checkasm: sw_scale: Produce more realistic test filter coefficients for yuv2yuvX

This avoids triggering overflows in the filters, and avoids stray
test failures in the approximate functions on x86; due to rounding
differences, one implementation might overflow while another one
doesn't.

Signed-off-by: Martin Storsjö <martin@martin.st>

1 files changed, 15 insertions, 1 deletions

diff --git a/tests/checkasm/sw_scale.c b/tests/checkasm/sw_scale.c
index 86d266fb3e..3b8dd310ec 100644
--- a/tests/checkasm/sw_scale.c
+++ b/tests/checkasm/sw_scale.c
@@ -187,7 +187,6 @@ static void check_yuv2yuvX(int accurate)
     uint8_t d_val = rnd();
     memset(dither, d_val, LARGEST_INPUT_SIZE);
     randomize_buffers((uint8_t*)src_pixels, LARGEST_FILTER * LARGEST_INPUT_SIZE * sizeof(int16_t));
-    randomize_buffers((uint8_t*)filter_coeff, LARGEST_FILTER * sizeof(int16_t));
     ctx = sws_alloc_context();
     if (accurate)
         ctx->flags |= SWS_ACCURATE_RND;
@@ -201,6 +200,21 @@ static void check_yuv2yuvX(int accurate)
             if (dstW <= osi)
                 continue;
             for (fsi = 0; fsi < FILTER_SIZES; ++fsi) {
+                // Generate filter coefficients for the given filter size,
+                // with some properties:
+                // - The coefficients add up to the intended sum (4096, 1<<12)
+                // - The coefficients contain negative values
+                // - The filter intermediates don't overflow for worst case
+                //   inputs (all positive coefficients are coupled with
+                //   input_max and all negative coefficients with input_min,
+                //   or vice versa).
+                // Produce a filter with all coefficients set to
+                // -((1<<12)/(filter_size-1)) except for one (randomly chosen)
+                // which is set to ((1<<13)-1).
+                for (i = 0; i < filter_sizes[fsi]; ++i)
+                    filter_coeff[i] = -((1 << 12) / (filter_sizes[fsi] - 1));
+                filter_coeff[rnd() % filter_sizes[fsi]] = (1 << 13) - 1;
+
                 src = av_malloc(sizeof(int16_t*) * filter_sizes[fsi]);
                 vFilterData = av_malloc((filter_sizes[fsi] + 2) * sizeof(union VFilterData));
                 memset(vFilterData, 0, (filter_sizes[fsi] + 2) * sizeof(union VFilterData));