*/
#include "config.h"
+
#include "libavutil/attributes.h"
#include "libavutil/intreadwrite.h"
+
#include "dcadsp.h"
+#include "dcamath.h"
-static void int8x8_fmul_int32_c(float *dst, const int8_t *src, int scale)
+static void decode_hf_c(int32_t dst[DCA_SUBBANDS][SAMPLES_PER_SUBBAND],
+ const int32_t vq_num[DCA_SUBBANDS],
+ const int8_t hf_vq[1024][32], intptr_t vq_offset,
+ int32_t scale[DCA_SUBBANDS][2],
+ intptr_t start, intptr_t end)
{
- float fscale = scale / 16.0;
- int i;
- for (i = 0; i < 8; i++)
- dst[i] = src[i] * fscale;
+ int i, j;
+
+ for (j = start; j < end; j++) {
+ const int8_t *ptr = &hf_vq[vq_num[j]][vq_offset];
+ for (i = 0; i < 8; i++)
+ dst[j][i] = ptr[i] * scale[j][0] + 8 >> 4;
+ }
}
-static inline void
-dca_lfe_fir(float *out, const float *in, const float *coefs,
- int decifactor)
+static inline void dca_lfe_fir(float *out, const float *in, const float *coefs,
+ int decifactor)
{
- float *out2 = out + decifactor;
- const float *cf0 = coefs;
- const float *cf1 = coefs + 256;
+ float *out2 = out + 2 * decifactor - 1;
+ int num_coeffs = 256 / decifactor;
int j, k;
/* One decimated sample generates 2*decifactor interpolated ones */
for (k = 0; k < decifactor; k++) {
float v0 = 0.0;
float v1 = 0.0;
- for (j = 0; j < 256 / decifactor; j++) {
- float s = in[-j];
- v0 += s * *cf0++;
- v1 += s * *--cf1;
+ for (j = 0; j < num_coeffs; j++, coefs++) {
+ v0 += in[-j] * *coefs;
+ v1 += in[j + 1 - num_coeffs] * *coefs;
}
*out++ = v0;
- *out2++ = v1;
+ *out2-- = v1;
}
}
-static void dca_qmf_32_subbands(float samples_in[32][8], int sb_act,
+static void dca_qmf_32_subbands(float samples_in[DCA_SUBBANDS][SAMPLES_PER_SUBBAND], int sb_act,
SynthFilterContext *synth, FFTContext *imdct,
float synth_buf_ptr[512],
int *synth_buf_offset, float synth_buf2[32],
}
synth->synth_filter_float(imdct, synth_buf_ptr, synth_buf_offset,
- synth_buf2, window, samples_out, raXin, scale);
+ synth_buf2, window, samples_out, raXin,
+ scale);
samples_out += 32;
}
}
+static void dequantize_c(int32_t *samples, uint32_t step_size, uint32_t scale)
+{
+ int64_t step = (int64_t)step_size * scale;
+ int shift, i;
+ int32_t step_scale;
+
+ if (step > (1 << 23))
+ shift = av_log2(step >> 23) + 1;
+ else
+ shift = 0;
+ step_scale = (int32_t)(step >> shift);
+
+ for (i = 0; i < SAMPLES_PER_SUBBAND; i++)
+ samples[i] = dca_clip23(dca_norm((int64_t)samples[i] * step_scale, 22 - shift));
+}
+
static void dca_lfe_fir0_c(float *out, const float *in, const float *coefs)
{
dca_lfe_fir(out, in, coefs, 32);
av_cold void ff_dcadsp_init(DCADSPContext *s)
{
- s->lfe_fir[0] = dca_lfe_fir0_c;
- s->lfe_fir[1] = dca_lfe_fir1_c;
+ s->lfe_fir[0] = dca_lfe_fir0_c;
+ s->lfe_fir[1] = dca_lfe_fir1_c;
s->qmf_32_subbands = dca_qmf_32_subbands;
- s->int8x8_fmul_int32 = int8x8_fmul_int32_c;
- if (ARCH_ARM) ff_dcadsp_init_arm(s);
- if (ARCH_X86) ff_dcadsp_init_x86(s);
+ s->decode_hf = decode_hf_c;
+ s->dequantize = dequantize_c;
+
+ if (ARCH_AARCH64)
+ ff_dcadsp_init_aarch64(s);
+ if (ARCH_ARM)
+ ff_dcadsp_init_arm(s);
+ if (ARCH_X86)
+ ff_dcadsp_init_x86(s);
}