/src/fftw3/dft/scalar/codelets/n1_2.c
Line | Count | Source |
1 | | /* |
2 | | * Copyright (c) 2003, 2007-14 Matteo Frigo |
3 | | * Copyright (c) 2003, 2007-14 Massachusetts Institute of Technology |
4 | | * |
5 | | * This program is free software; you can redistribute it and/or modify |
6 | | * it under the terms of the GNU General Public License as published by |
7 | | * the Free Software Foundation; either version 2 of the License, or |
8 | | * (at your option) any later version. |
9 | | * |
10 | | * This program is distributed in the hope that it will be useful, |
11 | | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
12 | | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
13 | | * GNU General Public License for more details. |
14 | | * |
15 | | * You should have received a copy of the GNU General Public License |
16 | | * along with this program; if not, write to the Free Software |
17 | | * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA |
18 | | * |
19 | | */ |
20 | | |
21 | | /* This file was automatically generated --- DO NOT EDIT */ |
22 | | /* Generated on Mon Sep 25 07:03:51 UTC 2023 */ |
23 | | |
24 | | #include "dft/codelet-dft.h" |
25 | | |
26 | | #if defined(ARCH_PREFERS_FMA) || defined(ISA_EXTENSION_PREFERS_FMA) |
27 | | |
28 | | /* Generated by: ../../../genfft/gen_notw.native -fma -compact -variables 4 -pipeline-latency 4 -n 2 -name n1_2 -include dft/scalar/n.h */ |
29 | | |
30 | | /* |
31 | | * This function contains 4 FP additions, 0 FP multiplications, |
32 | | * (or, 4 additions, 0 multiplications, 0 fused multiply/add), |
33 | | * 5 stack variables, 0 constants, and 8 memory accesses |
34 | | */ |
35 | | #include "dft/scalar/n.h" |
36 | | |
37 | | static void n1_2(const R *ri, const R *ii, R *ro, R *io, stride is, stride os, INT v, INT ivs, INT ovs) |
38 | | { |
39 | | { |
40 | | INT i; |
41 | | for (i = v; i > 0; i = i - 1, ri = ri + ivs, ii = ii + ivs, ro = ro + ovs, io = io + ovs, MAKE_VOLATILE_STRIDE(8, is), MAKE_VOLATILE_STRIDE(8, os)) { |
42 | | E T1, T2, T3, T4; |
43 | | T1 = ri[0]; |
44 | | T2 = ri[WS(is, 1)]; |
45 | | ro[WS(os, 1)] = T1 - T2; |
46 | | ro[0] = T1 + T2; |
47 | | T3 = ii[0]; |
48 | | T4 = ii[WS(is, 1)]; |
49 | | io[WS(os, 1)] = T3 - T4; |
50 | | io[0] = T3 + T4; |
51 | | } |
52 | | } |
53 | | } |
54 | | |
55 | | static const kdft_desc desc = { 2, "n1_2", { 4, 0, 0, 0 }, &GENUS, 0, 0, 0, 0 }; |
56 | | |
57 | | void X(codelet_n1_2) (planner *p) { X(kdft_register) (p, n1_2, &desc); |
58 | | } |
59 | | |
60 | | #else |
61 | | |
62 | | /* Generated by: ../../../genfft/gen_notw.native -compact -variables 4 -pipeline-latency 4 -n 2 -name n1_2 -include dft/scalar/n.h */ |
63 | | |
64 | | /* |
65 | | * This function contains 4 FP additions, 0 FP multiplications, |
66 | | * (or, 4 additions, 0 multiplications, 0 fused multiply/add), |
67 | | * 5 stack variables, 0 constants, and 8 memory accesses |
68 | | */ |
69 | | #include "dft/scalar/n.h" |
70 | | |
71 | | static void n1_2(const R *ri, const R *ii, R *ro, R *io, stride is, stride os, INT v, INT ivs, INT ovs) |
72 | 5 | { |
73 | 5 | { |
74 | 5 | INT i; |
75 | 10 | for (i = v; i > 0; i = i - 1, ri = ri + ivs, ii = ii + ivs, ro = ro + ovs, io = io + ovs, MAKE_VOLATILE_STRIDE(8, is), MAKE_VOLATILE_STRIDE(8, os)) { |
76 | 5 | E T1, T2, T3, T4; |
77 | 5 | T1 = ri[0]; |
78 | 5 | T2 = ri[WS(is, 1)]; |
79 | 5 | ro[WS(os, 1)] = T1 - T2; |
80 | 5 | ro[0] = T1 + T2; |
81 | 5 | T3 = ii[0]; |
82 | 5 | T4 = ii[WS(is, 1)]; |
83 | 5 | io[WS(os, 1)] = T3 - T4; |
84 | 5 | io[0] = T3 + T4; |
85 | 5 | } |
86 | 5 | } |
87 | 5 | } |
88 | | |
89 | | static const kdft_desc desc = { 2, "n1_2", { 4, 0, 0, 0 }, &GENUS, 0, 0, 0, 0 }; |
90 | | |
91 | 1 | void X(codelet_n1_2) (planner *p) { X(kdft_register) (p, n1_2, &desc); |
92 | 1 | } |
93 | | |
94 | | #endif |