distributed_do.py 12.2 KB
Newer Older
1
2
3
4
import numpy as np
from .random import Random
from mpi4py import MPI

Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
5
6
7
8
_comm = MPI.COMM_WORLD
ntask = _comm.Get_size()
rank = _comm.Get_rank()
master = rank==0
9
10


Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
11
def _shareSize(nwork, nshares, myshare):
12
13
    nbase = nwork//nshares
    return nbase if myshare>=nwork%nshares else nbase+1
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
14
15

def _shareRange(nwork, nshares, myshare):
Martin Reinecke's avatar
Martin Reinecke committed
16
17
18
19
20
    nbase = nwork//nshares;
    additional = nwork%nshares;
    lo = myshare*nbase + min(myshare, additional)
    hi = lo+nbase+ (1 if myshare<additional else 0)
    return lo,hi
21

Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
22
def local_shape(shape, distaxis):
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
23
24
    if len(shape)==0:
        distaxis = -1
25
26
27
    if distaxis==-1:
        return shape
    shape2=list(shape)
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
28
    shape2[distaxis]=_shareSize(shape[distaxis],ntask,rank)
29
30
31
32
33
    return tuple(shape2)

class data_object(object):
    def __init__(self, shape, data, distaxis):
        """Must not be called directly by users"""
Martin Reinecke's avatar
Martin Reinecke committed
34
        self._shape = tuple(shape)
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
35
36
        if len(self._shape)==0:
            distaxis = -1
37
        self._distaxis = distaxis
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
38
        lshape = local_shape(self._shape, self._distaxis)
39
40
        self._data = data

Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
41
    def _sanity_checks(self):
42
43
44
45
46
        # check whether the distaxis is consistent
        if self._distaxis<-1 or self._distaxis>=len(self._shape):
            raise ValueError
        itmp=np.array(self._distaxis)
        otmp=np.empty(ntask,dtype=np.int)
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
47
        _comm.Allgather(itmp,otmp)
48
49
50
51
        if np.any(otmp!=self._distaxis):
            raise ValueError
        # check whether the global shape is consistent
        itmp=np.array(self._shape)
Martin Reinecke's avatar
Martin Reinecke committed
52
        otmp=np.empty((ntask,len(self._shape)),dtype=np.int)
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
53
        _comm.Allgather(itmp,otmp)
54
        for i in range(ntask):
Martin Reinecke's avatar
Martin Reinecke committed
55
            if np.any(otmp[i,:]!=self._shape):
56
57
58
59
60
61
62
                raise ValueError
        # check shape of local data
        if self._distaxis<0:
            if self._data.shape!=self._shape:
                raise ValueError
        else:
            itmp=np.array(self._shape)
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
63
            itmp[self._distaxis] = _shareSize(self._shape[self._distaxis],ntask,rank)
Martin Reinecke's avatar
Martin Reinecke committed
64
            if np.any(self._data.shape!=itmp):
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
                raise ValueError

    @property
    def dtype(self):
        return self._data.dtype

    @property
    def shape(self):
        return self._shape

    @property
    def size(self):
        return np.prod(self._shape)

    @property
    def real(self):
Martin Reinecke's avatar
Martin Reinecke committed
81
        return data_object(self._shape, self._data.real, self._distaxis)
82
83
84

    @property
    def imag(self):
Martin Reinecke's avatar
Martin Reinecke committed
85
        return data_object(self._shape, self._data.imag, self._distaxis)
86

Martin Reinecke's avatar
Martin Reinecke committed
87
    def _contraction_helper(self, op, mpiop, axis):
88
89
90
91
        if axis is not None:
            if len(axis)==len(self._data.shape):
                axis = None
        if axis is None:
Martin Reinecke's avatar
Martin Reinecke committed
92
93
            res = np.array(getattr(self._data, op)())
            if (self._distaxis==-1):
Martin Reinecke's avatar
Martin Reinecke committed
94
                return res[0]
Martin Reinecke's avatar
Martin Reinecke committed
95
            res2 = np.empty(1,dtype=res.dtype)
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
96
            _comm.Allreduce(res,res2,mpiop)
Martin Reinecke's avatar
Martin Reinecke committed
97
            return res2[0]
98
99

        if self._distaxis in axis:
Martin Reinecke's avatar
Martin Reinecke committed
100
101
            res = getattr(self._data, op)(axis=axis)
            res2 = np.empty_like(res)
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
102
            _comm.Allreduce(res,res2,mpiop)
Martin Reinecke's avatar
Martin Reinecke committed
103
            return from_global_data(res2, distaxis=0)
104
        else:
Martin Reinecke's avatar
Martin Reinecke committed
105
            # perform the contraction on the local data
Martin Reinecke's avatar
Martin Reinecke committed
106
107
108
109
110
111
112
113
114
115
            res = getattr(self._data, op)(axis=axis)
            if self._distaxis == -1:
                return from_global_data(res,distaxis=0)
            shp = list(res.shape)
            shift=0
            for ax in axis:
                if ax<self._distaxis:
                    shift+=1
            shp[self._distaxis-shift] = self.shape[self._distaxis]
            return from_local_data(shp, res, self._distaxis-shift)
116
117
118
119
120
121
122
123
124
125

        # check if the result is scalar or if a result_field must be constr.
        if np.isscalar(data):
            return data
        else:
            return data_object(data)

    def sum(self, axis=None):
        return self._contraction_helper("sum", MPI.SUM, axis)

Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
126
127
128
129
130
131
132
133
    # FIXME: to be improved!
    def mean(self):
        return self.sum()/self.size
    def std(self):
        return np.sqrt(self.var())
    def var(self):
        return (abs(self-self.mean())**2).mean()

134
    def _binary_helper(self, other, op):
Martin Reinecke's avatar
Martin Reinecke committed
135
        a = self
136
        if isinstance(other, data_object):
Martin Reinecke's avatar
Martin Reinecke committed
137
            b = other
138
139
140
141
            if a._shape != b._shape:
                raise ValueError("shapes are incompatible.")
            if a._distaxis != b._distaxis:
                raise ValueError("distributions are incompatible.")
Martin Reinecke's avatar
Martin Reinecke committed
142
143
            a = a._data
            b = b._data
144
        else:
Martin Reinecke's avatar
Martin Reinecke committed
145
            a = a._data
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
            b = other

        tval = getattr(a, op)(b)
        return self if tval is a else data_object(self._shape, tval, self._distaxis)

    def __add__(self, other):
        return self._binary_helper(other, op='__add__')

    def __radd__(self, other):
        return self._binary_helper(other, op='__radd__')

    def __iadd__(self, other):
        return self._binary_helper(other, op='__iadd__')

    def __sub__(self, other):
        return self._binary_helper(other, op='__sub__')

    def __rsub__(self, other):
        return self._binary_helper(other, op='__rsub__')

    def __isub__(self, other):
        return self._binary_helper(other, op='__isub__')

    def __mul__(self, other):
        return self._binary_helper(other, op='__mul__')

    def __rmul__(self, other):
        return self._binary_helper(other, op='__rmul__')

    def __imul__(self, other):
        return self._binary_helper(other, op='__imul__')

    def __div__(self, other):
        return self._binary_helper(other, op='__div__')

    def __rdiv__(self, other):
        return self._binary_helper(other, op='__rdiv__')

Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
184
185
186
    def __idiv__(self, other):
        return self._binary_helper(other, op='__idiv__')

187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
    def __truediv__(self, other):
        return self._binary_helper(other, op='__truediv__')

    def __rtruediv__(self, other):
        return self._binary_helper(other, op='__rtruediv__')

    def __pow__(self, other):
        return self._binary_helper(other, op='__pow__')

    def __rpow__(self, other):
        return self._binary_helper(other, op='__rpow__')

    def __ipow__(self, other):
        return self._binary_helper(other, op='__ipow__')

    def __eq__(self, other):
        return self._binary_helper(other, op='__eq__')

    def __ne__(self, other):
        return self._binary_helper(other, op='__ne__')

    def __neg__(self):
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
209
        return data_object(self._shape,-self._data,self._distaxis)
210
211

    def __abs__(self):
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
212
        return data_object(self._shape,np.abs(self._data),self._distaxis)
213
214
215
216
217
218
219
220

    def all(self):
        return self._data.all()

    def any(self):
        return self._data.any()


Martin Reinecke's avatar
Martin Reinecke committed
221
def full(shape, fill_value, dtype=None, distaxis=0):
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
222
    return data_object(shape, np.full(local_shape(shape, distaxis), fill_value, dtype), distaxis)
223
224


Martin Reinecke's avatar
fixes    
Martin Reinecke committed
225
def empty(shape, dtype=None, distaxis=0):
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
226
    return data_object(shape, np.empty(local_shape(shape, distaxis), dtype), distaxis)
227
228


Martin Reinecke's avatar
fixes    
Martin Reinecke committed
229
def zeros(shape, dtype=None, distaxis=0):
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
230
    return data_object(shape, np.zeros(local_shape(shape, distaxis), dtype), distaxis)
231
232


Martin Reinecke's avatar
fixes    
Martin Reinecke committed
233
def ones(shape, dtype=None, distaxis=0):
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
234
    return data_object(shape, np.ones(local_shape(shape, distaxis), dtype), distaxis)
235
236
237
238
239
240
241


def empty_like(a, dtype=None):
    return data_object(np.empty_like(a._data, dtype))


def vdot(a, b):
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
242
    tmp = np.vdot(a._data, b._data)
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
243
    res = np.empty(1,dtype=type(tmp))
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
244
    _comm.Allreduce(tmp,res,MPI.SUM)
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
245
    return res[0]
246
247
248
249
250
251
252


def _math_helper(x, function, out):
    if out is not None:
        function(x._data, out=out._data)
        return out
    else:
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
253
        return data_object(x.shape,function(x._data),x._distaxis)
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279


def abs(a, out=None):
    return _math_helper(a, np.abs, out)


def exp(a, out=None):
    return _math_helper(a, np.exp, out)


def log(a, out=None):
    return _math_helper(a, np.log, out)


def sqrt(a, out=None):
    return _math_helper(a, np.sqrt, out)


def bincount(x, weights=None, minlength=None):
    if weights is not None:
        weights = weights._data
    res = np.bincount(x._data, weights, minlength)
    return data_object(res)


def from_object(object, dtype=None, copy=True):
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
280
    return data_object(object._shape, np.array(object._data, dtype=dtype, copy=copy), distaxis=object._distaxis)
281
282


Martin Reinecke's avatar
fixes    
Martin Reinecke committed
283
def from_random(random_type, shape, dtype=np.float64, distaxis=0, **kwargs):
284
    generator_function = getattr(Random, random_type)
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
285
286
287
    #lshape = local_shape(shape, distaxis)
    #return data_object(shape, generator_function(dtype=dtype, shape=lshape, **kwargs), distaxis=distaxis)
    return from_global_data(generator_function(dtype=dtype, shape=shape, **kwargs), distaxis=distaxis)
288

Martin Reinecke's avatar
Martin Reinecke committed
289
290
291
292
def local_data(arr):
    return arr._data


Martin Reinecke's avatar
fixes    
Martin Reinecke committed
293
294
def ibegin(arr):
    res = [0] * arr._data.ndim
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
295
    res[arr._distaxis] = _shareRange(arr._shape[arr._distaxis],ntask,rank)[0]
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
296
    return tuple(res)
Martin Reinecke's avatar
Martin Reinecke committed
297
298


Martin Reinecke's avatar
fixes    
Martin Reinecke committed
299
300
def np_allreduce_sum(arr):
    res = np.empty_like(arr)
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
301
    _comm.Allreduce(arr,res,MPI.SUM)
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
302
    return res
Martin Reinecke's avatar
Martin Reinecke committed
303
304
305
306
307
308
309
310
311
312
313
314
315


def distaxis(arr):
    return arr._distaxis


def from_local_data (shape, arr, distaxis):
    return data_object(shape, arr, distaxis)


def from_global_data (arr, distaxis=0):
    if distaxis==-1:
        return data_object(arr.shape, arr, distaxis)
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
316
    lo, hi = _shareRange(arr.shape[distaxis],ntask,rank)
Martin Reinecke's avatar
Martin Reinecke committed
317
318
319
320
321
    sl = [slice(None)]*len(arr.shape)
    sl[distaxis]=slice(lo,hi)
    return data_object(arr.shape, arr[sl], distaxis)


Martin Reinecke's avatar
fixes    
Martin Reinecke committed
322
323
324
325
326
327
328
def to_global_data (arr):
    if arr._distaxis==-1:
        return arr._data
    tmp = redistribute(arr, dist=-1)
    return tmp._data


Martin Reinecke's avatar
Martin Reinecke committed
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
def redistribute (arr, dist=None, nodist=None):
    if dist is not None:
        if nodist is not None:
            raise ValueError
        if dist==arr._distaxis:
            return arr
    else:
        if nodist is None:
            raise ValueError
        if arr._distaxis not in nodist:
            return arr
        dist=-1
        for i in range(len(arr.shape)):
            if i not in nodist:
                dist=i
                break
Martin Reinecke's avatar
Martin Reinecke committed
345

Martin Reinecke's avatar
Martin Reinecke committed
346
347
348
349
350
351
352
    if arr._distaxis==-1:  # just pick the proper subset
        return from_global_data(arr._data, dist)
    if dist==-1: # gather data
        tmp = np.moveaxis(arr._data, arr._distaxis, 0)
        slabsize=np.prod(tmp.shape[1:])*tmp.itemsize
        sz=np.empty(ntask,dtype=np.int)
        for i in range(ntask):
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
353
            sz[i]=slabsize*_shareSize(arr.shape[arr._distaxis],ntask,i)
Martin Reinecke's avatar
Martin Reinecke committed
354
355
356
357
358
        disp=np.empty(ntask,dtype=np.int)
        disp[0]=0
        disp[1:]=np.cumsum(sz[:-1])
        tmp=tmp.flatten()
        out = np.empty(arr.size,dtype=arr.dtype)
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
359
        _comm.Allgatherv(tmp,[out,sz,disp,MPI.BYTE])
Martin Reinecke's avatar
Martin Reinecke committed
360
361
362
363
        shp = np.array(arr._shape)
        shp[1:arr._distaxis+1] = shp[0:arr._distaxis]
        shp[0] = arr.shape[arr._distaxis]
        out = out.reshape(shp)
Martin Reinecke's avatar
Martin Reinecke committed
364
365
366
        out = np.moveaxis(out, 0, arr._distaxis)
        return from_global_data (out, distaxis=-1)
    # real redistribution via Alltoallv
Martin Reinecke's avatar
Martin Reinecke committed
367
    # temporary slow, but simple solution
368
    #return redistribute(redistribute(arr,dist=-1),dist=dist)
Martin Reinecke's avatar
Martin Reinecke committed
369

Martin Reinecke's avatar
Martin Reinecke committed
370
371
372
373
374
375
    tmp = np.moveaxis(arr._data, (dist, arr._distaxis), (0, 1))
    tshape = tmp.shape
    slabsize=np.prod(tmp.shape[2:])*tmp.itemsize
    ssz=np.empty(ntask,dtype=np.int)
    rsz=np.empty(ntask,dtype=np.int)
    for i in range(ntask):
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
376
377
        ssz[i]=_shareSize(arr.shape[dist],ntask,i)*tmp.shape[1]*slabsize
        rsz[i]=_shareSize(arr.shape[dist],ntask,rank)*_shareSize(arr.shape[arr._distaxis],ntask,i)*slabsize
Martin Reinecke's avatar
Martin Reinecke committed
378
379
380
381
382
383
384
    sdisp=np.empty(ntask,dtype=np.int)
    rdisp=np.empty(ntask,dtype=np.int)
    sdisp[0]=0
    rdisp[0]=0
    sdisp[1:]=np.cumsum(ssz[:-1])
    rdisp[1:]=np.cumsum(rsz[:-1])
    tmp=tmp.flatten()
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
385
    out = np.empty(np.prod(local_shape(arr.shape,dist)),dtype=arr.dtype)
Martin Reinecke's avatar
Martin Reinecke committed
386
387
    s_msg = [tmp, (ssz, sdisp), MPI.BYTE]
    r_msg = [out, (rsz, rdisp), MPI.BYTE]
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
388
389
    _comm.Alltoallv(s_msg, r_msg)
    out2 = np.empty([_shareSize(arr.shape[dist],ntask,rank), arr.shape[arr._distaxis]] +list(tshape[2:]), dtype=arr.dtype)
390
391
392
    ofs=0
    for i in range(ntask):
        lsize = rsz[i]//tmp.itemsize
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
393
394
        lo,hi = _shareRange(arr.shape[arr._distaxis],ntask,i)
        out2[slice(None),slice(lo,hi)] = out[ofs:ofs+lsize].reshape([_shareSize(arr.shape[dist],ntask,rank),_shareSize(arr.shape[arr._distaxis],ntask,i)]+list(tshape[2:]))
395
        ofs += lsize
Martin Reinecke's avatar
tweaks    
Martin Reinecke committed
396
    new_shape = [_shareSize(arr.shape[dist],ntask,rank), arr.shape[arr._distaxis]] +list(tshape[2:])
397
398
399
    out2=out2.reshape(new_shape)
    out2 = np.moveaxis(out2, (0, 1), (dist, arr._distaxis))
    return from_local_data (arr.shape, out2, dist)
Martin Reinecke's avatar
Martin Reinecke committed
400
401
402
403


def default_distaxis():
    return 0