Revert "[llvm] Improve llvm.objectsize computation by computing GEP, alloca and mallo...
[llvm-project.git] / clang / test / CodeGen / AArch64 / sme-intrinsics / acle_sme_mopa-za32.c
blob824c43e6d247c32dcf682f9cc726316070653d05
1 // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 3
2 // REQUIRES: aarch64-registered-target
3 // RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sme -target-feature +bf16 -O1 -Werror -emit-llvm -o - %s | FileCheck %s -check-prefixes=CHECK,CHECK-C
4 // RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sme -target-feature +bf16 -O1 -Werror -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefixes=CHECK,CHECK-CXX
5 // RUN: %clang_cc1 -fclang-abi-compat=latest -DSME_OVERLOADED_FORMS -triple aarch64 -target-feature +sme -target-feature +bf16 -O1 -Werror -emit-llvm -o - %s | FileCheck %s -check-prefixes=CHECK,CHECK-C
6 // RUN: %clang_cc1 -fclang-abi-compat=latest -DSME_OVERLOADED_FORMS -triple aarch64 -target-feature +sme -target-feature +bf16 -O1 -Werror -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefixes=CHECK,CHECK-CXX
7 // RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sme -target-feature +bf16 -S -O1 -Werror -o /dev/null %s
9 #include <arm_sme.h>
11 #ifdef SME_OVERLOADED_FORMS
12 #define SME_ACLE_FUNC(A1,A2_UNUSED,A3) A1##A3
13 #else
14 #define SME_ACLE_FUNC(A1,A2,A3) A1##A2##A3
15 #endif
17 // CHECK-C-LABEL: define dso_local void @test_svmopa_za32_s8(
18 // CHECK-C-SAME: <vscale x 16 x i1> [[PN:%.*]], <vscale x 16 x i1> [[PM:%.*]], <vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
19 // CHECK-C-NEXT: entry:
20 // CHECK-C-NEXT: tail call void @llvm.aarch64.sme.smopa.wide.nxv16i8(i32 0, <vscale x 16 x i1> [[PN]], <vscale x 16 x i1> [[PM]], <vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]])
21 // CHECK-C-NEXT: ret void
23 // CHECK-CXX-LABEL: define dso_local void @_Z19test_svmopa_za32_s8u10__SVBool_tS_u10__SVInt8_tS0_(
24 // CHECK-CXX-SAME: <vscale x 16 x i1> [[PN:%.*]], <vscale x 16 x i1> [[PM:%.*]], <vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
25 // CHECK-CXX-NEXT: entry:
26 // CHECK-CXX-NEXT: tail call void @llvm.aarch64.sme.smopa.wide.nxv16i8(i32 0, <vscale x 16 x i1> [[PN]], <vscale x 16 x i1> [[PM]], <vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]])
27 // CHECK-CXX-NEXT: ret void
29 void test_svmopa_za32_s8(svbool_t pn, svbool_t pm, svint8_t zn, svint8_t zm) __arm_streaming __arm_inout("za") {
30 SME_ACLE_FUNC(svmopa_za32, _s8, _m)(0, pn, pm, zn, zm);
33 // CHECK-C-LABEL: define dso_local void @test_svmopa_za32_u8(
34 // CHECK-C-SAME: <vscale x 16 x i1> [[PN:%.*]], <vscale x 16 x i1> [[PM:%.*]], <vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]]) local_unnamed_addr #[[ATTR0]] {
35 // CHECK-C-NEXT: entry:
36 // CHECK-C-NEXT: tail call void @llvm.aarch64.sme.umopa.wide.nxv16i8(i32 0, <vscale x 16 x i1> [[PN]], <vscale x 16 x i1> [[PM]], <vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]])
37 // CHECK-C-NEXT: ret void
39 // CHECK-CXX-LABEL: define dso_local void @_Z19test_svmopa_za32_u8u10__SVBool_tS_u11__SVUint8_tS0_(
40 // CHECK-CXX-SAME: <vscale x 16 x i1> [[PN:%.*]], <vscale x 16 x i1> [[PM:%.*]], <vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]]) local_unnamed_addr #[[ATTR0]] {
41 // CHECK-CXX-NEXT: entry:
42 // CHECK-CXX-NEXT: tail call void @llvm.aarch64.sme.umopa.wide.nxv16i8(i32 0, <vscale x 16 x i1> [[PN]], <vscale x 16 x i1> [[PM]], <vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]])
43 // CHECK-CXX-NEXT: ret void
45 void test_svmopa_za32_u8(svbool_t pn, svbool_t pm, svuint8_t zn, svuint8_t zm) __arm_streaming __arm_inout("za") {
46 SME_ACLE_FUNC(svmopa_za32, _u8, _m)(0, pn, pm, zn, zm);
49 // CHECK-C-LABEL: define dso_local void @test_svmopa_za32_bf16(
50 // CHECK-C-SAME: <vscale x 16 x i1> [[PN:%.*]], <vscale x 16 x i1> [[PM:%.*]], <vscale x 8 x bfloat> [[ZN:%.*]], <vscale x 8 x bfloat> [[ZM:%.*]]) local_unnamed_addr #[[ATTR0]] {
51 // CHECK-C-NEXT: entry:
52 // CHECK-C-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PN]])
53 // CHECK-C-NEXT: [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PM]])
54 // CHECK-C-NEXT: tail call void @llvm.aarch64.sme.mopa.wide.nxv8bf16(i32 0, <vscale x 8 x i1> [[TMP0]], <vscale x 8 x i1> [[TMP1]], <vscale x 8 x bfloat> [[ZN]], <vscale x 8 x bfloat> [[ZM]])
55 // CHECK-C-NEXT: ret void
57 // CHECK-CXX-LABEL: define dso_local void @_Z21test_svmopa_za32_bf16u10__SVBool_tS_u14__SVBfloat16_tS0_(
58 // CHECK-CXX-SAME: <vscale x 16 x i1> [[PN:%.*]], <vscale x 16 x i1> [[PM:%.*]], <vscale x 8 x bfloat> [[ZN:%.*]], <vscale x 8 x bfloat> [[ZM:%.*]]) local_unnamed_addr #[[ATTR0]] {
59 // CHECK-CXX-NEXT: entry:
60 // CHECK-CXX-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PN]])
61 // CHECK-CXX-NEXT: [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PM]])
62 // CHECK-CXX-NEXT: tail call void @llvm.aarch64.sme.mopa.wide.nxv8bf16(i32 0, <vscale x 8 x i1> [[TMP0]], <vscale x 8 x i1> [[TMP1]], <vscale x 8 x bfloat> [[ZN]], <vscale x 8 x bfloat> [[ZM]])
63 // CHECK-CXX-NEXT: ret void
65 void test_svmopa_za32_bf16(svbool_t pn, svbool_t pm, svbfloat16_t zn, svbfloat16_t zm) __arm_streaming __arm_inout("za") {
66 SME_ACLE_FUNC(svmopa_za32, _bf16, _m)(0, pn, pm, zn, zm);
69 // CHECK-C-LABEL: define dso_local void @test_svmopa_za32_f16(
70 // CHECK-C-SAME: <vscale x 16 x i1> [[PN:%.*]], <vscale x 16 x i1> [[PM:%.*]], <vscale x 8 x half> [[ZN:%.*]], <vscale x 8 x half> [[ZM:%.*]]) local_unnamed_addr #[[ATTR0]] {
71 // CHECK-C-NEXT: entry:
72 // CHECK-C-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PN]])
73 // CHECK-C-NEXT: [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PM]])
74 // CHECK-C-NEXT: tail call void @llvm.aarch64.sme.mopa.wide.nxv8f16(i32 1, <vscale x 8 x i1> [[TMP0]], <vscale x 8 x i1> [[TMP1]], <vscale x 8 x half> [[ZN]], <vscale x 8 x half> [[ZM]])
75 // CHECK-C-NEXT: ret void
77 // CHECK-CXX-LABEL: define dso_local void @_Z20test_svmopa_za32_f16u10__SVBool_tS_u13__SVFloat16_tS0_(
78 // CHECK-CXX-SAME: <vscale x 16 x i1> [[PN:%.*]], <vscale x 16 x i1> [[PM:%.*]], <vscale x 8 x half> [[ZN:%.*]], <vscale x 8 x half> [[ZM:%.*]]) local_unnamed_addr #[[ATTR0]] {
79 // CHECK-CXX-NEXT: entry:
80 // CHECK-CXX-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PN]])
81 // CHECK-CXX-NEXT: [[TMP1:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PM]])
82 // CHECK-CXX-NEXT: tail call void @llvm.aarch64.sme.mopa.wide.nxv8f16(i32 1, <vscale x 8 x i1> [[TMP0]], <vscale x 8 x i1> [[TMP1]], <vscale x 8 x half> [[ZN]], <vscale x 8 x half> [[ZM]])
83 // CHECK-CXX-NEXT: ret void
85 void test_svmopa_za32_f16(svbool_t pn, svbool_t pm, svfloat16_t zn, svfloat16_t zm) __arm_streaming __arm_inout("za") {
86 SME_ACLE_FUNC(svmopa_za32, _f16, _m)(1, pn, pm, zn, zm);
89 // CHECK-C-LABEL: define dso_local void @test_svmopa_za32_f32(
90 // CHECK-C-SAME: <vscale x 16 x i1> [[PN:%.*]], <vscale x 16 x i1> [[PM:%.*]], <vscale x 4 x float> [[ZN:%.*]], <vscale x 4 x float> [[ZM:%.*]]) local_unnamed_addr #[[ATTR0]] {
91 // CHECK-C-NEXT: entry:
92 // CHECK-C-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PN]])
93 // CHECK-C-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PM]])
94 // CHECK-C-NEXT: tail call void @llvm.aarch64.sme.mopa.nxv4f32(i32 1, <vscale x 4 x i1> [[TMP0]], <vscale x 4 x i1> [[TMP1]], <vscale x 4 x float> [[ZN]], <vscale x 4 x float> [[ZM]])
95 // CHECK-C-NEXT: ret void
97 // CHECK-CXX-LABEL: define dso_local void @_Z20test_svmopa_za32_f32u10__SVBool_tS_u13__SVFloat32_tS0_(
98 // CHECK-CXX-SAME: <vscale x 16 x i1> [[PN:%.*]], <vscale x 16 x i1> [[PM:%.*]], <vscale x 4 x float> [[ZN:%.*]], <vscale x 4 x float> [[ZM:%.*]]) local_unnamed_addr #[[ATTR0]] {
99 // CHECK-CXX-NEXT: entry:
100 // CHECK-CXX-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PN]])
101 // CHECK-CXX-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PM]])
102 // CHECK-CXX-NEXT: tail call void @llvm.aarch64.sme.mopa.nxv4f32(i32 1, <vscale x 4 x i1> [[TMP0]], <vscale x 4 x i1> [[TMP1]], <vscale x 4 x float> [[ZN]], <vscale x 4 x float> [[ZM]])
103 // CHECK-CXX-NEXT: ret void
105 void test_svmopa_za32_f32(svbool_t pn, svbool_t pm, svfloat32_t zn, svfloat32_t zm) __arm_streaming __arm_inout("za") {
106 SME_ACLE_FUNC(svmopa_za32, _f32, _m)(1, pn, pm, zn, zm);
109 // CHECK-C-LABEL: define dso_local void @test_svsumopa_za32_s8(
110 // CHECK-C-SAME: <vscale x 16 x i1> [[PN:%.*]], <vscale x 16 x i1> [[PM:%.*]], <vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]]) local_unnamed_addr #[[ATTR0]] {
111 // CHECK-C-NEXT: entry:
112 // CHECK-C-NEXT: tail call void @llvm.aarch64.sme.sumopa.wide.nxv16i8(i32 0, <vscale x 16 x i1> [[PN]], <vscale x 16 x i1> [[PM]], <vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]])
113 // CHECK-C-NEXT: ret void
115 // CHECK-CXX-LABEL: define dso_local void @_Z21test_svsumopa_za32_s8u10__SVBool_tS_u10__SVInt8_tu11__SVUint8_t(
116 // CHECK-CXX-SAME: <vscale x 16 x i1> [[PN:%.*]], <vscale x 16 x i1> [[PM:%.*]], <vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]]) local_unnamed_addr #[[ATTR0]] {
117 // CHECK-CXX-NEXT: entry:
118 // CHECK-CXX-NEXT: tail call void @llvm.aarch64.sme.sumopa.wide.nxv16i8(i32 0, <vscale x 16 x i1> [[PN]], <vscale x 16 x i1> [[PM]], <vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]])
119 // CHECK-CXX-NEXT: ret void
121 void test_svsumopa_za32_s8(svbool_t pn, svbool_t pm, svint8_t zn, svuint8_t zm) __arm_streaming __arm_inout("za") {
122 SME_ACLE_FUNC(svsumopa_za32, _s8, _m)(0, pn, pm, zn, zm);
125 // CHECK-C-LABEL: define dso_local void @test_svusmopa_za32_u8(
126 // CHECK-C-SAME: <vscale x 16 x i1> [[PN:%.*]], <vscale x 16 x i1> [[PM:%.*]], <vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]]) local_unnamed_addr #[[ATTR0]] {
127 // CHECK-C-NEXT: entry:
128 // CHECK-C-NEXT: tail call void @llvm.aarch64.sme.usmopa.wide.nxv16i8(i32 0, <vscale x 16 x i1> [[PN]], <vscale x 16 x i1> [[PM]], <vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]])
129 // CHECK-C-NEXT: ret void
131 // CHECK-CXX-LABEL: define dso_local void @_Z21test_svusmopa_za32_u8u10__SVBool_tS_u11__SVUint8_tu10__SVInt8_t(
132 // CHECK-CXX-SAME: <vscale x 16 x i1> [[PN:%.*]], <vscale x 16 x i1> [[PM:%.*]], <vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]]) local_unnamed_addr #[[ATTR0]] {
133 // CHECK-CXX-NEXT: entry:
134 // CHECK-CXX-NEXT: tail call void @llvm.aarch64.sme.usmopa.wide.nxv16i8(i32 0, <vscale x 16 x i1> [[PN]], <vscale x 16 x i1> [[PM]], <vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]])
135 // CHECK-CXX-NEXT: ret void
137 void test_svusmopa_za32_u8(svbool_t pn, svbool_t pm, svuint8_t zn, svint8_t zm) __arm_streaming __arm_inout("za") {
138 SME_ACLE_FUNC(svusmopa_za32, _u8, _m)(0, pn, pm, zn, zm);
140 //// NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
141 // CHECK: {{.*}}