1 // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
3 // REQUIRES: aarch64-registered-target
5 // RUN: %clang_cc1 -triple aarch64 -target-feature +bf16 -target-feature +sme -target-feature +sme2 -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s
6 // RUN: %clang_cc1 -triple aarch64 -target-feature +bf16 -target-feature +sme -target-feature +sme2 -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
7 // RUN: %clang_cc1 -triple aarch64 -target-feature +bf16 -target-feature +sme -target-feature +sme2 -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
11 // CHECK-LABEL: @test_svluti2_lane_zt_u8(
13 // CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv16i8(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
14 // CHECK-NEXT: ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
16 // CPP-CHECK-LABEL: @_Z23test_svluti2_lane_zt_u8u11__SVUint8_t(
17 // CPP-CHECK-NEXT: entry:
18 // CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv16i8(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
19 // CPP-CHECK-NEXT: ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
21 svuint8x4_t
test_svluti2_lane_zt_u8(svuint8_t zn
) __arm_streaming
__arm_in("zt0") {
22 return svluti2_lane_zt_u8_x4(0, zn
, 3);
26 // CHECK-LABEL: @test_svluti2_lane_zt_s8(
28 // CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv16i8(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
29 // CHECK-NEXT: ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
31 // CPP-CHECK-LABEL: @_Z23test_svluti2_lane_zt_s8u11__SVUint8_t(
32 // CPP-CHECK-NEXT: entry:
33 // CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv16i8(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
34 // CPP-CHECK-NEXT: ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
36 svint8x4_t
test_svluti2_lane_zt_s8(svuint8_t zn
) __arm_streaming
__arm_in("zt0") {
37 return svluti2_lane_zt_s8_x4(0, zn
, 3);
40 // CHECK-LABEL: @test_svluti2_lane_zt_u16(
42 // CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv8i16(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
43 // CHECK-NEXT: ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
45 // CPP-CHECK-LABEL: @_Z24test_svluti2_lane_zt_u16u11__SVUint8_t(
46 // CPP-CHECK-NEXT: entry:
47 // CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv8i16(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
48 // CPP-CHECK-NEXT: ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
50 svuint16x4_t
test_svluti2_lane_zt_u16(svuint8_t zn
) __arm_streaming
__arm_in("zt0") {
51 return svluti2_lane_zt_u16_x4(0, zn
, 3);
54 // CHECK-LABEL: @test_svluti2_lane_zt_s16(
56 // CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv8i16(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
57 // CHECK-NEXT: ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
59 // CPP-CHECK-LABEL: @_Z24test_svluti2_lane_zt_s16u11__SVUint8_t(
60 // CPP-CHECK-NEXT: entry:
61 // CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv8i16(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
62 // CPP-CHECK-NEXT: ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
64 svint16x4_t
test_svluti2_lane_zt_s16(svuint8_t zn
) __arm_streaming
__arm_in("zt0") {
65 return svluti2_lane_zt_s16_x4(0, zn
, 3);
68 // CHECK-LABEL: @test_svluti2_lane_zt_f16(
70 // CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv8f16(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
71 // CHECK-NEXT: ret { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
73 // CPP-CHECK-LABEL: @_Z24test_svluti2_lane_zt_f16u11__SVUint8_t(
74 // CPP-CHECK-NEXT: entry:
75 // CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv8f16(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
76 // CPP-CHECK-NEXT: ret { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
78 svfloat16x4_t
test_svluti2_lane_zt_f16(svuint8_t zn
) __arm_streaming
__arm_in("zt0") {
79 return svluti2_lane_zt_f16_x4(0, zn
, 3);
82 // CHECK-LABEL: @test_svluti2_lane_zt_bf16(
84 // CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv8bf16(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
85 // CHECK-NEXT: ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
87 // CPP-CHECK-LABEL: @_Z25test_svluti2_lane_zt_bf16u11__SVUint8_t(
88 // CPP-CHECK-NEXT: entry:
89 // CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv8bf16(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
90 // CPP-CHECK-NEXT: ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
92 svbfloat16x4_t
test_svluti2_lane_zt_bf16(svuint8_t zn
) __arm_streaming
__arm_in("zt0") {
93 return svluti2_lane_zt_bf16_x4(0, zn
, 3);
96 // CHECK-LABEL: @test_svluti2_lane_zt_u32(
98 // CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv4i32(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
99 // CHECK-NEXT: ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
101 // CPP-CHECK-LABEL: @_Z24test_svluti2_lane_zt_u32u11__SVUint8_t(
102 // CPP-CHECK-NEXT: entry:
103 // CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv4i32(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
104 // CPP-CHECK-NEXT: ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
106 svuint32x4_t
test_svluti2_lane_zt_u32(svuint8_t zn
) __arm_streaming
__arm_in("zt0") {
107 return svluti2_lane_zt_u32_x4(0, zn
, 3);
110 // CHECK-LABEL: @test_svluti2_lane_zt_s32(
111 // CHECK-NEXT: entry:
112 // CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv4i32(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
113 // CHECK-NEXT: ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
115 // CPP-CHECK-LABEL: @_Z24test_svluti2_lane_zt_s32u11__SVUint8_t(
116 // CPP-CHECK-NEXT: entry:
117 // CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv4i32(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
118 // CPP-CHECK-NEXT: ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
120 svint32x4_t
test_svluti2_lane_zt_s32(svuint8_t zn
) __arm_streaming
__arm_in("zt0") {
121 return svluti2_lane_zt_s32_x4(0, zn
, 3);
124 // CHECK-LABEL: @test_svluti2_lane_zt_f32(
125 // CHECK-NEXT: entry:
126 // CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv4f32(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
127 // CHECK-NEXT: ret { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
129 // CPP-CHECK-LABEL: @_Z24test_svluti2_lane_zt_f32u11__SVUint8_t(
130 // CPP-CHECK-NEXT: entry:
131 // CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.luti2.lane.zt.x4.nxv4f32(i32 0, <vscale x 16 x i8> [[ZN:%.*]], i32 3)
132 // CPP-CHECK-NEXT: ret { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
134 svfloat32x4_t
test_svluti2_lane_zt_f32(svuint8_t zn
) __arm_streaming
__arm_in("zt0") {
135 return svluti2_lane_zt_f32_x4(0, zn
, 3);