Files
ardour/libs
Ayan Shafqat 98eab68044 aarch64: fix unaligned count and peak computation
Clamp misaligned prefix loops to the remaining frame count to avoid
nframes underflow and potential out-of-bounds access for small buffers.

Apply vabsq_f32() to all SIMD loads before peak reduction to ensure
correct absolute peak calculation in unrolled NEON paths.
2025-12-29 20:12:43 -05:00
..
2025-02-01 11:30:14 +01:00
2025-12-13 16:05:09 +01:00
2025-10-22 19:34:48 +02:00
2025-12-16 19:59:40 +01:00
2025-10-22 19:34:48 +02:00
2025-12-20 12:27:09 +00:00
2025-10-22 18:26:08 +02:00
2025-10-22 18:48:40 +02:00