1 /*********************************************************************/
2 /* Copyright 2009, 2010 The University of Texas at Austin. */
3 /* All rights reserved. */
4 /* */
5 /* Redistribution and use in source and binary forms, with or */
6 /* without modification, are permitted provided that the following */
7 /* conditions are met: */
8 /* */
9 /* 1. Redistributions of source code must retain the above */
10 /* copyright notice, this list of conditions and the following */
11 /* disclaimer. */
12 /* */
13 /* 2. Redistributions in binary form must reproduce the above */
14 /* copyright notice, this list of conditions and the following */
15 /* disclaimer in the documentation and/or other materials */
16 /* provided with the distribution. */
17 /* */
18 /* THIS SOFTWARE IS PROVIDED BY THE UNIVERSITY OF TEXAS AT */
19 /* AUSTIN ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, */
20 /* INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF */
21 /* MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE */
22 /* DISCLAIMED. IN NO EVENT SHALL THE UNIVERSITY OF TEXAS AT */
23 /* AUSTIN OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, */
24 /* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES */
25 /* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE */
26 /* GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR */
27 /* BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF */
28 /* LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT */
29 /* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT */
30 /* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE */
31 /* POSSIBILITY OF SUCH DAMAGE. */
32 /* */
33 /* The views and conclusions contained in the software and */
34 /* documentation are those of the authors and should not be */
35 /* interpreted as representing official policies, either expressed */
36 /* or implied, of The University of Texas at Austin. */
37 /*********************************************************************/
38
39 #include <stdio.h>
40 #include "common.h"
41
inner_thread(blas_arg_t * args,BLASLONG * range_m,BLASLONG * range_n,FLOAT * sa,FLOAT * sb,BLASLONG mypos)42 static int inner_thread(blas_arg_t *args, BLASLONG *range_m, BLASLONG *range_n,
43 FLOAT *sa, FLOAT *sb, BLASLONG mypos) {
44
45 BLASLONG n = args -> n;
46 BLASLONG off = 0;
47
48 if (range_n) {
49 n = range_n[1] - range_n[0];
50 off = range_n[0];
51 }
52
53 #if TRANS == 1
54 LASWP_PLUS(n, 1, args -> m, ZERO, ZERO,
55 (FLOAT *)args -> b + off * args -> ldb * COMPSIZE, args -> ldb, NULL, 0, args -> c, 1);
56 TRSM_LNLU (args, range_m, range_n, sa, sb, 0);
57 TRSM_LNUN (args, range_m, range_n, sa, sb, 0);
58 #elif TRANS == 2
59 TRSM_LTUN (args, range_m, range_n, sa, sb, 0);
60 TRSM_LTLU (args, range_m, range_n, sa, sb, 0);
61 LASWP_MINUS(n, 1, args -> m, ZERO, ZERO,
62 (FLOAT *)args -> b + off * args -> ldb * COMPSIZE, args -> ldb, NULL, 0, args -> c, -1);
63 #elif TRANS == 3
64 LASWP_PLUS(n, 1, args -> m, ZERO, ZERO,
65 (FLOAT *)args -> b + off * args -> ldb * COMPSIZE, args -> ldb, NULL, 0, args -> c, 1);
66 TRSM_LRLU (args, range_m, range_n, sa, sb, 0);
67 TRSM_LRUN (args, range_m, range_n, sa, sb, 0);
68 #else
69 TRSM_LCUN (args, range_m, range_n, sa, sb, 0);
70 TRSM_LCLU (args, range_m, range_n, sa, sb, 0);
71 LASWP_MINUS(n, 1, args -> m, ZERO, ZERO,
72 (FLOAT *)args -> b + off * args -> ldb * COMPSIZE, args -> ldb, NULL, 0, args -> c, -1);
73 #endif
74
75 return 0;
76 }
77
CNAME(blas_arg_t * args,BLASLONG * range_m,BLASLONG * range_n,FLOAT * sa,FLOAT * sb,BLASLONG mypos)78 blasint CNAME(blas_arg_t *args, BLASLONG *range_m, BLASLONG *range_n, FLOAT *sa, FLOAT *sb, BLASLONG mypos) {
79
80 int mode;
81
82 if (args -> n == 1){
83 #if TRANS == 1
84 LASWP_PLUS(1, 1, args -> m, ZERO, ZERO, args -> b, args -> ldb, NULL, 0, args -> c, 1);
85 ZTRSV_NLU (args -> m, args -> a, args -> lda, args -> b, 1, sb);
86 ZTRSV_NUN (args -> m, args -> a, args -> lda, args -> b, 1, sb);
87 #elif TRANS == 2
88 ZTRSV_TUN (args -> m, args -> a, args -> lda, args -> b, 1, sb);
89 ZTRSV_TLU (args -> m, args -> a, args -> lda, args -> b, 1, sb);
90 LASWP_MINUS(1, 1, args -> m, ZERO, ZERO, args -> b, args -> ldb, NULL, 0, args -> c, -1);
91 #elif TRANS == 3
92 LASWP_PLUS(1, 1, args -> m, ZERO, ZERO, args -> b, args -> ldb, NULL, 0, args -> c, 1);
93 ZTRSV_RLU (args -> m, args -> a, args -> lda, args -> b, 1, sb);
94 ZTRSV_RUN (args -> m, args -> a, args -> lda, args -> b, 1, sb);
95 #else
96 ZTRSV_CUN (args -> m, args -> a, args -> lda, args -> b, 1, sb);
97 ZTRSV_CLU (args -> m, args -> a, args -> lda, args -> b, 1, sb);
98 LASWP_MINUS(1, 1, args -> m, ZERO, ZERO, args -> b, args -> ldb, NULL, 0, args -> c, -1);
99 #endif
100 } else {
101 #ifdef XDOUBLE
102 mode = BLAS_XDOUBLE | BLAS_COMPLEX;
103 #elif defined(DOUBLE)
104 mode = BLAS_DOUBLE | BLAS_COMPLEX;
105 #else
106 mode = BLAS_SINGLE | BLAS_COMPLEX;
107 #endif
108
109 gemm_thread_n(mode, args, NULL, NULL, inner_thread, sa, sb, args -> nthreads);
110 }
111
112 return 0;
113 }
114