/* * 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_twiddle_c -standalone -fma -reorder-insns -simd -compact -variables 100000 -include fftw-spu.h -trivial-stores -n 2 -name X(spu_t1fv_2) */ /* * This function contains 3 FP additions, 2 FP multiplications, * (or, 3 additions, 2 multiplications, 0 fused multiply/add), * 7 stack variables, 0 constants, and 4 memory accesses */ #include "fftw-spu.h" void X(spu_t1fv_2) (R *ri, R *ii, const R *W, stride rs, INT mb, INT me, INT ms) { INT m; R *x; x = ri; for (m = mb, W = W + (mb * ((TWVL / VL) * 2)); m < me; m = m + VL, x = x + (VL * ms), W = W + (TWVL * 2), MAKE_VOLATILE_STRIDE(rs)) { V T1, T3, T2, T5, T4; T1 = LD(&(x[0]), ms, &(x[0])); T2 = LD(&(x[WS(rs, 1)]), ms, &(x[WS(rs, 1)])); T3 = BYTWJ(&(W[0]), T2); T4 = VSUB(T1, T3); T5 = VADD(T1, T3); ST(&(x[WS(rs, 1)]), T4, ms, &(x[WS(rs, 1)])); ST(&(x[0]), T5, ms, &(x[0])); } }