xref: /llvm-project/clang/test/CodeGen/AArch64/sve-intrinsics/acle_sve_dup-bfloat.c (revision 207e5ccceec8d3cc3f32723e78f2a142bc61b07d)

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// REQUIRES: aarch64-registered-target
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +bf16 -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,instcombine,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +bf16 -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +bf16 -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,instcombine,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +bf16 -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK

// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +bf16 -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sme -target-feature +bf16 -S -disable-O0-optnone -Werror -Wall -o /dev/null %s

#include <arm_sve.h>

#if defined __ARM_FEATURE_SME
#define MODE_ATTR __arm_streaming
#else
#define MODE_ATTR
#endif

#ifdef SVE_OVERLOADED_FORMS
// A simple used,unused... macro, long enough to represent any SVE builtin.
#define SVE_ACLE_FUNC(A1, A2_UNUSED, A3, A4_UNUSED) A1##A3
#else
#define SVE_ACLE_FUNC(A1, A2, A3, A4) A1##A2##A3##A4
#endif

// CHECK-LABEL: @test_svdup_n_bf16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x bfloat> poison, bfloat [[OP:%.*]], i64 0
// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x bfloat> [[DOTSPLATINSERT]], <vscale x 8 x bfloat> poison, <vscale x 8 x i32> zeroinitializer
// CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z17test_svdup_n_bf16u6__bf16(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x bfloat> poison, bfloat [[OP:%.*]], i64 0
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x bfloat> [[DOTSPLATINSERT]], <vscale x 8 x bfloat> poison, <vscale x 8 x i32> zeroinitializer
// CPP-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
//
svbfloat16_t test_svdup_n_bf16(bfloat16_t op) MODE_ATTR {
  // expected-warning@+1 {{implicit declaration of function 'svdup_n_bf16'}}
  return SVE_ACLE_FUNC(svdup, _n, _bf16, )(op);
}

// CHECK-LABEL: @test_svdup_n_bf16_z(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.dup.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x i1> [[TMP0]], bfloat [[OP:%.*]])
// CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z19test_svdup_n_bf16_zu10__SVBool_tu6__bf16(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.dup.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x i1> [[TMP0]], bfloat [[OP:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP1]]
//
svbfloat16_t test_svdup_n_bf16_z(svbool_t pg, bfloat16_t op) MODE_ATTR {
  // expected-warning@+1 {{implicit declaration of function 'svdup_n_bf16_z'}}
  return SVE_ACLE_FUNC(svdup, _n, _bf16_z, )(pg, op);
}

// CHECK-LABEL: @test_svdup_n_bf16_m(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.dup.nxv8bf16(<vscale x 8 x bfloat> [[INACTIVE:%.*]], <vscale x 8 x i1> [[TMP0]], bfloat [[OP:%.*]])
// CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z19test_svdup_n_bf16_mu14__SVBfloat16_tu10__SVBool_tu6__bf16(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.dup.nxv8bf16(<vscale x 8 x bfloat> [[INACTIVE:%.*]], <vscale x 8 x i1> [[TMP0]], bfloat [[OP:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP1]]
//
svbfloat16_t test_svdup_n_bf16_m(svbfloat16_t inactive, svbool_t pg, bfloat16_t op) MODE_ATTR {
  // expected-warning@+1 {{implicit declaration of function 'svdup_n_bf16_m'}}
  return SVE_ACLE_FUNC(svdup, _n, _bf16_m, )(inactive, pg, op);
}

// CHECK-LABEL: @test_svdup_n_bf16_x(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.dup.nxv8bf16(<vscale x 8 x bfloat> undef, <vscale x 8 x i1> [[TMP0]], bfloat [[OP:%.*]])
// CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z19test_svdup_n_bf16_xu10__SVBool_tu6__bf16(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.dup.nxv8bf16(<vscale x 8 x bfloat> undef, <vscale x 8 x i1> [[TMP0]], bfloat [[OP:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP1]]
//
svbfloat16_t test_svdup_n_bf16_x(svbool_t pg, bfloat16_t op) MODE_ATTR {
  // expected-warning@+1 {{implicit declaration of function 'svdup_n_bf16_x'}}
  return SVE_ACLE_FUNC(svdup, _n, _bf16_x, )(pg, op);
}

// CHECK-LABEL: @test_svdup_lane_bf16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[INDEX:%.*]], i64 0
// CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.tbl.nxv8bf16(<vscale x 8 x bfloat> [[DATA:%.*]], <vscale x 8 x i16> [[DOTSPLAT]])
// CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z20test_svdup_lane_bf16u14__SVBfloat16_tt(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[INDEX:%.*]], i64 0
// CPP-CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.tbl.nxv8bf16(<vscale x 8 x bfloat> [[DATA:%.*]], <vscale x 8 x i16> [[DOTSPLAT]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
//
svbfloat16_t test_svdup_lane_bf16(svbfloat16_t data, uint16_t index) MODE_ATTR
{
  // expected-warning@+1 {{implicit declaration of function 'svdup_lane_bf16'}}
  return SVE_ACLE_FUNC(svdup_lane,_bf16,,)(data, index);
}