* Copyright (c) 2003 Romain Dolbeau <romain@dolbeau.org>
* Based on code Copyright (c) 2002 Fabrice Bellard.
*
- * This library is free software; you can redistribute it and/or
+ * This file is part of FFmpeg.
+ *
+ * FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
- * version 2 of the License, or (at your option) any later version.
+ * version 2.1 of the License, or (at your option) any later version.
*
- * This library is distributed in the hope that it will be useful,
+ * FFmpeg 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
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
- * License along with this library; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ * License along with FFmpeg; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
-#include "../dsputil.h"
+#include "dsputil.h"
#include "gcc_fixes.h"
-#include "dsputil_altivec.h"
-
+#include "dsputil_ppc.h"
+#include "util_altivec.h"
/*
those three macros are from libavcodec/fft.c
and are required for the reference C code
void ff_fft_calc_altivec(FFTContext *s, FFTComplex *z)
{
POWERPC_PERF_DECLARE(altivec_fft_num, s->nbits >= 6);
-#ifdef ALTIVEC_USE_REFERENCE_C_CODE
- int ln = s->nbits;
- int j, np, np2;
- int nblocks, nloops;
- register FFTComplex *p, *q;
- FFTComplex *exptab = s->exptab;
- int l;
- FFTSample tmp_re, tmp_im;
-
-POWERPC_PERF_START_COUNT(altivec_fft_num, s->nbits >= 6);
-
- np = 1 << ln;
-
- /* pass 0 */
-
- p=&z[0];
- j=(np >> 1);
- do {
- BF(p[0].re, p[0].im, p[1].re, p[1].im,
- p[0].re, p[0].im, p[1].re, p[1].im);
- p+=2;
- } while (--j != 0);
-
- /* pass 1 */
-
-
- p=&z[0];
- j=np >> 2;
- if (s->inverse) {
- do {
- BF(p[0].re, p[0].im, p[2].re, p[2].im,
- p[0].re, p[0].im, p[2].re, p[2].im);
- BF(p[1].re, p[1].im, p[3].re, p[3].im,
- p[1].re, p[1].im, -p[3].im, p[3].re);
- p+=4;
- } while (--j != 0);
- } else {
- do {
- BF(p[0].re, p[0].im, p[2].re, p[2].im,
- p[0].re, p[0].im, p[2].re, p[2].im);
- BF(p[1].re, p[1].im, p[3].re, p[3].im,
- p[1].re, p[1].im, p[3].im, -p[3].re);
- p+=4;
- } while (--j != 0);
- }
- /* pass 2 .. ln-1 */
-
- nblocks = np >> 3;
- nloops = 1 << 2;
- np2 = np >> 1;
- do {
- p = z;
- q = z + nloops;
- for (j = 0; j < nblocks; ++j) {
- BF(p->re, p->im, q->re, q->im,
- p->re, p->im, q->re, q->im);
-
- p++;
- q++;
- for(l = nblocks; l < np2; l += nblocks) {
- CMUL(tmp_re, tmp_im, exptab[l].re, exptab[l].im, q->re, q->im);
- BF(p->re, p->im, q->re, q->im,
- p->re, p->im, tmp_re, tmp_im);
- p++;
- q++;
- }
-
- p += nloops;
- q += nloops;
- }
- nblocks = nblocks >> 1;
- nloops = nloops << 1;
- } while (nblocks != 0);
-
-POWERPC_PERF_STOP_COUNT(altivec_fft_num, s->nbits >= 6);
-
-#else /* ALTIVEC_USE_REFERENCE_C_CODE */
-#ifdef CONFIG_DARWIN
- register const vector float vczero = (const vector float)(0.);
-#else
- register const vector float vczero = (const vector float){0.,0.,0.,0.};
-#endif
+ register const vector float vczero = (const vector float)vec_splat_u32(0.);
int ln = s->nbits;
- int j, np, np2;
- int nblocks, nloops;
+ int j, np, np2;
+ int nblocks, nloops;
register FFTComplex *p, *q;
FFTComplex *cptr, *cptr1;
int k;
} while (nblocks != 0);
POWERPC_PERF_STOP_COUNT(altivec_fft_num, s->nbits >= 6);
-
-#endif /* ALTIVEC_USE_REFERENCE_C_CODE */
}