1 /***************************************************************************
2 Copyright (c) 2013, The OpenBLAS Project
3 All rights reserved.
4 Redistribution and use in source and binary forms, with or without
5 modification, are permitted provided that the following conditions are
6 met:
7 1. Redistributions of source code must retain the above copyright
8 notice, this list of conditions and the following disclaimer.
9 2. Redistributions in binary form must reproduce the above copyright
10 notice, this list of conditions and the following disclaimer in
11 the documentation and/or other materials provided with the
12 distribution.
13 3. Neither the name of the OpenBLAS project nor the names of
14 its contributors may be used to endorse or promote products
15 derived from this software without specific prior written permission.
16 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
17 AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18 IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19 ARE DISCLAIMED. IN NO EVENT SHALL THE OPENBLAS PROJECT OR CONTRIBUTORS BE
20 LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
21 DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
22 SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
23 CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
24 OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
25 USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26 *****************************************************************************/
27
28 #include "common.h"
29
30 #if !defined(DOUBLE)
31 #define VSETVL(n) vsetvl_e32m4(n)
32 #define FLOAT_V_T vfloat32m4_t
33 #define VLSEV_FLOAT vlse_v_f32m4
34 #define VSSEV_FLOAT vsse_v_f32m4
35 #define VFMACCVF_FLOAT vfmacc_vf_f32m4
36 #define VFNMSACVF_FLOAT vfnmsac_vf_f32m4
37 #else
38 #define VSETVL(n) vsetvl_e64m4(n)
39 #define FLOAT_V_T vfloat64m4_t
40 #define VLSEV_FLOAT vlse_v_f64m4
41 #define VSSEV_FLOAT vsse_v_f64m4
42 #define VFMACCVF_FLOAT vfmacc_vf_f64m4
43 #define VFNMSACVF_FLOAT vfnmsac_vf_f64m4
44 #endif
45
CNAME(BLASLONG n,BLASLONG dummy0,BLASLONG dummy1,FLOAT da_r,FLOAT da_i,FLOAT * x,BLASLONG inc_x,FLOAT * y,BLASLONG inc_y,FLOAT * dummy,BLASLONG dummy2)46 int CNAME(BLASLONG n, BLASLONG dummy0, BLASLONG dummy1, FLOAT da_r, FLOAT da_i, FLOAT *x, BLASLONG inc_x, FLOAT *y, BLASLONG inc_y, FLOAT *dummy, BLASLONG dummy2)
47 {
48 BLASLONG i = 0, j = 0;
49 BLASLONG ix = 0,iy = 0;
50 if(n < 0) return(0);
51 if(da_r == 0.0 && da_i == 0.0) return(0);
52 unsigned int gvl = 0;
53 BLASLONG stride_x = inc_x * 2 * sizeof(FLOAT);
54 BLASLONG stride_y = inc_y * 2 * sizeof(FLOAT);
55
56 FLOAT_V_T vx0, vx1, vy0, vy1;
57 gvl = VSETVL(n);
58 BLASLONG inc_xv = inc_x * 2 * gvl;
59 BLASLONG inc_yv = inc_y * 2 * gvl;
60 for(i=0,j=0; i < n/gvl; i++){
61 vx0 = VLSEV_FLOAT(&x[ix], stride_x, gvl);
62 vx1 = VLSEV_FLOAT(&x[ix+1], stride_x, gvl);
63 vy0 = VLSEV_FLOAT(&y[iy], stride_y, gvl);
64 vy1 = VLSEV_FLOAT(&y[iy+1], stride_y, gvl);
65 #if !defined(CONJ)
66 vy0 = VFMACCVF_FLOAT(vy0, da_r, vx0, gvl);
67 vy0 = VFNMSACVF_FLOAT(vy0, da_i, vx1, gvl);
68 vy1 = VFMACCVF_FLOAT(vy1, da_r, vx1, gvl);
69 vy1 = VFMACCVF_FLOAT(vy1, da_i, vx0, gvl);
70 #else
71 vy0 = VFMACCVF_FLOAT(vy0, da_r, vx0, gvl);
72 vy0 = VFMACCVF_FLOAT(vy0, da_i, vx1, gvl);
73 vy1 = VFNMSACVF_FLOAT(vy1, da_r, vx1, gvl);
74 vy1 = VFMACCVF_FLOAT(vy1, da_i, vx0, gvl);
75 #endif
76 VSSEV_FLOAT(&y[iy], stride_y, vy0, gvl);
77 VSSEV_FLOAT(&y[iy+1], stride_y, vy1, gvl);
78 j += gvl;
79 ix += inc_xv;
80 iy += inc_yv;
81 }
82 if(j < n){
83 gvl = VSETVL(n-j);
84 vx0 = VLSEV_FLOAT(&x[ix], stride_x, gvl);
85 vx1 = VLSEV_FLOAT(&x[ix+1], stride_x, gvl);
86 vy0 = VLSEV_FLOAT(&y[iy], stride_y, gvl);
87 vy1 = VLSEV_FLOAT(&y[iy+1], stride_y, gvl);
88 #if !defined(CONJ)
89 vy0 = VFMACCVF_FLOAT(vy0, da_r, vx0, gvl);
90 vy0 = VFNMSACVF_FLOAT(vy0, da_i, vx1, gvl);
91 vy1 = VFMACCVF_FLOAT(vy1, da_r, vx1, gvl);
92 vy1 = VFMACCVF_FLOAT(vy1, da_i, vx0, gvl);
93 #else
94 vy0 = VFMACCVF_FLOAT(vy0, da_r, vx0, gvl);
95 vy0 = VFMACCVF_FLOAT(vy0, da_i, vx1, gvl);
96 vy1 = VFNMSACVF_FLOAT(vy1, da_r, vx1, gvl);
97 vy1 = VFMACCVF_FLOAT(vy1, da_i, vx0, gvl);
98 #endif
99 VSSEV_FLOAT(&y[iy], stride_y, vy0, gvl);
100 VSSEV_FLOAT(&y[iy+1], stride_y, vy1, gvl);
101 }
102 return(0);
103 }
104
105
106