From fddc5b9bea39968ed1f45c667869428865de7626 Mon Sep 17 00:00:00 2001 From: Mans Rullgard Date: Sat, 11 Aug 2012 04:18:53 +0100 Subject: [PATCH] celp: optimise ff_celp_lp_synthesis_filter() Adding instead of subtracting the products in the loop allows the compiler to generate more efficient multiply-accumulate instructions when 16-bit multiply-subtract is not available. ARM has only multiply-accumulate for 16-bit operands. In general, if only one variant exists, it is usually accumulate rather than subtract. In the same spirit, using the dedicated saturation function enables use of any special optimised versions of this. Signed-off-by: Mans Rullgard --- libavcodec/celp_filters.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/libavcodec/celp_filters.c b/libavcodec/celp_filters.c index 4e5bcda..d764d19 100644 --- a/libavcodec/celp_filters.c +++ b/libavcodec/celp_filters.c @@ -63,17 +63,16 @@ int ff_celp_lp_synthesis_filter(int16_t *out, const int16_t *filter_coeffs, int i,n; for (n = 0; n < buffer_length; n++) { - int sum = rounder; + int sum = -rounder, sum1; for (i = 1; i <= filter_length; i++) - sum -= filter_coeffs[i-1] * out[n-i]; + sum += filter_coeffs[i-1] * out[n-i]; - sum = ((sum >> 12) + in[n]) >> shift; + sum1 = ((-sum >> 12) + in[n]) >> shift; + sum = av_clip_int16(sum1); + + if (stop_on_overflow && sum != sum1) + return 1; - if (sum + 0x8000 > 0xFFFFU) { - if (stop_on_overflow) - return 1; - sum = (sum >> 31) ^ 32767; - } out[n] = sum; } -- 2.7.4