distributed_do.py 11.8 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
import numpy as np
from .random import Random
from mpi4py import MPI

comm = MPI.COMM_WORLD
ntask = comm.Get_size()
rank = comm.Get_rank()


def shareSize(nwork, nshares, myshare):
    nbase = nwork//nshares
    return nbase if myshare>=nwork%nshares else nbase+1
Martin Reinecke's avatar
Martin Reinecke committed
13
14
15
16
17
18
def shareRange(nwork, nshares, myshare):
    nbase = nwork//nshares;
    additional = nwork%nshares;
    lo = myshare*nbase + min(myshare, additional)
    hi = lo+nbase+ (1 if myshare<additional else 0)
    return lo,hi
19
20

def get_locshape(shape, distaxis):
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
21
22
    if len(shape)==0:
        distaxis = -1
23
24
    if distaxis==-1:
        return shape
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
25
26
    if distaxis<0 or distaxis>=len(shape):
        print distaxis,shape
27
28
29
    shape2=list(shape)
    shape2[distaxis]=shareSize(shape[distaxis],ntask,rank)
    return tuple(shape2)
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
30
31
def local_shape(shape, distaxis):
    return get_locshape(shape,distaxis)
32
33
34
35

class data_object(object):
    def __init__(self, shape, data, distaxis):
        """Must not be called directly by users"""
Martin Reinecke's avatar
Martin Reinecke committed
36
        self._shape = tuple(shape)
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
37
38
        if len(self._shape)==0:
            distaxis = -1
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
        self._distaxis = distaxis
        lshape = get_locshape(self._shape, self._distaxis)
        self._data = data

    def sanity_checks(self):
        # 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)
        comm.Allgather(itmp,otmp)
        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
54
        otmp=np.empty((ntask,len(self._shape)),dtype=np.int)
55
56
        comm.Allgather(itmp,otmp)
        for i in range(ntask):
Martin Reinecke's avatar
Martin Reinecke committed
57
            if np.any(otmp[i,:]!=self._shape):
58
59
60
61
62
63
64
                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
Martin Reinecke committed
65
66
            itmp[self._distaxis] = shareSize(self._shape[self._distaxis],ntask,rank)
            if np.any(self._data.shape!=itmp):
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
                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
83
        return data_object(self._shape, self._data.real, self._distaxis)
84
85
86

    @property
    def imag(self):
Martin Reinecke's avatar
Martin Reinecke committed
87
        return data_object(self._shape, self._data.imag, self._distaxis)
88

Martin Reinecke's avatar
Martin Reinecke committed
89
    def _contraction_helper(self, op, mpiop, axis):
90
91
92
93
        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
94
95
            res = np.array(getattr(self._data, op)())
            if (self._distaxis==-1):
Martin Reinecke's avatar
Martin Reinecke committed
96
                return res[0]
Martin Reinecke's avatar
Martin Reinecke committed
97
            res2 = np.empty(1,dtype=res.dtype)
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
98
            comm.Allreduce(res,res2,mpiop)
Martin Reinecke's avatar
Martin Reinecke committed
99
            return res2[0]
100
101

        if self._distaxis in axis:
Martin Reinecke's avatar
Martin Reinecke committed
102
103
104
105
            res = getattr(self._data, op)(axis=axis)
            res2 = np.empty_like(res)
            comm.Allreduce(res,res2,mpiop)
            return from_global_data(res2, distaxis=0)
106
        else:
Martin Reinecke's avatar
Martin Reinecke committed
107
            # perform the contraction on the local data
Martin Reinecke's avatar
Martin Reinecke committed
108
109
110
111
112
113
114
115
116
117
118
119
            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
            print (axis,self._distaxis,shift)
            shp[self._distaxis-shift] = self.shape[self._distaxis]
            print (self.shape, shp)
            return from_local_data(shp, res, self._distaxis-shift)
120
121
122
123
124
125
126
127
128
129
130

        # 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)

    def _binary_helper(self, other, op):
Martin Reinecke's avatar
Martin Reinecke committed
131
        a = self
132
        if isinstance(other, data_object):
Martin Reinecke's avatar
Martin Reinecke committed
133
            b = other
134
135
136
            if a._shape != b._shape:
                raise ValueError("shapes are incompatible.")
            if a._distaxis != b._distaxis:
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
137
                print (a._distaxis, b._distaxis)
138
                raise ValueError("distributions are incompatible.")
Martin Reinecke's avatar
Martin Reinecke committed
139
140
            a = a._data
            b = b._data
141
        else:
Martin Reinecke's avatar
Martin Reinecke committed
142
            a = a._data
143
144
145
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
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
            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__')

    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
203
        return data_object(self._shape,-self._data,self._distaxis)
204
205

    def __abs__(self):
Martin Reinecke's avatar
fixes    
Martin Reinecke committed
206
        return data_object(self._shape,np.abs(self._data),self._distaxis)
207

Martin Reinecke's avatar
fixes    
Martin Reinecke committed
208
209
    #def ravel(self):
    #    return data_object(self._data.ravel())
210

Martin Reinecke's avatar
fixes    
Martin Reinecke committed
211
212
    #def reshape(self, shape):
    #    return data_object(self._data.reshape(shape))
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
fixes    
Martin Reinecke committed
222
    return data_object(shape, np.full(get_locshape(shape, distaxis), fill_value, dtype), distaxis)
223
224


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


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


Martin Reinecke's avatar
fixes    
Martin Reinecke committed
233
234
def ones(shape, dtype=None, distaxis=0):
    return data_object(shape, np.ones(get_locshape(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
fixes    
Martin Reinecke committed
242
243
244
    tmp = np.vdot(a._data.ravel(), b._data.ravel())
    res = np.empty(1,dtype=type(tmp))
    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
fixes    
Martin Reinecke committed
285
286
    lshape = get_locshape(shape, distaxis)
    return data_object(shape, generator_function(dtype=dtype, shape=lshape, **kwargs), distaxis=distaxis)
287
288
289
290
291
292


def to_ndarray(arr):
    return arr._data


Martin Reinecke's avatar
fixes    
Martin Reinecke committed
293
294
def from_ndarray(arr,distaxis=0):
    return data_object(arr.shape,arr,distaxis)
Martin Reinecke's avatar
Martin Reinecke committed
295
296
297
298
299
300


def local_data(arr):
    return arr._data


Martin Reinecke's avatar
fixes    
Martin Reinecke committed
301
302
303
304
def ibegin(arr):
    res = [0] * arr._data.ndim
    res[arr._distaxis] = shareRange(arr._shape[arr._distaxis],ntask,rank)[0]
    return tuple(res)
Martin Reinecke's avatar
Martin Reinecke committed
305
306


Martin Reinecke's avatar
fixes    
Martin Reinecke committed
307
308
309
310
def np_allreduce_sum(arr):
    res = np.empty_like(arr)
    comm.Allreduce(arr,res,MPI.SUM)
    return res
Martin Reinecke's avatar
Martin Reinecke committed
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329


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)
    lo, hi = shareRange(arr.shape[distaxis],ntask,rank)
    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
330
331
332
333
334
335
336
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
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
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
    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):
            sz[i]=slabsize*shareSize(arr.shape[arr._distaxis],ntask,i)
        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)
        print tmp.shape, out.shape, sz, disp
        comm.Allgatherv(tmp,[out,sz,disp,MPI.BYTE])
        out = out.reshape(arr._shape)
        out = np.moveaxis(out, 0, arr._distaxis)
        return from_global_data (out, distaxis=-1)
    # real redistribution via Alltoallv
    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):
        ssz[i]=slabsize*tmp.shape[1]*shareSize(arr.shape[dist],ntask,i)
        rsz[i]=slabsize*shareSize(arr.shape[dist],ntask,rank)*shareSize(arr.shape[arr._distaxis],ntask,i)
    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])
    print ssz, rsz
    tmp=tmp.flatten()
    out = np.empty(np.prod(get_locshape(arr.shape,dist)),dtype=arr.dtype)
    s_msg = [tmp, (ssz, sdisp), MPI.BYTE]
    r_msg = [out, (rsz, rdisp), MPI.BYTE]
    comm.Alltoallv(s_msg, r_msg)
    new_shape = [shareSize(arr.shape[dist],ntask,rank), arr.shape[arr._distaxis]] +list(tshape[2:])
    out=out.reshape(new_shape)
    out = np.moveaxis(out, (0, 1), (dist, arr._distaxis))
    return from_local_data (arr.shape, out, dist)


def default_distaxis():
    return 0