Displaying 4 results from an estimated 4 matches for "interpolate_product_double".
2009 Oct 26
1
[PATCH] Fix miscompile of SSE resampler
...+534,7 @@ static int resampler_basic_interpolate_double(SpeexResamplerState *st, spx_uint3
sum = MULT16_32_Q15(interp[0],accum[0]) + MULT16_32_Q15(interp[1],accum[1]) + MULT16_32_Q15(interp[2],accum[2]) + MULT16_32_Q15(interp[3],accum[3]);
#else
cubic_coef(frac, interp);
- sum = interpolate_product_double(iptr, st->sinc_table + st->oversample + 4 - offset - 2, N, st->oversample, interp);
+ interpolate_product_double(&sum, iptr, st->sinc_table + st->oversample + 4 - offset - 2, N, st->oversample, interp);
#endif
out[out_stride * out_sample++] = PSHR32(sum,15...
2008 Nov 26
1
SSE2 code won't compile in VC
...sum = _mm_add_pd(sum, _mm_cvtps_pd(_mm_movehl_ps(t, t)));
}
- sum = _mm_add_sd(sum, (__m128d) _mm_movehl_ps((__m128) sum, (__m128)
sum));
+ sum = _mm_add_sd(sum, _mm_unpackhi_pd(sum, sum));
_mm_store_sd(&ret, sum);
return ret;
}
@@ -120,7 +120,7 @@ static inline double
interpolate_product_double(const float *a, const float *b,
sum1 = _mm_mul_pd(f1, sum1);
sum2 = _mm_mul_pd(f2, sum2);
sum = _mm_add_pd(sum1, sum2);
- sum = _mm_add_sd(sum, (__m128d) _mm_movehl_ps((__m128) sum, (__m128)
sum));
+ sum = _mm_add_sd(sum, _mm_unpackhi_pd(sum, sum));
_mm_store_sd(&ret, sum);
re...
2008 May 03
2
Resampler (no api)
...a+i+4), _mm_loadu_ps(b+i+4));
+ sum = _mm_add_pd(sum, _mm_cvtps_pd(t));
+ sum = _mm_add_pd(sum, _mm_cvtps_pd(_mm_movehl_ps(t, t)));
+ }
+ sum = _mm_add_sd(sum, (__m128d) _mm_movehl_ps((__m128) sum, (__m128) sum));
+ _mm_store_sd(&ret, sum);
+ return ret;
+}
+
+#define OVERRIDE_INTERPOLATE_PRODUCT_DOUBLE
+static inline double interpolate_product_double(const float *a, const float *b, unsigned int len, const spx_uint32_t oversample, float *frac) {
+ int i;
+ double ret;
+ __m128d sum;
+ __m128d sum1 = _mm_setzero_pd();
+ __m128d sum2 = _mm_setzero_pd();
+ __m128 f = _mm_loadu_ps(frac);
+ __m1...
2008 May 03
0
Resampler, memory only variant
...a+i+4), _mm_loadu_ps(b+i+4));
+ sum = _mm_add_pd(sum, _mm_cvtps_pd(t));
+ sum = _mm_add_pd(sum, _mm_cvtps_pd(_mm_movehl_ps(t, t)));
+ }
+ sum = _mm_add_sd(sum, (__m128d) _mm_movehl_ps((__m128) sum, (__m128) sum));
+ _mm_store_sd(&ret, sum);
+ return ret;
+}
+
+#define OVERRIDE_INTERPOLATE_PRODUCT_DOUBLE
+static inline double interpolate_product_double(const float *a, const float *b, unsigned int len, const spx_uint32_t oversample, float *frac) {
+ int i;
+ double ret;
+ __m128d sum;
+ __m128d sum1 = _mm_setzero_pd();
+ __m128d sum2 = _mm_setzero_pd();
+ __m128 f = _mm_loadu_ps(frac);
+ __m1...