Displaying 1 result from an estimated 1 matches for "vlit4".
2012 Jul 06
2
[LLVMdev] Excessive register spilling in large automatically generated functions, such as is found in FFTW
...///////////////////
#include <xmmintrin.h>
#define __INLINE static inline __attribute__((always_inline))
#define LOAD _mm_load_ps
#define STORE _mm_store_ps
#define ADD _mm_add_ps
#define SUB _mm_sub_ps
#define MULT _mm_mul_ps
#define STREAM _mm_stream_ps
#define SHUF _mm_shuffle_ps
#define VLIT4(a,b,c,d) _mm_set_ps(a,b,c,d)
#define SWAP(d) SHUF(d,d,_MM_SHUFFLE(2,3,0,1))
#define UNPACK2LO(a,b) SHUF(a,b,_MM_SHUFFLE(1,0,1,0))
#define UNPACK2HI(a,b) SHUF(a,b,_MM_SHUFFLE(3,2,3,2))
#define HALFBLEND(a,b) SHUF(a,b,_MM_SHUFFLE(3,2,1,0))
__INLINE void TX2(__m128 *a, __m128 *b) {
__m128 TX2_t0...