diff --git a/libavutil/mem.c b/libavutil/mem.c index 36b8940a0c..62163b4cb3 100644 --- a/libavutil/mem.c +++ b/libavutil/mem.c @@ -62,7 +62,7 @@ void free(void *ptr); #endif /* MALLOC_PREFIX */ -#define ALIGN (HAVE_AVX512 ? 64 : (HAVE_AVX ? 32 : 16)) +#define ALIGN (HAVE_SIMD_ALIGN_64 ? 64 : (HAVE_SIMD_ALIGN_32 ? 32 : 16)) /* NOTE: if you want to override these functions with your own * implementations (not recommended) you have to link libav* as diff --git a/libavutil/mem_internal.h b/libavutil/mem_internal.h index 2448c606f1..b1d89a0605 100644 --- a/libavutil/mem_internal.h +++ b/libavutil/mem_internal.h @@ -76,27 +76,50 @@ */ #if defined(__INTEL_COMPILER) && __INTEL_COMPILER < 1110 || defined(__SUNPRO_C) - #define DECLARE_ALIGNED(n,t,v) t __attribute__ ((aligned (n))) v + #define DECLARE_ALIGNED_T(n,t,v) t __attribute__ ((aligned (n))) v #define DECLARE_ASM_ALIGNED(n,t,v) t __attribute__ ((aligned (n))) v #define DECLARE_ASM_CONST(n,t,v) const t __attribute__ ((aligned (n))) v #elif defined(__DJGPP__) - #define DECLARE_ALIGNED(n,t,v) t __attribute__ ((aligned (FFMIN(n, 16)))) v + #define DECLARE_ALIGNED_T(n,t,v) t __attribute__ ((aligned (FFMIN(n, 16)))) v #define DECLARE_ASM_ALIGNED(n,t,v) t av_used __attribute__ ((aligned (FFMIN(n, 16)))) v #define DECLARE_ASM_CONST(n,t,v) static const t av_used __attribute__ ((aligned (FFMIN(n, 16)))) v #elif defined(__GNUC__) || defined(__clang__) - #define DECLARE_ALIGNED(n,t,v) t __attribute__ ((aligned (n))) v + #define DECLARE_ALIGNED_T(n,t,v) t __attribute__ ((aligned (n))) v #define DECLARE_ASM_ALIGNED(n,t,v) t av_used __attribute__ ((aligned (n))) v #define DECLARE_ASM_CONST(n,t,v) static const t av_used __attribute__ ((aligned (n))) v #elif defined(_MSC_VER) - #define DECLARE_ALIGNED(n,t,v) __declspec(align(n)) t v + #define DECLARE_ALIGNED_T(n,t,v) __declspec(align(n)) t v #define DECLARE_ASM_ALIGNED(n,t,v) __declspec(align(n)) t v #define DECLARE_ASM_CONST(n,t,v) __declspec(align(n)) static const t v #else - #define DECLARE_ALIGNED(n,t,v) t v + #define DECLARE_ALIGNED_T(n,t,v) t v #define DECLARE_ASM_ALIGNED(n,t,v) t v #define DECLARE_ASM_CONST(n,t,v) static const t v #endif +#if HAVE_SIMD_ALIGN_64 + #define ALIGN_64 64 + #define ALIGN_32 32 +#elif HAVE_SIMD_ALIGN_32 + #define ALIGN_64 32 + #define ALIGN_32 32 +#else + #define ALIGN_64 16 + #define ALIGN_32 16 +#endif + +#define DECLARE_ALIGNED(n,t,v) DECLARE_ALIGNED_V(n,t,v) + +// Macro needs to be double-wrapped in order to expand +// possible other macros being passed for n. +#define DECLARE_ALIGNED_V(n,t,v) DECLARE_ALIGNED_##n(t,v) + +#define DECLARE_ALIGNED_4(t,v) DECLARE_ALIGNED_T( 4, t, v) +#define DECLARE_ALIGNED_8(t,v) DECLARE_ALIGNED_T( 8, t, v) +#define DECLARE_ALIGNED_16(t,v) DECLARE_ALIGNED_T( 16, t, v) +#define DECLARE_ALIGNED_32(t,v) DECLARE_ALIGNED_T(ALIGN_32, t, v) +#define DECLARE_ALIGNED_64(t,v) DECLARE_ALIGNED_T(ALIGN_64, t, v) + // Some broken preprocessors need a second expansion // to be forced to tokenize __VA_ARGS__ #define E1(x) x