diff --git a/var/spack/repos/builtin/packages/fujitsu-fftw/package.py b/var/spack/repos/builtin/packages/fujitsu-fftw/package.py
new file mode 100644
index 0000000000..67a7b04aee
--- /dev/null
+++ b/var/spack/repos/builtin/packages/fujitsu-fftw/package.py
@@ -0,0 +1,112 @@
+# Copyright 2013-2021 Lawrence Livermore National Security, LLC and other
+# Spack Project Developers. See the top-level COPYRIGHT file for details.
+#
+# SPDX-License-Identifier: (Apache-2.0 OR MIT)
+
+from spack import *
+from spack.pkg.builtin.fftw import FftwBase
+from spack.error import SpackError
+
+
+def target_check(spec):
+    if spec.target != "a64fx":
+        error_msg = ("It can only be built on an A64FX machine.\n")
+        raise SpackError(error_msg)
+
+
+class FujitsuFftw(FftwBase):
+    """FFTW (Fujitsu Optimized version) is a comprehensive collection of
+    fast C routines for computing the Discrete Fourier Transform (DFT)
+    and various special cases thereof.
+
+    It is an open-source implementation of the Fast Fourier transform
+    algorithm. It can compute transforms of real and complex-values
+    arrays of arbitrary size and dimension.
+    Fujitsu Optimized FFTW is the optimized FFTW implementation targeted
+    for A64FX CPUs.
+
+    For single precision build, please use precision value as float.
+    Example : spack install fujitsufftw precision=float
+    """
+
+    _name = 'fujitsu-fftw'
+    homepage = "https://github.com/fujitsu/fftw3"
+
+    version('master', branch='fj_master', git='https://github.com/fujitsu/fftw3.git')
+
+    variant('shared', default=True, description='Builds a shared version of the library')
+    variant('openmp', default=True, description="Enable OpenMP support")
+    variant('debug', default=False, description='Builds a debug version of the library')
+
+    depends_on('texinfo')
+
+    provides('fftw-api@3', when='@2:')
+
+    conflicts('precision=quad', when='%fj', msg="Fujitsu Compiler doesn't support quad precision")
+    conflicts('precision=long_double', when='%fj', msg="ARM-SVE vector instructions only works in single or double precision")
+    conflicts('%arm')
+    conflicts('%cce')
+    conflicts('%apple-clang')
+    conflicts('%clang')
+    conflicts('%gcc')
+    conflicts('%intel')
+    conflicts('%nag')
+    conflicts('%pgi')
+    conflicts('%xl')
+    conflicts('%xl_r')
+
+    def autoreconf(self, spec, prefix):
+        if spec.target != "a64fx":
+            target_check(spec)
+
+        touch = which('touch')
+        touch('ChangeLog')
+        autoreconf = which('autoreconf')
+        autoreconf('-ifv')
+
+    def configure(self, spec, prefix):
+        """Configure function"""
+        # Base options
+        options = [
+            'CFLAGS=-Ofast',
+            'FFLAGS=-Kfast',
+            '--enable-sve',
+            '--enable-armv8-cntvct-el0',
+            '--enable-fma',
+            '--enable-fortran',
+            '--prefix={0}'.format(prefix),
+            'ac_cv_prog_f77_v=-###'
+        ]
+
+        if '+shared' in spec:
+            options.append('--enable-shared')
+        else:
+            options.append('--disable-shared')
+
+        if '+openmp' in spec:
+            options.append('--enable-openmp')
+            options.append('OPENMP_CFLAGS=-Kopenmp')
+        else:
+            options.append('--disable-openmp')
+
+        if '+mpi' in spec:
+            options.append('--enable-mpi')
+        else:
+            options.append('--disable-mpi')
+
+        # Double is the default precision, for all the others we need
+        # to enable the corresponding option.
+        enable_precision = {
+            'float': ['--enable-float'],
+            'double': None,
+            'long_double': ['--enable-long-double'],
+            'quad': ['--enable-quad-precision']
+        }
+
+        # Different precisions must be configured and compiled one at a time
+        configure = Executable('../configure')
+        for precision in self.selected_precisions:
+
+            opts = (enable_precision[precision] or []) + options[:]
+            with working_dir(precision, create=True):
+                configure(*opts)