// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// REQUIRES: aarch64-registered-target
// 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
// 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
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -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
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -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
// RUN: %clang_cc1 -triple aarch64 -target-feature +bf16 -target-feature +sme -target-feature +sme2 -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
#include <arm_sme.h>
#ifdef SVE_OVERLOADED_FORMS
// A simple used,unused... macro, long enough to represent any SVE builtin.
#define SVE_ACLE_FUNC(A1,A2_UNUSED) A1
#else
#define SVE_ACLE_FUNC(A1,A2) A1##A2
#endif
// 8-bit UZPs
// CHECK-LABEL: @test_svuzp_s8_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sve.uzp.x2.nxv16i8(<vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z16test_svuzp_s8_x210svint8x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sve.uzp.x2.nxv16i8(<vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svint8x2_t test_svuzp_s8_x2(svint8x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzp,_s8_x2)(zn);
}
// CHECK-LABEL: @test_svuzp_u8_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sve.uzp.x2.nxv16i8(<vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z16test_svuzp_u8_x211svuint8x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sve.uzp.x2.nxv16i8(<vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svuint8x2_t test_svuzp_u8_x2(svuint8x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzp,_u8_x2)(zn);
}
// 16-bit UZPs
// CHECK-LABEL: @test_svuzp_s16_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sve.uzp.x2.nxv8i16(<vscale x 8 x i16> [[ZN_COERCE0:%.*]], <vscale x 8 x i16> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z17test_svuzp_s16_x211svint16x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sve.uzp.x2.nxv8i16(<vscale x 8 x i16> [[ZN_COERCE0:%.*]], <vscale x 8 x i16> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
svint16x2_t test_svuzp_s16_x2(svint16x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzp,_s16_x2)(zn);
}
// CHECK-LABEL: @test_svuzp_u16_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sve.uzp.x2.nxv8i16(<vscale x 8 x i16> [[ZN_COERCE0:%.*]], <vscale x 8 x i16> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z17test_svuzp_u16_x212svuint16x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sve.uzp.x2.nxv8i16(<vscale x 8 x i16> [[ZN_COERCE0:%.*]], <vscale x 8 x i16> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
svuint16x2_t test_svuzp_u16_x2(svuint16x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzp,_u16_x2)(zn);
}
// CHECK-LABEL: @test_svuzp_f16_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sve.uzp.x2.nxv8f16(<vscale x 8 x half> [[ZN_COERCE0:%.*]], <vscale x 8 x half> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z17test_svuzp_f16_x213svfloat16x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sve.uzp.x2.nxv8f16(<vscale x 8 x half> [[ZN_COERCE0:%.*]], <vscale x 8 x half> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
//
svfloat16x2_t test_svuzp_f16_x2(svfloat16x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzp,_f16_x2)(zn);
}
// CHECK-LABEL: @test_svuzp_bf16_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sve.uzp.x2.nxv8bf16(<vscale x 8 x bfloat> [[ZN_COERCE0:%.*]], <vscale x 8 x bfloat> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z18test_svuzp_bf16_x214svbfloat16x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sve.uzp.x2.nxv8bf16(<vscale x 8 x bfloat> [[ZN_COERCE0:%.*]], <vscale x 8 x bfloat> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
//
svbfloat16x2_t test_svuzp_bf16_x2(svbfloat16x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzp,_bf16_x2)(zn);
}
// 32-bit UZPs
// CHECK-LABEL: @test_svuzp_s32_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sve.uzp.x2.nxv4i32(<vscale x 4 x i32> [[ZN_COERCE0:%.*]], <vscale x 4 x i32> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z17test_svuzp_s32_x211svint32x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sve.uzp.x2.nxv4i32(<vscale x 4 x i32> [[ZN_COERCE0:%.*]], <vscale x 4 x i32> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
svint32x2_t test_svuzp_s32_x2(svint32x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzp,_s32_x2)(zn);
}
// CHECK-LABEL: @test_svuzp_u32_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sve.uzp.x2.nxv4i32(<vscale x 4 x i32> [[ZN_COERCE0:%.*]], <vscale x 4 x i32> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z17test_svuzp_u32_x212svuint32x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sve.uzp.x2.nxv4i32(<vscale x 4 x i32> [[ZN_COERCE0:%.*]], <vscale x 4 x i32> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
svuint32x2_t test_svuzp_u32_x2(svuint32x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzp,_u32_x2)(zn);
}
// CHECK-LABEL: @test_svuzp_f32_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sve.uzp.x2.nxv4f32(<vscale x 4 x float> [[ZN_COERCE0:%.*]], <vscale x 4 x float> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z17test_svuzp_f32_x213svfloat32x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sve.uzp.x2.nxv4f32(<vscale x 4 x float> [[ZN_COERCE0:%.*]], <vscale x 4 x float> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
//
svfloat32x2_t test_svuzp_f32_x2(svfloat32x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzp,_f32_x2)(zn);
}
// 64-bit UZPs
// CHECK-LABEL: @test_svuzp_s64_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sve.uzp.x2.nxv2i64(<vscale x 2 x i64> [[ZN_COERCE0:%.*]], <vscale x 2 x i64> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z17test_svuzp_s64_x211svint64x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sve.uzp.x2.nxv2i64(<vscale x 2 x i64> [[ZN_COERCE0:%.*]], <vscale x 2 x i64> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
svint64x2_t test_svuzp_s64_x2(svint64x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzp,_s64_x2)(zn);
}
// CHECK-LABEL: @test_svuzp_u64_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sve.uzp.x2.nxv2i64(<vscale x 2 x i64> [[ZN_COERCE0:%.*]], <vscale x 2 x i64> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z17test_svuzp_u64_x212svuint64x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sve.uzp.x2.nxv2i64(<vscale x 2 x i64> [[ZN_COERCE0:%.*]], <vscale x 2 x i64> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
svuint64x2_t test_svuzp_u64_x2(svuint64x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzp,_u64_x2)(zn);
}
// CHECK-LABEL: @test_svuzp_f64_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sve.uzp.x2.nxv2f64(<vscale x 2 x double> [[ZN_COERCE0:%.*]], <vscale x 2 x double> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 2 x double>, <vscale x 2 x double> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z17test_svuzp_f64_x213svfloat64x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sve.uzp.x2.nxv2f64(<vscale x 2 x double> [[ZN_COERCE0:%.*]], <vscale x 2 x double> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 2 x double>, <vscale x 2 x double> } [[TMP0]]
//
svfloat64x2_t test_svuzp_f64_x2(svfloat64x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzp,_f64_x2)(zn);
}
// 128-bit UZPs
// CHECK-LABEL: @test_svuzpq_s8_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sve.uzpq.x2.nxv16i8(<vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z17test_svuzpq_s8_x210svint8x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sve.uzpq.x2.nxv16i8(<vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svint8x2_t test_svuzpq_s8_x2(svint8x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzpq,_s8_x2)(zn);
}
// CHECK-LABEL: @test_svuzpq_u8_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sve.uzpq.x2.nxv16i8(<vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z17test_svuzpq_u8_x211svuint8x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sve.uzpq.x2.nxv16i8(<vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svuint8x2_t test_svuzpq_u8_x2(svuint8x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzpq,_u8_x2)(zn);
}
// CHECK-LABEL: @test_svuzpq_s16_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sve.uzpq.x2.nxv8i16(<vscale x 8 x i16> [[ZN_COERCE0:%.*]], <vscale x 8 x i16> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z18test_svuzpq_s16_x211svint16x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sve.uzpq.x2.nxv8i16(<vscale x 8 x i16> [[ZN_COERCE0:%.*]], <vscale x 8 x i16> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
svint16x2_t test_svuzpq_s16_x2(svint16x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzpq,_s16_x2)(zn);
}
// CHECK-LABEL: @test_svuzpq_u16_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sve.uzpq.x2.nxv8i16(<vscale x 8 x i16> [[ZN_COERCE0:%.*]], <vscale x 8 x i16> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z18test_svuzpq_u16_x212svuint16x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sve.uzpq.x2.nxv8i16(<vscale x 8 x i16> [[ZN_COERCE0:%.*]], <vscale x 8 x i16> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
svuint16x2_t test_svuzpq_u16_x2(svuint16x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzpq,_u16_x2)(zn);
}
// CHECK-LABEL: @test_svuzpq_f16_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sve.uzpq.x2.nxv8f16(<vscale x 8 x half> [[ZN_COERCE0:%.*]], <vscale x 8 x half> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z18test_svuzpq_f16_x213svfloat16x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sve.uzpq.x2.nxv8f16(<vscale x 8 x half> [[ZN_COERCE0:%.*]], <vscale x 8 x half> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
//
svfloat16x2_t test_svuzpq_f16_x2(svfloat16x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzpq,_f16_x2)(zn);
}
// CHECK-LABEL: @test_svuzpq_bf16_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sve.uzpq.x2.nxv8bf16(<vscale x 8 x bfloat> [[ZN_COERCE0:%.*]], <vscale x 8 x bfloat> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z19test_svuzpq_bf16_x214svbfloat16x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sve.uzpq.x2.nxv8bf16(<vscale x 8 x bfloat> [[ZN_COERCE0:%.*]], <vscale x 8 x bfloat> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
//
svbfloat16x2_t test_svuzpq_bf16_x2(svbfloat16x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzpq,_bf16_x2)(zn);
}
// CHECK-LABEL: @test_svuzpq_s32_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sve.uzpq.x2.nxv4i32(<vscale x 4 x i32> [[ZN_COERCE0:%.*]], <vscale x 4 x i32> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z18test_svuzpq_s32_x211svint32x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sve.uzpq.x2.nxv4i32(<vscale x 4 x i32> [[ZN_COERCE0:%.*]], <vscale x 4 x i32> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
svint32x2_t test_svuzpq_s32_x2(svint32x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzpq,_s32_x2)(zn);
}
// CHECK-LABEL: @test_svuzpq_u32_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sve.uzpq.x2.nxv4i32(<vscale x 4 x i32> [[ZN_COERCE0:%.*]], <vscale x 4 x i32> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z18test_svuzpq_u32_x212svuint32x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sve.uzpq.x2.nxv4i32(<vscale x 4 x i32> [[ZN_COERCE0:%.*]], <vscale x 4 x i32> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
svuint32x2_t test_svuzpq_u32_x2(svuint32x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzpq,_u32_x2)(zn);
}
// CHECK-LABEL: @test_svuzpq_f32_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sve.uzpq.x2.nxv4f32(<vscale x 4 x float> [[ZN_COERCE0:%.*]], <vscale x 4 x float> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z18test_svuzpq_f32_x213svfloat32x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sve.uzpq.x2.nxv4f32(<vscale x 4 x float> [[ZN_COERCE0:%.*]], <vscale x 4 x float> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
//
svfloat32x2_t test_svuzpq_f32_x2(svfloat32x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzpq,_f32_x2)(zn);
}
// CHECK-LABEL: @test_svuzpq_s64_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sve.uzpq.x2.nxv2i64(<vscale x 2 x i64> [[ZN_COERCE0:%.*]], <vscale x 2 x i64> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z18test_svuzpq_s64_x211svint64x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sve.uzpq.x2.nxv2i64(<vscale x 2 x i64> [[ZN_COERCE0:%.*]], <vscale x 2 x i64> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
svint64x2_t test_svuzpq_s64_x2(svint64x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzpq,_s64_x2)(zn);
}
// CHECK-LABEL: @test_svuzpq_u64_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sve.uzpq.x2.nxv2i64(<vscale x 2 x i64> [[ZN_COERCE0:%.*]], <vscale x 2 x i64> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z18test_svuzpq_u64_x212svuint64x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sve.uzpq.x2.nxv2i64(<vscale x 2 x i64> [[ZN_COERCE0:%.*]], <vscale x 2 x i64> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
svuint64x2_t test_svuzpq_u64_x2(svuint64x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzpq,_u64_x2)(zn);
}
// CHECK-LABEL: @test_svuzpq_f64_x2(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sve.uzpq.x2.nxv2f64(<vscale x 2 x double> [[ZN_COERCE0:%.*]], <vscale x 2 x double> [[ZN_COERCE1:%.*]])
// CHECK-NEXT: ret { <vscale x 2 x double>, <vscale x 2 x double> } [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z18test_svuzpq_f64_x213svfloat64x2_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sve.uzpq.x2.nxv2f64(<vscale x 2 x double> [[ZN_COERCE0:%.*]], <vscale x 2 x double> [[ZN_COERCE1:%.*]])
// CPP-CHECK-NEXT: ret { <vscale x 2 x double>, <vscale x 2 x double> } [[TMP0]]
//
svfloat64x2_t test_svuzpq_f64_x2(svfloat64x2_t zn) __arm_streaming {
return SVE_ACLE_FUNC(svuzpq,_f64_x2)(zn);
}