acle_sve_nmla.c | Explore in Territory

// 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 -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sme -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_svnmla_f16_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:%.*]] = select <vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer
// CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP1]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[OP3:%.*]])
// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
//
// CPP-CHECK-LABEL: @_Z17test_svnmla_f16_zu10__SVBool_tu13__SVFloat16_tS0_S0_(
// 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:%.*]] = select <vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP1]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[OP3:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
//
svfloat16_t test_svnmla_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, svfloat16_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_f16,_z,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_f32_z(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer
// CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP1]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[OP3:%.*]])
// CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
//
// CPP-CHECK-LABEL: @_Z17test_svnmla_f32_zu10__SVBool_tu13__SVFloat32_tS0_S0_(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP1]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[OP3:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
//
svfloat32_t test_svnmla_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, svfloat32_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_f32,_z,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_f64_z(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer
// CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP1]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[OP3:%.*]])
// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
//
// CPP-CHECK-LABEL: @_Z17test_svnmla_f64_zu10__SVBool_tu13__SVFloat64_tS0_S0_(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP1]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[OP3:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
//
svfloat64_t test_svnmla_f64_z(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svfloat64_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_f64,_z,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_f16_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 half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[OP3:%.*]])
// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z17test_svnmla_f16_mu10__SVBool_tu13__SVFloat16_tS0_S0_(
// 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 half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[OP3:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
//
svfloat16_t test_svnmla_f16_m(svbool_t pg, svfloat16_t op1, svfloat16_t op2, svfloat16_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_f16,_m,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_f32_m(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[OP3:%.*]])
// CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z17test_svnmla_f32_mu10__SVBool_tu13__SVFloat32_tS0_S0_(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[OP3:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
//
svfloat32_t test_svnmla_f32_m(svbool_t pg, svfloat32_t op1, svfloat32_t op2, svfloat32_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_f32,_m,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_f64_m(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[OP3:%.*]])
// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z17test_svnmla_f64_mu10__SVBool_tu13__SVFloat64_tS0_S0_(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[OP3:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
//
svfloat64_t test_svnmla_f64_m(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svfloat64_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_f64,_m,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_f16_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 half> @llvm.aarch64.sve.fnmla.u.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[OP3:%.*]])
// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z17test_svnmla_f16_xu10__SVBool_tu13__SVFloat16_tS0_S0_(
// 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 half> @llvm.aarch64.sve.fnmla.u.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[OP3:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
//
svfloat16_t test_svnmla_f16_x(svbool_t pg, svfloat16_t op1, svfloat16_t op2, svfloat16_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_f16,_x,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_f32_x(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.u.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[OP3:%.*]])
// CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z17test_svnmla_f32_xu10__SVBool_tu13__SVFloat32_tS0_S0_(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.u.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[OP3:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
//
svfloat32_t test_svnmla_f32_x(svbool_t pg, svfloat32_t op1, svfloat32_t op2, svfloat32_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_f32,_x,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_f64_x(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.u.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[OP3:%.*]])
// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z17test_svnmla_f64_xu10__SVBool_tu13__SVFloat64_tS0_S0_(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.u.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[OP3:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
//
svfloat64_t test_svnmla_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svfloat64_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_f64,_x,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_n_f16_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:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i64 0
// CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
// CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer
// CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP1]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[DOTSPLAT]])
// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
//
// CPP-CHECK-LABEL: @_Z19test_svnmla_n_f16_zu10__SVBool_tu13__SVFloat16_tS0_Dh(
// 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:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i64 0
// CPP-CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP1]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[DOTSPLAT]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
//
svfloat16_t test_svnmla_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, float16_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_n_f16,_z,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_n_f32_z(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i64 0
// CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
// CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer
// CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP1]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[DOTSPLAT]])
// CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
//
// CPP-CHECK-LABEL: @_Z19test_svnmla_n_f32_zu10__SVBool_tu13__SVFloat32_tS0_f(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i64 0
// CPP-CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP1]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[DOTSPLAT]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
//
svfloat32_t test_svnmla_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, float32_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_n_f32,_z,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_n_f64_z(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i64 0
// CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
// CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer
// CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP1]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[DOTSPLAT]])
// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
//
// CPP-CHECK-LABEL: @_Z19test_svnmla_n_f64_zu10__SVBool_tu13__SVFloat64_tS0_d(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i64 0
// CPP-CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP1]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[DOTSPLAT]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
//
svfloat64_t test_svnmla_n_f64_z(svbool_t pg, svfloat64_t op1, svfloat64_t op2, float64_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_n_f64,_z,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_n_f16_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:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i64 0
// CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[DOTSPLAT]])
// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z19test_svnmla_n_f16_mu10__SVBool_tu13__SVFloat16_tS0_Dh(
// 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:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i64 0
// CPP-CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[DOTSPLAT]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
//
svfloat16_t test_svnmla_n_f16_m(svbool_t pg, svfloat16_t op1, svfloat16_t op2, float16_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_n_f16,_m,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_n_f32_m(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i64 0
// CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[DOTSPLAT]])
// CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z19test_svnmla_n_f32_mu10__SVBool_tu13__SVFloat32_tS0_f(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i64 0
// CPP-CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[DOTSPLAT]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
//
svfloat32_t test_svnmla_n_f32_m(svbool_t pg, svfloat32_t op1, svfloat32_t op2, float32_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_n_f32,_m,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_n_f64_m(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i64 0
// CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[DOTSPLAT]])
// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z19test_svnmla_n_f64_mu10__SVBool_tu13__SVFloat64_tS0_d(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i64 0
// CPP-CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[DOTSPLAT]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
//
svfloat64_t test_svnmla_n_f64_m(svbool_t pg, svfloat64_t op1, svfloat64_t op2, float64_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_n_f64,_m,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_n_f16_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:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i64 0
// CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.u.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[DOTSPLAT]])
// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z19test_svnmla_n_f16_xu10__SVBool_tu13__SVFloat16_tS0_Dh(
// 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:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i64 0
// CPP-CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.u.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[DOTSPLAT]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
//
svfloat16_t test_svnmla_n_f16_x(svbool_t pg, svfloat16_t op1, svfloat16_t op2, float16_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_n_f16,_x,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_n_f32_x(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i64 0
// CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.u.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[DOTSPLAT]])
// CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z19test_svnmla_n_f32_xu10__SVBool_tu13__SVFloat32_tS0_f(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i64 0
// CPP-CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.u.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[DOTSPLAT]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
//
svfloat32_t test_svnmla_n_f32_x(svbool_t pg, svfloat32_t op1, svfloat32_t op2, float32_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_n_f32,_x,)(pg, op1, op2, op3);
}

// CHECK-LABEL: @test_svnmla_n_f64_x(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i64 0
// CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.u.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[DOTSPLAT]])
// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z19test_svnmla_n_f64_xu10__SVBool_tu13__SVFloat64_tS0_d(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i64 0
// CPP-CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.u.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[DOTSPLAT]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
//
svfloat64_t test_svnmla_n_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, float64_t op3) MODE_ATTR
{
  return SVE_ACLE_FUNC(svnmla,_n_f64,_x,)(pg, op1, op2, op3);
}
llvm/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmla.c
