cannam@95: /* cannam@95: * Copyright (c) 2003, 2007-11 Matteo Frigo cannam@95: * Copyright (c) 2003, 2007-11 Massachusetts Institute of Technology cannam@95: * cannam@95: * This program is free software; you can redistribute it and/or modify cannam@95: * it under the terms of the GNU General Public License as published by cannam@95: * the Free Software Foundation; either version 2 of the License, or cannam@95: * (at your option) any later version. cannam@95: * cannam@95: * This program is distributed in the hope that it will be useful, cannam@95: * but WITHOUT ANY WARRANTY; without even the implied warranty of cannam@95: * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the cannam@95: * GNU General Public License for more details. cannam@95: * cannam@95: * You should have received a copy of the GNU General Public License cannam@95: * along with this program; if not, write to the Free Software cannam@95: * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA cannam@95: * cannam@95: */ cannam@95: cannam@95: /* This file was automatically generated --- DO NOT EDIT */ cannam@95: /* Generated on Sun Nov 25 07:35:42 EST 2012 */ cannam@95: cannam@95: #include "codelet-dft.h" cannam@95: cannam@95: #ifdef HAVE_FMA cannam@95: cannam@95: /* Generated by: ../../../genfft/gen_notw.native -fma -reorder-insns -schedule-for-pipeline -compact -variables 4 -pipeline-latency 4 -n 2 -name n1_2 -include n.h */ cannam@95: cannam@95: /* cannam@95: * This function contains 4 FP additions, 0 FP multiplications, cannam@95: * (or, 4 additions, 0 multiplications, 0 fused multiply/add), cannam@95: * 5 stack variables, 0 constants, and 8 memory accesses cannam@95: */ cannam@95: #include "n.h" cannam@95: cannam@95: static void n1_2(const R *ri, const R *ii, R *ro, R *io, stride is, stride os, INT v, INT ivs, INT ovs) cannam@95: { cannam@95: { cannam@95: INT i; cannam@95: 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)) { cannam@95: E T1, T2, T3, T4; cannam@95: T1 = ri[0]; cannam@95: T2 = ri[WS(is, 1)]; cannam@95: T3 = ii[0]; cannam@95: T4 = ii[WS(is, 1)]; cannam@95: ro[0] = T1 + T2; cannam@95: ro[WS(os, 1)] = T1 - T2; cannam@95: io[0] = T3 + T4; cannam@95: io[WS(os, 1)] = T3 - T4; cannam@95: } cannam@95: } cannam@95: } cannam@95: cannam@95: static const kdft_desc desc = { 2, "n1_2", {4, 0, 0, 0}, &GENUS, 0, 0, 0, 0 }; cannam@95: cannam@95: void X(codelet_n1_2) (planner *p) { cannam@95: X(kdft_register) (p, n1_2, &desc); cannam@95: } cannam@95: cannam@95: #else /* HAVE_FMA */ cannam@95: cannam@95: /* Generated by: ../../../genfft/gen_notw.native -compact -variables 4 -pipeline-latency 4 -n 2 -name n1_2 -include n.h */ cannam@95: cannam@95: /* cannam@95: * This function contains 4 FP additions, 0 FP multiplications, cannam@95: * (or, 4 additions, 0 multiplications, 0 fused multiply/add), cannam@95: * 5 stack variables, 0 constants, and 8 memory accesses cannam@95: */ cannam@95: #include "n.h" cannam@95: cannam@95: static void n1_2(const R *ri, const R *ii, R *ro, R *io, stride is, stride os, INT v, INT ivs, INT ovs) cannam@95: { cannam@95: { cannam@95: INT i; cannam@95: 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)) { cannam@95: E T1, T2, T3, T4; cannam@95: T1 = ri[0]; cannam@95: T2 = ri[WS(is, 1)]; cannam@95: ro[WS(os, 1)] = T1 - T2; cannam@95: ro[0] = T1 + T2; cannam@95: T3 = ii[0]; cannam@95: T4 = ii[WS(is, 1)]; cannam@95: io[WS(os, 1)] = T3 - T4; cannam@95: io[0] = T3 + T4; cannam@95: } cannam@95: } cannam@95: } cannam@95: cannam@95: static const kdft_desc desc = { 2, "n1_2", {4, 0, 0, 0}, &GENUS, 0, 0, 0, 0 }; cannam@95: cannam@95: void X(codelet_n1_2) (planner *p) { cannam@95: X(kdft_register) (p, n1_2, &desc); cannam@95: } cannam@95: cannam@95: #endif /* HAVE_FMA */