfloat [[TMP3]] to float
// CHECK-NBF16-NEXT:    [[SUB:%.*]] = fsub float [[EXT2]], [[EXT3]]
// CHECK-NBF16-NEXT:    [[UNPROMOTION4:%.*]] = fptrunc float [[SUB]] to bfloat
// CHECK-NBF16-NEXT:    store bfloat [[UNPROMOTION4]], ptr [[C]], align 2
// CHECK-NBF16-NEXT:    [[TMP4:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NBF16-NEXT:    [[EXT5:%.*]] = fpext bfloat [[TMP4]] to float
// CHECK-NBF16-NEXT:    [[TMP5:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NBF16-NEXT:    [[EXT6:%.*]] = fpext bfloat [[TMP5]] to float
// CHECK-NBF16-NEXT:    [[MUL:%.*]] = fmul float [[EXT5]], [[EXT6]]
// CHECK-NBF16-NEXT:    [[UNPROMOTION7:%.*]] = fptrunc float [[MUL]] to bfloat
// CHECK-NBF16-NEXT:    store bfloat [[UNPROMOTION7]], ptr [[C]], align 2
// CHECK-NBF16-NEXT:    [[TMP6:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NBF16-NEXT:    [[EXT8:%.*]] = fpext bfloat [[TMP6]] to float
// CHECK-NBF16-NEXT:    [[TMP7:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NBF16-NEXT:    [[EXT9:%.*]] = fpext bfloat [[TMP7]] to float
// CHECK-NBF16-NEXT:    [[DIV:%.*]] = fdiv float [[EXT8]], [[EXT9]]
// CHECK-NBF16-NEXT:    [[UNPROMOTION10:%.*]] = fptrunc float [[DIV]] to bfloat
// CHECK-NBF16-NEXT:    store bfloat [[UNPROMOTION10]], ptr [[C]], align 2
// CHECK-NBF16-NEXT:    ret void
//
void test_scalar(__bf16 a, __bf16 b) {
    __bf16 c;
    c = a + b;
    c = a - b;
    c = a * b;
    c = a / b;
}

typedef __bf16 v8bfloat16 __attribute__((__vector_size__(16)));

// CHECK-LABEL: define dso_local void @_Z11test_vectorDv8_DF16bS_
// CHECK-SAME: (<8 x bfloat> noundef [[A:%.*]], <8 x bfloat> noundef [[B:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK:         [[A_ADDR:%.*]] = alloca <8 x bfloat>, align 16
// CHECK-NEXT:    [[B_ADDR:%.*]] = alloca <8 x bfloat>, align 16
// CHECK-NEXT:    [[C:%.*]] = alloca <8 x bfloat>, align 16
// CHECK-NEXT:    store <8 x bfloat> [[A]], ptr [[A_ADDR]], align 16
// CHECK-NEXT:    store <8 x bfloat> [[B]], ptr [[B_ADDR]], align 16
// CHECK-NEXT:    [[TMP0:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16
// CHECK-NEXT:    [[TMP1:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16
// CHECK-NEXT:    [[ADD:%.*]] = fadd <8 x bfloat> [[TMP0]], [[TMP1]]
// CHECK-NEXT:    store <8 x bfloat> [[ADD]], ptr [[C]], align 16
// CHECK-NEXT:    [[TMP2:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16
// CHECK-NEXT:    [[TMP3:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16
// CHECK-NEXT:    [[SUB:%.*]] = fsub <8 x bfloat> [[TMP2]], [[TMP3]]
// CHECK-NEXT:    store <8 x bfloat> [[SUB]], ptr [[C]], align 16
// CHECK-NEXT:    [[TMP4:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16
// CHECK-NEXT:    [[TMP5:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16
// CHECK-NEXT:    [[MUL:%.*]] = fmul <8 x bfloat> [[TMP4]], [[TMP5]]
// CHECK-NEXT:    store <8 x bfloat> [[MUL]], ptr [[C]], align 16
// CHECK-NEXT:    [[TMP6:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16
// CHECK-NEXT:    [[TMP7:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16
// CHECK-NEXT:    [[DIV:%.*]] = fdiv <8 x bfloat> [[TMP6]], [[TMP7]]
// CHECK-NEXT:    store <8 x bfloat> [[DIV]], ptr [[C]], align 16
// CHECK-NEXT:    ret void
//
// CHECK-NBF16-LABEL: define dso_local void @_Z11test_vectorDv8_DF16bS_
// CHECK-NBF16-SAME: (<8 x bfloat> noundef [[A:%.*]], <8 x bfloat> noundef [[B:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NBF16:         [[A_ADDR:%.*]] = alloca <8 x bfloat>, align 16
// CHECK-NBF16-NEXT:    [[B_ADDR:%.*]] = alloca <8 x bfloat>, align 16
// CHECK-NBF16-NEXT:    [[C:%.*]] = alloca <8 x bfloat>, align 16
// CHECK-NBF16-NEXT:    store <8 x bfloat> [[A]], ptr [[A_ADDR]], align 16
// CHECK-NBF16-NEXT:    store <8 x bfloat> [[B]], ptr [[B_ADDR]], align 16
// CHECK-NBF16-NEXT:    [[TMP0:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16
// CHECK-NBF16-NEXT:    [[EXT:%.*]] = fpext <8 x bfloat> [[TMP0]] to <8 x float>
// CHECK-NBF16-NEXT:    [[TMP1:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16
// CHECK-NBF16-NEXT:    [[EXT1:%.*]] = fpext <8 x bfloat> [[TMP1]] to <8 x float>
// CHECK-NBF16-NEXT:    [[ADD:%.*]] = fadd <8 x float> [[EXT]], [[EXT1]]
// CHECK-NBF16-NEXT:    [[UNPROMOTION:%.*]] = fptrunc <8 x float> [[ADD]] to <8 x bfloat>
// CHECK-NBF16-NEXT:    store <8 x bfloat> [[UNPROMOTION]], ptr [[C]], align 16
// CHECK-NBF16-NEXT:    [[TMP2:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16
// CHECK-NBF16-NEXT:    [[EXT2:%.*]] = fpext <8 x bfloat> [[TMP2]] to <8 x float>
// CHECK-NBF16-NEXT:    [[TMP3:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16
// CHECK-NBF16-NEXT:    [[EXT3:%.*]] = fpext <8 x bfloat> [[TMP3]] to <8 x float>
// CHECK-NBF16-NEXT:    [[SUB:%.*]] = fsub <8 x float> [[EXT2]], [[EXT3]]
// CHECK-NBF16-NEXT:    [[UNPROMOTION4:%.*]] = fptrunc <8 x float> [[SUB]] to <8 x bfloat>
// CHECK-NBF16-NEXT:    store <8 x bfloat> [[UNPROMOTION4]], ptr [[C]], align 16
// CHECK-NBF16-NEXT:    [[TMP4:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16
// CHECK-NBF16-NEXT:    [[EXT5:%.*]] = fpext <8 x bfloat> [[TMP4]] to <8 x float>
// CHECK-NBF16-NEXT:    [[TMP5:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16
// CHECK-NBF16-NEXT:    [[EXT6:%.*]] = fpext <8 x bfloat> [[TMP5]] to <8 x float>
// CHECK-NBF16-NEXT:    [[MUL:%.*]] = fmul <8 x float> [[EXT5]], [[EXT6]]
// CHECK-NBF16-NEXT:    [[UNPROMOTION7:%.*]] = fptrunc <8 x float> [[MUL]] to <8 x bfloat>
// CHECK-NBF16-NEXT:    store <8 x bfloat> [[UNPROMOTION7]], ptr [[C]], align 16
// CHECK-NBF16-NEXT:    [[TMP6:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16
// CHECK-NBF16-NEXT:    [[EXT8:%.*]] = fpext <8 x bfloat> [[TMP6]] to <8 x float>
// CHECK-NBF16-NEXT:    [[TMP7:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16
// CHECK-NBF16-NEXT:    [[EXT9:%.*]] = fpext <8 x bfloat> [[TMP7]] to <8 x float>
// CHECK-NBF16-NEXT:    [[DIV:%.*]] = fdiv <8 x float> [[EXT8]], [[EXT9]]
// CHECK-NBF16-NEXT:    [[UNPROMOTION10:%.*]] = fptrunc <8 x float> [[DIV]] to <8 x bfloat>
// CHECK-NBF16-NEXT:    store <8 x bfloat> [[UNPROMOTION10]], ptr [[C]], align 16
// CHECK-NBF16-NEXT:    ret void
//
void test_vector(v8bfloat16 a, v8bfloat16 b) {
    v8bfloat16 c;
    c = a + b;
    c = a - b;
    c = a * b;
    c = a / b;
}