This is an automated email from the git hooks/post-receive script.

Git pushed a commit to branch master
in repository ffmpeg.

commit adacc96aa789602d6cc36350f0b9f27f59ece540
Author:     Niklas Haas <[email protected]>
AuthorDate: Sat Aug 29 15:37:22 2026 +0200
Commit:     Niklas Haas <[email protected]>
CommitDate: Tue Sep 1 13:15:06 2026 +0200

    tests/checkasm/vf_colordetect: benchmark on aligned width
    
    This gives a more faithful representation of the SIMD speedup, as the
    unaligned checkasm test case size is not representative of typical inputs.
    
    checkasm:
     - CPU: AMD Ryzen 9 9950X3D 16-Core Processor (00B40F40)
     - Timing source: x86 (rdtsc)
     - Bench duration: 100000 µs per function (432431813 cycles)
     - Random seed: 2646589325
    
    Benchmark results:
      name                                  cycles (vs ref)
      detect_alpha_8_full_c:                7335.9
      detect_alpha_8_full_avx2:              396.2 (18.51x)
      detect_alpha_8_full_avx512icl:         191.0 (38.41x)
      detect_alpha_8_full_off_c:            7324.1
      detect_alpha_8_full_off_avx2:          404.0 (18.13x)
      detect_alpha_8_full_off_avx512icl:     199.1 (36.74x)
      detect_alpha_8_limited_c:            12848.8
      detect_alpha_8_limited_avx2:          1088.7 (11.80x)
      detect_alpha_8_limited_avx512icl:      563.7 (22.79x)
      detect_alpha_16_full_c:               3360.0
      detect_alpha_16_full_avx2:             391.8 ( 8.57x)
      detect_alpha_16_full_avx512icl:        190.5 (17.64x)
      detect_alpha_16_full_off_c:           3362.8
      detect_alpha_16_full_off_avx2:         404.9 ( 8.31x)
      detect_alpha_16_full_off_avx512icl:    200.3 (16.76x)
      detect_alpha_16_limited_c:            7771.7
      detect_alpha_16_limited_avx2:         1210.8 ( 6.42x)
      detect_alpha_16_limited_avx512icl:     603.6 (12.88x)
      detect_range_8_c:                     1233.1
      detect_range_8_avx2:                   254.9 ( 4.84x)
      detect_range_8_avx512icl:              134.0 ( 9.20x)
      detect_range_16_c:                    1172.2
      detect_range_16_avx2:                  177.9 ( 6.58x)
      detect_range_16_avx512icl:              96.0 (12.20x)
    
    Sponsored-by: nxtedition AB
    Signed-off-by: Niklas Haas <[email protected]>
---
 tests/checkasm/vf_colordetect.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tests/checkasm/vf_colordetect.c b/tests/checkasm/vf_colordetect.c
index d16526090f..b033b1731f 100644
--- a/tests/checkasm/vf_colordetect.c
+++ b/tests/checkasm/vf_colordetect.c
@@ -65,7 +65,7 @@ static void check_range_detect(int depth)
 
         /* Test performance of base case without any out-of-range values */
         memset(in, 0x80, HEIGHT * STRIDE);
-        bench_new(in, STRIDE, w, HEIGHT, mpeg_min, mpeg_max);
+        bench_new(in, STRIDE, (w & ~31), HEIGHT, mpeg_min, mpeg_max);
     }
 }
 
@@ -146,7 +146,7 @@ static void check_alpha_detect(int depth, enum AVColorRange 
range, int offset)
         if (res_ref != res_new)
             fail();
 
-        bench_new(luma, STRIDE, alpha, STRIDE, w, HEIGHT, alpha_max, 
mpeg_range, offset);
+        bench_new(luma, STRIDE, alpha, STRIDE, (w & ~31), HEIGHT, alpha_max, 
mpeg_range, offset);
     }
 }
 

-- 
To stop receiving notification emails like this one, please contact
[email protected].
_______________________________________________
ffmpeg-cvslog mailing list -- [email protected]
To unsubscribe send an email to [email protected]

Reply via email to