Commit Graph

10 Commits

Author SHA1 Message Date
Martin Storsjö
8e4c904c8e checkasm: ac3dsp: Increase the float tolerance for sum_square_butterfly_float
Accept up to 13 ULP difference.

This fixes running "checkasm --test=ac3dsp 3044836819" on ARM.

Depending on how the SIMD implementations aggregate numbers,
larger/smaller values might not end up accumulated in exactly
the same way; the current NEON implementation for ARM aggregates
into vectors of 2 elements. If it would aggregate into vectors
of 4 elements instead, like the AArch64 version does, this particular
case would end up with a smaller difference.
2025-08-10 02:27:44 +00:00
Martin Storsjö
0400e05a1a checkasm: ac3dsp: Fix function name typos for sum_square_butterfly 2025-08-10 02:27:44 +00:00
Timo Rothenpieler
262d41c804 all: fix typos found by codespell 2025-08-03 13:48:47 +02:00
Martin Storsjö
97a708a507 checkasm: Increase the tolerance for ac3_sum_square_butterfly_float
Increase the tolerance from 10 ulp to 11 ulp. This fixes occasional
errors for some inputs; the errors could be reproduced on
aarch64/neon builds, with "checkasm --test=ac3dsp 3446175925".

Signed-off-by: Martin Storsjö <martin@martin.st>
2024-07-24 12:10:33 +03:00
Geoff Hill
ee1bc723de avcodec/ac3: Implement sum_square_butterfly_float for aarch64 NEON
Signed-off-by: Geoff Hill <geoff@geoffhill.org>
Signed-off-by: Martin Storsjö <martin@martin.st>
2024-04-08 13:36:40 +03:00
Geoff Hill
42e88f18f3 avcodec/ac3: Implement sum_square_butterfly_int32 for aarch64 NEON
Signed-off-by: Geoff Hill <geoff@geoffhill.org>
Signed-off-by: Martin Storsjö <martin@martin.st>
2024-04-08 13:36:40 +03:00
Geoff Hill
69cb34f885 avcodec/ac3: Implement ac3_extract_exponents for aarch64 NEON
Signed-off-by: Geoff Hill <geoff@geoffhill.org>
Signed-off-by: Martin Storsjö <martin@martin.st>
2024-04-08 13:36:40 +03:00
Geoff Hill
6f6bd10531 avcodec/ac3: Implement ac3_exponent_min for aarch64 NEON
Signed-off-by: Geoff Hill <geoff@geoffhill.org>
Signed-off-by: Martin Storsjö <martin@martin.st>
2024-04-08 13:36:40 +03:00
Martin Storsjö
12598e72e3 checkasm: Fix the signature of float_to_fixed24
The len parameter was changed from unsigned int to size_t in
567c67c6c8.

This fixes crashes in the reference C code, when running checkasm
on aarch64.

Signed-off-by: Martin Storsjö <martin@martin.st>
2023-12-02 18:16:09 +02:00
sunyuechi
d0ec826077 checkasm/ac3dsp: add float_to_fixed24 test
Signed-off-by: Rémi Denis-Courmont <remi@remlab.net>
2023-12-01 20:26:48 +02:00