Run DCE after a LoopFlatten test to reduce spurious output [nfc]
[llvm-project.git] / clang / test / CodeGen / aarch64-sve-intrinsics / acle_sve_set2-bfloat.c
blob0307dae2f69e69ec0ef8bacf6b62fee449c2d3fc
1 // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
2 // RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s
3 // RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
4 // RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s
5 // RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
7 // REQUIRES: aarch64-registered-target
9 #include <arm_sve.h>
11 #ifdef SVE_OVERLOADED_FORMS
12 // A simple used,unused... macro, long enough to represent any SVE builtin.
13 #define SVE_ACLE_FUNC(A1,A2_UNUSED,A3,A4_UNUSED) A1##A3
14 #else
15 #define SVE_ACLE_FUNC(A1,A2,A3,A4) A1##A2##A3##A4
16 #endif
18 // CHECK-LABEL: @test_svset2_bf16_0(
19 // CHECK-NEXT: entry:
20 // CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x bfloat> @llvm.vector.insert.nxv16bf16.nxv8bf16(<vscale x 16 x bfloat> [[TUPLE:%.*]], <vscale x 8 x bfloat> [[X:%.*]], i64 0)
21 // CHECK-NEXT: ret <vscale x 16 x bfloat> [[TMP0]]
23 // CPP-CHECK-LABEL: @_Z18test_svset2_bf16_014svbfloat16x2_tu14__SVBfloat16_t(
24 // CPP-CHECK-NEXT: entry:
25 // CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x bfloat> @llvm.vector.insert.nxv16bf16.nxv8bf16(<vscale x 16 x bfloat> [[TUPLE:%.*]], <vscale x 8 x bfloat> [[X:%.*]], i64 0)
26 // CPP-CHECK-NEXT: ret <vscale x 16 x bfloat> [[TMP0]]
28 svbfloat16x2_t test_svset2_bf16_0(svbfloat16x2_t tuple, svbfloat16_t x)
30 return SVE_ACLE_FUNC(svset2,_bf16,,)(tuple, 0, x);
33 // CHECK-LABEL: @test_svset2_bf16_1(
34 // CHECK-NEXT: entry:
35 // CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x bfloat> @llvm.vector.insert.nxv16bf16.nxv8bf16(<vscale x 16 x bfloat> [[TUPLE:%.*]], <vscale x 8 x bfloat> [[X:%.*]], i64 8)
36 // CHECK-NEXT: ret <vscale x 16 x bfloat> [[TMP0]]
38 // CPP-CHECK-LABEL: @_Z18test_svset2_bf16_114svbfloat16x2_tu14__SVBfloat16_t(
39 // CPP-CHECK-NEXT: entry:
40 // CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x bfloat> @llvm.vector.insert.nxv16bf16.nxv8bf16(<vscale x 16 x bfloat> [[TUPLE:%.*]], <vscale x 8 x bfloat> [[X:%.*]], i64 8)
41 // CPP-CHECK-NEXT: ret <vscale x 16 x bfloat> [[TMP0]]
43 svbfloat16x2_t test_svset2_bf16_1(svbfloat16x2_t tuple, svbfloat16_t x)
45 return SVE_ACLE_FUNC(svset2,_bf16,,)(tuple, 1, x);