static const char* decode(const char* p, uint32_t* a, uint32_t* b,
uint32_t* c, uint32_t* d) {
uint8_t key = p[0];
__m128i val = _mm_loadu_si128((const __m128i*)(p+1));
static const char* decode(const char* p, uint32_t* a, uint32_t* b,
uint32_t* c, uint32_t* d) {
uint8_t key = p[0];
__m128i val = _mm_loadu_si128((const __m128i*)(p+1));