File: ssymm_vbatched.cpp

package info (click to toggle)
magma 2.9.0%2Bds-2
  • links: PTS, VCS
  • area: contrib
  • in suites: forky, sid, trixie
  • size: 83,212 kB
  • sloc: cpp: 709,115; fortran: 121,916; ansic: 32,343; python: 25,603; f90: 15,208; makefile: 942; xml: 253; csh: 232; sh: 203; perl: 104
file content (260 lines) | stat: -rw-r--r-- 9,444 bytes parent folder | download | duplicates (2)
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
/*
    -- MAGMA (version 2.9.0) --
       Univ. of Tennessee, Knoxville
       Univ. of California, Berkeley
       Univ. of Colorado, Denver
       @date January 2025

       @generated from magmablas/zhemm_vbatched.cpp, normal z -> s, Wed Jan 22 14:42:08 2025
       
       @author Ahmad Abdelfattah
*/

#include "magma_internal.h"
#include "commonblas_s.h"

#define PRECISION_s
/******************************************************************************/
extern "C" void 
magmablas_ssymm_vbatched_max_nocheck(
        magma_side_t side, magma_uplo_t uplo, 
        magma_int_t *m, magma_int_t *n, 
        float alpha, 
        float **dA_array, magma_int_t *ldda,
        float **dB_array, magma_int_t *lddb, 
        float beta, 
        float **dC_array, magma_int_t *lddc, 
        magma_int_t batchCount, magma_int_t max_m, magma_int_t max_n, 
        magma_queue_t queue )
{
    magmablas_ssymm_vbatched_core( 
           side, uplo, m, n, 
           alpha, dA_array, ldda,
                  dB_array, lddb, 
           beta,  dC_array, lddc, 
           max_m, max_n, 
           0, 0, 0, 0, 0, 0, 0, 0, 
           batchCount, queue );
}

/******************************************************************************/
extern "C" void
magmablas_ssymm_vbatched_max(
        magma_side_t side, magma_uplo_t uplo, 
        magma_int_t *m, magma_int_t *n, 
        float alpha, 
        float **dA_array, magma_int_t *ldda,
        float **dB_array, magma_int_t *lddb, 
        float beta, 
        float **dC_array, magma_int_t *lddc, 
        magma_int_t batchCount, magma_int_t max_m, magma_int_t max_n, 
        magma_queue_t queue )
{
    magma_int_t info = 0;
    
    info = magma_hemm_vbatched_checker(side, uplo, m, n, ldda, lddb, lddc, batchCount, queue );

    if (info != 0) {
        magma_xerbla( __func__, -(info) );
        return;
    }
    
    magmablas_ssymm_vbatched_max_nocheck(
            side, uplo, 
            m, n, 
            alpha, dA_array, ldda, 
                   dB_array, lddb, 
            beta,  dC_array, lddc, 
            batchCount, max_m, max_n, 
            queue );
}

/******************************************************************************/
extern "C" void
magmablas_ssymm_vbatched_nocheck(
        magma_side_t side, magma_uplo_t uplo, 
        magma_int_t *m, magma_int_t *n, 
        float alpha, 
        float **dA_array, magma_int_t *ldda,
        float **dB_array, magma_int_t *lddb, 
        float beta, 
        float **dC_array, magma_int_t *lddc, 
        magma_int_t batchCount, magma_queue_t queue )
{
    // compute the max. dimensions
    magma_imax_size_2(m, n, batchCount, queue);
    magma_int_t max_m, max_n; 
    magma_igetvector_async(1, &m[batchCount], 1, &max_m, 1, queue);
    magma_igetvector_async(1, &n[batchCount], 1, &max_n, 1, queue);
    magma_queue_sync( queue );    // maybe not needed
    
    magmablas_ssymm_vbatched_max_nocheck(
            side, uplo, 
            m, n, 
            alpha, dA_array, ldda, 
                   dB_array, lddb, 
            beta,  dC_array, lddc, 
            batchCount, max_m, max_n, queue );
}

/***************************************************************************//**
    Purpose
    -------
    SSYMM performs one of the matrix-matrix operations

        C := alpha*A*B + beta*C,
    or
        C := alpha*B*A + beta*C,

    where alpha and beta are scalars, A is a symmetric matrix, and
    B and C are m by n matrices.

    Arguments
    ---------
    @param[in]
    side    magma_side_t
            On entry, side specifies whether each symmetric matrix A
            appears on the left or right in the operation as follows:

            SIDE = MagmaLeft    C := alpha*A*B + beta*C,
            SIDE = MagmaRight   C := alpha*B*A + beta*C.


    @param[in]
    uplo    magma_uplo_t
            On entry, uplo specifies whether the upper or lower
            triangular part of each symmetric matrix A is to be
            referenced as follows:

            uplo = MagmaUpper   Only the upper triangular part of the
                                symmetric matrix is to be referenced.
            uplo = MagmaLower   Only the lower triangular part of the
                                symmetric matrix is to be referenced.

    @param[in]
    m       INTEGER array, dimension(batchCount + 1).
            On entry, each element M specifies the number of rows of each matrix C.
            M >= 0.

    @param[in]
    n       INTEGER array, dimension(batchCount + 1). 
            On entry, each element N specifies the number of columns of each matrix C.
            N >= 0.

    @param[in]
    alpha   REAL
            On entry, alpha specifies the scalar alpha.

    @param[in]
    dA_array    Array of pointers, dimension(batchCount).
            Each is a REAL array A of DIMENSION ( LDDA, ka ), where ka is
            M when side = MagmaLower and is N otherwise.
            Before entry with side = MagmaLeft, the M by M part of
            the array A must contain the symmetric matrix, such that
            when uplo = MagmaUpper, the leading M by M upper triangular
            part of the array A must contain the upper triangular part
            of the symmetric matrix and the strictly lower triangular
            part of A is not referenced, and when uplo = MagmaLower,
            the leading M by M lower triangular part of the array A
            must contain the lower triangular part of the symmetric
            matrix and the strictly upper triangular part of A is not
            referenced.
            Before entry with side = MagmaRight, the N by N part of
            the array A must contain the symmetric matrix, such that
            when uplo = MagmaUpper, the leading N by N upper triangular
            part of the array A must contain the upper triangular part
            of the symmetric matrix and the strictly lower triangular
            part of A is not referenced, and when uplo = MagmaLower,
            the leading N by N lower triangular part of the array A
            must contain the lower triangular part of the symmetric
            matrix and the strictly upper triangular part of A is not
            referenced.
            Note that the imaginary parts of the diagonal elements need
            not be set, they are assumed to be zero.

    @param[in]
    ldda    INTEGER array, dimension(batchCount + 1).
            On entry, each element LDDA specifies the first dimension of each A as declared
            in the calling (sub) program.
            When side = MagmaLower then LDDA >= max( 1, M ),
            otherwise                   LDDA >= max( 1, N ).

    @param[in]
    dB_array      Array of pointers, dimension(batchCount). 
            Each is a REAL array B of DIMENSION ( LDDB, N ).
            Before entry, the leading M by N part of the array B must
            contain the matrix B.

    @param[in]
    lddb    INTEGER array, dimension(batchCount + 1).
            On entry, each element LDDB specifies the first dimension of B as declared
            in the calling (sub) program. LDDB >= max( 1, M ).

    @param[in]
    beta    REAL
            On entry, BETA specifies the scalar beta. When BETA is
            supplied as zero then C need not be set on input.

    @param[in,out]
    dC_array      Array of pointers, dimension(batchCount). 
            Each is a REAL array C of DIMENSION ( LDDC, N ).
            Before entry, the leading M by N part of the array C must
            contain the matrix C, except when beta is zero, in which
            case C need not be set on entry.
            On exit, the array C is overwritten by the M by N updated
            matrix.

    @param[in]
    lddc    INTEGER array, dimension(batchCount + 1).
            On entry, each element LDDC specifies the first dimension of C as declared
            in the calling (sub) program. LDDC >= max( 1, M ).

    @param[in]
    batchCount  INTEGER
                The number of matrices to operate on.

    @param[in]
    queue   magma_queue_t
            Queue to execute in.
    

    @ingroup magma_hemm_batched
*******************************************************************************/

extern "C" void
magmablas_ssymm_vbatched(
        magma_side_t side, magma_uplo_t uplo, 
        magma_int_t *m, magma_int_t *n, 
        float alpha, 
        float **dA_array, magma_int_t *ldda,
        float **dB_array, magma_int_t *lddb, 
        float beta, 
        float **dC_array, magma_int_t *lddc, 
        magma_int_t batchCount, magma_queue_t queue )
{
    magma_int_t info = 0;
    
    info = magma_hemm_vbatched_checker(side, uplo, m, n, ldda, lddb, lddc, batchCount, queue );
        
    if (info != 0) {
        magma_xerbla( __func__, -(info) );
        return;
    }

    // compute the max. dimensions
    magma_imax_size_2(m, n, batchCount, queue);
    magma_int_t max_m, max_n; 
    magma_igetvector_async(1, &m[batchCount], 1, &max_m, 1, queue);
    magma_igetvector_async(1, &n[batchCount], 1, &max_n, 1, queue);
    magma_queue_sync( queue );    // maybe not needed

    magmablas_ssymm_vbatched_max_nocheck(
            side, uplo, 
            m, n, 
            alpha, dA_array, ldda, 
                   dB_array, lddb, 
            beta,  dC_array, lddc, 
            batchCount, max_m, max_n, queue );
}

/******************************************************************************/