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
|
/*
-- MAGMA (version 2.9.0) --
Univ. of Tennessee, Knoxville
Univ. of California, Berkeley
Univ. of Colorado, Denver
@date January 2025
@generated from magmablas/zhemv_vbatched.cpp, normal z -> d, Wed Jan 22 14:42:08 2025
@author Ahmad Abdelfattah
*/
#include "magma_internal.h"
#include "commonblas_d.h"
#define PRECISION_d
/******************************************************************************/
extern "C" void
magmablas_dsymv_vbatched_max(
magma_uplo_t uplo, magma_int_t* n,
double alpha,
magmaDouble_ptr dA_array[], magma_int_t* ldda,
magmaDouble_ptr dx_array[], magma_int_t* incx,
double beta,
magmaDouble_ptr dy_array[], magma_int_t* incy,
magma_int_t batchCount,
magma_int_t max_n, magma_queue_t queue)
{
magma_int_t info = 0;
info = magma_hemv_vbatched_checker( uplo, n, ldda, incx, incy, batchCount, queue );
if (info != 0) {
magma_xerbla( __func__, -(info) );
return;
}
magmablas_dsymv_vbatched_max_nocheck(
uplo, n,
alpha, dA_array, ldda,
dx_array, incx,
beta, dy_array, incy,
batchCount, max_n, queue);
}
/******************************************************************************/
extern "C" void
magmablas_dsymv_vbatched_nocheck(
magma_uplo_t uplo, magma_int_t* n,
double alpha,
magmaDouble_ptr dA_array[], magma_int_t* ldda,
magmaDouble_ptr dx_array[], magma_int_t* incx,
double beta,
magmaDouble_ptr dy_array[], magma_int_t* incy,
magma_int_t batchCount, magma_queue_t queue)
{
// compute the max. dimensions
magma_imax_size_1(n, batchCount, queue);
magma_int_t max_n;
magma_igetvector_async(1, &n[batchCount], 1, &max_n, 1, queue);
magma_queue_sync( queue );
magmablas_dsymv_vbatched_max_nocheck(
uplo, n,
alpha, dA_array, ldda,
dx_array, incx,
beta, dy_array, incy,
batchCount, max_n, queue);
}
/***************************************************************************//**
Purpose
-------
DSYMV performs the matrix-vector operation:
y := alpha*A*x + beta*y,
where alpha and beta are scalars, x and y are n element vectors and
A is an n by n symmetric matrix.
This is the variable size batched version of the operation.
Arguments
----------
@param[in]
uplo magma_uplo_t.
On entry, UPLO specifies whether the upper or lower
triangular part of the array A is to be referenced as
follows:
- = MagmaUpper: Only the upper triangular part of A is to be referenced.
- = MagmaLower: Only the lower triangular part of A is to be referenced.
@param[in]
n INTEGER array, dimension(batchCoutn + 1).
On entry, each element N specifies the order of each matrix A.
N must be at least zero.
@param[in]
alpha DOUBLE PRECISION.
On entry, ALPHA specifies the scalar alpha.
@param[in]
dA_array Array of pointers, dimension(batchCount).
Each is a DOUBLE PRECISION array A of DIMENSION ( LDDA, N ).
Before entry with 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.
Before entry with 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 and 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. LDDA must be at least
max( 1, n ).
It is recommended that LDDA is multiple of 16. Otherwise
performance would be deteriorated as the memory accesses
would not be fully coalescent.
@param[in]
dx_array Array of pointers, dimension(batchCount).
Each is a DOUBLE PRECISION array X of dimension at least
( 1 + ( n - 1 )*abs( INCX ) ).
Before entry, the incremented array X must contain the n
element vector X.
@param[in]
incx INTEGER array, dimension(batchCount + 1).
On entry, each element INCX specifies the increment for the elements of
each X. INCX must not be zero.
@param[in]
beta DOUBLE PRECISION.
On entry, BETA specifies the scalar beta. When BETA is
supplied as zero then Y need not be set on input.
@param[in,out]
dy_array Array of pointers, dimension(batchCount).
Each is a DOUBLE PRECISION array Y of dimension at least
( 1 + ( n - 1 )*abs( INCY ) ).
Before entry, the incremented array Y must contain the n
element vector Y. On exit, Y is overwritten by the updated
vector Y.
@param[in]
incy INTEGER array, dimension(batchCount + 1).
On entry, each element INCY specifies the increment for the elements of
each Y. INCY must not be zero.
@param[in]
batchCount INTEGER.
The number of problems to operate on.
@param[in]
queue magma_queue_t
Queue to execute in.
@ingroup magma_hemv_batched
*******************************************************************************/
extern "C" void
magmablas_dsymv_vbatched(
magma_uplo_t uplo, magma_int_t* n,
double alpha,
magmaDouble_ptr dA_array[], magma_int_t* ldda,
magmaDouble_ptr dx_array[], magma_int_t* incx,
double beta,
magmaDouble_ptr dy_array[], magma_int_t* incy,
magma_int_t batchCount, magma_queue_t queue)
{
magma_int_t info = 0;
info = magma_hemv_vbatched_checker( uplo, n, ldda, incx, incy, batchCount, queue );
if (info != 0) {
magma_xerbla( __func__, -(info) );
return;
}
// compute the max. dimensions
magma_imax_size_1(n, batchCount, queue);
magma_int_t max_n;
magma_igetvector_async(1, &n[batchCount], 1, &max_n, 1, queue);
magma_queue_sync( queue );
magmablas_dsymv_vbatched_max_nocheck(
uplo, n,
alpha, dA_array, ldda,
dx_array, incx,
beta, dy_array, incy,
batchCount, max_n, queue);
}
|
