akallabeth
e049be9837
[codec] log primitives used
2025-06-13 13:52:28 +02:00
akallabeth
0bb49c94c9
[restrict] unify restrict keyword usage
2025-03-10 18:48:16 +01:00
akallabeth
22efdfbc8f
[simd] move CPU feature detection
...
Use static inline functions in header to do CPU feature detection.
The c files are already compiled/linked with SIMD support and might have
used instructions from that featureset already.
2025-02-12 14:24:10 +01:00
akallabeth
fd13e9b919
[primitives,sse] unify load/store
...
* Use LOAD_SI128 to load __m128i values
* Use STORE_SI128 to store __m128i values
2025-02-12 14:24:10 +01:00
akallabeth
01a6b1e7e5
[codec,sse] split nsc_encode_argb_to_aycocg_sse2
2025-02-11 10:14:43 +01:00
Armin Novak
664321dd04
[clang,tidy] fix cast warnings
2025-01-15 15:35:09 +01:00
akallabeth
cc934795e4
[warnings] fix integer casting
...
* use asserting casts to detect overflows or sign conversions
* code cleanup for issues uncovered by casts
2025-01-01 12:58:34 +01:00
akallabeth
b4976163cd
[CMake,simd] unify WITH_SSE2, WITH_AVX2, WITH_NEON
...
* Add new CMake option WITH_SIMD to enable best available instruction
type
* Unify simd related defines in single header
2024-12-03 11:54:36 +01:00
akallabeth
239440e28d
[warnings] remove or comment unused macros
2024-09-20 18:49:38 +02:00
akallabeth
36c3184a0f
[warnings] fix clang-tidy issues in libfreerdp
2024-08-29 15:34:22 +02:00
akallabeth
15456e1ee1
[warnings] fix implicit widening conversion
2024-08-29 10:47:20 +02:00
akallabeth
896ea3c445
[primitives,codec] guard SSE code with platform
...
SSE optimized code might be used in multiarch/universal builds.
So not only guard with WITH_SSE2 but also with architecture defines from
winpr/platform.h
2024-06-25 09:56:52 +02:00
akallabeth
2ee987e665
[cmake,codec] refactor codec
...
* move sse and neon implementations to own subdirectories
* add stubs for missing optimizations (with log messages)
2024-06-11 12:16:20 +02:00
