nmatrix 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.autotest +23 -0
- data/.gemtest +0 -0
- data/Gemfile +7 -0
- data/History.txt +6 -0
- data/LICENSE.txt +21 -0
- data/Manifest.txt +51 -0
- data/README.rdoc +63 -0
- data/Rakefile +154 -0
- data/ext/nmatrix/cblas.c +150 -0
- data/ext/nmatrix/dense.c +307 -0
- data/ext/nmatrix/dense/blas_header.template.c +52 -0
- data/ext/nmatrix/dense/elementwise.template.c +107 -0
- data/ext/nmatrix/dense/gemm.template.c +159 -0
- data/ext/nmatrix/dense/gemv.template.c +130 -0
- data/ext/nmatrix/dense/rationalmath.template.c +68 -0
- data/ext/nmatrix/depend +18 -0
- data/ext/nmatrix/extconf.rb +143 -0
- data/ext/nmatrix/generator.rb +594 -0
- data/ext/nmatrix/generator/syntax_tree.rb +481 -0
- data/ext/nmatrix/list.c +774 -0
- data/ext/nmatrix/nmatrix.c +1977 -0
- data/ext/nmatrix/nmatrix.h +912 -0
- data/ext/nmatrix/rational.c +98 -0
- data/ext/nmatrix/yale.c +726 -0
- data/ext/nmatrix/yale/complexmath.template.c +71 -0
- data/ext/nmatrix/yale/elementwise.template.c +46 -0
- data/ext/nmatrix/yale/elementwise_op.template.c +73 -0
- data/ext/nmatrix/yale/numbmm.template.c +94 -0
- data/ext/nmatrix/yale/smmp1.template.c +21 -0
- data/ext/nmatrix/yale/smmp1_header.template.c +38 -0
- data/ext/nmatrix/yale/smmp2.template.c +43 -0
- data/ext/nmatrix/yale/smmp2_header.template.c +46 -0
- data/ext/nmatrix/yale/sort_columns.template.c +56 -0
- data/ext/nmatrix/yale/symbmm.template.c +54 -0
- data/ext/nmatrix/yale/transp.template.c +68 -0
- data/lib/array.rb +67 -0
- data/lib/nmatrix.rb +263 -0
- data/lib/string.rb +65 -0
- data/spec/nmatrix_spec.rb +395 -0
- data/spec/nmatrix_yale_spec.rb +239 -0
- data/spec/nvector_spec.rb +43 -0
- data/spec/syntax_tree_spec.rb +46 -0
- metadata +150 -0
@@ -0,0 +1,1977 @@
|
|
1
|
+
/////////////////////////////////////////////////////////////////////
|
2
|
+
// = NMatrix
|
3
|
+
//
|
4
|
+
// A linear algebra library for scientific computation in Ruby.
|
5
|
+
// NMatrix is part of SciRuby.
|
6
|
+
//
|
7
|
+
// NMatrix was originally inspired by and derived from NArray, by
|
8
|
+
// Masahiro Tanaka: http://narray.rubyforge.org
|
9
|
+
//
|
10
|
+
// == Copyright Information
|
11
|
+
//
|
12
|
+
// SciRuby is Copyright (c) 2010 - 2012, Ruby Science Foundation
|
13
|
+
// NMatrix is Copyright (c) 2012, Ruby Science Foundation
|
14
|
+
//
|
15
|
+
// Please see LICENSE.txt for additional copyright notices.
|
16
|
+
//
|
17
|
+
// == Contributing
|
18
|
+
//
|
19
|
+
// By contributing source code to SciRuby, you agree to be bound by
|
20
|
+
// our Contributor Agreement:
|
21
|
+
//
|
22
|
+
// * https://github.com/SciRuby/sciruby/wiki/Contributor-Agreement
|
23
|
+
//
|
24
|
+
// == nmatrix.c
|
25
|
+
//
|
26
|
+
#ifndef NMATRIX_C
|
27
|
+
# define NMATRIX_C
|
28
|
+
|
29
|
+
#include <ruby.h>
|
30
|
+
|
31
|
+
#include "nmatrix.h"
|
32
|
+
//#include "types.h"
|
33
|
+
|
34
|
+
VALUE cNMatrix, cNVector;
|
35
|
+
VALUE nm_eDataTypeError, nm_eStorageTypeError;
|
36
|
+
|
37
|
+
ID nm_id_real, nm_id_imag;
|
38
|
+
ID nm_id_numer, nm_id_denom;
|
39
|
+
ID nm_id_transpose, nm_id_no_transpose, nm_id_complex_conjugate; // cblas
|
40
|
+
ID nm_id_list, nm_id_dense;
|
41
|
+
ID nm_id_mult, nm_id_multeq;
|
42
|
+
ID nm_id_add;
|
43
|
+
|
44
|
+
#include "dtypes.c"
|
45
|
+
|
46
|
+
#ifdef BENCHMARK
|
47
|
+
double get_time() {
|
48
|
+
struct timeval t;
|
49
|
+
struct timezone tzp;
|
50
|
+
gettimeofday(&t, &tzp);
|
51
|
+
return t.tv_sec + t.tv_usec*1e-6;
|
52
|
+
}
|
53
|
+
#endif
|
54
|
+
|
55
|
+
|
56
|
+
const char *nm_stypestring[] = {
|
57
|
+
"dense",
|
58
|
+
"list",
|
59
|
+
"yale",
|
60
|
+
"stypes"
|
61
|
+
};
|
62
|
+
|
63
|
+
|
64
|
+
nm_delete_t DeleteFuncs = {
|
65
|
+
delete_dense_storage,
|
66
|
+
delete_list_storage,
|
67
|
+
delete_yale_storage
|
68
|
+
};
|
69
|
+
|
70
|
+
|
71
|
+
nm_mark_t MarkFuncs = {
|
72
|
+
mark_dense_storage,
|
73
|
+
mark_list_storage,
|
74
|
+
mark_yale_storage
|
75
|
+
};
|
76
|
+
|
77
|
+
|
78
|
+
nm_gemv_t GemvFuncs = {
|
79
|
+
NULL,
|
80
|
+
cblas_bgemv_,
|
81
|
+
cblas_i8gemv_,
|
82
|
+
cblas_i16gemv_,
|
83
|
+
cblas_i32gemv_,
|
84
|
+
cblas_i64gemv_,
|
85
|
+
cblas_sgemv_,
|
86
|
+
cblas_dgemv_,
|
87
|
+
cblas_cgemv_,
|
88
|
+
cblas_zgemv_,
|
89
|
+
cblas_r32gemv_,
|
90
|
+
cblas_r64gemv_,
|
91
|
+
cblas_r128gemv_,
|
92
|
+
NULL
|
93
|
+
};
|
94
|
+
|
95
|
+
|
96
|
+
nm_gemm_t GemmFuncs = { // by NM_TYPES
|
97
|
+
NULL,
|
98
|
+
cblas_bgemm_,
|
99
|
+
cblas_i8gemm_,
|
100
|
+
cblas_i16gemm_,
|
101
|
+
cblas_i32gemm_,
|
102
|
+
cblas_i64gemm_,
|
103
|
+
cblas_sgemm_,
|
104
|
+
cblas_dgemm_,
|
105
|
+
cblas_cgemm_,
|
106
|
+
cblas_zgemm_,
|
107
|
+
cblas_r32gemm_,
|
108
|
+
cblas_r64gemm_,
|
109
|
+
cblas_r128gemm_,
|
110
|
+
cblas_vgemm_
|
111
|
+
};
|
112
|
+
|
113
|
+
static void TransposeTypeErr(y_size_t n, y_size_t m, YALE_PARAM A, YALE_PARAM B, bool move) {
|
114
|
+
rb_raise(nm_eDataTypeError, "illegal operation with this matrix type");
|
115
|
+
}
|
116
|
+
|
117
|
+
|
118
|
+
// First dimension is dtype, second dimension is index dtype (so lots of nulls)
|
119
|
+
nm_smmp_transpose_t SparseTransposeFuncs = {
|
120
|
+
{TransposeTypeErr, TransposeTypeErr, TransposeTypeErr, TransposeTypeErr, TransposeTypeErr, TransposeTypeErr}, // NM_NONE
|
121
|
+
{TransposeTypeErr, TransposeTypeErr, i8_b_transp_, i16_b_transp_, i32_b_transp_, i64_b_transp_}, // NM_BYTE
|
122
|
+
{TransposeTypeErr, TransposeTypeErr, i8_i8_transp_, i16_i8_transp_, i32_i8_transp_, i64_i8_transp_}, // NM_INT8
|
123
|
+
{TransposeTypeErr, TransposeTypeErr, i8_i16_transp_, i16_i16_transp_, i32_i16_transp_, i64_i16_transp_}, // NM_INT16
|
124
|
+
{TransposeTypeErr, TransposeTypeErr, i8_i32_transp_, i16_i32_transp_, i32_i32_transp_, i64_i32_transp_}, // NM_INT32
|
125
|
+
{TransposeTypeErr, TransposeTypeErr, i8_i64_transp_, i16_i64_transp_, i32_i64_transp_, i64_i64_transp_}, // NM_INT64
|
126
|
+
{TransposeTypeErr, TransposeTypeErr, i8_f32_transp_, i16_f32_transp_, i32_f32_transp_, i64_f32_transp_}, // NM_FLOAT32
|
127
|
+
{TransposeTypeErr, TransposeTypeErr, i8_f64_transp_, i16_f64_transp_, i32_f64_transp_, i64_f64_transp_}, // NM_FLOAT64
|
128
|
+
{TransposeTypeErr, TransposeTypeErr, i8_c64_transp_, i16_c64_transp_, i32_c64_transp_, i64_c64_transp_}, // NM_COMPLEX64
|
129
|
+
{TransposeTypeErr, TransposeTypeErr, i8_c128_transp_, i16_c128_transp_, i32_c128_transp_, i64_c128_transp_}, // NM_COMPLEX128
|
130
|
+
{TransposeTypeErr, TransposeTypeErr, i8_r32_transp_, i16_r32_transp_, i32_r32_transp_, i64_r32_transp_}, // NM_RATIONAL32
|
131
|
+
{TransposeTypeErr, TransposeTypeErr, i8_r64_transp_, i16_r64_transp_, i32_r64_transp_, i64_r64_transp_}, // NM_RATIONAL64
|
132
|
+
{TransposeTypeErr, TransposeTypeErr, i8_r128_transp_, i16_r128_transp_, i32_r128_transp_, i64_r128_transp_}, // NM_RATIONAL128
|
133
|
+
{TransposeTypeErr, TransposeTypeErr, i8_v_transp_, i16_v_transp_, i32_v_transp_, i64_v_transp_} // NM_ROBJ
|
134
|
+
};
|
135
|
+
|
136
|
+
/*
|
137
|
+
// Currently commented out because dense_transpose_generic is about the same speed. Let's resurrect this when we write
|
138
|
+
// an in-place transpose (e.g., transpose!).
|
139
|
+
|
140
|
+
static void DenseTransTypeErr(int M, int N, void* A, int lda, void* B, int ldb, bool move) {
|
141
|
+
rb_raise(nm_eDataTypeError, "illegal operation with this matrix type");
|
142
|
+
}
|
143
|
+
|
144
|
+
nm_dense_transpose_t DenseTransposeFuncs = {
|
145
|
+
DenseTransTypeErr,
|
146
|
+
btransp,
|
147
|
+
i8transp,
|
148
|
+
i16transp,
|
149
|
+
i32transp,
|
150
|
+
i64transp,
|
151
|
+
f32transp,
|
152
|
+
f64transp,
|
153
|
+
c64transp,
|
154
|
+
c128transp,
|
155
|
+
r32transp,
|
156
|
+
r64transp,
|
157
|
+
r128transp,
|
158
|
+
vtransp
|
159
|
+
}; */
|
160
|
+
|
161
|
+
|
162
|
+
static void SmmpTypeErr(y_size_t n, y_size_t m, YALE_PARAM A, YALE_PARAM B, YALE_PARAM C) {
|
163
|
+
rb_raise(nm_eDataTypeError, "illegal operation with this matrix type");
|
164
|
+
}
|
165
|
+
|
166
|
+
// First dimension is dtype, second dimension is index dtype (so lots of nulls)
|
167
|
+
nm_smmp_t SmmpFuncs = {
|
168
|
+
{SmmpTypeErr, SmmpTypeErr, SmmpTypeErr, SmmpTypeErr, SmmpTypeErr, SmmpTypeErr}, // NM_NONE
|
169
|
+
{SmmpTypeErr, SmmpTypeErr, i8_b_smmp, i16_b_smmp, i32_b_smmp, i64_b_smmp}, // NM_BYTE
|
170
|
+
{SmmpTypeErr, SmmpTypeErr, i8_i8_smmp, i16_i8_smmp, i32_i8_smmp, i64_i8_smmp}, // NM_INT8
|
171
|
+
{SmmpTypeErr, SmmpTypeErr, i8_i16_smmp, i16_i16_smmp, i32_i16_smmp, i64_i16_smmp}, // NM_INT16
|
172
|
+
{SmmpTypeErr, SmmpTypeErr, i8_i32_smmp, i16_i32_smmp, i32_i32_smmp, i64_i32_smmp}, // NM_INT32
|
173
|
+
{SmmpTypeErr, SmmpTypeErr, i8_i64_smmp, i16_i64_smmp, i32_i64_smmp, i64_i64_smmp}, // NM_INT64
|
174
|
+
{SmmpTypeErr, SmmpTypeErr, i8_f32_smmp, i16_f32_smmp, i32_f32_smmp, i64_f32_smmp}, // NM_FLOAT32
|
175
|
+
{SmmpTypeErr, SmmpTypeErr, i8_f64_smmp, i16_f64_smmp, i32_f64_smmp, i64_f64_smmp}, // NM_FLOAT64
|
176
|
+
{SmmpTypeErr, SmmpTypeErr, i8_c64_smmp, i16_c64_smmp, i32_c64_smmp, i64_c64_smmp}, // NM_COMPLEX64
|
177
|
+
{SmmpTypeErr, SmmpTypeErr, i8_c128_smmp, i16_c128_smmp, i32_c128_smmp, i64_c128_smmp}, // NM_COMPLEX128
|
178
|
+
{SmmpTypeErr, SmmpTypeErr, i8_r32_smmp, i16_r32_smmp, i32_r32_smmp, i64_r32_smmp}, // NM_RATIONAL32
|
179
|
+
{SmmpTypeErr, SmmpTypeErr, i8_r64_smmp, i16_r64_smmp, i32_r64_smmp, i64_r64_smmp}, // NM_RATIONAL64
|
180
|
+
{SmmpTypeErr, SmmpTypeErr, i8_r128_smmp, i16_r128_smmp, i32_r128_smmp, i64_r128_smmp}, // NM_RATIONAL128
|
181
|
+
{SmmpTypeErr, SmmpTypeErr, i8_v_smmp, i16_v_smmp, i32_v_smmp, i64_v_smmp} // NM_ROBJ
|
182
|
+
};
|
183
|
+
|
184
|
+
|
185
|
+
static inline DENSE_PARAM cblas_params_for_multiply(const DENSE_STORAGE* left, const DENSE_STORAGE* right, const DENSE_STORAGE* result, bool vector) {
|
186
|
+
DENSE_PARAM p;
|
187
|
+
|
188
|
+
p.A = left->elements;
|
189
|
+
p.B = right->elements; // for vector, this is actually x
|
190
|
+
p.C = result->elements; // vector Y
|
191
|
+
|
192
|
+
p.M = left->shape[0];
|
193
|
+
p.lda = left->shape[1];
|
194
|
+
|
195
|
+
if (vector) {
|
196
|
+
p.N = left->shape[1];
|
197
|
+
|
198
|
+
p.ldb = 1; // incX
|
199
|
+
p.ldc = 1; // incY
|
200
|
+
} else {
|
201
|
+
p.N = right->shape[1];
|
202
|
+
p.K = left->shape[1];
|
203
|
+
|
204
|
+
p.ldb = right->shape[1];
|
205
|
+
p.ldc = result->shape[1];
|
206
|
+
}
|
207
|
+
|
208
|
+
switch(left->dtype) {
|
209
|
+
case NM_FLOAT32:
|
210
|
+
case NM_FLOAT64:
|
211
|
+
p.alpha.d[0] = 1.0;
|
212
|
+
p.beta.d[0] = 0.0;
|
213
|
+
break;
|
214
|
+
|
215
|
+
case NM_COMPLEX64:
|
216
|
+
p.alpha.c[0].r = 1.0;
|
217
|
+
p.alpha.c[0].i = 0.0;
|
218
|
+
p.beta.c[0].r = 0.0;
|
219
|
+
p.beta.c[0].i = 0.0;
|
220
|
+
break;
|
221
|
+
|
222
|
+
case NM_COMPLEX128:
|
223
|
+
p.alpha.z.r = 1.0;
|
224
|
+
p.alpha.z.i = 0.0;
|
225
|
+
p.beta.z.r = 0.0;
|
226
|
+
p.beta.z.i = 0.0;
|
227
|
+
break;
|
228
|
+
|
229
|
+
case NM_BYTE:
|
230
|
+
p.alpha.b[0] = 1;
|
231
|
+
p.beta.b[0] = 0;
|
232
|
+
break;
|
233
|
+
|
234
|
+
case NM_INT8:
|
235
|
+
case NM_INT16:
|
236
|
+
case NM_INT32:
|
237
|
+
case NM_INT64:
|
238
|
+
p.alpha.i[0] = 1;
|
239
|
+
p.beta.i[0] = 0;
|
240
|
+
break;
|
241
|
+
|
242
|
+
case NM_RATIONAL32:
|
243
|
+
p.alpha.r[0].n = 1;
|
244
|
+
p.alpha.r[0].d = 1;
|
245
|
+
p.beta.r[0].n = 0;
|
246
|
+
p.beta.r[0].d = 1;
|
247
|
+
break;
|
248
|
+
|
249
|
+
case NM_RATIONAL64:
|
250
|
+
p.alpha.ra[0].n = 1;
|
251
|
+
p.alpha.ra[0].d = 1;
|
252
|
+
p.beta.ra[0].n = 0;
|
253
|
+
p.beta.ra[0].d = 1;
|
254
|
+
break;
|
255
|
+
|
256
|
+
case NM_RATIONAL128:
|
257
|
+
p.alpha.rat.n = 1;
|
258
|
+
p.alpha.rat.d = 1;
|
259
|
+
p.beta.rat.n = 0;
|
260
|
+
p.beta.rat.d = 1;
|
261
|
+
break;
|
262
|
+
|
263
|
+
case NM_ROBJ:
|
264
|
+
p.alpha.v[0] = INT2FIX(1);
|
265
|
+
p.beta.v[0] = RUBY_ZERO;
|
266
|
+
break;
|
267
|
+
|
268
|
+
default:
|
269
|
+
rb_raise(nm_eDataTypeError, "unexpected dtype");
|
270
|
+
|
271
|
+
}
|
272
|
+
|
273
|
+
return p;
|
274
|
+
}
|
275
|
+
|
276
|
+
|
277
|
+
static NMATRIX* multiply_matrix_dense_casted(STORAGE_PAIR casted_storage, size_t* resulting_shape, bool vector) {
|
278
|
+
DENSE_STORAGE *left = (DENSE_STORAGE*)(casted_storage.left),
|
279
|
+
*right = (DENSE_STORAGE*)(casted_storage.right),
|
280
|
+
*result;
|
281
|
+
|
282
|
+
// We can safely get dtype from the casted matrices; post-condition of binary_storage_cast_alloc is that dtype is the
|
283
|
+
// same for left and right.
|
284
|
+
int8_t dtype = left->dtype;
|
285
|
+
|
286
|
+
// Create result storage.
|
287
|
+
result = create_dense_storage(dtype, resulting_shape, 2, NULL, 0);
|
288
|
+
|
289
|
+
// Do the multiplication
|
290
|
+
if (vector) GemvFuncs[dtype](CblasRowMajor, CblasNoTrans, cblas_params_for_multiply(left, right, result, true));
|
291
|
+
else GemmFuncs[dtype](CblasRowMajor, CblasNoTrans, CblasNoTrans, cblas_params_for_multiply(left, right, result, false));
|
292
|
+
|
293
|
+
return nm_create(S_DENSE, result);
|
294
|
+
}
|
295
|
+
|
296
|
+
|
297
|
+
static NMATRIX* multiply_matrix_yale_casted(STORAGE_PAIR casted_storage, size_t* resulting_shape, bool vector) {
|
298
|
+
YALE_STORAGE *left = (YALE_STORAGE*)(casted_storage.left),
|
299
|
+
*right = (YALE_STORAGE*)(casted_storage.right),
|
300
|
+
*result;
|
301
|
+
YALE_PARAM A, B, C;
|
302
|
+
|
303
|
+
// We can safely get dtype from the casted matrices; post-condition of binary_storage_cast_alloc is that dtype is the
|
304
|
+
// same for left and right.
|
305
|
+
int8_t dtype = left->dtype;
|
306
|
+
|
307
|
+
// Create result storage.
|
308
|
+
result = create_yale_storage(dtype, resulting_shape, 2, left->capacity + right->capacity);
|
309
|
+
init_yale_storage(result);
|
310
|
+
|
311
|
+
// Set multiplication parameters
|
312
|
+
A.ia = A.ja = left->ija;
|
313
|
+
A.a = left->a;
|
314
|
+
B.ia = B.ja = right->ija;
|
315
|
+
B.a = right->a;
|
316
|
+
C.ia = C.ja = result->ija;
|
317
|
+
C.a = result->a;
|
318
|
+
|
319
|
+
A.diag = B.diag = C.diag = true;
|
320
|
+
|
321
|
+
// Do the multiplication
|
322
|
+
SmmpFuncs[dtype][left->index_dtype](result->shape[0], result->shape[1], A, B, C);
|
323
|
+
|
324
|
+
return nm_create(S_YALE, result);
|
325
|
+
}
|
326
|
+
|
327
|
+
|
328
|
+
static NMATRIX* multiply_matrix_list_casted(STORAGE_PAIR casted_storage, size_t* resulting_shape) {
|
329
|
+
rb_raise(rb_eNotImpError, "multiplication not implemented for list-of-list matrices");
|
330
|
+
free(resulting_shape);
|
331
|
+
return NULL;
|
332
|
+
}
|
333
|
+
|
334
|
+
|
335
|
+
nm_matrix_multiply_op_t CastedMultiplyFuncs = {
|
336
|
+
multiply_matrix_dense_casted,
|
337
|
+
multiply_matrix_list_casted,
|
338
|
+
multiply_matrix_yale_casted
|
339
|
+
};
|
340
|
+
|
341
|
+
|
342
|
+
nm_d_elementwise_binary_op_t DenseElementwiseFuncs = { // only for dense!
|
343
|
+
NULL,
|
344
|
+
nm_d_b_elementwise,
|
345
|
+
nm_d_i8_elementwise,
|
346
|
+
nm_d_i16_elementwise,
|
347
|
+
nm_d_i32_elementwise,
|
348
|
+
nm_d_i64_elementwise,
|
349
|
+
nm_d_f32_elementwise,
|
350
|
+
nm_d_f64_elementwise,
|
351
|
+
nm_d_c64_elementwise,
|
352
|
+
nm_d_c128_elementwise,
|
353
|
+
nm_d_r32_elementwise,
|
354
|
+
nm_d_r64_elementwise,
|
355
|
+
nm_d_r128_elementwise,
|
356
|
+
nm_d_v_elementwise,
|
357
|
+
NULL
|
358
|
+
};
|
359
|
+
|
360
|
+
static void EwTypeErr(y_size_t n, enum NMatrix_Ops op, void* ija, void* ijb, void* ijc, void* a, void* b, void* c) {
|
361
|
+
rb_raise(nm_eDataTypeError, "illegal operation with this matrix type");
|
362
|
+
}
|
363
|
+
|
364
|
+
// First dimension is dtype, second dimension is index dtype (so lots of nulls)
|
365
|
+
nm_y_elementwise_binary_op_t YaleElementwiseFuncs = { // only for yale!
|
366
|
+
{EwTypeErr, EwTypeErr, EwTypeErr, EwTypeErr, EwTypeErr, EwTypeErr},
|
367
|
+
{EwTypeErr, EwTypeErr, EwTypeErr, EwTypeErr, EwTypeErr, EwTypeErr},
|
368
|
+
{EwTypeErr, EwTypeErr, i8_i8_ew, i16_i8_ew, i32_i8_ew, i64_i8_ew},
|
369
|
+
{EwTypeErr, EwTypeErr, i8_i16_ew, i16_i16_ew, i32_i16_ew, i64_i16_ew},
|
370
|
+
{EwTypeErr, EwTypeErr, i8_i32_ew, i16_i32_ew, i32_i32_ew, i64_i32_ew},
|
371
|
+
{EwTypeErr, EwTypeErr, i8_i64_ew, i16_i64_ew, i32_i64_ew, i64_i64_ew},
|
372
|
+
{EwTypeErr, EwTypeErr, i8_f32_ew, i16_f32_ew, i32_f32_ew, i64_f32_ew},
|
373
|
+
{EwTypeErr, EwTypeErr, i8_f64_ew, i16_f64_ew, i32_f64_ew, i64_f64_ew},
|
374
|
+
{EwTypeErr, EwTypeErr, i8_c64_ew, i16_c64_ew, i32_c64_ew, i64_c64_ew},
|
375
|
+
{EwTypeErr, EwTypeErr, i8_c128_ew,i16_c128_ew,i32_c128_ew,i64_c128_ew},
|
376
|
+
{EwTypeErr, EwTypeErr, i8_r32_ew, i16_r32_ew, i32_r32_ew, i64_r32_ew},
|
377
|
+
{EwTypeErr, EwTypeErr, i8_r64_ew, i16_r64_ew, i32_r64_ew, i64_r64_ew},
|
378
|
+
{EwTypeErr, EwTypeErr, i8_r128_ew,i16_r128_ew,i32_r128_ew,i64_r128_ew},
|
379
|
+
{EwTypeErr, EwTypeErr, i8_v_ew, i16_v_ew, i32_v_ew, i64_v_ew}
|
380
|
+
};
|
381
|
+
|
382
|
+
|
383
|
+
static NMATRIX* elementwise_dense_casted(STORAGE_PAIR casted_storage, char op) {
|
384
|
+
DENSE_STORAGE *left = (DENSE_STORAGE*)(casted_storage.left),
|
385
|
+
*right = (DENSE_STORAGE*)(casted_storage.right),
|
386
|
+
*result;
|
387
|
+
|
388
|
+
// We can safely get dtype from the casted matrices; post-condition of binary_storage_cast_alloc is that dtype is the
|
389
|
+
// same for left and right.
|
390
|
+
size_t i;
|
391
|
+
int8_t dtype = left->dtype;
|
392
|
+
|
393
|
+
// Setup matrix shape for result
|
394
|
+
size_t* shape = ALLOC_N(size_t, left->rank);
|
395
|
+
for (i = 0; i < left->rank; ++i) shape[i] = left->shape[i];
|
396
|
+
|
397
|
+
// Create result storage.
|
398
|
+
result = create_dense_storage(dtype, shape, left->rank, NULL, 0);
|
399
|
+
|
400
|
+
// Do the operation
|
401
|
+
DenseElementwiseFuncs[dtype](left->elements, right->elements, result->elements, count_dense_storage_elements(result), op);
|
402
|
+
|
403
|
+
return nm_create(S_DENSE, result);
|
404
|
+
}
|
405
|
+
|
406
|
+
|
407
|
+
static NMATRIX* elementwise_list_casted(STORAGE_PAIR casted_storage, char op) {
|
408
|
+
rb_raise(rb_eNotImpError, "elementwise operations not implemented for list-of-list matrices");
|
409
|
+
return NULL;
|
410
|
+
}
|
411
|
+
|
412
|
+
|
413
|
+
static NMATRIX* elementwise_yale_casted(STORAGE_PAIR casted_storage, char op) {
|
414
|
+
YALE_STORAGE *left = (YALE_STORAGE*)(casted_storage.left),
|
415
|
+
*right = (YALE_STORAGE*)(casted_storage.right);
|
416
|
+
YALE_STORAGE *result = create_merged_yale_storage(left, right);
|
417
|
+
|
418
|
+
fprintf(stderr, "result: %d, %d\n", result->dtype, result->index_dtype);
|
419
|
+
|
420
|
+
//fprintf(stderr, "Remember to fix elementwise for yale!\n");
|
421
|
+
YaleElementwiseFuncs[result->dtype][result->index_dtype](result->shape[0], result->shape[1], op, left->ija, right->ija, result->ija, left->a, right->a, result->a);
|
422
|
+
|
423
|
+
return nm_create(S_YALE, result);
|
424
|
+
}
|
425
|
+
|
426
|
+
|
427
|
+
nm_elementwise_binary_op_casted_t CastedElementwiseFuncs = {
|
428
|
+
elementwise_dense_casted,
|
429
|
+
elementwise_list_casted,
|
430
|
+
elementwise_yale_casted
|
431
|
+
};
|
432
|
+
|
433
|
+
|
434
|
+
nm_compare_t EqEqFuncs = {
|
435
|
+
dense_storage_eqeq,
|
436
|
+
list_storage_eqeq,
|
437
|
+
yale_storage_eqeq
|
438
|
+
};
|
439
|
+
|
440
|
+
|
441
|
+
static void nm_delete(NMATRIX* mat) {
|
442
|
+
DeleteFuncs[mat->stype](mat->storage);
|
443
|
+
}
|
444
|
+
|
445
|
+
|
446
|
+
static STORAGE* nm_dense_new(size_t* shape, size_t rank, int8_t dtype, void* init_val, size_t init_val_len, VALUE self) {
|
447
|
+
return (STORAGE*)(create_dense_storage(dtype, shape, rank, init_val, init_val_len));
|
448
|
+
}
|
449
|
+
|
450
|
+
static STORAGE* nm_list_new(size_t* shape, size_t rank, int8_t dtype, void* init_val, size_t init_val_len, VALUE self) {
|
451
|
+
if (init_val_len > 1) {
|
452
|
+
rb_raise(rb_eArgError, "list storage needs initial size, not initial value\n");
|
453
|
+
return NULL;
|
454
|
+
}
|
455
|
+
return (STORAGE*)(create_list_storage(dtype, shape, rank, init_val));
|
456
|
+
}
|
457
|
+
|
458
|
+
|
459
|
+
static STORAGE* nm_yale_new(size_t* shape, size_t rank, int8_t dtype, void* init_val, size_t init_val_len, VALUE self) {
|
460
|
+
YALE_STORAGE* s;
|
461
|
+
|
462
|
+
if (init_val_len > 1) {
|
463
|
+
rb_raise(rb_eArgError, "list storage needs initial size, not initial value\n");
|
464
|
+
return NULL;
|
465
|
+
}
|
466
|
+
|
467
|
+
s = create_yale_storage(dtype, shape, rank, *(size_t*)init_val);
|
468
|
+
init_yale_storage(s);
|
469
|
+
free(init_val);
|
470
|
+
|
471
|
+
if (!s) rb_raise(rb_eNoMemError, "Yale allocation failed");
|
472
|
+
|
473
|
+
return (STORAGE*)(s);
|
474
|
+
//return Data_Wrap_Struct(self, NULL, nm_delete, matrix);
|
475
|
+
}
|
476
|
+
|
477
|
+
|
478
|
+
nm_create_storage_t CreateFuncs = {
|
479
|
+
nm_dense_new,
|
480
|
+
nm_list_new,
|
481
|
+
nm_yale_new
|
482
|
+
};
|
483
|
+
|
484
|
+
|
485
|
+
nm_cast_copy_storage_t CastCopyFuncs = {
|
486
|
+
cast_copy_dense_storage,
|
487
|
+
cast_copy_list_storage,
|
488
|
+
cast_copy_yale_storage
|
489
|
+
};
|
490
|
+
|
491
|
+
|
492
|
+
|
493
|
+
nm_scast_copy_storage_t ScastCopyFuncs = {
|
494
|
+
{cast_copy_dense_storage, scast_copy_dense_list, scast_copy_dense_yale},
|
495
|
+
{scast_copy_list_dense, cast_copy_list_storage, scast_copy_list_yale},
|
496
|
+
{scast_copy_yale_dense, scast_copy_yale_list, cast_copy_yale_storage}
|
497
|
+
};
|
498
|
+
|
499
|
+
|
500
|
+
nm_stype_ref_t RefFuncs = {
|
501
|
+
dense_storage_get,
|
502
|
+
list_storage_get,
|
503
|
+
yale_storage_ref
|
504
|
+
};
|
505
|
+
|
506
|
+
|
507
|
+
VALUE nm_dense_set(STORAGE* s, size_t* coords, VALUE val) {
|
508
|
+
void* v = ALLOCA_N(char, nm_sizeof[s->dtype]);
|
509
|
+
SetFuncs[s->dtype][NM_ROBJ](1, v, 0, &val, 0);
|
510
|
+
dense_storage_set( (DENSE_STORAGE*)s, coords, v );
|
511
|
+
return val;
|
512
|
+
}
|
513
|
+
|
514
|
+
|
515
|
+
// Should work exactly the same as nm_dense_set.
|
516
|
+
VALUE nm_yale_set(STORAGE* s, size_t* coords, VALUE val) {
|
517
|
+
void* v = ALLOCA_N(char, nm_sizeof[s->dtype]);
|
518
|
+
SetFuncs[s->dtype][NM_ROBJ](1, v, 0, &val, 0);
|
519
|
+
yale_storage_set( (YALE_STORAGE*)s, coords, v );
|
520
|
+
return val;
|
521
|
+
}
|
522
|
+
|
523
|
+
|
524
|
+
// TODO: Why can't you be more like your brothers, nm_dense_set and nm_yale_set?
|
525
|
+
VALUE nm_list_set(STORAGE* s, size_t* coords, VALUE val) {
|
526
|
+
void *v = ALLOC_N(char, nm_sizeof[s->dtype]), *rm;
|
527
|
+
LIST_STORAGE* ls = (LIST_STORAGE*)s;
|
528
|
+
|
529
|
+
//fprintf(stderr, " create_val: %p\n", v);
|
530
|
+
|
531
|
+
SetFuncs[s->dtype][NM_ROBJ](1, v, 0, &val, 0);
|
532
|
+
|
533
|
+
if (!memcmp(ls->default_val, v, nm_sizeof[s->dtype])) {
|
534
|
+
// User asked to insert default_value, which is actually node *removal*.
|
535
|
+
// So let's do that instead.
|
536
|
+
|
537
|
+
rm = list_storage_remove( ls, coords );
|
538
|
+
|
539
|
+
//if (rm) fprintf(stderr, " remove_val: %p\n", rm);
|
540
|
+
|
541
|
+
if (rm) free(rm);
|
542
|
+
return val;
|
543
|
+
|
544
|
+
} else if (list_storage_insert( ls, coords, v )) return val;
|
545
|
+
return Qnil;
|
546
|
+
// No need to free; the list keeps v.
|
547
|
+
}
|
548
|
+
|
549
|
+
|
550
|
+
|
551
|
+
nm_stype_ins_t InsFuncs = {
|
552
|
+
nm_dense_set,
|
553
|
+
nm_list_set,
|
554
|
+
nm_yale_set,
|
555
|
+
};
|
556
|
+
|
557
|
+
|
558
|
+
|
559
|
+
// Converts a typestring to a typecode for storage. Only looks at the first three characters.
|
560
|
+
int8_t nm_stypestring_to_stype(VALUE str) {
|
561
|
+
int8_t i;
|
562
|
+
for (i = 0; i < S_TYPES; ++i)
|
563
|
+
if ( !strncmp(RSTRING_PTR(str), nm_stypestring[i], 3) ) return i;
|
564
|
+
return S_DENSE;
|
565
|
+
}
|
566
|
+
|
567
|
+
int8_t nm_stypesymbol_to_stype(VALUE sym) {
|
568
|
+
int8_t i;
|
569
|
+
for (i = 0; i < S_TYPES; ++i)
|
570
|
+
if (SYM2ID(sym) == rb_intern(nm_stypestring[i])) return i;
|
571
|
+
return S_DENSE;
|
572
|
+
}
|
573
|
+
|
574
|
+
|
575
|
+
int8_t nm_dtypestring_to_dtype(VALUE str) {
|
576
|
+
int8_t i;
|
577
|
+
for (i = 0; i < NM_TYPES; ++i)
|
578
|
+
if ( !strncmp(RSTRING_PTR(str), nm_dtypestring[i], RSTRING_LEN(str)) ) return i;
|
579
|
+
return NM_NONE;
|
580
|
+
}
|
581
|
+
|
582
|
+
int8_t nm_dtypesymbol_to_dtype(VALUE sym) {
|
583
|
+
int8_t i;
|
584
|
+
for (i = 0; i < NM_TYPES; ++i)
|
585
|
+
if (SYM2ID(sym) == rb_intern(nm_dtypestring[i])) return i;
|
586
|
+
return NM_NONE;
|
587
|
+
}
|
588
|
+
|
589
|
+
|
590
|
+
// TODO: Probably needs some work for Bignum.
|
591
|
+
int8_t nm_guess_dtype(VALUE v) {
|
592
|
+
switch(TYPE(v)) {
|
593
|
+
case T_TRUE:
|
594
|
+
case T_FALSE:
|
595
|
+
return NM_BYTE;
|
596
|
+
case T_STRING:
|
597
|
+
if (RSTRING_LEN(v) == 1) return NM_BYTE;
|
598
|
+
else return NM_NONE;
|
599
|
+
|
600
|
+
#if SIZEOF_INT == 8
|
601
|
+
case T_FIXNUM:
|
602
|
+
return NM_INT64;
|
603
|
+
case T_RATIONAL:
|
604
|
+
return NM_RATIONAL128;
|
605
|
+
#else
|
606
|
+
# if SIZEOF_INT == 4
|
607
|
+
case T_FIXNUM:
|
608
|
+
return NM_INT32;
|
609
|
+
case T_RATIONAL:
|
610
|
+
return NM_RATIONAL64;
|
611
|
+
#else
|
612
|
+
case T_FIXNUM:
|
613
|
+
return NM_INT16;
|
614
|
+
case T_RATIONAL:
|
615
|
+
return NM_RATIONAL32;
|
616
|
+
# endif
|
617
|
+
#endif
|
618
|
+
|
619
|
+
case T_BIGNUM:
|
620
|
+
return NM_INT64;
|
621
|
+
|
622
|
+
#if SIZEOF_FLOAT == 4
|
623
|
+
case T_COMPLEX:
|
624
|
+
return NM_COMPLEX128;
|
625
|
+
case T_FLOAT:
|
626
|
+
return NM_FLOAT64;
|
627
|
+
#else
|
628
|
+
# if SIZEOF_FLOAT == 2
|
629
|
+
case T_COMPLEX:
|
630
|
+
return NM_COMPLEX64;
|
631
|
+
case T_FLOAT:
|
632
|
+
return NM_FLOAT32;
|
633
|
+
# endif
|
634
|
+
#endif
|
635
|
+
|
636
|
+
case T_ARRAY: // may be passed for dense -- for now, just look at the first element.
|
637
|
+
return nm_guess_dtype(RARRAY_PTR(v)[0]);
|
638
|
+
// TODO: Look at entire array for most specific type.
|
639
|
+
|
640
|
+
case T_NIL:
|
641
|
+
default:
|
642
|
+
return NM_NONE;
|
643
|
+
}
|
644
|
+
}
|
645
|
+
|
646
|
+
// Used for scasting (changing stype)
|
647
|
+
inline void cast_copy_value_single(void* to, const void* from, int8_t l_dtype, int8_t r_dtype) {
|
648
|
+
if (l_dtype == r_dtype) memcpy(to, from, nm_sizeof[l_dtype]);
|
649
|
+
else SetFuncs[l_dtype][r_dtype](1, to, 0, from, 0);
|
650
|
+
}
|
651
|
+
|
652
|
+
|
653
|
+
|
654
|
+
// Read the shape argument to NMatrix.new, which may be either an array or a single number.
|
655
|
+
// Second argument is where the shape is stored at the end of the function; returns the rank.
|
656
|
+
// You are responsible for freeing shape!
|
657
|
+
size_t* nm_interpret_shape_arg(VALUE arg, size_t* rank) {
|
658
|
+
size_t i;
|
659
|
+
size_t* shape;
|
660
|
+
|
661
|
+
if (TYPE(arg) == T_ARRAY) {
|
662
|
+
*rank = RARRAY_LEN(arg);
|
663
|
+
shape = ALLOC_N(size_t, *rank);
|
664
|
+
for (i = 0; i < *rank; ++i)
|
665
|
+
shape[i] = (size_t)(FIX2UINT(RARRAY_PTR(arg)[i]));
|
666
|
+
} else if (FIXNUM_P(arg)) {
|
667
|
+
*rank = 2;
|
668
|
+
shape = ALLOC_N(size_t, *rank);
|
669
|
+
for (i = 0; i < *rank; ++i)
|
670
|
+
shape[i] = (size_t)(FIX2UINT(arg));
|
671
|
+
} else {
|
672
|
+
*rank = 0;
|
673
|
+
shape = NULL;
|
674
|
+
rb_raise(rb_eArgError, "Expected an array of numbers or a single fixnum for matrix shape");
|
675
|
+
}
|
676
|
+
|
677
|
+
return shape;
|
678
|
+
}
|
679
|
+
|
680
|
+
|
681
|
+
// argv will be either 1 or 2 elements. If 1, could be either initial or dtype. If 2, is initial and dtype.
|
682
|
+
// This function returns the dtype.
|
683
|
+
int8_t nm_interpret_dtype(int argc, VALUE* argv, int8_t stype) {
|
684
|
+
int offset = 0; // if argc == 1
|
685
|
+
if (argc == 2) offset = 1;
|
686
|
+
else if (argc != 1) rb_raise(rb_eArgError, "Need an initial value or a dtype");
|
687
|
+
|
688
|
+
if (SYMBOL_P(argv[offset])) return nm_dtypesymbol_to_dtype(argv[offset]);
|
689
|
+
else if (IS_STRING(argv[offset])) return nm_dtypestring_to_dtype(StringValue(argv[offset]));
|
690
|
+
else if (stype == S_YALE) rb_raise(rb_eArgError, "yale requires dtype");
|
691
|
+
else return nm_guess_dtype(argv[0]);
|
692
|
+
|
693
|
+
return NM_NONE;
|
694
|
+
}
|
695
|
+
|
696
|
+
int8_t nm_interpret_stype(VALUE arg) {
|
697
|
+
if (SYMBOL_P(arg)) return nm_stypesymbol_to_stype(arg);
|
698
|
+
else if (IS_STRING(arg)) return nm_stypestring_to_stype(StringValue(arg));
|
699
|
+
else rb_raise(rb_eArgError, "Expected storage type");
|
700
|
+
return S_DENSE;
|
701
|
+
}
|
702
|
+
|
703
|
+
|
704
|
+
void* nm_interpret_initial_value(VALUE arg, int8_t dtype) {
|
705
|
+
void* init_val;
|
706
|
+
|
707
|
+
if (TYPE(arg) == T_ARRAY) { // array
|
708
|
+
init_val = ALLOC_N(char, nm_sizeof[dtype] * RARRAY_LEN(arg));
|
709
|
+
SetFuncs[dtype][NM_ROBJ](RARRAY_LEN(arg), init_val, nm_sizeof[dtype], RARRAY_PTR(arg), nm_sizeof[NM_ROBJ]);
|
710
|
+
} else { // single value
|
711
|
+
init_val = ALLOC_N(char, nm_sizeof[dtype]);
|
712
|
+
SetFuncs[dtype][NM_ROBJ](1, init_val, 0, &arg, 0);
|
713
|
+
}
|
714
|
+
|
715
|
+
return init_val;
|
716
|
+
}
|
717
|
+
|
718
|
+
|
719
|
+
size_t* nm_interpret_initial_capacity(VALUE arg) {
|
720
|
+
size_t* init_cap = ALLOC(size_t);
|
721
|
+
*init_cap = FIX2UINT(arg);
|
722
|
+
return init_cap;
|
723
|
+
}
|
724
|
+
|
725
|
+
|
726
|
+
/*
|
727
|
+
* Create a new NMatrix.
|
728
|
+
*
|
729
|
+
* There are several ways to do this. At a minimum, dimensions and either a dtype or initial values are needed, e.g.,
|
730
|
+
*
|
731
|
+
* NMatrix.new(3, :int64) # square 3x3 dense matrix
|
732
|
+
* NMatrix.new([3,4], :float32) # 3x4 matrix
|
733
|
+
* NMatrix.new(3, 0) # 3x3 dense matrix initialized to all zeros
|
734
|
+
* NMatrix.new([3,3], [1,2,3]) # [[1,2,3],[1,2,3],[1,2,3]]
|
735
|
+
*
|
736
|
+
* NMatrix will try to guess the dtype from the first value in the initial values array.
|
737
|
+
*
|
738
|
+
* You can also provide the stype prior to the dimensions. However, non-dense matrices cannot take initial values, and
|
739
|
+
* require a dtype (e.g., :int64):
|
740
|
+
*
|
741
|
+
* NMatrix.new(:yale, [4,3], :int64)
|
742
|
+
* NMatrix.new(:list, 5, :rational128)
|
743
|
+
*
|
744
|
+
* Finally, you can be extremely specific, and define a matrix very exactly:
|
745
|
+
*
|
746
|
+
* NMatrix.new(:dense, [2,2,2], [0,1,2,3,4,5,6,7], :int8)
|
747
|
+
*
|
748
|
+
* Just be careful! There are no overflow warnings in NMatrix.
|
749
|
+
*/
|
750
|
+
static VALUE nm_init(int argc, VALUE* argv, VALUE nm) {
|
751
|
+
char ZERO = 0;
|
752
|
+
VALUE QNIL = Qnil;
|
753
|
+
int8_t dtype, stype, offset = 0;
|
754
|
+
size_t rank;
|
755
|
+
size_t* shape;
|
756
|
+
size_t init_val_len = 0;
|
757
|
+
void* init_val = NULL;
|
758
|
+
NMATRIX* nmatrix;
|
759
|
+
|
760
|
+
// READ ARGUMENTS
|
761
|
+
|
762
|
+
//fprintf(stderr, "Called nmatrix new with %d arguments\n", argc);
|
763
|
+
|
764
|
+
if (argc < 2 || argc > 4) { rb_raise(rb_eArgError, "Expected 2, 3, or 4 arguments"); return Qnil; }
|
765
|
+
|
766
|
+
if (!SYMBOL_P(argv[0]) && !IS_STRING(argv[0])) {
|
767
|
+
stype = S_DENSE;
|
768
|
+
} else {
|
769
|
+
stype = nm_interpret_stype(argv[0]); // 0: String or Symbol
|
770
|
+
offset = 1;
|
771
|
+
}
|
772
|
+
shape = nm_interpret_shape_arg(argv[offset], &rank); // 1: String or Symbol
|
773
|
+
dtype = nm_interpret_dtype(argc-1-offset, argv+offset+1, stype); // 2-3: dtype
|
774
|
+
|
775
|
+
if (IS_NUMERIC(argv[1+offset]) || TYPE(argv[1+offset]) == T_ARRAY) { // initial value provided (could also be initial capacity, if yale)
|
776
|
+
if (stype == S_YALE) {
|
777
|
+
init_val = nm_interpret_initial_capacity(argv[1+offset]);
|
778
|
+
init_val_len = 1;
|
779
|
+
} else {
|
780
|
+
init_val = nm_interpret_initial_value(argv[1+offset], dtype);// 4: initial value / dtype
|
781
|
+
if (TYPE(argv[1+offset]) == T_ARRAY) init_val_len = RARRAY_LEN(argv[1+offset]);
|
782
|
+
else init_val_len = 1;
|
783
|
+
}
|
784
|
+
} else {
|
785
|
+
if (stype == S_DENSE) { // no need to initialize dense with any kind of default value unless it's an NM_ROBJ matrix
|
786
|
+
if (dtype == NM_ROBJ) { // pretend [nil] was passed for ROBJ.
|
787
|
+
init_val = ALLOC(VALUE);
|
788
|
+
SetFuncs[NM_ROBJ][NM_ROBJ](1, init_val, 0, &QNIL, 0);
|
789
|
+
init_val_len = 1;
|
790
|
+
} else init_val = NULL;
|
791
|
+
} else if (stype == S_YALE) { // if it's a list or compressed, we want to assume default of 0 even if none provided
|
792
|
+
init_val = ALLOC(size_t);
|
793
|
+
*(size_t*)init_val = 0;
|
794
|
+
} else {
|
795
|
+
init_val = ALLOC_N(char, nm_sizeof[dtype]);
|
796
|
+
//memset(init_val, 0, nm_sizeof[dtype]); // TODO: See if this works instead of the next line (with NM_ROBJ matrix). Cleaner.
|
797
|
+
SetFuncs[dtype][NM_BYTE](1, init_val, 0, &ZERO, 0);
|
798
|
+
}
|
799
|
+
}
|
800
|
+
|
801
|
+
|
802
|
+
// TODO: Update to allow an array as the initial value.
|
803
|
+
|
804
|
+
if (dtype == NM_NONE) {
|
805
|
+
rb_raise(rb_eArgError, "Could not recognize dtype");
|
806
|
+
free(init_val);
|
807
|
+
free(shape);
|
808
|
+
return nm;
|
809
|
+
}
|
810
|
+
|
811
|
+
if (stype < S_TYPES) {
|
812
|
+
UnwrapNMatrix( nm, nmatrix );
|
813
|
+
|
814
|
+
nmatrix->stype = stype;
|
815
|
+
nmatrix->storage = CreateFuncs[stype](shape, rank, dtype, init_val, init_val_len, nm);
|
816
|
+
|
817
|
+
return nm;
|
818
|
+
} else
|
819
|
+
rb_raise(rb_eNotImpError, "Unrecognized storage type");
|
820
|
+
|
821
|
+
free(shape);
|
822
|
+
free(init_val);
|
823
|
+
return nm;
|
824
|
+
}
|
825
|
+
|
826
|
+
|
827
|
+
static VALUE nm_alloc(VALUE klass) {
|
828
|
+
NMATRIX* mat = ALLOC(NMATRIX);
|
829
|
+
mat->storage = NULL;
|
830
|
+
mat->stype = S_TYPES;
|
831
|
+
return Data_Wrap_Struct(klass, MarkFuncs[mat->stype], nm_delete, mat);
|
832
|
+
}
|
833
|
+
|
834
|
+
|
835
|
+
// This is the "back-door initializer," for when Ruby needs to create the object in an atypical way.
|
836
|
+
//
|
837
|
+
// Note that objects created this way will have NULL storage.
|
838
|
+
/*static VALUE nm_initialize(VALUE self, VALUE stype, VALUE dtype) {
|
839
|
+
NMATRIX* matrix;
|
840
|
+
UnwrapNMatrix(self, matrix);
|
841
|
+
|
842
|
+
matrix->stype = nm_interpret_stype(stype);
|
843
|
+
matrix->dtype = nm_interpret_dtype(1, &dtype, stype);
|
844
|
+
matrix->storage = NULL;
|
845
|
+
|
846
|
+
return self;
|
847
|
+
}*/
|
848
|
+
|
849
|
+
|
850
|
+
static VALUE nm_init_copy(VALUE copy, VALUE original) {
|
851
|
+
NMATRIX *lhs, *rhs;
|
852
|
+
|
853
|
+
CheckNMatrixType(original);
|
854
|
+
|
855
|
+
if (copy == original) return copy;
|
856
|
+
|
857
|
+
UnwrapNMatrix( original, rhs );
|
858
|
+
UnwrapNMatrix( copy, lhs );
|
859
|
+
|
860
|
+
lhs->stype = rhs->stype;
|
861
|
+
|
862
|
+
// Copy the storage
|
863
|
+
lhs->storage = CastCopyFuncs[rhs->stype](rhs->storage, rhs->storage->dtype);
|
864
|
+
|
865
|
+
return copy;
|
866
|
+
}
|
867
|
+
|
868
|
+
|
869
|
+
static VALUE nm_init_cast_copy(VALUE copy, VALUE original, VALUE new_dtype_symbol) {
|
870
|
+
NMATRIX *lhs, *rhs;
|
871
|
+
int8_t new_dtype = nm_dtypesymbol_to_dtype(new_dtype_symbol);
|
872
|
+
//fprintf(stderr,"In copy constructor\n");
|
873
|
+
|
874
|
+
CheckNMatrixType(original);
|
875
|
+
|
876
|
+
if (copy == original) return copy;
|
877
|
+
|
878
|
+
UnwrapNMatrix( original, rhs );
|
879
|
+
UnwrapNMatrix( copy, lhs );
|
880
|
+
|
881
|
+
lhs->stype = rhs->stype;
|
882
|
+
|
883
|
+
// Copy the storage
|
884
|
+
lhs->storage = CastCopyFuncs[rhs->stype](rhs->storage, new_dtype);
|
885
|
+
|
886
|
+
return copy;
|
887
|
+
}
|
888
|
+
|
889
|
+
|
890
|
+
/*
|
891
|
+
* Create a copy of an NMatrix with a different dtype. See also cast.
|
892
|
+
*/
|
893
|
+
// TODO: Deprecate this function and farm it out to scast_copy. as_dtype will still work, but it'll be in pure Ruby and
|
894
|
+
// just use ::cast instead.
|
895
|
+
static VALUE nm_cast_copy(VALUE self, VALUE new_dtype_symbol) {
|
896
|
+
NMATRIX *original, *copy;
|
897
|
+
int8_t new_dtype = nm_dtypesymbol_to_dtype(new_dtype_symbol);
|
898
|
+
|
899
|
+
CheckNMatrixType(self);
|
900
|
+
|
901
|
+
UnwrapNMatrix(self, original);
|
902
|
+
|
903
|
+
copy = ALLOC(NMATRIX);
|
904
|
+
copy->stype = original->stype;
|
905
|
+
copy->storage = CastCopyFuncs[original->stype](original->storage, new_dtype);
|
906
|
+
|
907
|
+
return Data_Wrap_Struct(cNMatrix, MarkFuncs[copy->stype], nm_delete, copy);
|
908
|
+
}
|
909
|
+
|
910
|
+
|
911
|
+
/*
|
912
|
+
* Create a copy of an NMatrix with a different stype and dtype. See also cast.
|
913
|
+
*
|
914
|
+
* m.cast(:dense, :int64)
|
915
|
+
*
|
916
|
+
*/
|
917
|
+
static VALUE nm_scast_copy(VALUE self, VALUE new_stype_symbol, VALUE new_dtype_symbol) {
|
918
|
+
NMATRIX* original, *copy;
|
919
|
+
int8_t new_dtype = nm_dtypesymbol_to_dtype(new_dtype_symbol);
|
920
|
+
int8_t new_stype = nm_stypesymbol_to_stype(new_stype_symbol);
|
921
|
+
|
922
|
+
CheckNMatrixType(self);
|
923
|
+
|
924
|
+
UnwrapNMatrix(self, original);
|
925
|
+
|
926
|
+
copy = ALLOC(NMATRIX);
|
927
|
+
copy->stype = new_stype;
|
928
|
+
|
929
|
+
// Copy and scast the storage.
|
930
|
+
if (new_stype == original->stype) copy->storage = CastCopyFuncs[original->stype](original->storage, new_dtype);
|
931
|
+
else copy->storage = ScastCopyFuncs[copy->stype][original->stype](original->storage, new_dtype);
|
932
|
+
|
933
|
+
return Data_Wrap_Struct(cNMatrix, MarkFuncs[copy->stype], nm_delete, copy);
|
934
|
+
}
|
935
|
+
|
936
|
+
|
937
|
+
|
938
|
+
// Cast a single matrix to a new dtype (unless it's already casted, then just return it). Helper for binary_storage_cast_alloc.
|
939
|
+
static inline STORAGE* storage_cast_alloc(NMATRIX* matrix, int8_t new_dtype) {
|
940
|
+
if (matrix->storage->dtype == new_dtype) return matrix->storage;
|
941
|
+
else return CastCopyFuncs[matrix->stype](matrix->storage, new_dtype);
|
942
|
+
}
|
943
|
+
|
944
|
+
|
945
|
+
// Cast a pair of matrices for a binary operation to a new dtype (which this function determines). Technically, only
|
946
|
+
// does an actual cast on matrices that are the wrong dtype; otherwise returns a reference to the original. Bear this in
|
947
|
+
// mind when freeing memory!
|
948
|
+
static inline STORAGE_PAIR binary_storage_cast_alloc(NMATRIX* left_matrix, NMATRIX* right_matrix) {
|
949
|
+
STORAGE_PAIR casted;
|
950
|
+
int8_t new_dtype = Upcast[left_matrix->storage->dtype][right_matrix->storage->dtype];
|
951
|
+
|
952
|
+
casted.left = storage_cast_alloc(left_matrix, new_dtype);
|
953
|
+
casted.right = storage_cast_alloc(right_matrix, new_dtype);
|
954
|
+
|
955
|
+
return casted;
|
956
|
+
}
|
957
|
+
|
958
|
+
/*
|
959
|
+
* Equality operator. Returns a single true or false value indicating whether the matrices are equivalent.
|
960
|
+
*
|
961
|
+
* For elementwise, use == instead.
|
962
|
+
*
|
963
|
+
* This method will raise an exception if dimensions do not match.
|
964
|
+
*/
|
965
|
+
static VALUE nm_eqeq(VALUE left, VALUE right) {
|
966
|
+
bool result;
|
967
|
+
NMATRIX *l, *r;
|
968
|
+
STORAGE_PAIR casted;
|
969
|
+
|
970
|
+
CheckNMatrixType(left);
|
971
|
+
CheckNMatrixType(right);
|
972
|
+
|
973
|
+
UnwrapNMatrix(left, l);
|
974
|
+
UnwrapNMatrix(right, r);
|
975
|
+
|
976
|
+
if (l->stype != r->stype) //rb_raise(nm_eStorageTypeError, "wrong storage type");
|
977
|
+
rb_raise(rb_eNotImpError, "comparison between different matrix stypes not yet implemented");
|
978
|
+
|
979
|
+
casted = binary_storage_cast_alloc(l, r);
|
980
|
+
|
981
|
+
result = EqEqFuncs[l->stype](casted.left, casted.right);
|
982
|
+
|
983
|
+
// Free any casted-storage we created for the comparison.
|
984
|
+
// TODO: Can we make the Ruby GC take care of this stuff now that we're using it?
|
985
|
+
// If we did that, we night not have to re-create these every time, right? Or wrong? Need to do
|
986
|
+
// more research.
|
987
|
+
if (l->storage != casted.left) DeleteFuncs[l->stype](casted.left);
|
988
|
+
if (r->storage != casted.right) DeleteFuncs[l->stype](casted.right);
|
989
|
+
|
990
|
+
return result ? Qtrue : Qfalse;
|
991
|
+
}
|
992
|
+
|
993
|
+
|
994
|
+
static VALUE multiply_matrix(NMATRIX* left, NMATRIX* right) {
|
995
|
+
///TODO: multiplication for non-dense and/or non-decimal matrices
|
996
|
+
size_t* resulting_shape = ALLOC_N(size_t, 2);
|
997
|
+
NMATRIX* result;
|
998
|
+
bool vector = false;
|
999
|
+
|
1000
|
+
// Make sure both of our matrices are of the correct type.
|
1001
|
+
STORAGE_PAIR casted = binary_storage_cast_alloc(left, right);
|
1002
|
+
|
1003
|
+
resulting_shape[0] = left->storage->shape[0];
|
1004
|
+
resulting_shape[1] = right->storage->shape[1];
|
1005
|
+
|
1006
|
+
// Sometimes we only need to use matrix-vector multiplication (e.g., GEMM versus GEMV). Find out.
|
1007
|
+
if (resulting_shape[1] == 1) vector = true;
|
1008
|
+
|
1009
|
+
result = CastedMultiplyFuncs[left->stype](casted, resulting_shape, vector);
|
1010
|
+
|
1011
|
+
// Free any casted-storage we created for the multiplication.
|
1012
|
+
// TODO: Can we make the Ruby GC take care of this stuff now that we're using it?
|
1013
|
+
// If we did that, we night not have to re-create these every time, right? Or wrong? Need to do
|
1014
|
+
// more research.
|
1015
|
+
if (left->storage != casted.left) DeleteFuncs[left->stype](casted.left);
|
1016
|
+
if (right->storage != casted.right) DeleteFuncs[left->stype](casted.right);
|
1017
|
+
|
1018
|
+
if (result) return Data_Wrap_Struct(cNMatrix, MarkFuncs[result->stype], nm_delete, result);
|
1019
|
+
return Qnil; // Only if we try to multiply list matrices should we return Qnil.
|
1020
|
+
}
|
1021
|
+
|
1022
|
+
|
1023
|
+
static VALUE multiply_scalar(NMATRIX* left, VALUE scalar) {
|
1024
|
+
rb_raise(rb_eNotImpError, "matrix-scalar multiplication not implemented yet");
|
1025
|
+
return Qnil;
|
1026
|
+
}
|
1027
|
+
|
1028
|
+
|
1029
|
+
/*
|
1030
|
+
* Matrix multiply (dot product): against another matrix or a vector.
|
1031
|
+
*
|
1032
|
+
* For elementwise, use * instead.
|
1033
|
+
*
|
1034
|
+
* The two matrices must be of the same stype (for now). If dtype differs, an upcast will occur.
|
1035
|
+
*/
|
1036
|
+
static VALUE nm_multiply(VALUE left_v, VALUE right_v) {
|
1037
|
+
NMATRIX *left, *right;
|
1038
|
+
|
1039
|
+
// left has to be of type NMatrix.
|
1040
|
+
CheckNMatrixType(left_v);
|
1041
|
+
|
1042
|
+
UnwrapNMatrix( left_v, left );
|
1043
|
+
|
1044
|
+
if (IS_NUMERIC(right_v))
|
1045
|
+
return multiply_scalar(left, right_v);
|
1046
|
+
|
1047
|
+
else if (TYPE(right_v) == T_ARRAY)
|
1048
|
+
rb_raise(rb_eNotImpError, "for matrix-vector multiplication, please use an NVector instead of an Array for now");
|
1049
|
+
|
1050
|
+
//if (RDATA(right_v)->dfree != (RUBY_DATA_FUNC)nm_delete) {
|
1051
|
+
else if (TYPE(right_v) == T_DATA && RDATA(right_v)->dfree == (RUBY_DATA_FUNC)nm_delete) { // both are matrices
|
1052
|
+
UnwrapNMatrix( right_v, right );
|
1053
|
+
|
1054
|
+
if (left->storage->shape[1] != right->storage->shape[0])
|
1055
|
+
rb_raise(rb_eArgError, "incompatible dimensions");
|
1056
|
+
|
1057
|
+
if (left->stype != right->stype)
|
1058
|
+
rb_raise(rb_eNotImpError, "matrices must have same stype");
|
1059
|
+
|
1060
|
+
return multiply_matrix(left, right);
|
1061
|
+
|
1062
|
+
} else rb_raise(rb_eTypeError, "expected right operand to be NMatrix, NVector, or single numeric value");
|
1063
|
+
|
1064
|
+
return Qnil;
|
1065
|
+
}
|
1066
|
+
|
1067
|
+
|
1068
|
+
static VALUE nm_elementwise(VALUE leftv, VALUE rightv, char op) {
|
1069
|
+
///TODO: multiplication for non-dense and/or non-decimal matrices
|
1070
|
+
NMATRIX *result, *left, *right;
|
1071
|
+
STORAGE_PAIR casted;
|
1072
|
+
|
1073
|
+
CheckNMatrixType(leftv);
|
1074
|
+
CheckNMatrixType(rightv);
|
1075
|
+
|
1076
|
+
UnwrapNMatrix(rightv, right);
|
1077
|
+
UnwrapNMatrix(leftv, left);
|
1078
|
+
|
1079
|
+
// Make sure both of our matrices are of the correct type.
|
1080
|
+
casted = binary_storage_cast_alloc(left, right);
|
1081
|
+
|
1082
|
+
result = CastedElementwiseFuncs[left->stype](casted, op);
|
1083
|
+
|
1084
|
+
// Free up temporary casted matrices
|
1085
|
+
if (left->storage != casted.left) DeleteFuncs[left->stype](casted.left);
|
1086
|
+
if (right->storage != casted.right) DeleteFuncs[left->stype](casted.right);
|
1087
|
+
|
1088
|
+
if (result) return Data_Wrap_Struct(cNMatrix, MarkFuncs[result->stype], nm_delete, result);
|
1089
|
+
return Qnil; // Only if we try to multiply list matrices should we return Qnil.
|
1090
|
+
}
|
1091
|
+
|
1092
|
+
|
1093
|
+
/*
|
1094
|
+
* Matrix element-wise addition.
|
1095
|
+
*
|
1096
|
+
* The two matrices must be of the same stype (for now). If dtype differs, an upcast will occur.
|
1097
|
+
*
|
1098
|
+
* Not available for list matrices. You should cast to a yale or dense matrix first.
|
1099
|
+
*/
|
1100
|
+
static VALUE nm_ew_add(VALUE left, VALUE right) {
|
1101
|
+
return nm_elementwise(left, right, '+');
|
1102
|
+
}
|
1103
|
+
|
1104
|
+
/*
|
1105
|
+
* Matrix element-wise subtraction.
|
1106
|
+
*
|
1107
|
+
* The two matrices must be of the same stype (for now). If dtype differs, an upcast will occur.
|
1108
|
+
*
|
1109
|
+
* Not available for list matrices. You should cast to a yale or dense matrix first.
|
1110
|
+
*/
|
1111
|
+
static VALUE nm_ew_subtract(VALUE left, VALUE right) {
|
1112
|
+
return nm_elementwise(left, right, '-');
|
1113
|
+
}
|
1114
|
+
|
1115
|
+
/*
|
1116
|
+
* Matrix element-wise multiplication.
|
1117
|
+
*
|
1118
|
+
* The two matrices must be of the same stype (for now). If dtype differs, an upcast will occur.
|
1119
|
+
*
|
1120
|
+
* Not available for list matrices. You should cast to a yale or dense matrix first.
|
1121
|
+
*
|
1122
|
+
* For dot product, use +dot+ instead.
|
1123
|
+
*/
|
1124
|
+
static VALUE nm_ew_multiply(VALUE left, VALUE right) {
|
1125
|
+
return nm_elementwise(left, right, '*');
|
1126
|
+
}
|
1127
|
+
|
1128
|
+
/*
|
1129
|
+
* Matrix element-wise division.
|
1130
|
+
*
|
1131
|
+
* The two matrices must be of the same stype (for now). If dtype differs, an upcast will occur.
|
1132
|
+
*
|
1133
|
+
* Not available for list matrices. You should cast to a yale or dense matrix first.
|
1134
|
+
*/
|
1135
|
+
static VALUE nm_ew_divide(VALUE left, VALUE right) {
|
1136
|
+
return nm_elementwise(left, right, '/');
|
1137
|
+
}
|
1138
|
+
|
1139
|
+
|
1140
|
+
/*
|
1141
|
+
* Matrix element-wise comparison (equality) operator.
|
1142
|
+
*
|
1143
|
+
* The two matrices must be of the same stype (for now). If dtype differs, an upcast will occur.
|
1144
|
+
*
|
1145
|
+
* Not available for list matrices. You should cast to a yale or dense matrix first.
|
1146
|
+
*
|
1147
|
+
* Note that the matrix returned will be of the same dtype as the upcast of the input matrices. If that's not what you
|
1148
|
+
* want, use +cast+.
|
1149
|
+
*/
|
1150
|
+
static VALUE nm_ew_eqeq(VALUE left, VALUE right) {
|
1151
|
+
return nm_elementwise(left, right, NM_OP_EQEQ);
|
1152
|
+
}
|
1153
|
+
|
1154
|
+
/*
|
1155
|
+
* Matrix element-wise less-than-or-equals operator.
|
1156
|
+
*
|
1157
|
+
* The two matrices must be of the same stype (for now). If dtype differs, an upcast will occur.
|
1158
|
+
*
|
1159
|
+
* Not available for list matrices. You should cast to a yale or dense matrix first.
|
1160
|
+
*
|
1161
|
+
* Note that the matrix returned will be of the same dtype as the upcast of the input matrices. If that's not what you
|
1162
|
+
* want, use +cast+.
|
1163
|
+
*/
|
1164
|
+
static VALUE nm_ew_leq(VALUE left, VALUE right) {
|
1165
|
+
return nm_elementwise(left, right, NM_OP_LTE);
|
1166
|
+
}
|
1167
|
+
|
1168
|
+
|
1169
|
+
/*
|
1170
|
+
* Matrix element-wise greater-than-or-equals operator.
|
1171
|
+
*
|
1172
|
+
* The two matrices must be of the same stype (for now). If dtype differs, an upcast will occur.
|
1173
|
+
*
|
1174
|
+
* Not available for list matrices. You should cast to a yale or dense matrix first.
|
1175
|
+
*
|
1176
|
+
* Note that the matrix returned will be of the same dtype as the upcast of the input matrices. If that's not what you
|
1177
|
+
* want, use +cast+.
|
1178
|
+
*/
|
1179
|
+
static VALUE nm_ew_geq(VALUE left, VALUE right) {
|
1180
|
+
return nm_elementwise(left, right, NM_OP_GTE);
|
1181
|
+
}
|
1182
|
+
|
1183
|
+
|
1184
|
+
/*
|
1185
|
+
* Matrix element-wise strictly-less-than operator.
|
1186
|
+
*
|
1187
|
+
* The two matrices must be of the same stype (for now). If dtype differs, an upcast will occur.
|
1188
|
+
*
|
1189
|
+
* Not available for list matrices. You should cast to a yale or dense matrix first.
|
1190
|
+
*
|
1191
|
+
* Note that the matrix returned will be of the same dtype as the upcast of the input matrices. If that's not what you
|
1192
|
+
* want, use +cast+.
|
1193
|
+
*/
|
1194
|
+
static VALUE nm_ew_lt(VALUE left, VALUE right) {
|
1195
|
+
return nm_elementwise(left, right, '<');
|
1196
|
+
}
|
1197
|
+
|
1198
|
+
|
1199
|
+
/*
|
1200
|
+
* Matrix element-wise strictly-greater-than operator.
|
1201
|
+
*
|
1202
|
+
* The two matrices must be of the same stype (for now). If dtype differs, an upcast will occur.
|
1203
|
+
*
|
1204
|
+
* Not available for list matrices. You should cast to a yale or dense matrix first.
|
1205
|
+
*
|
1206
|
+
* Note that the matrix returned will be of the same dtype as the upcast of the input matrices. If that's not what you
|
1207
|
+
* want, use +cast+.
|
1208
|
+
*/
|
1209
|
+
static VALUE nm_ew_gt(VALUE left, VALUE right) {
|
1210
|
+
return nm_elementwise(left, right, '>');
|
1211
|
+
}
|
1212
|
+
|
1213
|
+
|
1214
|
+
/*
|
1215
|
+
* Matrix element-wise inequality operator.
|
1216
|
+
*
|
1217
|
+
* The two matrices must be of the same stype (for now). If dtype differs, an upcast will occur.
|
1218
|
+
*
|
1219
|
+
* Not available for list matrices. You should cast to a yale or dense matrix first.
|
1220
|
+
*
|
1221
|
+
* Note that the matrix returned will be of the same dtype as the upcast of the input matrices. If that's not what you
|
1222
|
+
* want, use +cast+.
|
1223
|
+
*/
|
1224
|
+
static VALUE nm_ew_neq(VALUE left, VALUE right) {
|
1225
|
+
return nm_elementwise(left, right, NM_OP_NEQ);
|
1226
|
+
}
|
1227
|
+
|
1228
|
+
|
1229
|
+
// Borrowed this function from NArray. Handles 'each' iteration on a dense matrix.
|
1230
|
+
//
|
1231
|
+
// Additionally, handles separately matrices containing VALUEs and matrices containing
|
1232
|
+
// other types of data.
|
1233
|
+
static VALUE nm_dense_each(VALUE nmatrix) {
|
1234
|
+
DENSE_STORAGE* s = (DENSE_STORAGE*)(NM_STORAGE(nmatrix));
|
1235
|
+
VALUE v;
|
1236
|
+
size_t i;
|
1237
|
+
|
1238
|
+
void (*copy)();
|
1239
|
+
|
1240
|
+
if (NM_DTYPE(nmatrix) == NM_ROBJ) {
|
1241
|
+
|
1242
|
+
// matrix of Ruby objects -- yield directly
|
1243
|
+
for (i = 0; i < count_dense_storage_elements(s); ++i)
|
1244
|
+
rb_yield( *((VALUE*)((char*)(s->elements) + i*nm_sizeof[NM_DTYPE(nmatrix)])) );
|
1245
|
+
|
1246
|
+
} else {
|
1247
|
+
// We're going to copy the matrix element into a Ruby VALUE and then operate on it.
|
1248
|
+
copy = SetFuncs[NM_ROBJ][NM_DTYPE(nmatrix)];
|
1249
|
+
|
1250
|
+
for (i = 0; i < count_dense_storage_elements(s); ++i) {
|
1251
|
+
(*copy)(1, &v, 0, (char*)(s->elements) + i*nm_sizeof[NM_DTYPE(nmatrix)], 0);
|
1252
|
+
rb_yield(v); // yield to the copy we made
|
1253
|
+
}
|
1254
|
+
}
|
1255
|
+
|
1256
|
+
return nmatrix;
|
1257
|
+
}
|
1258
|
+
|
1259
|
+
|
1260
|
+
/*
|
1261
|
+
* Iterate over the matrix as you would an Enumerable (e.g., Array).
|
1262
|
+
*
|
1263
|
+
* Currently only works for dense.
|
1264
|
+
*/
|
1265
|
+
static VALUE nm_each(VALUE nmatrix) {
|
1266
|
+
volatile VALUE nm = nmatrix; // not sure why we do this, but it gets done in ruby's array.c.
|
1267
|
+
|
1268
|
+
switch(NM_STYPE(nm)) {
|
1269
|
+
case S_DENSE:
|
1270
|
+
return nm_dense_each(nm);
|
1271
|
+
default:
|
1272
|
+
rb_raise(rb_eNotImpError, "only dense each works right now");
|
1273
|
+
}
|
1274
|
+
}
|
1275
|
+
|
1276
|
+
|
1277
|
+
// Does not create storage, but does destroy it.
|
1278
|
+
NMATRIX* nm_create(int8_t stype, void* storage) {
|
1279
|
+
NMATRIX* mat = ALLOC(NMATRIX);
|
1280
|
+
|
1281
|
+
mat->stype = stype;
|
1282
|
+
mat->storage = storage;
|
1283
|
+
|
1284
|
+
return mat;
|
1285
|
+
}
|
1286
|
+
|
1287
|
+
|
1288
|
+
static size_t* convert_coords(size_t rank, VALUE* c, VALUE self) {
|
1289
|
+
size_t r;
|
1290
|
+
size_t* coords = ALLOC_N(size_t,rank);
|
1291
|
+
|
1292
|
+
for (r = 0; r < rank; ++r) {
|
1293
|
+
coords[r] = FIX2UINT(c[r]);
|
1294
|
+
if (coords[r] >= NM_SHAPE(self,r)) rb_raise(rb_eArgError, "out of range");
|
1295
|
+
}
|
1296
|
+
|
1297
|
+
return coords;
|
1298
|
+
}
|
1299
|
+
|
1300
|
+
|
1301
|
+
/*
|
1302
|
+
* Access the contents of an NMatrix at given coordinates.
|
1303
|
+
*
|
1304
|
+
* n[3,3] # => 5.0
|
1305
|
+
*
|
1306
|
+
*/
|
1307
|
+
VALUE nm_mref(int argc, VALUE* argv, VALUE self) {
|
1308
|
+
VALUE v;
|
1309
|
+
|
1310
|
+
if (NM_RANK(self) == (size_t)(argc)) {
|
1311
|
+
|
1312
|
+
SetFuncs[NM_ROBJ][NM_DTYPE(self)](1, &v, 0,
|
1313
|
+
RefFuncs[NM_STYPE(self)](NM_STORAGE(self),
|
1314
|
+
convert_coords((size_t)(argc), argv, self)
|
1315
|
+
), 0);
|
1316
|
+
return v;
|
1317
|
+
|
1318
|
+
} else if (NM_RANK(self) < (size_t)(argc)) {
|
1319
|
+
rb_raise(rb_eArgError, "Coordinates given exceed matrix rank");
|
1320
|
+
} else {
|
1321
|
+
rb_raise(rb_eNotImpError, "Slicing not supported yet");
|
1322
|
+
}
|
1323
|
+
return Qnil;
|
1324
|
+
}
|
1325
|
+
|
1326
|
+
|
1327
|
+
/*
|
1328
|
+
* Modify the contents of an NMatrix in the given cell
|
1329
|
+
*
|
1330
|
+
* n[3,3] = 5.0
|
1331
|
+
*
|
1332
|
+
* Also returns the new contents, so you can chain:
|
1333
|
+
*
|
1334
|
+
* n[3,3] = n[2,3] = 5.0
|
1335
|
+
*/
|
1336
|
+
VALUE nm_mset(int argc, VALUE* argv, VALUE self) {
|
1337
|
+
size_t rank = argc - 1; // last arg is the value
|
1338
|
+
|
1339
|
+
if (argc <= 1) {
|
1340
|
+
rb_raise(rb_eArgError, "Expected coordinates and r-value");
|
1341
|
+
|
1342
|
+
} else if (NM_RANK(self) == rank) {
|
1343
|
+
return (*(InsFuncs[NM_STYPE(self)]))( NM_STORAGE(self),
|
1344
|
+
convert_coords(rank, argv, self),
|
1345
|
+
argv[rank] );
|
1346
|
+
|
1347
|
+
} else if (NM_RANK(self) < rank) {
|
1348
|
+
rb_raise(rb_eArgError, "Coordinates given exceed matrix rank");
|
1349
|
+
} else {
|
1350
|
+
rb_raise(rb_eNotImpError, "Slicing not supported yet");
|
1351
|
+
}
|
1352
|
+
return Qnil;
|
1353
|
+
}
|
1354
|
+
|
1355
|
+
|
1356
|
+
/*
|
1357
|
+
* Get the rank of an NMatrix (the number of dimensions).
|
1358
|
+
*
|
1359
|
+
* In other words, if you set your matrix to be 3x4, the rank is 2. If the matrix was initialized as 3x4x3, the rank
|
1360
|
+
* is 3.
|
1361
|
+
*
|
1362
|
+
* This function may lie slightly for NVectors, which are internally stored as rank 2 (and have an orientation), but
|
1363
|
+
* act as if they're rank 1.
|
1364
|
+
*/
|
1365
|
+
VALUE nm_rank(VALUE self) {
|
1366
|
+
VALUE ret;
|
1367
|
+
SetFuncs[NM_ROBJ][NM_INT64]( 1, &ret, 0, &(NM_STORAGE(self)->rank), 0 );
|
1368
|
+
return ret;
|
1369
|
+
}
|
1370
|
+
|
1371
|
+
|
1372
|
+
/*
|
1373
|
+
* Get the shape (dimensions) of a matrix.
|
1374
|
+
*/
|
1375
|
+
VALUE nm_shape(VALUE self) {
|
1376
|
+
STORAGE* s = NM_STORAGE(self);
|
1377
|
+
|
1378
|
+
// Copy elements into a VALUE array and then use those to create a Ruby array with rb_ary_new4.
|
1379
|
+
VALUE* shape = ALLOCA_N(VALUE, s->rank);
|
1380
|
+
SetFuncs[NM_ROBJ][NM_SIZE_T]( s->rank, shape, sizeof(VALUE), s->shape, sizeof(size_t));
|
1381
|
+
|
1382
|
+
return rb_ary_new4(s->rank, shape);
|
1383
|
+
}
|
1384
|
+
|
1385
|
+
|
1386
|
+
/*
|
1387
|
+
* Get the storage type (stype) of a matrix, e.g., :yale, :dense, or :list.
|
1388
|
+
*/
|
1389
|
+
static VALUE nm_stype(VALUE self) {
|
1390
|
+
ID stype = rb_intern(nm_stypestring[NM_STYPE(self)]);
|
1391
|
+
return ID2SYM(stype);
|
1392
|
+
}
|
1393
|
+
|
1394
|
+
|
1395
|
+
/*
|
1396
|
+
* Get the data type (dtype) of a matrix, e.g., :byte, :int8, :int16, :int32, :int64, :float32, :float64, :complex64,
|
1397
|
+
* :complex128, :rational32, :rational64, :rational128, or :object (the last is a Ruby object).
|
1398
|
+
*/
|
1399
|
+
static VALUE nm_dtype(VALUE self) {
|
1400
|
+
ID dtype = rb_intern(nm_dtypestring[NM_DTYPE(self)]);
|
1401
|
+
return ID2SYM(dtype);
|
1402
|
+
}
|
1403
|
+
|
1404
|
+
|
1405
|
+
/* Interprets cblas argument which could be any of false/:no_transpose, :transpose, or :complex_conjugate,
|
1406
|
+
* into an enum recognized by cblas.
|
1407
|
+
*
|
1408
|
+
* Called by nm_cblas_gemm -- basically inline.
|
1409
|
+
*
|
1410
|
+
*/
|
1411
|
+
static char gemm_op_sym(VALUE op) {
|
1412
|
+
if (op == false || rb_to_id(op) == nm_id_no_transpose) return CblasNoTrans;
|
1413
|
+
else if (rb_to_id(op) == nm_id_transpose) return CblasTrans;
|
1414
|
+
else if (rb_to_id(op) == nm_id_complex_conjugate) return CblasConjTrans;
|
1415
|
+
else rb_raise(rb_eArgError, "Expected false, :transpose, or :complex_conjugate");
|
1416
|
+
return CblasNoTrans;
|
1417
|
+
}
|
1418
|
+
|
1419
|
+
|
1420
|
+
/* Call any of the cblas_xgemm functions as directly as possible.
|
1421
|
+
*
|
1422
|
+
* The cblas_xgemm functions (dgemm, sgemm, cgemm, and zgemm) define the following operation:
|
1423
|
+
*
|
1424
|
+
* C = alpha*op(A)*op(B) + beta*C
|
1425
|
+
*
|
1426
|
+
* where op(X) is one of <tt>op(X) = X</tt>, <tt>op(X) = X**T</tt>, or the complex conjugate of X.
|
1427
|
+
*
|
1428
|
+
* Note that this will only work for dense matrices that are of types :float32, :float64, :complex64, and :complex128.
|
1429
|
+
* Other types are not implemented in BLAS, and while they exist in NMatrix, this method is intended only to
|
1430
|
+
* expose the ultra-optimized ATLAS versions.
|
1431
|
+
*
|
1432
|
+
* == Arguments
|
1433
|
+
* See: http://www.netlib.org/blas/dgemm.f
|
1434
|
+
*
|
1435
|
+
* You probably don't want to call this function. Instead, why don't you try cblas_gemm, which is more flexible
|
1436
|
+
* with its arguments?
|
1437
|
+
*
|
1438
|
+
* This function does almost no type checking. Seriously, be really careful when you call it! There's no exception
|
1439
|
+
* handling, so you can easily crash Ruby!
|
1440
|
+
*/
|
1441
|
+
static VALUE nm_cblas_gemm(VALUE self,
|
1442
|
+
VALUE trans_a, VALUE trans_b,
|
1443
|
+
VALUE m, VALUE n, VALUE k,
|
1444
|
+
VALUE alpha,
|
1445
|
+
VALUE a, VALUE lda,
|
1446
|
+
VALUE b, VALUE ldb,
|
1447
|
+
VALUE beta,
|
1448
|
+
VALUE c, VALUE ldc)
|
1449
|
+
{
|
1450
|
+
struct cblas_param_t p = cblas_params_for_multiply(((DENSE_STORAGE*)(NM_STORAGE(a))), ((DENSE_STORAGE*)(NM_STORAGE(b))), ((DENSE_STORAGE*)(NM_STORAGE(c))), false);
|
1451
|
+
p.M = FIX2INT(m);
|
1452
|
+
p.N = FIX2INT(n);
|
1453
|
+
p.K = FIX2INT(k);
|
1454
|
+
|
1455
|
+
p.lda = FIX2INT(lda);
|
1456
|
+
p.ldb = FIX2INT(ldb);
|
1457
|
+
p.ldc = FIX2INT(ldc);
|
1458
|
+
|
1459
|
+
switch(NM_DTYPE(c)) {
|
1460
|
+
case NM_FLOAT32:
|
1461
|
+
case NM_FLOAT64:
|
1462
|
+
p.alpha.d[0] = NUM2DBL(alpha);
|
1463
|
+
p.beta.d[0] = NUM2DBL(beta);
|
1464
|
+
break;
|
1465
|
+
|
1466
|
+
case NM_COMPLEX64:
|
1467
|
+
p.alpha.c[0].r = REAL2DBL(alpha);
|
1468
|
+
p.alpha.c[0].i = IMAG2DBL(alpha);
|
1469
|
+
p.beta.c[0].r = REAL2DBL(beta);
|
1470
|
+
p.beta.c[0].i = IMAG2DBL(beta);
|
1471
|
+
break;
|
1472
|
+
|
1473
|
+
case NM_COMPLEX128:
|
1474
|
+
p.alpha.z.r = REAL2DBL(alpha);
|
1475
|
+
p.alpha.z.i = IMAG2DBL(alpha);
|
1476
|
+
p.beta.z.r = REAL2DBL(beta);
|
1477
|
+
p.beta.z.i = IMAG2DBL(beta);
|
1478
|
+
break;
|
1479
|
+
|
1480
|
+
case NM_BYTE:
|
1481
|
+
p.alpha.b[0] = FIX2INT(alpha);
|
1482
|
+
p.beta.b[0] = FIX2INT(beta);
|
1483
|
+
break;
|
1484
|
+
|
1485
|
+
case NM_INT8:
|
1486
|
+
case NM_INT16:
|
1487
|
+
case NM_INT32:
|
1488
|
+
case NM_INT64:
|
1489
|
+
p.alpha.i[0] = FIX2INT(alpha);
|
1490
|
+
p.beta.i[0] = FIX2INT(beta);
|
1491
|
+
break;
|
1492
|
+
|
1493
|
+
case NM_RATIONAL32:
|
1494
|
+
p.alpha.r[0].n = NUMER2INT(alpha);
|
1495
|
+
p.alpha.r[0].d = DENOM2INT(alpha);
|
1496
|
+
p.beta.r[0].n = NUMER2INT(beta);
|
1497
|
+
p.beta.r[0].d = DENOM2INT(beta);
|
1498
|
+
break;
|
1499
|
+
|
1500
|
+
case NM_RATIONAL64:
|
1501
|
+
p.alpha.ra[0].n = NUMER2INT(alpha);
|
1502
|
+
p.alpha.ra[0].d = DENOM2INT(alpha);
|
1503
|
+
p.beta.ra[0].n = NUMER2INT(beta);
|
1504
|
+
p.beta.ra[0].d = DENOM2INT(beta);
|
1505
|
+
break;
|
1506
|
+
|
1507
|
+
case NM_RATIONAL128:
|
1508
|
+
p.alpha.rat.n = NUMER2INT(alpha);
|
1509
|
+
p.alpha.rat.d = DENOM2INT(alpha);
|
1510
|
+
p.beta.rat.n = NUMER2INT(beta);
|
1511
|
+
p.beta.rat.d = DENOM2INT(beta);
|
1512
|
+
break;
|
1513
|
+
|
1514
|
+
case NM_ROBJ:
|
1515
|
+
p.alpha.v[0] = alpha;
|
1516
|
+
p.beta.v[0] = beta;
|
1517
|
+
break;
|
1518
|
+
|
1519
|
+
default:
|
1520
|
+
rb_raise(nm_eDataTypeError, "unexpected dtype");
|
1521
|
+
|
1522
|
+
}
|
1523
|
+
|
1524
|
+
/* fprintf(stderr, "cblas_gemm: %d %d %d %d %d %f %d %d %f %d\n", trans_a_, trans_b_,
|
1525
|
+
m_, n_, k_, alpha_, lda_, ldb_, beta_, ldc_); */
|
1526
|
+
|
1527
|
+
GemmFuncs[NM_DTYPE(c)](CblasRowMajor, gemm_op_sym(trans_a), gemm_op_sym(trans_b), p);
|
1528
|
+
|
1529
|
+
return Qtrue;
|
1530
|
+
}
|
1531
|
+
|
1532
|
+
|
1533
|
+
/* Call any of the cblas_xgemv functions as directly as possible.
|
1534
|
+
*
|
1535
|
+
* The cblas_xgemv functions (dgemv, sgemv, cgemv, and zgemv) define the following operation:
|
1536
|
+
*
|
1537
|
+
* y = alpha*op(A)*x + beta*y
|
1538
|
+
*
|
1539
|
+
* where op(A) is one of <tt>op(A) = A</tt>, <tt>op(A) = A**T</tt>, or the complex conjugate of A.
|
1540
|
+
*
|
1541
|
+
* Note that this will only work for dense matrices that are of types :float32, :float64, :complex64, and :complex128.
|
1542
|
+
* Other types are not implemented in BLAS, and while they exist in NMatrix, this method is intended only to
|
1543
|
+
* expose the ultra-optimized ATLAS versions.
|
1544
|
+
*
|
1545
|
+
* == Arguments
|
1546
|
+
* See: http://www.netlib.org/blas/dgemm.f
|
1547
|
+
*
|
1548
|
+
* You probably don't want to call this function. Instead, why don't you try cblas_gemv, which is more flexible
|
1549
|
+
* with its arguments?
|
1550
|
+
*
|
1551
|
+
* This function does almost no type checking. Seriously, be really careful when you call it! There's no exception
|
1552
|
+
* handling, so you can easily crash Ruby!
|
1553
|
+
*/
|
1554
|
+
static VALUE nm_cblas_gemv(VALUE self,
|
1555
|
+
VALUE trans_a,
|
1556
|
+
VALUE m, VALUE n,
|
1557
|
+
VALUE alpha,
|
1558
|
+
VALUE a, VALUE lda,
|
1559
|
+
VALUE x, VALUE incx,
|
1560
|
+
VALUE beta,
|
1561
|
+
VALUE y, VALUE incy) {
|
1562
|
+
|
1563
|
+
struct cblas_param_t p;
|
1564
|
+
p.M = FIX2INT(m);
|
1565
|
+
p.N = FIX2INT(n);
|
1566
|
+
p.A = ((DENSE_STORAGE*)(NM_STORAGE(a)))->elements;
|
1567
|
+
p.B = ((DENSE_STORAGE*)(NM_STORAGE(x)))->elements;
|
1568
|
+
p.C = ((DENSE_STORAGE*)(NM_STORAGE(y)))->elements;
|
1569
|
+
p.lda = FIX2INT(lda);
|
1570
|
+
p.ldb = FIX2INT(incx);
|
1571
|
+
p.ldc = FIX2INT(incy);
|
1572
|
+
|
1573
|
+
switch(NM_DTYPE(y)) {
|
1574
|
+
case NM_FLOAT32:
|
1575
|
+
case NM_FLOAT64:
|
1576
|
+
p.alpha.d[0] = REAL2DBL(alpha);
|
1577
|
+
p.beta.d[0] = REAL2DBL(beta);
|
1578
|
+
break;
|
1579
|
+
case NM_COMPLEX64:
|
1580
|
+
p.alpha.c[0].r = REAL2DBL(alpha);
|
1581
|
+
p.alpha.c[0].i = IMAG2DBL(alpha);
|
1582
|
+
p.beta.c[0].r = REAL2DBL(beta);
|
1583
|
+
p.beta.c[0].i = IMAG2DBL(beta);
|
1584
|
+
break;
|
1585
|
+
case NM_COMPLEX128:
|
1586
|
+
p.alpha.z.r = REAL2DBL(alpha);
|
1587
|
+
p.alpha.z.i = IMAG2DBL(alpha);
|
1588
|
+
p.beta.z.r = REAL2DBL(beta);
|
1589
|
+
p.beta.z.i = IMAG2DBL(beta);
|
1590
|
+
break;
|
1591
|
+
}
|
1592
|
+
|
1593
|
+
/* fprintf(stderr, "cblas_gemm: %d %d %d %d %d %f %d %d %f %d\n", trans_a_, trans_b_,
|
1594
|
+
m_, n_, k_, alpha_, lda_, ldb_, beta_, ldc_); */
|
1595
|
+
|
1596
|
+
GemvFuncs[NM_DTYPE(y)](CblasRowMajor, gemm_op_sym(trans_a), p);
|
1597
|
+
|
1598
|
+
return Qtrue;
|
1599
|
+
}
|
1600
|
+
|
1601
|
+
|
1602
|
+
/*
|
1603
|
+
* Find the capacity of an NMatrix. The capacity only differs from the size for Yale matrices, which occasionally
|
1604
|
+
* allocate more space than they need. For list and dense, capacity gives the number of elements in the matrix.
|
1605
|
+
*/
|
1606
|
+
static VALUE nm_capacity(VALUE self) {
|
1607
|
+
VALUE cap;
|
1608
|
+
|
1609
|
+
switch(NM_STYPE(self)) {
|
1610
|
+
case S_YALE:
|
1611
|
+
cap = UINT2NUM(((YALE_STORAGE*)(NM_STORAGE(self)))->capacity);
|
1612
|
+
break;
|
1613
|
+
|
1614
|
+
case S_DENSE:
|
1615
|
+
cap = UINT2NUM(count_dense_storage_elements( (DENSE_STORAGE*)(NM_STORAGE(self)) ));
|
1616
|
+
break;
|
1617
|
+
|
1618
|
+
case S_LIST:
|
1619
|
+
cap = UINT2NUM(count_list_storage_elements( (LIST_STORAGE*)(NM_STORAGE(self)) ));
|
1620
|
+
break;
|
1621
|
+
|
1622
|
+
default:
|
1623
|
+
//rb_raise(rb_eNotImpError, "TODO: implement capacity/size on other storage types");
|
1624
|
+
rb_raise(nm_eStorageTypeError, "unrecognized stype");
|
1625
|
+
}
|
1626
|
+
|
1627
|
+
return cap;
|
1628
|
+
}
|
1629
|
+
|
1630
|
+
|
1631
|
+
/*
|
1632
|
+
* Get the size of a Yale matrix (the number of elements actually stored).
|
1633
|
+
*
|
1634
|
+
* For capacity (the maximum number of elements that can be stored without a resize), use capacity instead.
|
1635
|
+
*/
|
1636
|
+
static VALUE nm_yale_size(VALUE self) {
|
1637
|
+
VALUE sz;
|
1638
|
+
YALE_STORAGE* s = (YALE_STORAGE*)NM_STORAGE(self);
|
1639
|
+
|
1640
|
+
if (NM_STYPE(self) != S_YALE) rb_raise(nm_eStorageTypeError, "wrong storage type");
|
1641
|
+
|
1642
|
+
SetFuncs[NM_ROBJ][s->index_dtype](1, &sz, 0, (YALE_SIZE_PTR((s), nm_sizeof[s->index_dtype])), 0);
|
1643
|
+
return sz;
|
1644
|
+
}
|
1645
|
+
|
1646
|
+
|
1647
|
+
/*
|
1648
|
+
* Get the A array of a Yale matrix (which stores the diagonal and the LU portions of the matrix).
|
1649
|
+
*/
|
1650
|
+
static VALUE nm_yale_a(VALUE self) {
|
1651
|
+
y_size_t sz, i;
|
1652
|
+
void* vals;
|
1653
|
+
VALUE ary;
|
1654
|
+
YALE_STORAGE* s = (YALE_STORAGE*)NM_STORAGE(self);
|
1655
|
+
|
1656
|
+
if (NM_STYPE(self) != S_YALE) rb_raise(nm_eStorageTypeError, "wrong storage type");
|
1657
|
+
|
1658
|
+
YaleGetSize(sz, s);
|
1659
|
+
vals = ALLOC_N(char, nm_sizeof[NM_ROBJ]*sz);
|
1660
|
+
|
1661
|
+
SetFuncs[NM_ROBJ][s->dtype](sz, vals, nm_sizeof[NM_ROBJ], s->a, nm_sizeof[s->dtype]);
|
1662
|
+
ary = rb_ary_new4(sz, vals);
|
1663
|
+
|
1664
|
+
for (i = sz; i < s->capacity; ++i)
|
1665
|
+
rb_ary_push(ary, Qnil);
|
1666
|
+
|
1667
|
+
return ary;
|
1668
|
+
}
|
1669
|
+
|
1670
|
+
|
1671
|
+
/*
|
1672
|
+
* Get the diagonal ("D") portion of the A array of a Yale matrix.
|
1673
|
+
*/
|
1674
|
+
static VALUE nm_yale_d(VALUE self) {
|
1675
|
+
y_size_t sz;
|
1676
|
+
void* vals;
|
1677
|
+
VALUE ary;
|
1678
|
+
YALE_STORAGE* s = (YALE_STORAGE*)NM_STORAGE(self);
|
1679
|
+
|
1680
|
+
if (NM_STYPE(self) != S_YALE) rb_raise(nm_eStorageTypeError, "wrong storage type");
|
1681
|
+
|
1682
|
+
YaleGetSize(sz, s);
|
1683
|
+
vals = ALLOC_N(char, nm_sizeof[NM_ROBJ]*s->shape[0]);
|
1684
|
+
|
1685
|
+
SetFuncs[NM_ROBJ][s->dtype](s->shape[0], vals, nm_sizeof[NM_ROBJ], s->a, nm_sizeof[s->dtype]);
|
1686
|
+
ary = rb_ary_new4(s->shape[0], vals);
|
1687
|
+
|
1688
|
+
return ary;
|
1689
|
+
}
|
1690
|
+
|
1691
|
+
|
1692
|
+
/*
|
1693
|
+
* Get the non-diagonal ("LU") portion of the A array of a Yale matrix.
|
1694
|
+
*/
|
1695
|
+
static VALUE nm_yale_lu(VALUE self) {
|
1696
|
+
y_size_t sz, i;
|
1697
|
+
void* vals;
|
1698
|
+
VALUE ary;
|
1699
|
+
YALE_STORAGE* s = (YALE_STORAGE*)NM_STORAGE(self);
|
1700
|
+
|
1701
|
+
if (NM_STYPE(self) != S_YALE) rb_raise(nm_eStorageTypeError, "wrong storage type");
|
1702
|
+
|
1703
|
+
YaleGetSize(sz, s);
|
1704
|
+
vals = ALLOC_N(char, nm_sizeof[NM_ROBJ]*(s->capacity - s->shape[0]));
|
1705
|
+
|
1706
|
+
SetFuncs[NM_ROBJ][s->dtype](sz - s->shape[0] - 1, vals, nm_sizeof[NM_ROBJ], (char*)(s->a) + (s->shape[0] + 1)*nm_sizeof[s->dtype], nm_sizeof[s->dtype]);
|
1707
|
+
ary = rb_ary_new4(sz - s->shape[0] - 1, vals);
|
1708
|
+
|
1709
|
+
for (i = sz; i < s->capacity; ++i)
|
1710
|
+
rb_ary_push(ary, Qnil);
|
1711
|
+
|
1712
|
+
return ary;
|
1713
|
+
}
|
1714
|
+
|
1715
|
+
|
1716
|
+
/*
|
1717
|
+
* Get the IA portion of the IJA array of a Yale matrix. This gives the start and end positions of rows in the
|
1718
|
+
* JA and LU portions of the IJA and A arrays, respectively.
|
1719
|
+
*/
|
1720
|
+
static VALUE nm_yale_ia(VALUE self) {
|
1721
|
+
y_size_t sz;
|
1722
|
+
void* vals;
|
1723
|
+
VALUE ary;
|
1724
|
+
YALE_STORAGE* s = (YALE_STORAGE*)NM_STORAGE(self);
|
1725
|
+
|
1726
|
+
if (NM_STYPE(self) != S_YALE) rb_raise(nm_eStorageTypeError, "wrong storage type");
|
1727
|
+
|
1728
|
+
YaleGetSize(sz, s);
|
1729
|
+
vals = ALLOC_N(char, nm_sizeof[NM_ROBJ]*(s->shape[0]+1));
|
1730
|
+
|
1731
|
+
SetFuncs[NM_ROBJ][s->index_dtype](s->shape[0]+1, vals, nm_sizeof[NM_ROBJ], s->ija, nm_sizeof[s->index_dtype]);
|
1732
|
+
ary = rb_ary_new4(s->shape[0]+1, vals);
|
1733
|
+
|
1734
|
+
return ary;
|
1735
|
+
}
|
1736
|
+
|
1737
|
+
|
1738
|
+
/*
|
1739
|
+
* Get the JA portion of the IJA array of a Yale matrix. This gives the column indices for entries in corresponding
|
1740
|
+
* positions in the LU portion of the A array.
|
1741
|
+
*/
|
1742
|
+
static VALUE nm_yale_ja(VALUE self) {
|
1743
|
+
y_size_t sz, i;
|
1744
|
+
void* vals;
|
1745
|
+
VALUE ary;
|
1746
|
+
YALE_STORAGE* s = (YALE_STORAGE*)NM_STORAGE(self);
|
1747
|
+
|
1748
|
+
if (NM_STYPE(self) != S_YALE) rb_raise(nm_eStorageTypeError, "wrong storage type");
|
1749
|
+
|
1750
|
+
YaleGetSize(sz, s);
|
1751
|
+
vals = ALLOC_N(char, nm_sizeof[NM_ROBJ]*(s->capacity - s->shape[0]));
|
1752
|
+
|
1753
|
+
SetFuncs[NM_ROBJ][s->index_dtype](sz - s->shape[0] - 1, vals, nm_sizeof[NM_ROBJ], (char*)(s->ija) + (s->shape[0] + 1)*nm_sizeof[s->index_dtype], nm_sizeof[s->index_dtype]);
|
1754
|
+
ary = rb_ary_new4(sz - s->shape[0] - 1, vals);
|
1755
|
+
|
1756
|
+
for (i = sz; i < s->capacity; ++i)
|
1757
|
+
rb_ary_push(ary, Qnil);
|
1758
|
+
|
1759
|
+
return ary;
|
1760
|
+
}
|
1761
|
+
|
1762
|
+
|
1763
|
+
/*
|
1764
|
+
* Get the IJA array of a Yale matrix.
|
1765
|
+
*/
|
1766
|
+
static VALUE nm_yale_ija(VALUE self) {
|
1767
|
+
y_size_t sz, i;
|
1768
|
+
void* vals;
|
1769
|
+
VALUE ary;
|
1770
|
+
YALE_STORAGE* s = (YALE_STORAGE*)NM_STORAGE(self);
|
1771
|
+
|
1772
|
+
if (NM_STYPE(self) != S_YALE) rb_raise(nm_eStorageTypeError, "wrong storage type");
|
1773
|
+
|
1774
|
+
YaleGetSize(sz, s);
|
1775
|
+
vals = ALLOC_N(char, nm_sizeof[NM_ROBJ]*s->capacity);
|
1776
|
+
|
1777
|
+
SetFuncs[NM_ROBJ][s->index_dtype](sz, vals, nm_sizeof[NM_ROBJ], s->ija, nm_sizeof[s->index_dtype]);
|
1778
|
+
ary = rb_ary_new4(sz, vals);
|
1779
|
+
|
1780
|
+
for (i = sz; i < s->capacity; ++i)
|
1781
|
+
rb_ary_push(ary, Qnil);
|
1782
|
+
|
1783
|
+
return ary;
|
1784
|
+
}
|
1785
|
+
|
1786
|
+
|
1787
|
+
// This is probably faster and smaller than writing an array of transpose functions. But if you want to see what it would look like,
|
1788
|
+
// see transp.template.c (not the yale one).
|
1789
|
+
//
|
1790
|
+
// Note that this is a copy-transpose. In-place transpose is a whole different operation and bag of worms.
|
1791
|
+
static void dense_transpose_generic(const unsigned int M, const unsigned int N, const char* A, const int lda, char* B, const int ldb, size_t dtype_size) {
|
1792
|
+
unsigned int i, j;
|
1793
|
+
|
1794
|
+
for (i = 0; i < N; ++i) {
|
1795
|
+
for (j = 0; j < M; ++j) {
|
1796
|
+
memcpy(B + (i*ldb+j)*dtype_size, A + (j*lda+i)*dtype_size, dtype_size);
|
1797
|
+
}
|
1798
|
+
}
|
1799
|
+
}
|
1800
|
+
|
1801
|
+
|
1802
|
+
/*
|
1803
|
+
* Create a transposed copy of this matrix.
|
1804
|
+
*/
|
1805
|
+
static VALUE nm_transpose_new(VALUE self) {
|
1806
|
+
NMATRIX *self_m, *result, *result2;
|
1807
|
+
size_t sz;
|
1808
|
+
size_t* shape = ALLOC_N(size_t, 2);
|
1809
|
+
YALE_PARAM A, B;
|
1810
|
+
#ifdef BENCHMARK
|
1811
|
+
double t1, t2;
|
1812
|
+
#endif
|
1813
|
+
|
1814
|
+
UnwrapNMatrix( self, self_m );
|
1815
|
+
|
1816
|
+
// switch the dimensions
|
1817
|
+
shape[1] = self_m->storage->shape[0];
|
1818
|
+
shape[0] = self_m->storage->shape[1];
|
1819
|
+
|
1820
|
+
switch(self_m->stype) {
|
1821
|
+
case S_DENSE:
|
1822
|
+
result = nm_create(S_DENSE, create_dense_storage(self_m->storage->dtype, shape, 2, NULL, 0));
|
1823
|
+
dense_transpose_generic(
|
1824
|
+
self_m->storage->shape[0],
|
1825
|
+
self_m->storage->shape[1],
|
1826
|
+
((DENSE_STORAGE*)(self_m->storage))->elements,
|
1827
|
+
self_m->storage->shape[1],
|
1828
|
+
((DENSE_STORAGE*)(result->storage))->elements,
|
1829
|
+
result->storage->shape[1],
|
1830
|
+
nm_sizeof[self_m->storage->dtype]);
|
1831
|
+
|
1832
|
+
break;
|
1833
|
+
case S_YALE:
|
1834
|
+
YaleGetSize(sz, (YALE_STORAGE*)(self_m->storage)); // size of new matrix is going to be size of old matrix
|
1835
|
+
result = nm_create(S_YALE, create_yale_storage(self_m->storage->dtype, shape, 2, sz));
|
1836
|
+
|
1837
|
+
// TODO: Do we really need to initialize the whole thing? Or just the A portion?
|
1838
|
+
init_yale_storage((YALE_STORAGE*)(result->storage));
|
1839
|
+
|
1840
|
+
result2 = nm_create(S_YALE, create_yale_storage(self_m->storage->dtype, shape, 2, sz));
|
1841
|
+
init_yale_storage((YALE_STORAGE*)(result2->storage));
|
1842
|
+
|
1843
|
+
A.ia = A.ja = ((YALE_STORAGE*)(self_m->storage))->ija;
|
1844
|
+
B.ia = B.ja = ((YALE_STORAGE*)(result->storage))->ija;
|
1845
|
+
A.a = ((YALE_STORAGE*)(self_m->storage))->a;
|
1846
|
+
B.a = ((YALE_STORAGE*)(result->storage))->a;
|
1847
|
+
A.diag = true;
|
1848
|
+
|
1849
|
+
#ifdef BENCHMARK
|
1850
|
+
t1 = get_time();
|
1851
|
+
#endif
|
1852
|
+
|
1853
|
+
// call the appropriate function pointer
|
1854
|
+
SparseTransposeFuncs[ self_m->storage->dtype ][ ((YALE_STORAGE*)(self_m->storage))->index_dtype ](shape[0], shape[1], A, B, true);
|
1855
|
+
#ifdef BENCHMARK
|
1856
|
+
t1 = get_time() - t1;
|
1857
|
+
/*
|
1858
|
+
t2 = get_time();
|
1859
|
+
transp(
|
1860
|
+
shape[0],
|
1861
|
+
shape[1],
|
1862
|
+
((YALE_STORAGE*)(self_m->storage))->ija,
|
1863
|
+
((YALE_STORAGE*)(self_m->storage))->ija,
|
1864
|
+
true,
|
1865
|
+
((YALE_STORAGE*)(self_m->storage))->a,
|
1866
|
+
((YALE_STORAGE*)(result2->storage))->ija,
|
1867
|
+
((YALE_STORAGE*)(result2->storage))->ija,
|
1868
|
+
((YALE_STORAGE*)(result2->storage))->a,
|
1869
|
+
true, // move
|
1870
|
+
((YALE_STORAGE*)(self_m->storage))->index_dtype,
|
1871
|
+
self_m->storage->dtype
|
1872
|
+
);
|
1873
|
+
|
1874
|
+
t2 = get_time() - t2;
|
1875
|
+
fprintf(stderr, "t1: %f\nt2: %f\n", t1, t2);
|
1876
|
+
*/
|
1877
|
+
#endif
|
1878
|
+
|
1879
|
+
break;
|
1880
|
+
default:
|
1881
|
+
rb_raise(rb_eNotImpError, "transpose for this type not implemented yet");
|
1882
|
+
}
|
1883
|
+
|
1884
|
+
return Data_Wrap_Struct(cNMatrix, MarkFuncs[result->stype], nm_delete, result);
|
1885
|
+
}
|
1886
|
+
|
1887
|
+
//static VALUE nm_transpose_auto(VALUE self) {
|
1888
|
+
//
|
1889
|
+
//}
|
1890
|
+
|
1891
|
+
void Init_nmatrix() {
|
1892
|
+
/* Require Complex class */
|
1893
|
+
//rb_require("complex");
|
1894
|
+
//cComplex = rb_const_get( rb_cObject, rb_intern("Complex") );
|
1895
|
+
|
1896
|
+
/* Define NMatrix class */
|
1897
|
+
cNMatrix = rb_define_class("NMatrix", rb_cObject);
|
1898
|
+
|
1899
|
+
/* class methods */
|
1900
|
+
rb_define_singleton_method(cNMatrix, "__cblas_gemm__", nm_cblas_gemm, 13);
|
1901
|
+
rb_define_singleton_method(cNMatrix, "__cblas_gemv__", nm_cblas_gemv, 11);
|
1902
|
+
|
1903
|
+
rb_define_alloc_func(cNMatrix, nm_alloc);
|
1904
|
+
rb_define_method(cNMatrix, "initialize", nm_init, -1);
|
1905
|
+
// rb_define_singleton_method(cNMatrix, "new", nm_init, -1);
|
1906
|
+
|
1907
|
+
|
1908
|
+
rb_define_method(cNMatrix, "initialize_copy", nm_init_copy, 1);
|
1909
|
+
rb_define_method(cNMatrix, "initialize_cast_copy", nm_init_cast_copy, 2);
|
1910
|
+
rb_define_method(cNMatrix, "as_dtype", nm_cast_copy, 1);
|
1911
|
+
|
1912
|
+
/* methods */
|
1913
|
+
rb_define_method(cNMatrix, "dtype", nm_dtype, 0);
|
1914
|
+
rb_define_method(cNMatrix, "stype", nm_stype, 0);
|
1915
|
+
rb_define_method(cNMatrix, "cast", nm_scast_copy, 2);
|
1916
|
+
|
1917
|
+
rb_define_method(cNMatrix, "[]", nm_mref, -1);
|
1918
|
+
rb_define_method(cNMatrix, "[]=", nm_mset, -1);
|
1919
|
+
rb_define_method(cNMatrix, "rank", nm_rank, 0);
|
1920
|
+
rb_define_alias(cNMatrix, "dim", "rank");
|
1921
|
+
rb_define_method(cNMatrix, "shape", nm_shape, 0);
|
1922
|
+
rb_define_method(cNMatrix, "transpose", nm_transpose_new, 0);
|
1923
|
+
//rb_define_method(cNMatrix, "transpose!", nm_transpose_auto, 0);
|
1924
|
+
|
1925
|
+
rb_define_method(cNMatrix, "each", nm_each, 0);
|
1926
|
+
|
1927
|
+
rb_define_method(cNMatrix, "*", nm_ew_multiply, 1);
|
1928
|
+
rb_define_method(cNMatrix, "/", nm_ew_divide, 1);
|
1929
|
+
rb_define_method(cNMatrix, "+", nm_ew_add, 1);
|
1930
|
+
rb_define_method(cNMatrix, "-", nm_ew_subtract, 1);
|
1931
|
+
rb_define_method(cNMatrix, "==", nm_ew_eqeq, 1);
|
1932
|
+
rb_define_method(cNMatrix, "!=", nm_ew_neq, 1);
|
1933
|
+
rb_define_method(cNMatrix, "<=", nm_ew_leq, 1);
|
1934
|
+
rb_define_method(cNMatrix, ">=", nm_ew_geq, 1);
|
1935
|
+
rb_define_method(cNMatrix, "<", nm_ew_lt, 1);
|
1936
|
+
rb_define_method(cNMatrix, ">", nm_ew_gt, 1);
|
1937
|
+
rb_define_method(cNMatrix, "equal?", nm_eqeq, 1);
|
1938
|
+
rb_define_method(cNMatrix, "dot", nm_multiply, 1);
|
1939
|
+
rb_define_alias(cNMatrix, "equal?", "eql?");
|
1940
|
+
|
1941
|
+
|
1942
|
+
rb_define_method(cNMatrix, "capacity", nm_capacity, 0);
|
1943
|
+
|
1944
|
+
rb_define_method(cNMatrix, "__yale_ija__", nm_yale_ija, 0);
|
1945
|
+
rb_define_method(cNMatrix, "__yale_a__", nm_yale_a, 0);
|
1946
|
+
rb_define_method(cNMatrix, "__yale_size__", nm_yale_size, 0);
|
1947
|
+
rb_define_method(cNMatrix, "__yale_ia__", nm_yale_ia, 0);
|
1948
|
+
rb_define_method(cNMatrix, "__yale_ja__", nm_yale_ja, 0);
|
1949
|
+
rb_define_method(cNMatrix, "__yale_d__", nm_yale_d, 0);
|
1950
|
+
rb_define_method(cNMatrix, "__yale_lu__", nm_yale_lu, 0);
|
1951
|
+
rb_define_const(cNMatrix, "YALE_GROWTH_CONSTANT", rb_float_new(YALE_GROWTH_CONSTANT));
|
1952
|
+
|
1953
|
+
|
1954
|
+
cNVector = rb_define_class("NVector", cNMatrix);
|
1955
|
+
|
1956
|
+
// Special exceptions
|
1957
|
+
nm_eDataTypeError = rb_define_class("DataTypeError", rb_eStandardError);
|
1958
|
+
nm_eStorageTypeError = rb_define_class("StorageTypeError", rb_eStandardError);
|
1959
|
+
|
1960
|
+
nm_id_real = rb_intern("real");
|
1961
|
+
nm_id_imag = rb_intern("imag");
|
1962
|
+
nm_id_numer = rb_intern("numerator");
|
1963
|
+
nm_id_denom = rb_intern("denominator");
|
1964
|
+
nm_id_mult = rb_intern("*");
|
1965
|
+
nm_id_add = rb_intern("+");
|
1966
|
+
nm_id_multeq= rb_intern("*=");
|
1967
|
+
|
1968
|
+
nm_id_transpose = rb_intern("transpose");
|
1969
|
+
nm_id_no_transpose = rb_intern("no_transpose");
|
1970
|
+
nm_id_complex_conjugate = rb_intern("complex_conjugate");
|
1971
|
+
|
1972
|
+
nm_id_dense = rb_intern("dense");
|
1973
|
+
nm_id_list = rb_intern("list");
|
1974
|
+
|
1975
|
+
}
|
1976
|
+
|
1977
|
+
#endif
|