/* * Copyright (c) 2003, 2007-8 Matteo Frigo * Copyright (c) 2003, 2007-8 Massachusetts Institute of Technology * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA * */ /* Generated by: ../../genfft/gen_notw_c -standalone -fma -reorder-insns -simd -compact -variables 100000 -with-ostride 2 -include fftw-spu.h -n 3 -name X(spu_n2fv_3) */ /* * This function contains 6 FP additions, 4 FP multiplications, * (or, 3 additions, 1 multiplications, 3 fused multiply/add), * 11 stack variables, 2 constants, and 6 memory accesses */ #include "fftw-spu.h" void X(spu_n2fv_3) (const R *ri, const R *ii, R *ro, R *io, stride is, stride os, INT v, INT ivs, INT ovs) { DVK(KP500000000, +0.500000000000000000000000000000000000000000000); DVK(KP866025403, +0.866025403784438646763723170752936183471402627); INT i; const R *xi; R *xo; xi = ri; xo = ro; for (i = v; i > 0; i = i - VL, xi = xi + (VL * ivs), xo = xo + (VL * ovs), MAKE_VOLATILE_STRIDE(is), MAKE_VOLATILE_STRIDE(os)) { V T1, T4, T6, T2, T3, T5; T1 = LD(&(xi[0]), ivs, &(xi[0])); T2 = LD(&(xi[WS(is, 1)]), ivs, &(xi[WS(is, 1)])); T3 = LD(&(xi[WS(is, 2)]), ivs, &(xi[0])); T4 = VADD(T2, T3); T6 = VMUL(LDK(KP866025403), VSUB(T3, T2)); ST(&(xo[0]), VADD(T1, T4), ovs, &(xo[0])); T5 = VFNMS(LDK(KP500000000), T4, T1); ST(&(xo[4]), VFNMSI(T6, T5), ovs, &(xo[0])); ST(&(xo[2]), VFMAI(T6, T5), ovs, &(xo[2])); } }