shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
llvm-project/clang/test/CodeGen/LoongArch/bfloat-abi.c
Ami-zhang 0ed5d9aff6
[LoongArch][BF16] Add support for the __bf16 type (#142548) 
The LoongArch psABI recently added __bf16 type support. Now we can
enable this new type in clang.

Currently, bf16 operations are automatically supported by promoting to
float. This patch adds bf16 support by ensuring that load extension /
truncate store operations are properly expanded.

And this commit implements support for bf16 truncate/extend on hard FP
targets. The extend operation is implemented by a shift just as in the
standard legalization. This requires custom lowering of the truncate
libcall on hard float ABIs (the normal libcall code path is used on soft
ABIs).
2025-06-09 11:15:41 +08:00

533 lines
30 KiB
C
Raw Blame History

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 2
// RUN: %clang_cc1 -triple loongarch64 -emit-llvm %s -o - | FileCheck %s --check-prefixes=CHECK,CHECK-LA64
// RUN: %clang_cc1 -triple loongarch32 -emit-llvm %s -o - | FileCheck %s --check-prefixes=CHECK,CHECK-LA32
struct bfloat1 {
__bf16 a;
};
// CHECK-LABEL: define dso_local bfloat @h1
// CHECK-SAME: (bfloat noundef [[A:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_BFLOAT1:%.*]], align 2
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-NEXT: store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-NEXT: [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT1]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-NEXT: store bfloat [[TMP0]], ptr [[A1]], align 2
// CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds nuw { bfloat }, ptr [[RETVAL]], i32 0, i32 0
// CHECK-NEXT: [[TMP2:%.*]] = load bfloat, ptr [[TMP1]], align 2
// CHECK-NEXT: ret bfloat [[TMP2]]
//
struct bfloat1 h1(__bf16 a) {
struct bfloat1 x;
x.a = a;
return x;
}
struct bfloat2 {
__bf16 a;
__bf16 b;
};
// CHECK-LABEL: define dso_local { bfloat, bfloat } @h2
// CHECK-SAME: (bfloat noundef [[A:%.*]], bfloat noundef [[B:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_BFLOAT2:%.*]], align 2
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-NEXT: [[B_ADDR:%.*]] = 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: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT2]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-NEXT: store bfloat [[TMP0]], ptr [[A1]], align 2
// CHECK-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NEXT: [[B2:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT2]], ptr [[RETVAL]], i32 0, i32 1
// CHECK-NEXT: store bfloat [[TMP1]], ptr [[B2]], align 2
// CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds nuw { bfloat, bfloat }, ptr [[RETVAL]], i32 0, i32 0
// CHECK-NEXT: [[TMP3:%.*]] = load bfloat, ptr [[TMP2]], align 2
// CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds nuw { bfloat, bfloat }, ptr [[RETVAL]], i32 0, i32 1
// CHECK-NEXT: [[TMP5:%.*]] = load bfloat, ptr [[TMP4]], align 2
// CHECK-NEXT: [[TMP6:%.*]] = insertvalue { bfloat, bfloat } poison, bfloat [[TMP3]], 0
// CHECK-NEXT: [[TMP7:%.*]] = insertvalue { bfloat, bfloat } [[TMP6]], bfloat [[TMP5]], 1
// CHECK-NEXT: ret { bfloat, bfloat } [[TMP7]]
//
struct bfloat2 h2(__bf16 a, __bf16 b) {
struct bfloat2 x;
x.a = a;
x.b = b;
return x;
}
struct bfloat3 {
__bf16 a;
__bf16 b;
__bf16 c;
};
// CHECK-LA64-LABEL: define dso_local i64 @h3
// CHECK-LA64-SAME: (bfloat noundef [[A:%.*]], bfloat noundef [[B:%.*]], bfloat noundef [[C:%.*]]) #[[ATTR0]] {
// CHECK-LA64-NEXT: entry:
// CHECK-LA64-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_BFLOAT3:%.*]], align 2
// CHECK-LA64-NEXT: [[A_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[C_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[RETVAL_COERCE:%.*]] = alloca i64, align 8
// CHECK-LA64-NEXT: store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-LA64-NEXT: store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-LA64-NEXT: store bfloat [[C]], ptr [[C_ADDR]], align 2
// CHECK-LA64-NEXT: [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-LA64-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT3]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-LA64-NEXT: store bfloat [[TMP0]], ptr [[A1]], align 2
// CHECK-LA64-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-LA64-NEXT: [[B2:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT3]], ptr [[RETVAL]], i32 0, i32 1
// CHECK-LA64-NEXT: store bfloat [[TMP1]], ptr [[B2]], align 2
// CHECK-LA64-NEXT: [[TMP2:%.*]] = load bfloat, ptr [[C_ADDR]], align 2
// CHECK-LA64-NEXT: [[C3:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT3]], ptr [[RETVAL]], i32 0, i32 2
// CHECK-LA64-NEXT: store bfloat [[TMP2]], ptr [[C3]], align 2
// CHECK-LA64-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 8 [[RETVAL_COERCE]], ptr align 2 [[RETVAL]], i64 6, i1 false)
// CHECK-LA64-NEXT: [[TMP3:%.*]] = load i64, ptr [[RETVAL_COERCE]], align 8
// CHECK-LA64-NEXT: ret i64 [[TMP3]]
//
// CHECK-LA32-LABEL: define dso_local [2 x i32] @h3
// CHECK-LA32-SAME: (bfloat noundef [[A:%.*]], bfloat noundef [[B:%.*]], bfloat noundef [[C:%.*]]) #[[ATTR0]] {
// CHECK-LA32-NEXT: entry:
// CHECK-LA32-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_BFLOAT3:%.*]], align 2
// CHECK-LA32-NEXT: [[A_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: [[C_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: [[RETVAL_COERCE:%.*]] = alloca [2 x i32], align 4
// CHECK-LA32-NEXT: store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-LA32-NEXT: store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-LA32-NEXT: store bfloat [[C]], ptr [[C_ADDR]], align 2
// CHECK-LA32-NEXT: [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-LA32-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT3]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-LA32-NEXT: store bfloat [[TMP0]], ptr [[A1]], align 2
// CHECK-LA32-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-LA32-NEXT: [[B2:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT3]], ptr [[RETVAL]], i32 0, i32 1
// CHECK-LA32-NEXT: store bfloat [[TMP1]], ptr [[B2]], align 2
// CHECK-LA32-NEXT: [[TMP2:%.*]] = load bfloat, ptr [[C_ADDR]], align 2
// CHECK-LA32-NEXT: [[C3:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT3]], ptr [[RETVAL]], i32 0, i32 2
// CHECK-LA32-NEXT: store bfloat [[TMP2]], ptr [[C3]], align 2
// CHECK-LA32-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 4 [[RETVAL_COERCE]], ptr align 2 [[RETVAL]], i32 6, i1 false)
// CHECK-LA32-NEXT: [[TMP3:%.*]] = load [2 x i32], ptr [[RETVAL_COERCE]], align 4
// CHECK-LA32-NEXT: ret [2 x i32] [[TMP3]]
//
struct bfloat3 h3(__bf16 a, __bf16 b, __bf16 c) {
struct bfloat3 x;
x.a = a;
x.b = b;
x.c = c;
return x;
}
struct bfloat4 {
__bf16 a;
__bf16 b;
__bf16 c;
__bf16 d;
};
// CHECK-LA64-LABEL: define dso_local i64 @h4
// CHECK-LA64-SAME: (bfloat noundef [[A:%.*]], bfloat noundef [[B:%.*]], bfloat noundef [[C:%.*]], bfloat noundef [[D:%.*]]) #[[ATTR0]] {
// CHECK-LA64-NEXT: entry:
// CHECK-LA64-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_BFLOAT4:%.*]], align 2
// CHECK-LA64-NEXT: [[A_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[C_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[D_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-LA64-NEXT: store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-LA64-NEXT: store bfloat [[C]], ptr [[C_ADDR]], align 2
// CHECK-LA64-NEXT: store bfloat [[D]], ptr [[D_ADDR]], align 2
// CHECK-LA64-NEXT: [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-LA64-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT4]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-LA64-NEXT: store bfloat [[TMP0]], ptr [[A1]], align 2
// CHECK-LA64-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-LA64-NEXT: [[B2:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT4]], ptr [[RETVAL]], i32 0, i32 1
// CHECK-LA64-NEXT: store bfloat [[TMP1]], ptr [[B2]], align 2
// CHECK-LA64-NEXT: [[TMP2:%.*]] = load bfloat, ptr [[C_ADDR]], align 2
// CHECK-LA64-NEXT: [[C3:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT4]], ptr [[RETVAL]], i32 0, i32 2
// CHECK-LA64-NEXT: store bfloat [[TMP2]], ptr [[C3]], align 2
// CHECK-LA64-NEXT: [[TMP3:%.*]] = load bfloat, ptr [[D_ADDR]], align 2
// CHECK-LA64-NEXT: [[D4:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT4]], ptr [[RETVAL]], i32 0, i32 3
// CHECK-LA64-NEXT: store bfloat [[TMP3]], ptr [[D4]], align 2
// CHECK-LA64-NEXT: [[TMP4:%.*]] = load i64, ptr [[RETVAL]], align 2
// CHECK-LA64-NEXT: ret i64 [[TMP4]]
//
// CHECK-LA32-LABEL: define dso_local [2 x i32] @h4
// CHECK-LA32-SAME: (bfloat noundef [[A:%.*]], bfloat noundef [[B:%.*]], bfloat noundef [[C:%.*]], bfloat noundef [[D:%.*]]) #[[ATTR0]] {
// CHECK-LA32-NEXT: entry:
// CHECK-LA32-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_BFLOAT4:%.*]], align 2
// CHECK-LA32-NEXT: [[A_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: [[C_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: [[D_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-LA32-NEXT: store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-LA32-NEXT: store bfloat [[C]], ptr [[C_ADDR]], align 2
// CHECK-LA32-NEXT: store bfloat [[D]], ptr [[D_ADDR]], align 2
// CHECK-LA32-NEXT: [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-LA32-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT4]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-LA32-NEXT: store bfloat [[TMP0]], ptr [[A1]], align 2
// CHECK-LA32-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-LA32-NEXT: [[B2:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT4]], ptr [[RETVAL]], i32 0, i32 1
// CHECK-LA32-NEXT: store bfloat [[TMP1]], ptr [[B2]], align 2
// CHECK-LA32-NEXT: [[TMP2:%.*]] = load bfloat, ptr [[C_ADDR]], align 2
// CHECK-LA32-NEXT: [[C3:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT4]], ptr [[RETVAL]], i32 0, i32 2
// CHECK-LA32-NEXT: store bfloat [[TMP2]], ptr [[C3]], align 2
// CHECK-LA32-NEXT: [[TMP3:%.*]] = load bfloat, ptr [[D_ADDR]], align 2
// CHECK-LA32-NEXT: [[D4:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT4]], ptr [[RETVAL]], i32 0, i32 3
// CHECK-LA32-NEXT: store bfloat [[TMP3]], ptr [[D4]], align 2
// CHECK-LA32-NEXT: [[TMP4:%.*]] = load [2 x i32], ptr [[RETVAL]], align 2
// CHECK-LA32-NEXT: ret [2 x i32] [[TMP4]]
//
struct bfloat4 h4(__bf16 a, __bf16 b, __bf16 c, __bf16 d) {
struct bfloat4 x;
x.a = a;
x.b = b;
x.c = c;
x.d = d;
return x;
}
struct floatbfloat {
float a;
__bf16 b;
};
// CHECK-LABEL: define dso_local { float, bfloat } @fh
// CHECK-SAME: (float noundef [[A:%.*]], bfloat noundef [[B:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_FLOATBFLOAT:%.*]], align 4
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-NEXT: store float [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_FLOATBFLOAT]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-NEXT: store float [[TMP0]], ptr [[A1]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NEXT: [[B2:%.*]] = getelementptr inbounds nuw [[STRUCT_FLOATBFLOAT]], ptr [[RETVAL]], i32 0, i32 1
// CHECK-NEXT: store bfloat [[TMP1]], ptr [[B2]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds nuw { float, bfloat }, ptr [[RETVAL]], i32 0, i32 0
// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[TMP2]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds nuw { float, bfloat }, ptr [[RETVAL]], i32 0, i32 1
// CHECK-NEXT: [[TMP5:%.*]] = load bfloat, ptr [[TMP4]], align 4
// CHECK-NEXT: [[TMP6:%.*]] = insertvalue { float, bfloat } poison, float [[TMP3]], 0
// CHECK-NEXT: [[TMP7:%.*]] = insertvalue { float, bfloat } [[TMP6]], bfloat [[TMP5]], 1
// CHECK-NEXT: ret { float, bfloat } [[TMP7]]
//
struct floatbfloat fh(float a, __bf16 b) {
struct floatbfloat x;
x.a = a;
x.b = b;
return x;
}
struct floatbfloat2 {
float a;
__bf16 b;
__bf16 c;
};
// CHECK-LA64-LABEL: define dso_local i64 @fh2
// CHECK-LA64-SAME: (float noundef [[A:%.*]], bfloat noundef [[B:%.*]], bfloat noundef [[C:%.*]]) #[[ATTR0]] {
// CHECK-LA64-NEXT: entry:
// CHECK-LA64-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_FLOATBFLOAT2:%.*]], align 4
// CHECK-LA64-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK-LA64-NEXT: [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[C_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: store float [[A]], ptr [[A_ADDR]], align 4
// CHECK-LA64-NEXT: store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-LA64-NEXT: store bfloat [[C]], ptr [[C_ADDR]], align 2
// CHECK-LA64-NEXT: [[TMP0:%.*]] = load float, ptr [[A_ADDR]], align 4
// CHECK-LA64-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_FLOATBFLOAT2]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-LA64-NEXT: store float [[TMP0]], ptr [[A1]], align 4
// CHECK-LA64-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-LA64-NEXT: [[B2:%.*]] = getelementptr inbounds nuw [[STRUCT_FLOATBFLOAT2]], ptr [[RETVAL]], i32 0, i32 1
// CHECK-LA64-NEXT: store bfloat [[TMP1]], ptr [[B2]], align 4
// CHECK-LA64-NEXT: [[TMP2:%.*]] = load bfloat, ptr [[C_ADDR]], align 2
// CHECK-LA64-NEXT: [[C3:%.*]] = getelementptr inbounds nuw [[STRUCT_FLOATBFLOAT2]], ptr [[RETVAL]], i32 0, i32 2
// CHECK-LA64-NEXT: store bfloat [[TMP2]], ptr [[C3]], align 2
// CHECK-LA64-NEXT: [[TMP3:%.*]] = load i64, ptr [[RETVAL]], align 4
// CHECK-LA64-NEXT: ret i64 [[TMP3]]
//
// CHECK-LA32-LABEL: define dso_local [2 x i32] @fh2
// CHECK-LA32-SAME: (float noundef [[A:%.*]], bfloat noundef [[B:%.*]], bfloat noundef [[C:%.*]]) #[[ATTR0]] {
// CHECK-LA32-NEXT: entry:
// CHECK-LA32-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_FLOATBFLOAT2:%.*]], align 4
// CHECK-LA32-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK-LA32-NEXT: [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: [[C_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: store float [[A]], ptr [[A_ADDR]], align 4
// CHECK-LA32-NEXT: store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-LA32-NEXT: store bfloat [[C]], ptr [[C_ADDR]], align 2
// CHECK-LA32-NEXT: [[TMP0:%.*]] = load float, ptr [[A_ADDR]], align 4
// CHECK-LA32-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_FLOATBFLOAT2]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-LA32-NEXT: store float [[TMP0]], ptr [[A1]], align 4
// CHECK-LA32-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-LA32-NEXT: [[B2:%.*]] = getelementptr inbounds nuw [[STRUCT_FLOATBFLOAT2]], ptr [[RETVAL]], i32 0, i32 1
// CHECK-LA32-NEXT: store bfloat [[TMP1]], ptr [[B2]], align 4
// CHECK-LA32-NEXT: [[TMP2:%.*]] = load bfloat, ptr [[C_ADDR]], align 2
// CHECK-LA32-NEXT: [[C3:%.*]] = getelementptr inbounds nuw [[STRUCT_FLOATBFLOAT2]], ptr [[RETVAL]], i32 0, i32 2
// CHECK-LA32-NEXT: store bfloat [[TMP2]], ptr [[C3]], align 2
// CHECK-LA32-NEXT: [[TMP3:%.*]] = load [2 x i32], ptr [[RETVAL]], align 4
// CHECK-LA32-NEXT: ret [2 x i32] [[TMP3]]
//
struct floatbfloat2 fh2(float a, __bf16 b, __bf16 c) {
struct floatbfloat2 x;
x.a = a;
x.b = b;
x.c = c;
return x;
}
struct bfloatfloat {
__bf16 a;
float b;
};
// CHECK-LABEL: define dso_local { bfloat, float } @hf
// CHECK-SAME: (bfloat noundef [[A:%.*]], float noundef [[B:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_BFLOATFLOAT:%.*]], align 4
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca float, align 4
// CHECK-NEXT: store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-NEXT: store float [[B]], ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOATFLOAT]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-NEXT: store bfloat [[TMP0]], ptr [[A1]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[B2:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOATFLOAT]], ptr [[RETVAL]], i32 0, i32 1
// CHECK-NEXT: store float [[TMP1]], ptr [[B2]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds nuw { bfloat, float }, ptr [[RETVAL]], i32 0, i32 0
// CHECK-NEXT: [[TMP3:%.*]] = load bfloat, ptr [[TMP2]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds nuw { bfloat, float }, ptr [[RETVAL]], i32 0, i32 1
// CHECK-NEXT: [[TMP5:%.*]] = load float, ptr [[TMP4]], align 4
// CHECK-NEXT: [[TMP6:%.*]] = insertvalue { bfloat, float } poison, bfloat [[TMP3]], 0
// CHECK-NEXT: [[TMP7:%.*]] = insertvalue { bfloat, float } [[TMP6]], float [[TMP5]], 1
// CHECK-NEXT: ret { bfloat, float } [[TMP7]]
//
struct bfloatfloat hf(__bf16 a, float b) {
struct bfloatfloat x;
x.a = a;
x.b = b;
return x;
}
struct bfloat2float {
__bf16 a;
__bf16 b;
float c;
};
// CHECK-LA64-LABEL: define dso_local i64 @h2f
// CHECK-LA64-SAME: (bfloat noundef [[A:%.*]], bfloat noundef [[B:%.*]], float noundef [[C:%.*]]) #[[ATTR0]] {
// CHECK-LA64-NEXT: entry:
// CHECK-LA64-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_BFLOAT2FLOAT:%.*]], align 4
// CHECK-LA64-NEXT: [[A_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[C_ADDR:%.*]] = alloca float, align 4
// CHECK-LA64-NEXT: store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-LA64-NEXT: store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-LA64-NEXT: store float [[C]], ptr [[C_ADDR]], align 4
// CHECK-LA64-NEXT: [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-LA64-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT2FLOAT]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-LA64-NEXT: store bfloat [[TMP0]], ptr [[A1]], align 4
// CHECK-LA64-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-LA64-NEXT: [[B2:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT2FLOAT]], ptr [[RETVAL]], i32 0, i32 1
// CHECK-LA64-NEXT: store bfloat [[TMP1]], ptr [[B2]], align 2
// CHECK-LA64-NEXT: [[TMP2:%.*]] = load float, ptr [[C_ADDR]], align 4
// CHECK-LA64-NEXT: [[C3:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT2FLOAT]], ptr [[RETVAL]], i32 0, i32 2
// CHECK-LA64-NEXT: store float [[TMP2]], ptr [[C3]], align 4
// CHECK-LA64-NEXT: [[TMP3:%.*]] = load i64, ptr [[RETVAL]], align 4
// CHECK-LA64-NEXT: ret i64 [[TMP3]]
//
// CHECK-LA32-LABEL: define dso_local [2 x i32] @h2f
// CHECK-LA32-SAME: (bfloat noundef [[A:%.*]], bfloat noundef [[B:%.*]], float noundef [[C:%.*]]) #[[ATTR0]] {
// CHECK-LA32-NEXT: entry:
// CHECK-LA32-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_BFLOAT2FLOAT:%.*]], align 4
// CHECK-LA32-NEXT: [[A_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: [[C_ADDR:%.*]] = alloca float, align 4
// CHECK-LA32-NEXT: store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-LA32-NEXT: store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-LA32-NEXT: store float [[C]], ptr [[C_ADDR]], align 4
// CHECK-LA32-NEXT: [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-LA32-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT2FLOAT]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-LA32-NEXT: store bfloat [[TMP0]], ptr [[A1]], align 4
// CHECK-LA32-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-LA32-NEXT: [[B2:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT2FLOAT]], ptr [[RETVAL]], i32 0, i32 1
// CHECK-LA32-NEXT: store bfloat [[TMP1]], ptr [[B2]], align 2
// CHECK-LA32-NEXT: [[TMP2:%.*]] = load float, ptr [[C_ADDR]], align 4
// CHECK-LA32-NEXT: [[C3:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT2FLOAT]], ptr [[RETVAL]], i32 0, i32 2
// CHECK-LA32-NEXT: store float [[TMP2]], ptr [[C3]], align 4
// CHECK-LA32-NEXT: [[TMP3:%.*]] = load [2 x i32], ptr [[RETVAL]], align 4
// CHECK-LA32-NEXT: ret [2 x i32] [[TMP3]]
//
struct bfloat2float h2f(__bf16 a, __bf16 b, float c) {
struct bfloat2float x;
x.a = a;
x.b = b;
x.c = c;
return x;
}
struct floatbfloat3 {
float a;
__bf16 b;
__bf16 c;
__bf16 d;
};
// CHECK-LA64-LABEL: define dso_local [2 x i64] @fh3
// CHECK-LA64-SAME: (float noundef [[A:%.*]], bfloat noundef [[B:%.*]], bfloat noundef [[C:%.*]], bfloat noundef [[D:%.*]]) #[[ATTR0]] {
// CHECK-LA64-NEXT: entry:
// CHECK-LA64-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_FLOATBFLOAT3:%.*]], align 4
// CHECK-LA64-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK-LA64-NEXT: [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[C_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[D_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[RETVAL_COERCE:%.*]] = alloca [2 x i64], align 8
// CHECK-LA64-NEXT: store float [[A]], ptr [[A_ADDR]], align 4
// CHECK-LA64-NEXT: store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-LA64-NEXT: store bfloat [[C]], ptr [[C_ADDR]], align 2
// CHECK-LA64-NEXT: store bfloat [[D]], ptr [[D_ADDR]], align 2
// CHECK-LA64-NEXT: [[TMP0:%.*]] = load float, ptr [[A_ADDR]], align 4
// CHECK-LA64-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_FLOATBFLOAT3]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-LA64-NEXT: store float [[TMP0]], ptr [[A1]], align 4
// CHECK-LA64-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-LA64-NEXT: [[B2:%.*]] = getelementptr inbounds nuw [[STRUCT_FLOATBFLOAT3]], ptr [[RETVAL]], i32 0, i32 1
// CHECK-LA64-NEXT: store bfloat [[TMP1]], ptr [[B2]], align 4
// CHECK-LA64-NEXT: [[TMP2:%.*]] = load bfloat, ptr [[C_ADDR]], align 2
// CHECK-LA64-NEXT: [[C3:%.*]] = getelementptr inbounds nuw [[STRUCT_FLOATBFLOAT3]], ptr [[RETVAL]], i32 0, i32 2
// CHECK-LA64-NEXT: store bfloat [[TMP2]], ptr [[C3]], align 2
// CHECK-LA64-NEXT: [[TMP3:%.*]] = load bfloat, ptr [[D_ADDR]], align 2
// CHECK-LA64-NEXT: [[D4:%.*]] = getelementptr inbounds nuw [[STRUCT_FLOATBFLOAT3]], ptr [[RETVAL]], i32 0, i32 3
// CHECK-LA64-NEXT: store bfloat [[TMP3]], ptr [[D4]], align 4
// CHECK-LA64-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 8 [[RETVAL_COERCE]], ptr align 4 [[RETVAL]], i64 12, i1 false)
// CHECK-LA64-NEXT: [[TMP4:%.*]] = load [2 x i64], ptr [[RETVAL_COERCE]], align 8
// CHECK-LA64-NEXT: ret [2 x i64] [[TMP4]]
//
// CHECK-LA32-LABEL: define dso_local void @fh3
// CHECK-LA32-SAME: (ptr dead_on_unwind noalias writable sret([[STRUCT_FLOATBFLOAT3:%.*]]) align 4 [[AGG_RESULT:%.*]], float noundef [[A:%.*]], bfloat noundef [[B:%.*]], bfloat noundef [[C:%.*]], bfloat noundef [[D:%.*]]) #[[ATTR0]] {
// CHECK-LA32-NEXT: entry:
// CHECK-LA32-NEXT: [[RESULT_PTR:%.*]] = alloca ptr, align 4
// CHECK-LA32-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK-LA32-NEXT: [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: [[C_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: [[D_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: store ptr [[AGG_RESULT]], ptr [[RESULT_PTR]], align 4
// CHECK-LA32-NEXT: store float [[A]], ptr [[A_ADDR]], align 4
// CHECK-LA32-NEXT: store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-LA32-NEXT: store bfloat [[C]], ptr [[C_ADDR]], align 2
// CHECK-LA32-NEXT: store bfloat [[D]], ptr [[D_ADDR]], align 2
// CHECK-LA32-NEXT: [[TMP0:%.*]] = load float, ptr [[A_ADDR]], align 4
// CHECK-LA32-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_FLOATBFLOAT3]], ptr [[AGG_RESULT]], i32 0, i32 0
// CHECK-LA32-NEXT: store float [[TMP0]], ptr [[A1]], align 4
// CHECK-LA32-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-LA32-NEXT: [[B2:%.*]] = getelementptr inbounds nuw [[STRUCT_FLOATBFLOAT3]], ptr [[AGG_RESULT]], i32 0, i32 1
// CHECK-LA32-NEXT: store bfloat [[TMP1]], ptr [[B2]], align 4
// CHECK-LA32-NEXT: [[TMP2:%.*]] = load bfloat, ptr [[C_ADDR]], align 2
// CHECK-LA32-NEXT: [[C3:%.*]] = getelementptr inbounds nuw [[STRUCT_FLOATBFLOAT3]], ptr [[AGG_RESULT]], i32 0, i32 2
// CHECK-LA32-NEXT: store bfloat [[TMP2]], ptr [[C3]], align 2
// CHECK-LA32-NEXT: [[TMP3:%.*]] = load bfloat, ptr [[D_ADDR]], align 2
// CHECK-LA32-NEXT: [[D4:%.*]] = getelementptr inbounds nuw [[STRUCT_FLOATBFLOAT3]], ptr [[AGG_RESULT]], i32 0, i32 3
// CHECK-LA32-NEXT: store bfloat [[TMP3]], ptr [[D4]], align 4
// CHECK-LA32-NEXT: ret void
//
struct floatbfloat3 fh3(float a, __bf16 b, __bf16 c, __bf16 d) {
struct floatbfloat3 x;
x.a = a;
x.b = b;
x.c = c;
x.d = d;
return x;
}
struct bfloat5 {
__bf16 a;
__bf16 b;
__bf16 c;
__bf16 d;
__bf16 e;
};
// CHECK-LA64-LABEL: define dso_local [2 x i64] @h5
// CHECK-LA64-SAME: (bfloat noundef [[A:%.*]], bfloat noundef [[B:%.*]], bfloat noundef [[C:%.*]], bfloat noundef [[D:%.*]], bfloat noundef [[E:%.*]]) #[[ATTR0]] {
// CHECK-LA64-NEXT: entry:
// CHECK-LA64-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_BFLOAT5:%.*]], align 2
// CHECK-LA64-NEXT: [[A_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[C_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[D_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[E_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA64-NEXT: [[RETVAL_COERCE:%.*]] = alloca [2 x i64], align 8
// CHECK-LA64-NEXT: store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-LA64-NEXT: store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-LA64-NEXT: store bfloat [[C]], ptr [[C_ADDR]], align 2
// CHECK-LA64-NEXT: store bfloat [[D]], ptr [[D_ADDR]], align 2
// CHECK-LA64-NEXT: store bfloat [[E]], ptr [[E_ADDR]], align 2
// CHECK-LA64-NEXT: [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-LA64-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT5]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-LA64-NEXT: store bfloat [[TMP0]], ptr [[A1]], align 2
// CHECK-LA64-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-LA64-NEXT: [[B2:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT5]], ptr [[RETVAL]], i32 0, i32 1
// CHECK-LA64-NEXT: store bfloat [[TMP1]], ptr [[B2]], align 2
// CHECK-LA64-NEXT: [[TMP2:%.*]] = load bfloat, ptr [[C_ADDR]], align 2
// CHECK-LA64-NEXT: [[C3:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT5]], ptr [[RETVAL]], i32 0, i32 2
// CHECK-LA64-NEXT: store bfloat [[TMP2]], ptr [[C3]], align 2
// CHECK-LA64-NEXT: [[TMP3:%.*]] = load bfloat, ptr [[D_ADDR]], align 2
// CHECK-LA64-NEXT: [[D4:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT5]], ptr [[RETVAL]], i32 0, i32 3
// CHECK-LA64-NEXT: store bfloat [[TMP3]], ptr [[D4]], align 2
// CHECK-LA64-NEXT: [[TMP4:%.*]] = load bfloat, ptr [[E_ADDR]], align 2
// CHECK-LA64-NEXT: [[E5:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT5]], ptr [[RETVAL]], i32 0, i32 4
// CHECK-LA64-NEXT: store bfloat [[TMP4]], ptr [[E5]], align 2
// CHECK-LA64-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 8 [[RETVAL_COERCE]], ptr align 2 [[RETVAL]], i64 10, i1 false)
// CHECK-LA64-NEXT: [[TMP5:%.*]] = load [2 x i64], ptr [[RETVAL_COERCE]], align 8
// CHECK-LA64-NEXT: ret [2 x i64] [[TMP5]]
//
// CHECK-LA32-LABEL: define dso_local void @h5
// CHECK-LA32-SAME: (ptr dead_on_unwind noalias writable sret([[STRUCT_BFLOAT5:%.*]]) align 2 [[AGG_RESULT:%.*]], bfloat noundef [[A:%.*]], bfloat noundef [[B:%.*]], bfloat noundef [[C:%.*]], bfloat noundef [[D:%.*]], bfloat noundef [[E:%.*]]) #[[ATTR0]] {
// CHECK-LA32-NEXT: entry:
// CHECK-LA32-NEXT: [[RESULT_PTR:%.*]] = alloca ptr, align 4
// CHECK-LA32-NEXT: [[A_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: [[C_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: [[D_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: [[E_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-LA32-NEXT: store ptr [[AGG_RESULT]], ptr [[RESULT_PTR]], align 4
// CHECK-LA32-NEXT: store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-LA32-NEXT: store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-LA32-NEXT: store bfloat [[C]], ptr [[C_ADDR]], align 2
// CHECK-LA32-NEXT: store bfloat [[D]], ptr [[D_ADDR]], align 2
// CHECK-LA32-NEXT: store bfloat [[E]], ptr [[E_ADDR]], align 2
// CHECK-LA32-NEXT: [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-LA32-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT5]], ptr [[AGG_RESULT]], i32 0, i32 0
// CHECK-LA32-NEXT: store bfloat [[TMP0]], ptr [[A1]], align 2
// CHECK-LA32-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-LA32-NEXT: [[B2:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT5]], ptr [[AGG_RESULT]], i32 0, i32 1
// CHECK-LA32-NEXT: store bfloat [[TMP1]], ptr [[B2]], align 2
// CHECK-LA32-NEXT: [[TMP2:%.*]] = load bfloat, ptr [[C_ADDR]], align 2
// CHECK-LA32-NEXT: [[C3:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT5]], ptr [[AGG_RESULT]], i32 0, i32 2
// CHECK-LA32-NEXT: store bfloat [[TMP2]], ptr [[C3]], align 2
// CHECK-LA32-NEXT: [[TMP3:%.*]] = load bfloat, ptr [[D_ADDR]], align 2
// CHECK-LA32-NEXT: [[D4:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT5]], ptr [[AGG_RESULT]], i32 0, i32 3
// CHECK-LA32-NEXT: store bfloat [[TMP3]], ptr [[D4]], align 2
// CHECK-LA32-NEXT: [[TMP4:%.*]] = load bfloat, ptr [[E_ADDR]], align 2
// CHECK-LA32-NEXT: [[E5:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT5]], ptr [[AGG_RESULT]], i32 0, i32 4
// CHECK-LA32-NEXT: store bfloat [[TMP4]], ptr [[E5]], align 2
// CHECK-LA32-NEXT: ret void
//
struct bfloat5 h5(__bf16 a, __bf16 b, __bf16 c, __bf16 d, __bf16 e) {
struct bfloat5 x;
x.a = a;
x.b = b;
x.c = c;
x.d = d;
x.e = e;
return x;
}
Reference in New Issue View Git Blame Copy Permalink