1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
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
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
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
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
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
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
|
/*
File: vectorOps.h
Contains: vector and matrix functions for AltiVec
Version: QuickTime 7.3
Copyright: (c) 2007 (c) 1999-2001 by Apple Computer, Inc., all rights reserved.
Bugs?: For bug reports, consult the following page on
the World Wide Web:
http://developer.apple.com/bugreporter/
*/
#ifndef __VECTOROPS__
#define __VECTOROPS__
#ifndef __CONDITIONALMACROS__
#include <ConditionalMacros.h>
#endif
#if PRAGMA_ONCE
#pragma once
#endif
#ifdef __cplusplus
extern "C" {
#endif
#if PRAGMA_IMPORT
#pragma import on
#endif
/*
-------------------------------------------------------------------------------------
This section is a collection of Basic Linear Algebra Subprograms (BLAS), which
use AltiVec technology for their implementations. The functions are grouped into
three categories (called levels), as follows:
1) Vector-scalar linear algebra subprograms
2) Matrix-vector linear algebra subprograms
3) Matrix operations
Following is a list of subprograms and a short description of each one.
-------------------------------------------------------------------------------------
*/
#ifdef __VEC__
/*
-------------------------------------------------------------------------------------
Level 1
-------------------------------------------------------------------------------------
*/
/**************************************************
vIsamax finds the position of the first vector
element having the largest magnitude.
count length of vector x (count is a
multiple of 4)
x array of floats
**************************************************/
/*
* vIsamax()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( long )
vIsamax(
long count,
const vector float x[]);
/**************************************************
vIsamin finds the position of the first vector
element having minimum absolute value.
count length of vector x (count is a
multiple of 4)
x array of floats
**************************************************/
/*
* vIsamin()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( long )
vIsamin(
long count,
const vector float x[]);
/**************************************************
vIsmax finds the position of the first vector
element having maximum value.
count length of vector x (count is a
multiple of 4)
x array of floats
**************************************************/
/*
* vIsmax()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( long )
vIsmax(
long count,
const vector float x[]);
/**************************************************
vIsmin finds the position of the first vector
element having minimum value.
count length of vector x (count is a
multiple of 4)
x array of floats
**************************************************/
/*
* vIsmin()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( long )
vIsmin(
long count,
const vector float x[]);
/**************************************************
vSasum finds the sum of the magnitudes of the
elements in a vector.
count length of vector x (count is a
multiple of 4)
x array of floats
**************************************************/
/*
* vSasum()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( float )
vSasum(
long count,
const vector float x[]);
/**************************************************
vSsum is the vector version of sasum but without
the absolute value. It takes the value of each
element of the array and adds them together.
multiple of 4)
x array of floats
**************************************************/
/*
* vSsum()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( float )
vSsum(
long count,
const vector float x[]);
/**************************************************
vSaxpy multiplies a vector x, by a scalar and
adds it to a vector y and stores the result in y
n number of floats in x (n is a
multiple of 4)
alpha scalar number is single-precision
floating-point
x array of vector floats
y array of vector floats, where the
the result is stored
**************************************************/
/*
* vSaxpy()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSaxpy(
long n,
float alpha,
const vector float x[],
vector float y[]);
/*************************************************************
vScopy copies a vector x, into another vector y.
n mumber of floats in x and y (n is a
multiple of 4)
x array of vector floats
y array of vector floats
*************************************************************/
/*
* vScopy()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vScopy(
long n,
const vector float x[],
vector float y[]);
/*************************************************************
vSdot finds the dot product of two vectors.
n mumber of floats in x and y (n is a
multiple of 4)
x array of vector floats
y array of vector floats
*************************************************************/
/*
* vSdot()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( float )
vSdot(
long n,
const vector float x[],
const vector float y[]);
/*************************************************************
vSnaxpy computes saxpy "n" times.
n number of saxpyV computations to be
performed and the number of elements
in vector A (n is a multiple of 4)
m number of floats in each vector x(i)
or y(i)
a array of vector floats containing
scalars a(i)
x matrix containing arrays of vector-
floats x(i)
y matrix containing vectors y(i)
*************************************************************/
/*
* vSnaxpy()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSnaxpy(
long n,
long m,
const vector float a[],
const vector float x[],
vector float y[]);
/*************************************************************
vSndot computes the dot products "n" times.
n number of dot product computations
to be performed and the number of
elements in vector S
m number of elements in vectors x(i)
and y(i) for each dot product
computation (m is a multiple of 4)
s array of floats. Depending on the
value of "isw" different computations/
are performed and the results are
stored in the array S
isw indicates the type of computation
to perform.
if isw=1, S(i) <-- x(i) y(i)
if isw=2, S(i) <-- - x(i) y(i)
if isw=3, S(i) <-- S(i) + x(i) y(i)/
if isw=4, S(i) <-- S(i) - x(i) y(i)/
x matrix containing arrays x(i)
y matrix containing arrays y(i)
*************************************************************/
/*
* vSndot()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSndot(
long n,
long m,
float s[],
long isw,
const vector float x[],
const vector float y[]);
/*************************************************************
vSnrm2 finds the Euclidean length of a vector
with scaling of input to avoid destructive
underflow and overflow.
count length of vector (multiple of 4)
x array of vector floats
*************************************************************/
/*
* vSnrm2()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( float )
vSnrm2(
long count,
const vector float x[]);
/*************************************************************
vSnorm2 finds the Euclidean length of a vector
with no scaling of input.
count length of vector (multiple of 4)
x array of vector floats
*************************************************************/
/*
* vSnorm2()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( float )
vSnorm2(
long count,
const vector float x[]);
/*************************************************************
vSrot applies a plane rotation.
n number of points to be rotated, also
number of elements in x and y (n is
a multiple of 4)
x array of vector floats. It is a
vector of length n, containing x(i)
coordinates of points to be rotated
y array of vector floats. It is a
vector of length n, containing y(i)
coordinates of points to be rotated
c cosine of angle of rotation
s sine of angle of rotation
*************************************************************/
/*
* vSrot()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSrot(
long n,
vector float x[],
vector float y[],
float c,
float s);
/*************************************************************
vSscal multiplies a vector x, by a scalar and
stores the result in the vector x.
n number of floats in x (n is a
multiple of 4)
alpha scalar number is single-precision
floating-point
x array of vector floats
*************************************************************/
/*
* vSscal()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSscal(
long n,
float alpha,
vector float x[]);
/*************************************************************
vSswap interchanges the elements of vectors x
and y
n number of floats in x and y (n is a
multiple of 4)
x array of vector floats
y array of vector floats
*************************************************************/
/*
* vSswap()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSswap(
long n,
vector float x[],
vector float y[]);
/*************************************************************
vSyax multiplies a vector x, by a scalar and
stores the result in a vector y.
n number of floats in x (n is a
multiple of 4)
alpha scalar number is single-precision
floating-point
x array of vector floats
y array of vector floats
*************************************************************/
/*
* vSyax()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSyax(
long n,
float alpha,
const vector float x[],
vector float y[]);
/*************************************************************
vSzaxpy multiplies a vector x, by a scalar and
adds it to a vector y and stores the result in
vector Z.
n number of floats in x (n is a
multiple of 4)
alpha scalar number is single-precision
floating-point
x array of vector floats
y array of vector floats
Z array of vector floats, where the
is stored
*************************************************************/
/*
* vSzaxpy()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSzaxpy(
long n,
float alpha,
const vector float x[],
const vector float yY[],
vector float z[]);
/*
-------------------------------------------------------------------------------------
Level 2
-------------------------------------------------------------------------------------
*/
/*************************************************************
vSgemv multiplies an array of vector floats y by
a scalar beta, and takes the result and adds it
to the product of a scalar alpha multiplied by
a matrix A multiplied by a vector x. The above
result is stored in array y. Futhermore, the
same function also performs the above calculation/
with the transpose of matrix A, instead of
matrix A. In this function argument "forma"
distinguishes between the above two cases.
forma indicates the form of matrix A to
use in the computation, where:
If forma = "n", Matrix A is used
If forma = "T", Transpose of Matrix
A is used
m number of rows in matrix A and
depending on value of forma
if forma = "n", it is the length of
vector y
if forma = "T", it is the length of
vector x. m is a multiple of 4
n number of columns in matrix A and
depending on value of forma
if forma = "n", it is the length of
vector x
if forma = "T", it is the length of
vector y. m is a multiple of 4
alpha is a scaling constant
A is an m by n matrix. Its elements
are vector floats
x is an array of vector floats
beta is a scaling constant
y is an array of vector floats
*************************************************************/
/*
* vSgemv()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSgemv(
char forma,
long m,
long n,
float alpha,
const vector float a[],
const vector float x[],
float beta,
vector float y[]);
/*************************************************************
vSgemx adds an array of vector floats y to the
product of an scalar alpha by a mtrix A
multiplied by an array of vector floats x. It
then stores the result in the vector y.
m number of rows in matrix A and
the length of vector y. m is a
multiple of 4
n number of columns in matrix A and
the length of vector x. m is a
multiple of 4
alpha is a scaling constant
a is an m by n matrix. Its elements
are vector floats
x is an array of vector floats
y is an array of vector floats
*************************************************************/
/*
* vSgemx()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSgemx(
long m,
long n,
float alpha,
const vector float a[],
const vector float x[],
vector float y[]);
/*************************************************************
vSgemtx takes the transpose of a mtrix A and
multiplies it by an array x. It then multiplies
the result by a scalar alpha. Finally adds the
above result to an array y and stores the result
in array y.
m number of rows in matrix A and
the length of vector x. m is a
multiple of 4
n number of columns in matrix A and
the length of vector y. m is a
multiple of 4
alpha is a scaling constant
a is an m by n matrix. Its elements
are vector floats
x is an array of vector floats
y is an array of vector floats
*************************************************************/
/*
* vSgemtx()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSgemtx(
long m,
long n,
float alpha,
const vector float a[],
const vector float x[],
vector float y[]);
/*
-------------------------------------------------------------------------------------
Level 3
-------------------------------------------------------------------------------------
*/
/*************************************************************
vSgeadd performs matrix addition for general
matrices or their transposes.
height height of the matrix (it is multiple
of 4)
width width of the matrix (it is multiple
of 4)
A matrix A, and depending on forma:
if forma='n', A is used in the
computation, and A has m rows and
n columns
if forma='T', A(T) is used in the
computation, and A has n rows and
m columns
forma indicates the form of matrix A to
use in the computation, where:
if forma='n', A is used in the
computation
if forma='T', A(T) is used in the
computation
b matrix b, and depending on formb:
if formb='n', b is used in the
computation, and b has m rows and
n columns
if formb='T', b(T) is used in the
computation, and b has n rows and
m columns
formb indicates the form of matrix b to
use in the computation, where:
if forma='n', b is used in the
computation
if forma='T', b(T) is used in the
computation
c is an m by n matrix c, containing
the reults of the computation
*************************************************************/
/*
* vSgeadd()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSgeadd(
long height,
long width,
const vector float a[],
char forma,
const vector float b[],
char formb,
vector float c[]);
/*************************************************************
vSgesub performs matrix subtraction for general
matrices or their transposes.
height height of the matrix (it is multiple
of 4)
width width of the matrix (it is multiple
of 4)
A matrix A, and depending on forma:
if forma='n', A is used in the
computation, and A has m rows and
n columns
if forma='T', A(T) is used in the
computation, and A has n rows and
m columns
forma indicates the form of matrix A to
use in the computation, where:
if forma='n', A is used in the
computation
if forma='T', A(T) is used in the
computation
b matrix b, and depending on formb:
if formb='n', b is used in the
computation, and b has m rows and
n columns
if formb='T', b(T) is used in the
computation, and b has n rows and
m columns
formb indicates the form of matrix b to
use in the computation, where:
if forma='n', b is used in the
computation
if forma='T', b(T) is used in the
computation
c is an m by n matrix c, containing
the reults of the computation
*************************************************************/
/*
* vSgesub()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSgesub(
long height,
long width,
const vector float a[],
char forma,
const vector float b[],
char formb,
vector float c[]);
/*************************************************************
vSgemul performs matrix multiplication for
general matrices or their transposes.
l height of the matrix A (it is
multiple of 4)
m width of matrix A (it is multiple
of 4)
n width of matrix b (it is multiple
of 4)
A matrix A, and depending on forma:
if forma='n', A is used in the
computation, and A has l rows and
m columns
if forma='T', A(T) is used in the
computation, and A has m rows and
l columns
forma indicates the form of matrix A to
use in the computation, where:
if forma='n', A is used in the
computation
if forma='T', A(T) is used in the
computation
b matrix b, and depending on formb:
if formb='n', b is used in the
computation, and b has m rows and
n columns
if formb='T', b(T) is used in the
computation, and b has n rows and
m columns
formb indicates the form of matrix b to
use in the computation, where:
if forma='n', b is used in the
computation
if forma='T', b(T) is used in the
computation
matrix is the matrix containing the
results of the computation
*************************************************************/
/*
* vSgemul()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSgemul(
long l,
long m,
long n,
const vector float a[],
char forma,
const vector float b[],
char formb,
vector float matrix[]);
/*************************************************************
vSgemm performs combined matrix multiplication
and addition for general matrices or their transposes.
l number of rows in matrix c (it is
multiple of 4)
m has the following meaning:
if forma='n', it is the number of
columns in matrix A
if forma='T', it is the number of
rows in matrix A. In addition
if formb='n', it is the number of
rows in matrix b
if formb='T', it is the number of
columns in matrix b
n columns in matrix c
A matrix A, and depending on forma:
if forma='n', A is used in the
computation, and A has l rows and
m columns
if forma='T', A(T) is used in the
computation, and A has m rows and
l columns
forma indicates the form of matrix A to
use in the computation, where:
if forma='n', A is used in the
computation
if forma='T', A(T) is used in the
computation
b matrix b, and depending on formb:
if formb='n', b is used in the
computation, and b has m rows and
n columns
if formb='T', b(T) is used in the
computation, and b has n rows and
m columns
formb indicates the form of matrix b to
use in the computation, where:
if forma='n', b is used in the
computation
if forma='T', b(T) is used in the
computation
alpha is a scalar
beta is a scalar
matrix is the l by n matrix
*************************************************************/
/*
* vSgemm()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSgemm(
long l,
long m,
long n,
const vector float a[],
char forma,
const vector float b[],
char formb,
vector float c[],
float alpha,
float beta,
vector float matrix[]);
/*************************************************************
vSgetmi performs general matrix transpose (in place).
size is the number of rows and columns
in matrix x
*************************************************************/
/*
* vSgetmi()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSgetmi(
long size,
vector float x[]);
/*************************************************************
vSgetmo performs general matrix transpose (out-of-place).
height is the height of the matrix
width is the width of the matrix
x array of vector floats
y array of vector floats
*************************************************************/
/*
* vSgetmo()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSgetmo(
long height,
long width,
const vector float x[],
vector float y[]);
/*************************************************************
vSgevv is a new function. It takes matrix A and
multiplies it by matrix b and puts the result in
matrix m.
l is the height of the matrix
n is the width of the matrix
A array of vector floats of at least
l * m in length
b array of vector floats of at least
m * n in length
m array of vector floats, containing
the results of multiplication. It
is m * n in size
*************************************************************/
/*
* vSgevv()
*
* Availability:
* Non-Carbon CFM: in vecLib 1.0 and later
* CarbonLib: not in Carbon, but vecLib is compatible with CarbonLib
* Mac OS X: in version 10.0 and later
*/
EXTERN_API_C( void )
vSgevv(
long l,
long n,
const vector float a[],
const vector float b[],
vector float m[]);
#endif /* defined(__VEC__) */
#ifdef PRAGMA_IMPORT_OFF
#pragma import off
#elif PRAGMA_IMPORT
#pragma import reset
#endif
#ifdef __cplusplus
}
#endif
#endif /* __VECTOROPS__ */
|