def ecp_int(cell, kpts=None):
if rank == 0:
comm.bcast(cell.dumps())
else:
cell = pgto.loads(comm.bcast(None))
if kpts is None:
kpts_lst = numpy.zeros((1,3))
else:
kpts_lst = numpy.reshape(kpts, (-1,3))
ecpcell = gto.Mole()
ecpcell._atm = cell._atm
# append a fictitious s function to mimic the auxiliary index in pbc.incore.
# ptr2last_env_idx to force PBCnr3c_fill_* function to copy the entire "env"
ptr2last_env_idx = len(cell._env) - 1
ecpbas = numpy.vstack([[0, 0, 1, 1, 0, ptr2last_env_idx, 0, 0],
cell._ecpbas]).astype(numpy.int32)
ecpcell._bas = ecpbas
ecpcell._env = cell._env
# In pbc.incore _ecpbas is appended to two sets of cell._bas and the
# fictitious s function.
cell._env[AS_ECPBAS_OFFSET] = cell.nbas * 2 + 1
cell._env[AS_NECPBAS] = len(cell._ecpbas)
kptij_lst = numpy.hstack((kpts_lst,kpts_lst)).reshape(-1,2,3)
nkpts = len(kpts_lst)
if abs(kpts_lst).sum() < 1e-9: # gamma_point
dtype = numpy.double
else:
dtype = numpy.complex128
ao_loc = cell.ao_loc_nr()
nao = ao_loc[-1]
mat = numpy.zeros((nkpts,nao,nao), dtype=dtype)
intor = cell._add_suffix('ECPscalar')
int3c = incore.wrap_int3c(cell, ecpcell, intor, kptij_lst=kptij_lst)
# shls_slice of auxiliary index (0,1) corresponds to the fictitious s function
tasks = [(i, i+1, j, j+1, 0, 1) # shls_slice
for i in range(cell.nbas) for j in range(i+1)]
for shls_slice in mpi.work_stealing_partition(tasks):
i0 = ao_loc[shls_slice[0]]
i1 = ao_loc[shls_slice[1]]
j0 = ao_loc[shls_slice[2]]
j1 = ao_loc[shls_slice[3]]
buf = numpy.empty((nkpts,i1-i0,j1-j0), dtype=dtype)
mat[:,i0:i1,j0:j1] = int3c(shls_slice, buf)
buf = mpi.reduce(mat)
if rank == 0:
mat = []
for k, kpt in enumerate(kpts_lst):
v = lib.unpack_tril(lib.pack_tril(buf[k]), lib.HERMITIAN)
if abs(kpt).sum() < 1e-9: # gamma_point:
v = v.real
mat.append(v)
if kpts is None or numpy.shape(kpts) == (3,):
mat = mat[0]
return mat
def _make_j3c(mydf, cell, auxcell, kptij_lst, cderi_file):
log = logger.Logger(mydf.stdout, mydf.verbose)
t1 = t0 = (time.clock(), time.time())
fused_cell, fuse = fuse_auxcell(mydf, mydf.auxcell)
ao_loc = cell.ao_loc_nr()
nao = ao_loc[-1]
naux = auxcell.nao_nr()
nkptij = len(kptij_lst)
mesh = mydf.mesh
Gv, Gvbase, kws = cell.get_Gv_weights(mesh)
b = cell.reciprocal_vectors()
gxyz = lib.cartesian_prod([numpy.arange(len(x)) for x in Gvbase])
ngrids = gxyz.shape[0]
kptis = kptij_lst[:, 0]
kptjs = kptij_lst[:, 1]
kpt_ji = kptjs - kptis
uniq_kpts, uniq_index, uniq_inverse = unique(kpt_ji)
log.debug('Num uniq kpts %d', len(uniq_kpts))
log.debug2('uniq_kpts %s', uniq_kpts)
# j2c ~ (-kpt_ji | kpt_ji)
j2c = fused_cell.pbc_intor('int2c2e', hermi=1, kpts=uniq_kpts)
j2ctags = []
t1 = log.timer_debug1('2c2e', *t1)
swapfile = tempfile.NamedTemporaryFile(dir=os.path.dirname(cderi_file))
fswap = lib.H5TmpFile(swapfile.name)
# Unlink swapfile to avoid trash
swapfile = None
mem_now = max(comm.allgather(lib.current_memory()[0]))
max_memory = max(2000, mydf.max_memory - mem_now)
blksize = max(2048, int(max_memory * .5e6 / 16 / fused_cell.nao_nr()))
log.debug2('max_memory %s (MB) blocksize %s', max_memory, blksize)
for k, kpt in enumerate(uniq_kpts):
coulG = mydf.weighted_coulG(kpt, False, mesh)
j2c_k = numpy.zeros_like(j2c[k])
for p0, p1 in mydf.prange(0, ngrids, blksize):
aoaux = ft_ao.ft_ao(fused_cell, Gv[p0:p1], None, b, gxyz[p0:p1],
Gvbase, kpt).T
LkR = numpy.asarray(aoaux.real, order='C')
LkI = numpy.asarray(aoaux.imag, order='C')
aoaux = None
if is_zero(kpt): # kpti == kptj
j2c_k[naux:] += lib.ddot(LkR[naux:] * coulG[p0:p1], LkR.T)
j2c_k[naux:] += lib.ddot(LkI[naux:] * coulG[p0:p1], LkI.T)
else:
j2cR, j2cI = zdotCN(LkR[naux:] * coulG[p0:p1],
LkI[naux:] * coulG[p0:p1], LkR.T, LkI.T)
j2c_k[naux:] += j2cR + j2cI * 1j
kLR = kLI = None
j2c_k[:naux, naux:] = j2c_k[naux:, :naux].conj().T
j2c[k] -= mpi.allreduce(j2c_k)
j2c[k] = fuse(fuse(j2c[k]).T).T
try:
fswap['j2c/%d' % k] = scipy.linalg.cholesky(j2c[k], lower=True)
j2ctags.append('CD')
except scipy.linalg.LinAlgError as e:
#msg =('===================================\n'
# 'J-metric not positive definite.\n'
# 'It is likely that mesh is not enough.\n'
# '===================================')
#log.error(msg)
#raise scipy.linalg.LinAlgError('\n'.join([str(e), msg]))
w, v = scipy.linalg.eigh(j2c[k])
log.debug2('metric linear dependency for kpt %s', k)
log.debug2('cond = %.4g, drop %d bfns', w[0] / w[-1],
numpy.count_nonzero(w < mydf.linear_dep_threshold))
v1 = v[:, w > mydf.linear_dep_threshold].T.conj()
v1 /= numpy.sqrt(w[w > mydf.linear_dep_threshold]).reshape(-1, 1)
fswap['j2c/%d' % k] = v1
if cell.dimension == 2 and cell.low_dim_ft_type != 'inf_vacuum':
idx = numpy.where(w < -mydf.linear_dep_threshold)[0]
if len(idx) > 0:
fswap['j2c-/%d' % k] = (v[:, idx] /
numpy.sqrt(-w[idx])).conj().T
w = v = v1 = None
j2ctags.append('eig')
j2c = coulG = None
aosym_s2 = numpy.einsum('ix->i', abs(kptis - kptjs)) < 1e-9
j_only = numpy.all(aosym_s2)
if gamma_point(kptij_lst):
dtype = 'f8'
else:
dtype = 'c16'
t1 = log.timer_debug1('aoaux and int2c', *t1)
# Estimates the buffer size based on the last contraction in G-space.
# This contraction requires to hold nkptj copies of (naux,?) array
# simultaneously in memory.
mem_now = max(comm.allgather(lib.current_memory()[0]))
max_memory = max(2000, mydf.max_memory - mem_now)
nkptj_max = max((uniq_inverse == x).sum() for x in set(uniq_inverse))
buflen = max(
int(
min(max_memory * .5e6 / 16 / naux / (nkptj_max + 2) / nao,
nao / 3 / mpi.pool.size)), 1)
chunks = (buflen, nao)
j3c_jobs = grids2d_int3c_jobs(cell, auxcell, kptij_lst, chunks, j_only)
log.debug1('max_memory = %d MB (%d in use) chunks %s', max_memory,
mem_now, chunks)
log.debug2('j3c_jobs %s', j3c_jobs)
if j_only:
int3c = wrap_int3c(cell, fused_cell, 'int3c2e', 's2', 1, kptij_lst)
else:
int3c = wrap_int3c(cell, fused_cell, 'int3c2e', 's1', 1, kptij_lst)
idxb = numpy.tril_indices(nao)
idxb = (idxb[0] * nao + idxb[1]).astype('i')
aux_loc = fused_cell.ao_loc_nr('ssc' in 'int3c2e')
def gen_int3c(job_id, ish0, ish1):
dataname = 'j3c-chunks/%d' % job_id
i0 = ao_loc[ish0]
i1 = ao_loc[ish1]
dii = i1 * (i1 + 1) // 2 - i0 * (i0 + 1) // 2
if j_only:
dij = dii
buflen = max(8, int(max_memory * 1e6 / 16 / (nkptij * dii + dii)))
else:
dij = (i1 - i0) * nao
buflen = max(8, int(max_memory * 1e6 / 16 / (nkptij * dij + dij)))
auxranges = balance_segs(aux_loc[1:] - aux_loc[:-1], buflen)
buflen = max([x[2] for x in auxranges])
buf = numpy.empty(nkptij * dij * buflen, dtype=dtype)
buf1 = numpy.empty(dij * buflen, dtype=dtype)
naux = aux_loc[-1]
for kpt_id, kptij in enumerate(kptij_lst):
key = '%s/%d' % (dataname, kpt_id)
if aosym_s2[kpt_id]:
shape = (naux, dii)
else:
shape = (naux, dij)
if gamma_point(kptij):
fswap.create_dataset(key, shape, 'f8')
else:
fswap.create_dataset(key, shape, 'c16')
naux0 = 0
for istep, auxrange in enumerate(auxranges):
log.alldebug2("aux_e1 job_id %d step %d", job_id, istep)
sh0, sh1, nrow = auxrange
sub_slice = (ish0, ish1, 0, cell.nbas, sh0, sh1)
mat = numpy.ndarray((nkptij, dij, nrow), dtype=dtype, buffer=buf)
mat = int3c(sub_slice, mat)
for k, kptij in enumerate(kptij_lst):
h5dat = fswap['%s/%d' % (dataname, k)]
v = lib.transpose(mat[k], out=buf1)
if not j_only and aosym_s2[k]:
idy = idxb[i0 * (i0 + 1) // 2:i1 *
(i1 + 1) // 2] - i0 * nao
out = numpy.ndarray((nrow, dii),
dtype=v.dtype,
buffer=mat[k])
v = numpy.take(v, idy, axis=1, out=out)
if gamma_point(kptij):
h5dat[naux0:naux0 + nrow] = v.real
else:
h5dat[naux0:naux0 + nrow] = v
naux0 += nrow
def ft_fuse(job_id, uniq_kptji_id, sh0, sh1):
kpt = uniq_kpts[uniq_kptji_id] # kpt = kptj - kpti
adapted_ji_idx = numpy.where(uniq_inverse == uniq_kptji_id)[0]
adapted_kptjs = kptjs[adapted_ji_idx]
nkptj = len(adapted_kptjs)
j2c = numpy.asarray(fswap['j2c/%d' % uniq_kptji_id])
j2ctag = j2ctags[uniq_kptji_id]
naux0 = j2c.shape[0]
if ('j2c-/%d' % uniq_kptji_id) in fswap:
j2c_negative = numpy.asarray(fswap['j2c-/%d' % uniq_kptji_id])
else:
j2c_negative = None
if is_zero(kpt):
aosym = 's2'
else:
aosym = 's1'
if aosym == 's2' and cell.dimension == 3:
vbar = fuse(mydf.auxbar(fused_cell))
ovlp = cell.pbc_intor('int1e_ovlp', hermi=1, kpts=adapted_kptjs)
ovlp = [lib.pack_tril(s) for s in ovlp]
j3cR = [None] * nkptj
j3cI = [None] * nkptj
i0 = ao_loc[sh0]
i1 = ao_loc[sh1]
for k, idx in enumerate(adapted_ji_idx):
key = 'j3c-chunks/%d/%d' % (job_id, idx)
v = numpy.asarray(fswap[key])
if aosym == 's2' and cell.dimension == 3:
for i in numpy.where(vbar != 0)[0]:
v[i] -= vbar[i] * ovlp[k][i0 * (i0 + 1) // 2:i1 *
(i1 + 1) // 2].ravel()
j3cR[k] = numpy.asarray(v.real, order='C')
if v.dtype == numpy.complex128:
j3cI[k] = numpy.asarray(v.imag, order='C')
v = None
ncol = j3cR[0].shape[1]
Gblksize = max(16, int(max_memory * 1e6 / 16 / ncol /
(nkptj + 1))) # +1 for pqkRbuf/pqkIbuf
Gblksize = min(Gblksize, ngrids, 16384)
pqkRbuf = numpy.empty(ncol * Gblksize)
pqkIbuf = numpy.empty(ncol * Gblksize)
buf = numpy.empty(nkptj * ncol * Gblksize, dtype=numpy.complex128)
log.alldebug2('job_id %d blksize (%d,%d)', job_id, Gblksize, ncol)
wcoulG = mydf.weighted_coulG(kpt, False, mesh)
fused_cell_slice = (auxcell.nbas, fused_cell.nbas)
if aosym == 's2':
shls_slice = (sh0, sh1, 0, sh1)
else:
shls_slice = (sh0, sh1, 0, cell.nbas)
for p0, p1 in lib.prange(0, ngrids, Gblksize):
Gaux = ft_ao.ft_ao(fused_cell, Gv[p0:p1], fused_cell_slice, b,
gxyz[p0:p1], Gvbase, kpt)
Gaux *= wcoulG[p0:p1, None]
kLR = Gaux.real.copy('C')
kLI = Gaux.imag.copy('C')
Gaux = None
dat = ft_ao._ft_aopair_kpts(cell,
Gv[p0:p1],
shls_slice,
aosym,
b,
gxyz[p0:p1],
Gvbase,
kpt,
adapted_kptjs,
out=buf)
nG = p1 - p0
for k, ji in enumerate(adapted_ji_idx):
aoao = dat[k].reshape(nG, ncol)
pqkR = numpy.ndarray((ncol, nG), buffer=pqkRbuf)
pqkI = numpy.ndarray((ncol, nG), buffer=pqkIbuf)
pqkR[:] = aoao.real.T
pqkI[:] = aoao.imag.T
lib.dot(kLR.T, pqkR.T, -1, j3cR[k][naux:], 1)
lib.dot(kLI.T, pqkI.T, -1, j3cR[k][naux:], 1)
if not (is_zero(kpt) and gamma_point(adapted_kptjs[k])):
lib.dot(kLR.T, pqkI.T, -1, j3cI[k][naux:], 1)
lib.dot(kLI.T, pqkR.T, 1, j3cI[k][naux:], 1)
kLR = kLI = None
for k, idx in enumerate(adapted_ji_idx):
if is_zero(kpt) and gamma_point(adapted_kptjs[k]):
v = fuse(j3cR[k])
else:
v = fuse(j3cR[k] + j3cI[k] * 1j)
if j2ctag == 'CD':
v = scipy.linalg.solve_triangular(j2c,
v,
lower=True,
overwrite_b=True)
fswap['j3c-chunks/%d/%d' % (job_id, idx)][:naux0] = v
else:
fswap['j3c-chunks/%d/%d' % (job_id, idx)][:naux0] = lib.dot(
j2c, v)
# low-dimension systems
if j2c_negative is not None:
fswap['j3c-/%d/%d' % (job_id, idx)] = lib.dot(j2c_negative, v)
_assemble(mydf, kptij_lst, j3c_jobs, gen_int3c, ft_fuse, cderi_file, fswap,
log)
def aux_e1(cell,
auxcell,
erifile,
intor='int3c2e',
aosym='s2ij',
comp=None,
kptij_lst=None,
dataname='eri_mo',
shls_slice=None,
max_memory=2000,
verbose=0):
r'''3-center AO integrals (L|ij) with double lattice sum:
\sum_{lm} (L[0]|i[l]j[m]), where L is the auxiliary basis.
Three-index integral tensor (kptij_idx, naux, nao_pair) or four-index
integral tensor (kptij_idx, comp, naux, nao_pair) are stored on disk.
Args:
kptij_lst : (*,2,3) array
A list of (kpti, kptj)
'''
intor, comp = gto.moleintor._get_intor_and_comp(cell._add_suffix(intor),
comp)
if isinstance(erifile, h5py.Group):
feri = erifile
elif h5py.is_hdf5(erifile):
feri = h5py.File(erifile, 'a')
else:
feri = h5py.File(erifile, 'w')
if dataname in feri:
del (feri[dataname])
if dataname + '-kptij' in feri:
del (feri[dataname + '-kptij'])
if kptij_lst is None:
kptij_lst = numpy.zeros((1, 2, 3))
feri[dataname + '-kptij'] = kptij_lst
if shls_slice is None:
shls_slice = (0, cell.nbas, 0, cell.nbas, 0, auxcell.nbas)
ao_loc = cell.ao_loc_nr()
aux_loc = auxcell.ao_loc_nr(auxcell.cart
or 'ssc' in intor)[:shls_slice[5] + 1]
ni = ao_loc[shls_slice[1]] - ao_loc[shls_slice[0]]
nj = ao_loc[shls_slice[3]] - ao_loc[shls_slice[2]]
naux = aux_loc[shls_slice[5]] - aux_loc[shls_slice[4]]
nkptij = len(kptij_lst)
nii = (ao_loc[shls_slice[1]] * (ao_loc[shls_slice[1]] + 1) // 2 -
ao_loc[shls_slice[0]] * (ao_loc[shls_slice[0]] + 1) // 2)
nij = ni * nj
kpti = kptij_lst[:, 0]
kptj = kptij_lst[:, 1]
aosym_ks2 = abs(kpti - kptj).sum(axis=1) < KPT_DIFF_TOL
j_only = numpy.all(aosym_ks2)
#aosym_ks2 &= (aosym[:2] == 's2' and shls_slice[:2] == shls_slice[2:4])
aosym_ks2 &= aosym[:2] == 's2'
for k, kptij in enumerate(kptij_lst):
key = '%s/%d' % (dataname, k)
if gamma_point(kptij):
dtype = 'f8'
else:
dtype = 'c16'
if aosym_ks2[k]:
nao_pair = nii
else:
nao_pair = nij
if comp == 1:
shape = (naux, nao_pair)
else:
shape = (comp, naux, nao_pair)
feri.create_dataset(key, shape, dtype)
if naux == 0:
feri.close()
return erifile
if j_only and aosym[:2] == 's2':
assert (shls_slice[2] == 0)
nao_pair = nii
else:
nao_pair = nij
if gamma_point(kptij_lst):
dtype = numpy.double
else:
dtype = numpy.complex128
buflen = max(8, int(max_memory * 1e6 / 16 / (nkptij * ni * nj * comp)))
auxdims = aux_loc[shls_slice[4] + 1:shls_slice[5] +
1] - aux_loc[shls_slice[4]:shls_slice[5]]
auxranges = balance_segs(auxdims, buflen)
buflen = max([x[2] for x in auxranges])
buf = numpy.empty(nkptij * comp * ni * nj * buflen, dtype=dtype)
buf1 = numpy.empty(ni * nj * buflen, dtype=dtype)
int3c = wrap_int3c(cell, auxcell, intor, aosym, comp, kptij_lst)
naux0 = 0
for istep, auxrange in enumerate(auxranges):
sh0, sh1, nrow = auxrange
sub_slice = (shls_slice[0], shls_slice[1], shls_slice[2],
shls_slice[3], shls_slice[4] + sh0, shls_slice[4] + sh1)
mat = numpy.ndarray((nkptij, comp, nao_pair, nrow),
dtype=dtype,
buffer=buf)
mat = int3c(sub_slice, mat)
for k, kptij in enumerate(kptij_lst):
h5dat = feri['%s/%d' % (dataname, k)]
for icomp, v in enumerate(mat[k]):
v = lib.transpose(v, out=buf1)
if gamma_point(kptij):
v = v.real
if aosym_ks2[k] and v.shape[1] == ni**2:
v = lib.pack_tril(v.reshape(-1, ni, ni))
if comp == 1:
h5dat[naux0:naux0 + nrow] = v
else:
h5dat[icomp, naux0:naux0 + nrow] = v
naux0 += nrow
if not isinstance(erifile, h5py.Group):
feri.close()
return erifile
def _aux_e2(cell,
auxcell,
erifile,
intor='int3c2e',
aosym='s2ij',
comp=None,
kptij_lst=None,
dataname='eri_mo',
shls_slice=None,
max_memory=2000,
verbose=0):
r'''3-center AO integrals (ij|L) with double lattice sum:
\sum_{lm} (i[l]j[m]|L[0]), where L is the auxiliary basis.
Three-index integral tensor (kptij_idx, nao_pair, naux) or four-index
integral tensor (kptij_idx, comp, nao_pair, naux) are stored on disk.
**This function should be only used by df and mdf initialization function
_make_j3c**
Args:
kptij_lst : (*,2,3) array
A list of (kpti, kptj)
'''
intor, comp = gto.moleintor._get_intor_and_comp(cell._add_suffix(intor),
comp)
if isinstance(erifile, h5py.Group):
feri = erifile
elif h5py.is_hdf5(erifile):
feri = h5py.File(erifile, 'a')
else:
feri = h5py.File(erifile, 'w')
if dataname in feri:
del (feri[dataname])
if dataname + '-kptij' in feri:
del (feri[dataname + '-kptij'])
if kptij_lst is None:
kptij_lst = numpy.zeros((1, 2, 3))
feri[dataname + '-kptij'] = kptij_lst
if shls_slice is None:
shls_slice = (0, cell.nbas, 0, cell.nbas, 0, auxcell.nbas)
ao_loc = cell.ao_loc_nr()
aux_loc = auxcell.ao_loc_nr(auxcell.cart
or 'ssc' in intor)[:shls_slice[5] + 1]
ni = ao_loc[shls_slice[1]] - ao_loc[shls_slice[0]]
nj = ao_loc[shls_slice[3]] - ao_loc[shls_slice[2]]
naux = aux_loc[shls_slice[5]] - aux_loc[shls_slice[4]]
nkptij = len(kptij_lst)
nii = (ao_loc[shls_slice[1]] * (ao_loc[shls_slice[1]] + 1) // 2 -
ao_loc[shls_slice[0]] * (ao_loc[shls_slice[0]] + 1) // 2)
nij = ni * nj
kpti = kptij_lst[:, 0]
kptj = kptij_lst[:, 1]
aosym_ks2 = abs(kpti - kptj).sum(axis=1) < KPT_DIFF_TOL
j_only = numpy.all(aosym_ks2)
#aosym_ks2 &= (aosym[:2] == 's2' and shls_slice[:2] == shls_slice[2:4])
aosym_ks2 &= aosym[:2] == 's2'
if j_only and aosym[:2] == 's2':
assert (shls_slice[2] == 0)
nao_pair = nii
else:
nao_pair = nij
if gamma_point(kptij_lst):
dtype = numpy.double
else:
dtype = numpy.complex128
buflen = max(8, int(max_memory * .47e6 / 16 / (nkptij * ni * nj * comp)))
auxdims = aux_loc[shls_slice[4] + 1:shls_slice[5] +
1] - aux_loc[shls_slice[4]:shls_slice[5]]
auxranges = balance_segs(auxdims, buflen)
buflen = max([x[2] for x in auxranges])
buf = numpy.empty(nkptij * comp * ni * nj * buflen, dtype=dtype)
buf1 = numpy.empty_like(buf)
int3c = wrap_int3c(cell, auxcell, intor, aosym, comp, kptij_lst)
kptis = kptij_lst[:, 0]
kptjs = kptij_lst[:, 1]
kpt_ji = kptjs - kptis
uniq_kpts, uniq_index, uniq_inverse = unique(kpt_ji)
# sorted_ij_idx: Sort and group the kptij_lst according to the ordering in
# df._make_j3c to reduce the data fragment in the hdf5 file. When datasets
# are written to hdf5, they are saved sequentially. If the integral data are
# saved as the order of kptij_lst, removing the datasets in df._make_j3c will
# lead to holes that can not be reused.
sorted_ij_idx = numpy.hstack(
[numpy.where(uniq_inverse == k)[0] for k, kpt in enumerate(uniq_kpts)])
tril_idx = numpy.tril_indices(ni)
tril_idx = tril_idx[0] * ni + tril_idx[1]
def save(istep, mat):
for k in sorted_ij_idx:
v = mat[k]
if gamma_point(kptij_lst[k]):
v = v.real
if aosym_ks2[k] and nao_pair == ni**2:
v = v[:, tril_idx]
feri['%s/%d/%d' % (dataname, k, istep)] = v
with lib.call_in_background(save) as bsave:
for istep, auxrange in enumerate(auxranges):
sh0, sh1, nrow = auxrange
sub_slice = (shls_slice[0], shls_slice[1], shls_slice[2],
shls_slice[3], shls_slice[4] + sh0,
shls_slice[4] + sh1)
mat = numpy.ndarray((nkptij, comp, nao_pair, nrow),
dtype=dtype,
buffer=buf)
bsave(istep, int3c(sub_slice, mat))
buf, buf1 = buf1, buf
if not isinstance(erifile, h5py.Group):
feri.close()
return erifile
def _make_j3c(mydf, cell, auxcell, kptij_lst, cderi_file):
log = logger.Logger(mydf.stdout, mydf.verbose)
t1 = t0 = (time.clock(), time.time())
fused_cell, fuse = fuse_auxcell(mydf, mydf.auxcell)
ao_loc = cell.ao_loc_nr()
nao = ao_loc[-1]
naux = auxcell.nao_nr()
nkptij = len(kptij_lst)
gs = mydf.gs
Gv, Gvbase, kws = cell.get_Gv_weights(gs)
b = cell.reciprocal_vectors()
gxyz = lib.cartesian_prod([numpy.arange(len(x)) for x in Gvbase])
ngs = gxyz.shape[0]
kptis = kptij_lst[:, 0]
kptjs = kptij_lst[:, 1]
kpt_ji = kptjs - kptis
uniq_kpts, uniq_index, uniq_inverse = unique(kpt_ji)
log.debug('Num uniq kpts %d', len(uniq_kpts))
log.debug2('uniq_kpts %s', uniq_kpts)
# j2c ~ (-kpt_ji | kpt_ji)
j2c = fused_cell.pbc_intor('int2c2e_sph', hermi=1, kpts=uniq_kpts)
j2ctags = []
nauxs = []
t1 = log.timer_debug1('2c2e', *t1)
if h5py.is_hdf5(cderi_file):
feri = h5py.File(cderi_file)
else:
feri = h5py.File(cderi_file, 'w')
for k, kpt in enumerate(uniq_kpts):
aoaux = ft_ao.ft_ao(fused_cell, Gv, None, b, gxyz, Gvbase, kpt).T
coulG = numpy.sqrt(mydf.weighted_coulG(kpt, False, gs))
kLR = (aoaux.real * coulG).T
kLI = (aoaux.imag * coulG).T
if not kLR.flags.c_contiguous: kLR = lib.transpose(kLR.T)
if not kLI.flags.c_contiguous: kLI = lib.transpose(kLI.T)
aoaux = None
kLR1 = numpy.asarray(kLR[:, naux:], order='C')
kLI1 = numpy.asarray(kLI[:, naux:], order='C')
if is_zero(kpt): # kpti == kptj
for p0, p1 in mydf.mpi_prange(0, ngs):
j2cR = lib.ddot(kLR1[p0:p1].T, kLR[p0:p1])
j2cR = lib.ddot(kLI1[p0:p1].T, kLI[p0:p1], 1, j2cR, 1)
j2c[k][naux:] -= mpi.allreduce(j2cR)
j2c[k][:naux, naux:] = j2c[k][naux:, :naux].T
else:
for p0, p1 in mydf.mpi_prange(0, ngs):
j2cR, j2cI = zdotCN(kLR1[p0:p1].T, kLI1[p0:p1].T, kLR[p0:p1],
kLI[p0:p1])
j2cR = mpi.allreduce(j2cR)
j2cI = mpi.allreduce(j2cI)
j2c[k][naux:] -= j2cR + j2cI * 1j
j2c[k][:naux, naux:] = j2c[k][naux:, :naux].T.conj()
j2c[k] = fuse(fuse(j2c[k]).T).T
try:
feri['j2c/%d' % k] = scipy.linalg.cholesky(j2c[k], lower=True)
j2ctags.append('CD')
nauxs.append(naux)
except scipy.linalg.LinAlgError as e:
#msg =('===================================\n'
# 'J-metric not positive definite.\n'
# 'It is likely that gs is not enough.\n'
# '===================================')
#log.error(msg)
#raise scipy.linalg.LinAlgError('\n'.join([e.message, msg]))
w, v = scipy.linalg.eigh(j2c)
log.debug2('metric linear dependency for kpt %s', uniq_kptji_id)
log.debug2('cond = %.4g, drop %d bfns', w[0] / w[-1],
numpy.count_nonzero(w < LINEAR_DEP_THR))
v = v[:, w > LINEAR_DEP_THR].T.conj()
v /= numpy.sqrt(w[w > LINEAR_DEP_THR]).reshape(-1, 1)
feri['j2c/%d' % k] = v
j2ctags.append('eig')
nauxs.append(v.shape[0])
kLR = kLI = kLR1 = kLI1 = coulG = None
j2c = None
aosym_s2 = numpy.einsum('ix->i', abs(kptis - kptjs)) < 1e-9
j_only = numpy.all(aosym_s2)
if gamma_point(kptij_lst):
dtype = 'f8'
else:
dtype = 'c16'
vbar = mydf.auxbar(fused_cell)
vbar = fuse(vbar)
ovlp = cell.pbc_intor('int1e_ovlp_sph', hermi=1, kpts=kptjs[aosym_s2])
ovlp = [lib.pack_tril(s) for s in ovlp]
t1 = log.timer_debug1('aoaux and int2c', *t1)
# Estimates the buffer size based on the last contraction in G-space.
# This contraction requires to hold nkptj copies of (naux,?) array
# simultaneously in memory.
mem_now = max(comm.allgather(lib.current_memory()[0]))
max_memory = max(2000, mydf.max_memory - mem_now)
nkptj_max = max((uniq_inverse == x).sum() for x in set(uniq_inverse))
buflen = max(
int(
min(max_memory * .5e6 / 16 / naux / (nkptj_max + 2) / nao,
nao / 3 / mpi.pool.size)), 1)
chunks = (buflen, nao)
j3c_jobs = grids2d_int3c_jobs(cell, auxcell, kptij_lst, chunks, j_only)
log.debug1('max_memory = %d MB (%d in use) chunks %s', max_memory,
mem_now, chunks)
log.debug2('j3c_jobs %s', j3c_jobs)
if j_only:
int3c = wrap_int3c(cell, fused_cell, 'int3c2e_sph', 's2', 1, kptij_lst)
else:
int3c = wrap_int3c(cell, fused_cell, 'int3c2e_sph', 's1', 1, kptij_lst)
idxb = numpy.tril_indices(nao)
idxb = (idxb[0] * nao + idxb[1]).astype('i')
aux_loc = fused_cell.ao_loc_nr('ssc' in 'int3c2e_sph')
def gen_int3c(auxcell, job_id, ish0, ish1):
dataname = 'j3c-chunks/%d' % job_id
if dataname in feri:
del (feri[dataname])
i0 = ao_loc[ish0]
i1 = ao_loc[ish1]
dii = i1 * (i1 + 1) // 2 - i0 * (i0 + 1) // 2
dij = (i1 - i0) * nao
if j_only:
buflen = max(8, int(max_memory * 1e6 / 16 / (nkptij * dii + dii)))
else:
buflen = max(8, int(max_memory * 1e6 / 16 / (nkptij * dij + dij)))
auxranges = balance_segs(aux_loc[1:] - aux_loc[:-1], buflen)
buflen = max([x[2] for x in auxranges])
buf = numpy.empty(nkptij * dij * buflen, dtype=dtype)
buf1 = numpy.empty(dij * buflen, dtype=dtype)
naux = aux_loc[-1]
for kpt_id, kptij in enumerate(kptij_lst):
key = '%s/%d' % (dataname, kpt_id)
if aosym_s2[kpt_id]:
shape = (naux, dii)
else:
shape = (naux, dij)
if gamma_point(kptij):
feri.create_dataset(key, shape, 'f8')
else:
feri.create_dataset(key, shape, 'c16')
naux0 = 0
for istep, auxrange in enumerate(auxranges):
log.alldebug2("aux_e2 job_id %d step %d", job_id, istep)
sh0, sh1, nrow = auxrange
sub_slice = (ish0, ish1, 0, cell.nbas, sh0, sh1)
if j_only:
mat = numpy.ndarray((nkptij, dii, nrow),
dtype=dtype,
buffer=buf)
else:
mat = numpy.ndarray((nkptij, dij, nrow),
dtype=dtype,
buffer=buf)
mat = int3c(sub_slice, mat)
for k, kptij in enumerate(kptij_lst):
h5dat = feri['%s/%d' % (dataname, k)]
v = lib.transpose(mat[k], out=buf1)
if not j_only and aosym_s2[k]:
idy = idxb[i0 * (i0 + 1) // 2:i1 *
(i1 + 1) // 2] - i0 * nao
out = numpy.ndarray((nrow, dii),
dtype=v.dtype,
buffer=mat[k])
v = numpy.take(v, idy, axis=1, out=out)
if gamma_point(kptij):
h5dat[naux0:naux0 + nrow] = v.real
else:
h5dat[naux0:naux0 + nrow] = v
naux0 += nrow
def ft_fuse(job_id, uniq_kptji_id, sh0, sh1):
kpt = uniq_kpts[uniq_kptji_id] # kpt = kptj - kpti
adapted_ji_idx = numpy.where(uniq_inverse == uniq_kptji_id)[0]
adapted_kptjs = kptjs[adapted_ji_idx]
nkptj = len(adapted_kptjs)
shls_slice = (auxcell.nbas, fused_cell.nbas)
Gaux = ft_ao.ft_ao(fused_cell, Gv, shls_slice, b, gxyz, Gvbase, kpt)
Gaux *= mydf.weighted_coulG(kpt, False, gs).reshape(-1, 1)
kLR = Gaux.real.copy('C')
kLI = Gaux.imag.copy('C')
j2c = numpy.asarray(feri['j2c/%d' % uniq_kptji_id])
j2ctag = j2ctags[uniq_kptji_id]
naux0 = j2c.shape[0]
if is_zero(kpt):
aosym = 's2'
else:
aosym = 's1'
j3cR = [None] * nkptj
j3cI = [None] * nkptj
i0 = ao_loc[sh0]
i1 = ao_loc[sh1]
for k, idx in enumerate(adapted_ji_idx):
key = 'j3c-chunks/%d/%d' % (job_id, idx)
v = numpy.asarray(feri[key])
if is_zero(kpt):
for i, c in enumerate(vbar):
if c != 0:
v[i] -= c * ovlp[k][i0 * (i0 + 1) // 2:i1 *
(i1 + 1) // 2].ravel()
j3cR[k] = numpy.asarray(v.real, order='C')
if v.dtype == numpy.complex128:
j3cI[k] = numpy.asarray(v.imag, order='C')
v = None
ncol = j3cR[0].shape[1]
Gblksize = max(16, int(max_memory * 1e6 / 16 / ncol /
(nkptj + 1))) # +1 for pqkRbuf/pqkIbuf
Gblksize = min(Gblksize, ngs, 16384)
pqkRbuf = numpy.empty(ncol * Gblksize)
pqkIbuf = numpy.empty(ncol * Gblksize)
buf = numpy.empty(nkptj * ncol * Gblksize, dtype=numpy.complex128)
log.alldebug2(' blksize (%d,%d)', Gblksize, ncol)
shls_slice = (sh0, sh1, 0, cell.nbas)
for p0, p1 in lib.prange(0, ngs, Gblksize):
dat = ft_ao._ft_aopair_kpts(cell,
Gv[p0:p1],
shls_slice,
aosym,
b,
gxyz[p0:p1],
Gvbase,
kpt,
adapted_kptjs,
out=buf)
nG = p1 - p0
for k, ji in enumerate(adapted_ji_idx):
aoao = dat[k].reshape(nG, ncol)
pqkR = numpy.ndarray((ncol, nG), buffer=pqkRbuf)
pqkI = numpy.ndarray((ncol, nG), buffer=pqkIbuf)
pqkR[:] = aoao.real.T
pqkI[:] = aoao.imag.T
lib.dot(kLR[p0:p1].T, pqkR.T, -1, j3cR[k][naux:], 1)
lib.dot(kLI[p0:p1].T, pqkI.T, -1, j3cR[k][naux:], 1)
if not (is_zero(kpt) and gamma_point(adapted_kptjs[k])):
lib.dot(kLR[p0:p1].T, pqkI.T, -1, j3cI[k][naux:], 1)
lib.dot(kLI[p0:p1].T, pqkR.T, 1, j3cI[k][naux:], 1)
for k, idx in enumerate(adapted_ji_idx):
if is_zero(kpt) and gamma_point(adapted_kptjs[k]):
v = fuse(j3cR[k])
else:
v = fuse(j3cR[k] + j3cI[k] * 1j)
if j2ctag == 'CD':
v = scipy.linalg.solve_triangular(j2c,
v,
lower=True,
overwrite_b=True)
else:
v = lib.dot(j2c, v)
feri['j3c-chunks/%d/%d' % (job_id, idx)][:naux0] = v
t2 = t1
j3c_workers = numpy.zeros(len(j3c_jobs), dtype=int)
#for job_id, ish0, ish1 in mpi.work_share_partition(j3c_jobs):
for job_id, ish0, ish1 in mpi.work_stealing_partition(j3c_jobs):
gen_int3c(fused_cell, job_id, ish0, ish1)
t2 = log.alltimer_debug2('int j3c %d' % job_id, *t2)
for k, kpt in enumerate(uniq_kpts):
ft_fuse(job_id, k, ish0, ish1)
t2 = log.alltimer_debug2('ft-fuse %d k %d' % (job_id, k), *t2)
j3c_workers[job_id] = rank
j3c_workers = mpi.allreduce(j3c_workers)
log.debug2('j3c_workers %s', j3c_workers)
j2c = kLRs = kLIs = ovlp = vbar = fuse = gen_int3c = ft_fuse = None
t1 = log.timer_debug1('int3c and fuse', *t1)
def get_segs_loc(aosym):
off0 = numpy.asarray([ao_loc[i0] for x, i0, i1 in j3c_jobs])
off1 = numpy.asarray([ao_loc[i1] for x, i0, i1 in j3c_jobs])
if aosym: # s2
dims = off1 * (off1 + 1) // 2 - off0 * (off0 + 1) // 2
else:
dims = (off1 - off0) * nao
#dims = numpy.asarray([ao_loc[i1]-ao_loc[i0] for x,i0,i1 in j3c_jobs])
dims = numpy.hstack(
[dims[j3c_workers == w] for w in range(mpi.pool.size)])
job_idx = numpy.hstack(
[numpy.where(j3c_workers == w)[0] for w in range(mpi.pool.size)])
segs_loc = numpy.append(0, numpy.cumsum(dims))
segs_loc = [(segs_loc[j], segs_loc[j + 1])
for j in numpy.argsort(job_idx)]
return segs_loc
segs_loc_s1 = get_segs_loc(False)
segs_loc_s2 = get_segs_loc(True)
if 'j3c' in feri: del (feri['j3c'])
segsize = (max(nauxs) + mpi.pool.size - 1) // mpi.pool.size
naux0 = rank * segsize
for k, kptij in enumerate(kptij_lst):
naux1 = min(nauxs[uniq_inverse[k]], naux0 + segsize)
nrow = max(0, naux1 - naux0)
if gamma_point(kptij):
dtype = 'f8'
else:
dtype = 'c16'
if aosym_s2[k]:
nao_pair = nao * (nao + 1) // 2
else:
nao_pair = nao * nao
feri.create_dataset('j3c/%d' % k, (nrow, nao_pair),
dtype,
maxshape=(None, nao_pair))
def load(k, p0, p1):
naux1 = nauxs[uniq_inverse[k]]
slices = [(min(i * segsize + p0, naux1), min(i * segsize + p1, naux1))
for i in range(mpi.pool.size)]
segs = []
for p0, p1 in slices:
val = []
for job_id, worker in enumerate(j3c_workers):
if rank == worker:
key = 'j3c-chunks/%d/%d' % (job_id, k)
val.append(feri[key][p0:p1].ravel())
if val:
segs.append(numpy.hstack(val))
else:
segs.append(numpy.zeros(0))
return segs
def save(k, p0, p1, segs):
segs = mpi.alltoall(segs)
naux1 = nauxs[uniq_inverse[k]]
loc0, loc1 = min(p0, naux1 - naux0), min(p1, naux1 - naux0)
nL = loc1 - loc0
if nL > 0:
if aosym_s2[k]:
segs = numpy.hstack([
segs[i0 * nL:i1 * nL].reshape(nL, -1)
for i0, i1 in segs_loc_s2
])
else:
segs = numpy.hstack([
segs[i0 * nL:i1 * nL].reshape(nL, -1)
for i0, i1 in segs_loc_s1
])
feri['j3c/%d' % k][loc0:loc1] = segs
mem_now = max(comm.allgather(lib.current_memory()[0]))
max_memory = max(2000, min(8000, mydf.max_memory - mem_now))
if numpy.all(aosym_s2):
if gamma_point(kptij_lst):
blksize = max(16, int(max_memory * .5e6 / 8 / nao**2))
else:
blksize = max(16, int(max_memory * .5e6 / 16 / nao**2))
else:
blksize = max(16, int(max_memory * .5e6 / 16 / nao**2 / 2))
log.debug1('max_momory %d MB (%d in use), blksize %d', max_memory, mem_now,
blksize)
t2 = t1
with lib.call_in_background(save) as async_write:
for k, kptji in enumerate(kptij_lst):
for p0, p1 in lib.prange(0, segsize, blksize):
segs = load(k, p0, p1)
async_write(k, p0, p1, segs)
t2 = log.timer_debug1(
'assemble k=%d %d:%d (in %d)' % (k, p0, p1, segsize), *t2)
if 'j3c-chunks' in feri: del (feri['j3c-chunks'])
if 'j3c-kptij' in feri: del (feri['j3c-kptij'])
feri['j3c-kptij'] = kptij_lst
t1 = log.alltimer_debug1('assembling j3c', *t1)
feri.close()
def _make_j3c(mydf, cell, auxcell, kptij_lst, cderi_file):
log = logger.Logger(mydf.stdout, mydf.verbose)
t1 = t0 = (time.clock(), time.time())
fused_cell, fuse = fuse_auxcell(mydf, mydf.auxcell)
ao_loc = cell.ao_loc_nr()
nao = ao_loc[-1]
naux = auxcell.nao_nr()
nkptij = len(kptij_lst)
mesh = mydf.mesh
Gv, Gvbase, kws = cell.get_Gv_weights(mesh)
b = cell.reciprocal_vectors()
gxyz = lib.cartesian_prod([numpy.arange(len(x)) for x in Gvbase])
ngrids = gxyz.shape[0]
kptis = kptij_lst[:,0]
kptjs = kptij_lst[:,1]
kpt_ji = kptjs - kptis
uniq_kpts, uniq_index, uniq_inverse = unique(kpt_ji)
log.debug('Num uniq kpts %d', len(uniq_kpts))
log.debug2('uniq_kpts %s', uniq_kpts)
# j2c ~ (-kpt_ji | kpt_ji)
j2c = fused_cell.pbc_intor('int2c2e', hermi=1, kpts=uniq_kpts)
j2ctags = []
t1 = log.timer_debug1('2c2e', *t1)
swapfile = tempfile.NamedTemporaryFile(dir=os.path.dirname(cderi_file))
fswap = lib.H5TmpFile(swapfile.name)
# Unlink swapfile to avoid trash
swapfile = None
for k, kpt in enumerate(uniq_kpts):
coulG = mydf.weighted_coulG(kpt, False, mesh)
j2c[k] = fuse(fuse(j2c[k]).T).T.copy()
j2c_k = numpy.zeros_like(j2c[k])
for p0, p1 in mydf.mpi_prange(0, ngrids):
aoaux = ft_ao.ft_ao(fused_cell, Gv[p0:p1], None, b, gxyz[p0:p1], Gvbase, kpt).T
aoaux = fuse(aoaux)
LkR = numpy.asarray(aoaux.real, order='C')
LkI = numpy.asarray(aoaux.imag, order='C')
aoaux = None
if is_zero(kpt): # kpti == kptj
j2cR = lib.dot(LkR*coulG[p0:p1], LkR.T)
j2c_k += lib.dot(LkI*coulG[p0:p1], LkI.T, 1, j2cR, 1)
else:
# aoaux ~ kpt_ij, aoaux.conj() ~ kpt_kl
j2cR, j2cI = zdotCN(LkR*coulG[p0:p1], LkI*coulG[p0:p1], LkR.T, LkI.T)
j2c_k += j2cR + j2cI * 1j
LkR = LkI = None
j2c[k] -= mpi.allreduce(j2c_k)
try:
fswap['j2c/%d'%k] = scipy.linalg.cholesky(j2c[k], lower=True)
j2ctags.append('CD')
except scipy.linalg.LinAlgError:
w, v = scipy.linalg.eigh(j2c[k])
log.debug2('metric linear dependency for kpt %s', k)
log.debug2('cond = %.4g, drop %d bfns',
w[0]/w[-1], numpy.count_nonzero(w<mydf.linear_dep_threshold))
v1 = v[:,w>mydf.linear_dep_threshold].T.conj()
v1 /= numpy.sqrt(w[w>mydf.linear_dep_threshold]).reshape(-1,1)
fswap['j2c/%d'%k] = v1
if cell.dimension == 2 and cell.low_dim_ft_type != 'inf_vacuum':
idx = numpy.where(w < -mydf.linear_dep_threshold)[0]
if len(idx) > 0:
fswap['j2c-/%d'%k] = (v[:,idx]/numpy.sqrt(-w[idx])).conj().T
w = v = v1 = v2 = None
j2ctags.append('eig')
aoaux = kLR = kLI = j2cR = j2cI = coulG = None
j2c = None
aosym_s2 = numpy.einsum('ix->i', abs(kptis-kptjs)) < 1e-9
j_only = numpy.all(aosym_s2)
if gamma_point(kptij_lst):
dtype = 'f8'
else:
dtype = 'c16'
t1 = log.timer_debug1('aoaux and int2c', *t1)
# Estimates the buffer size based on the last contraction in G-space.
# This contraction requires to hold nkptj copies of (naux,?) array
# simultaneously in memory.
mem_now = max(comm.allgather(lib.current_memory()[0]))
max_memory = max(2000, mydf.max_memory - mem_now)
nkptj_max = max((uniq_inverse==x).sum() for x in set(uniq_inverse))
buflen = max(int(min(max_memory*.5e6/16/naux/(nkptj_max+2)/nao,
nao/3/mpi.pool.size)), 1)
chunks = (buflen, nao)
j3c_jobs = mpi_df.grids2d_int3c_jobs(cell, auxcell, kptij_lst, chunks, j_only)
log.debug1('max_memory = %d MB (%d in use) chunks %s',
max_memory, mem_now, chunks)
log.debug2('j3c_jobs %s', j3c_jobs)
if j_only:
int3c = wrap_int3c(cell, fused_cell, 'int3c2e', 's2', 1, kptij_lst)
else:
int3c = wrap_int3c(cell, fused_cell, 'int3c2e', 's1', 1, kptij_lst)
idxb = numpy.tril_indices(nao)
idxb = (idxb[0] * nao + idxb[1]).astype('i')
aux_loc = fused_cell.ao_loc_nr(fused_cell.cart)
def gen_int3c(job_id, ish0, ish1):
dataname = 'j3c-chunks/%d' % job_id
i0 = ao_loc[ish0]
i1 = ao_loc[ish1]
dii = i1*(i1+1)//2 - i0*(i0+1)//2
dij = (i1 - i0) * nao
if j_only:
buflen = max(8, int(max_memory*1e6/16/(nkptij*dii+dii)))
else:
buflen = max(8, int(max_memory*1e6/16/(nkptij*dij+dij)))
auxranges = balance_segs(aux_loc[1:]-aux_loc[:-1], buflen)
buflen = max([x[2] for x in auxranges])
buf = numpy.empty(nkptij*dij*buflen, dtype=dtype)
buf1 = numpy.empty(dij*buflen, dtype=dtype)
naux = aux_loc[-1]
for kpt_id, kptij in enumerate(kptij_lst):
key = '%s/%d' % (dataname, kpt_id)
if aosym_s2[kpt_id]:
shape = (naux, dii)
else:
shape = (naux, dij)
if gamma_point(kptij):
fswap.create_dataset(key, shape, 'f8')
else:
fswap.create_dataset(key, shape, 'c16')
naux0 = 0
for istep, auxrange in enumerate(auxranges):
log.alldebug2("aux_e1 job_id %d step %d", job_id, istep)
sh0, sh1, nrow = auxrange
sub_slice = (ish0, ish1, 0, cell.nbas, sh0, sh1)
if j_only:
mat = numpy.ndarray((nkptij,dii,nrow), dtype=dtype, buffer=buf)
else:
mat = numpy.ndarray((nkptij,dij,nrow), dtype=dtype, buffer=buf)
mat = int3c(sub_slice, mat)
for k, kptij in enumerate(kptij_lst):
h5dat = fswap['%s/%d'%(dataname,k)]
v = lib.transpose(mat[k], out=buf1)
if not j_only and aosym_s2[k]:
idy = idxb[i0*(i0+1)//2:i1*(i1+1)//2] - i0 * nao
out = numpy.ndarray((nrow,dii), dtype=v.dtype, buffer=mat[k])
v = numpy.take(v, idy, axis=1, out=out)
if gamma_point(kptij):
h5dat[naux0:naux0+nrow] = v.real
else:
h5dat[naux0:naux0+nrow] = v
naux0 += nrow
def ft_fuse(job_id, uniq_kptji_id, sh0, sh1):
kpt = uniq_kpts[uniq_kptji_id] # kpt = kptj - kpti
adapted_ji_idx = numpy.where(uniq_inverse == uniq_kptji_id)[0]
adapted_kptjs = kptjs[adapted_ji_idx]
nkptj = len(adapted_kptjs)
Gaux = ft_ao.ft_ao(fused_cell, Gv, None, b, gxyz, Gvbase, kpt).T
Gaux = fuse(Gaux)
Gaux *= mydf.weighted_coulG(kpt, False, mesh)
kLR = lib.transpose(numpy.asarray(Gaux.real, order='C'))
kLI = lib.transpose(numpy.asarray(Gaux.imag, order='C'))
j2c = numpy.asarray(fswap['j2c/%d'%uniq_kptji_id])
j2ctag = j2ctags[uniq_kptji_id]
naux0 = j2c.shape[0]
if ('j2c-/%d' % uniq_kptji_id) in fswap:
j2c_negative = numpy.asarray(fswap['j2c-/%d'%uniq_kptji_id])
else:
j2c_negative = None
if is_zero(kpt):
aosym = 's2'
else:
aosym = 's1'
if aosym == 's2' and cell.dimension == 3:
vbar = fuse(mydf.auxbar(fused_cell))
ovlp = cell.pbc_intor('int1e_ovlp', hermi=1, kpts=adapted_kptjs)
ovlp = [lib.pack_tril(s) for s in ovlp]
j3cR = [None] * nkptj
j3cI = [None] * nkptj
i0 = ao_loc[sh0]
i1 = ao_loc[sh1]
for k, idx in enumerate(adapted_ji_idx):
key = 'j3c-chunks/%d/%d' % (job_id, idx)
v = fuse(numpy.asarray(fswap[key]))
if aosym == 's2' and cell.dimension == 3:
for i in numpy.where(vbar != 0)[0]:
v[i] -= vbar[i] * ovlp[k][i0*(i0+1)//2:i1*(i1+1)//2].ravel()
j3cR[k] = numpy.asarray(v.real, order='C')
if v.dtype == numpy.complex128:
j3cI[k] = numpy.asarray(v.imag, order='C')
v = None
ncol = j3cR[0].shape[1]
Gblksize = max(16, int(max_memory*1e6/16/ncol/(nkptj+1))) # +1 for pqkRbuf/pqkIbuf
Gblksize = min(Gblksize, ngrids, 16384)
pqkRbuf = numpy.empty(ncol*Gblksize)
pqkIbuf = numpy.empty(ncol*Gblksize)
buf = numpy.empty(nkptj*ncol*Gblksize, dtype=numpy.complex128)
log.alldebug2(' blksize (%d,%d)', Gblksize, ncol)
if aosym == 's2':
shls_slice = (sh0, sh1, 0, sh1)
else:
shls_slice = (sh0, sh1, 0, cell.nbas)
for p0, p1 in lib.prange(0, ngrids, Gblksize):
dat = ft_ao._ft_aopair_kpts(cell, Gv[p0:p1], shls_slice, aosym, b,
gxyz[p0:p1], Gvbase, kpt,
adapted_kptjs, out=buf)
nG = p1 - p0
for k, ji in enumerate(adapted_ji_idx):
aoao = dat[k].reshape(nG,ncol)
pqkR = numpy.ndarray((ncol,nG), buffer=pqkRbuf)
pqkI = numpy.ndarray((ncol,nG), buffer=pqkIbuf)
pqkR[:] = aoao.real.T
pqkI[:] = aoao.imag.T
lib.dot(kLR[p0:p1].T, pqkR.T, -1, j3cR[k], 1)
lib.dot(kLI[p0:p1].T, pqkI.T, -1, j3cR[k], 1)
if not (is_zero(kpt) and gamma_point(adapted_kptjs[k])):
lib.dot(kLR[p0:p1].T, pqkI.T, -1, j3cI[k], 1)
lib.dot(kLI[p0:p1].T, pqkR.T, 1, j3cI[k], 1)
for k, idx in enumerate(adapted_ji_idx):
if is_zero(kpt) and gamma_point(adapted_kptjs[k]):
v = j3cR[k]
else:
v = j3cR[k] + j3cI[k] * 1j
if j2ctag == 'CD':
v = scipy.linalg.solve_triangular(j2c, v, lower=True, overwrite_b=True)
fswap['j3c-chunks/%d/%d'%(job_id,idx)][:naux0] = v
else:
fswap['j3c-chunks/%d/%d'%(job_id,idx)][:naux0] = lib.dot(j2c, v)
# low-dimension systems
if j2c_negative is not None:
fswap['j3c-/%d/%d'%(job_id,idx)] = lib.dot(j2c_negative, v)
mpi_df._assemble(mydf, kptij_lst, j3c_jobs, gen_int3c, ft_fuse, cderi_file, fswap, log)
def aux_e1(cell, auxcell, erifile, intor='int3c2e', aosym='s2ij', comp=None,
kptij_lst=None, dataname='eri_mo', shls_slice=None, max_memory=2000,
verbose=0):
r'''3-center AO integrals (L|ij) with double lattice sum:
\sum_{lm} (L[0]|i[l]j[m]), where L is the auxiliary basis.
Three-index integral tensor (kptij_idx, naux, nao_pair) or four-index
integral tensor (kptij_idx, comp, naux, nao_pair) are stored on disk.
Args:
kptij_lst : (*,2,3) array
A list of (kpti, kptj)
'''
intor, comp = gto.moleintor._get_intor_and_comp(cell._add_suffix(intor), comp)
if isinstance(erifile, h5py.Group):
feri = erifile
elif h5py.is_hdf5(erifile):
feri = h5py.File(erifile)
else:
feri = h5py.File(erifile, 'w')
if dataname in feri:
del(feri[dataname])
if dataname+'-kptij' in feri:
del(feri[dataname+'-kptij'])
if kptij_lst is None:
kptij_lst = numpy.zeros((1,2,3))
feri[dataname+'-kptij'] = kptij_lst
if shls_slice is None:
shls_slice = (0, cell.nbas, 0, cell.nbas, 0, auxcell.nbas)
ao_loc = cell.ao_loc_nr()
aux_loc = auxcell.ao_loc_nr(auxcell.cart or 'ssc' in intor)[:shls_slice[5]+1]
ni = ao_loc[shls_slice[1]] - ao_loc[shls_slice[0]]
nj = ao_loc[shls_slice[3]] - ao_loc[shls_slice[2]]
naux = aux_loc[shls_slice[5]] - aux_loc[shls_slice[4]]
nkptij = len(kptij_lst)
nii = (ao_loc[shls_slice[1]]*(ao_loc[shls_slice[1]]+1)//2 -
ao_loc[shls_slice[0]]*(ao_loc[shls_slice[0]]+1)//2)
nij = ni * nj
kpti = kptij_lst[:,0]
kptj = kptij_lst[:,1]
aosym_ks2 = abs(kpti-kptj).sum(axis=1) < KPT_DIFF_TOL
j_only = numpy.all(aosym_ks2)
#aosym_ks2 &= (aosym[:2] == 's2' and shls_slice[:2] == shls_slice[2:4])
aosym_ks2 &= aosym[:2] == 's2'
for k, kptij in enumerate(kptij_lst):
key = '%s/%d' % (dataname, k)
if gamma_point(kptij):
dtype = 'f8'
else:
dtype = 'c16'
if aosym_ks2[k]:
nao_pair = nii
else:
nao_pair = nij
if comp == 1:
shape = (naux,nao_pair)
else:
shape = (comp,naux,nao_pair)
feri.create_dataset(key, shape, dtype)
if naux == 0:
feri.close()
return erifile
if j_only and aosym[:2] == 's2':
assert(shls_slice[2] == 0)
nao_pair = nii
else:
nao_pair = nij
if gamma_point(kptij_lst):
dtype = numpy.double
else:
dtype = numpy.complex128
buflen = max(8, int(max_memory*1e6/16/(nkptij*ni*nj*comp)))
auxdims = aux_loc[shls_slice[4]+1:shls_slice[5]+1] - aux_loc[shls_slice[4]:shls_slice[5]]
auxranges = balance_segs(auxdims, buflen)
buflen = max([x[2] for x in auxranges])
buf = numpy.empty(nkptij*comp*ni*nj*buflen, dtype=dtype)
buf1 = numpy.empty(ni*nj*buflen, dtype=dtype)
int3c = wrap_int3c(cell, auxcell, intor, aosym, comp, kptij_lst)
naux0 = 0
for istep, auxrange in enumerate(auxranges):
sh0, sh1, nrow = auxrange
sub_slice = (shls_slice[0], shls_slice[1],
shls_slice[2], shls_slice[3],
shls_slice[4]+sh0, shls_slice[4]+sh1)
mat = numpy.ndarray((nkptij,comp,nao_pair,nrow), dtype=dtype, buffer=buf)
mat = int3c(sub_slice, mat)
for k, kptij in enumerate(kptij_lst):
h5dat = feri['%s/%d'%(dataname,k)]
for icomp, v in enumerate(mat[k]):
v = lib.transpose(v, out=buf1)
if gamma_point(kptij):
v = v.real
if aosym_ks2[k] and v.shape[1] == ni**2:
v = lib.pack_tril(v.reshape(-1,ni,ni))
if comp == 1:
h5dat[naux0:naux0+nrow] = v
else:
h5dat[icomp,naux0:naux0+nrow] = v
naux0 += nrow
if not isinstance(erifile, h5py.Group):
feri.close()
return erifile
def _aux_e2(cell, auxcell, erifile, intor='int3c2e', aosym='s2ij', comp=None,
kptij_lst=None, dataname='eri_mo', shls_slice=None, max_memory=2000,
verbose=0):
r'''3-center AO integrals (ij|L) with double lattice sum:
\sum_{lm} (i[l]j[m]|L[0]), where L is the auxiliary basis.
Three-index integral tensor (kptij_idx, nao_pair, naux) or four-index
integral tensor (kptij_idx, comp, nao_pair, naux) are stored on disk.
**This function should be only used by df and mdf initialization function
_make_j3c**
Args:
kptij_lst : (*,2,3) array
A list of (kpti, kptj)
'''
intor, comp = gto.moleintor._get_intor_and_comp(cell._add_suffix(intor), comp)
if isinstance(erifile, h5py.Group):
feri = erifile
elif h5py.is_hdf5(erifile):
feri = h5py.File(erifile)
else:
feri = h5py.File(erifile, 'w')
if dataname in feri:
del(feri[dataname])
if dataname+'-kptij' in feri:
del(feri[dataname+'-kptij'])
if kptij_lst is None:
kptij_lst = numpy.zeros((1,2,3))
feri[dataname+'-kptij'] = kptij_lst
if shls_slice is None:
shls_slice = (0, cell.nbas, 0, cell.nbas, 0, auxcell.nbas)
ao_loc = cell.ao_loc_nr()
aux_loc = auxcell.ao_loc_nr(auxcell.cart or 'ssc' in intor)[:shls_slice[5]+1]
ni = ao_loc[shls_slice[1]] - ao_loc[shls_slice[0]]
nj = ao_loc[shls_slice[3]] - ao_loc[shls_slice[2]]
naux = aux_loc[shls_slice[5]] - aux_loc[shls_slice[4]]
nkptij = len(kptij_lst)
nii = (ao_loc[shls_slice[1]]*(ao_loc[shls_slice[1]]+1)//2 -
ao_loc[shls_slice[0]]*(ao_loc[shls_slice[0]]+1)//2)
nij = ni * nj
kpti = kptij_lst[:,0]
kptj = kptij_lst[:,1]
aosym_ks2 = abs(kpti-kptj).sum(axis=1) < KPT_DIFF_TOL
j_only = numpy.all(aosym_ks2)
#aosym_ks2 &= (aosym[:2] == 's2' and shls_slice[:2] == shls_slice[2:4])
aosym_ks2 &= aosym[:2] == 's2'
if j_only and aosym[:2] == 's2':
assert(shls_slice[2] == 0)
nao_pair = nii
else:
nao_pair = nij
if gamma_point(kptij_lst):
dtype = numpy.double
else:
dtype = numpy.complex128
buflen = max(8, int(max_memory*.47e6/16/(nkptij*ni*nj*comp)))
auxdims = aux_loc[shls_slice[4]+1:shls_slice[5]+1] - aux_loc[shls_slice[4]:shls_slice[5]]
auxranges = balance_segs(auxdims, buflen)
buflen = max([x[2] for x in auxranges])
buf = numpy.empty(nkptij*comp*ni*nj*buflen, dtype=dtype)
buf1 = numpy.empty_like(buf)
int3c = wrap_int3c(cell, auxcell, intor, aosym, comp, kptij_lst)
kptis = kptij_lst[:,0]
kptjs = kptij_lst[:,1]
kpt_ji = kptjs - kptis
uniq_kpts, uniq_index, uniq_inverse = unique(kpt_ji)
# sorted_ij_idx: Sort and group the kptij_lst according to the ordering in
# df._make_j3c to reduce the data fragment in the hdf5 file. When datasets
# are written to hdf5, they are saved sequentially. If the integral data are
# saved as the order of kptij_lst, removing the datasets in df._make_j3c will
# lead to holes that can not be reused.
sorted_ij_idx = numpy.hstack([numpy.where(uniq_inverse == k)[0]
for k, kpt in enumerate(uniq_kpts)])
tril_idx = numpy.tril_indices(ni)
tril_idx = tril_idx[0] * ni + tril_idx[1]
def save(istep, mat):
for k in sorted_ij_idx:
v = mat[k]
if gamma_point(kptij_lst[k]):
v = v.real
if aosym_ks2[k] and nao_pair == ni**2:
v = v[:,tril_idx]
feri['%s/%d/%d' % (dataname,k,istep)] = v
with lib.call_in_background(save) as bsave:
for istep, auxrange in enumerate(auxranges):
sh0, sh1, nrow = auxrange
sub_slice = (shls_slice[0], shls_slice[1],
shls_slice[2], shls_slice[3],
shls_slice[4]+sh0, shls_slice[4]+sh1)
mat = numpy.ndarray((nkptij,comp,nao_pair,nrow), dtype=dtype, buffer=buf)
bsave(istep, int3c(sub_slice, mat))
buf, buf1 = buf1, buf
if not isinstance(erifile, h5py.Group):
feri.close()
return erifile