WANG Rui
c1259aa26f
Add LSX accelerated implementation for source file analysis ...
This patch introduces an LSX-optimized version of `analyze_source_file`
for the `loongarch64` target. Similar to existing SSE2 implementation
for x86, this version:
- Processes 16-byte chunks at a time using LSX vector intrinsics.
- Quickly identifies newlines in ASCII-only chunks.
- Falls back to the generic implementation when multi-byte UTF-8
characters are detected or in the tail portion.
2025-09-28 09:35:07 +08:00
2025-09-26 04:34:09 +00:00
2025-09-27 11:29:49 +02:00
2025-09-26 18:11:09 +02:00
2025-09-24 20:34:19 +02:00
2025-09-25 20:31:56 +10:00
2025-09-25 20:31:53 +10:00
2025-09-25 20:31:53 +10:00
2025-09-26 18:11:11 +02:00
2025-09-26 18:11:09 +02:00
2025-09-26 19:09:23 -04:00
2025-09-19 20:56:07 +00:00
2025-09-26 18:11:14 +02:00
2025-09-27 11:30:57 +02:00
2025-09-26 18:11:09 +02:00
2025-09-25 20:31:53 +10:00
2025-09-26 16:37:08 +02:00
2025-09-26 19:09:23 -04:00
2025-09-26 16:37:08 +02:00
2025-09-25 20:31:58 +10:00
2025-09-22 15:10:41 -04:00
2025-09-21 10:42:47 -04:00
2025-09-26 19:09:23 -04:00
2025-09-25 20:32:00 +10:00
2025-09-25 20:36:14 +03:00
2025-09-21 13:12:18 -04:00
2025-09-27 03:50:03 +00:00
2025-09-26 09:25:56 +00:00
2025-09-26 20:44:06 +00:00
2025-09-26 16:33:15 +02:00
2025-09-27 11:29:50 +02:00
2025-09-26 09:25:56 +00:00
2025-09-26 18:11:08 +02:00
2025-09-24 13:04:19 +00:00
2025-09-28 09:35:07 +08:00
2025-09-23 10:59:29 +00:00
2025-09-26 18:11:10 +02:00
2025-09-22 14:04:04 -07:00
2025-09-26 16:33:15 +02:00
2025-09-23 20:47:34 -04:00
2025-09-25 20:31:53 +10:00
2025-09-26 16:33:15 +02:00
2025-09-19 12:00:30 -07:00
c1259aa26f