#define vec_load(a) (*(a))
#define vec_store(a,b) *(a)=(b)
#define vec_add_16(a,b) _mm_add_pi16(a,b)
#define vec_sub_16(a,b) _mm_sub_pi16(a,b)
#define vec_load_psqt(a) (*(a))
#define vec_store_psqt(a,b) *(a)=(b)
#define vec_load(a) (*(a))
#define vec_store(a,b) *(a)=(b)
#define vec_add_16(a,b) _mm_add_pi16(a,b)
#define vec_sub_16(a,b) _mm_sub_pi16(a,b)
#define vec_load_psqt(a) (*(a))
#define vec_store_psqt(a,b) *(a)=(b)
- #define vec_add_psqt_32(a,b) a+b
- #define vec_sub_psqt_32(a,b) a-b
- #define vec_zero_psqt() 0
+ #define vec_add_psqt_32(a,b) _mm_add_pi32(a,b)
+ #define vec_sub_psqt_32(a,b) _mm_sub_pi32(a,b)
+ #define vec_zero_psqt() _mm_setzero_si64()
// Number of output dimensions for one side
static constexpr IndexType HalfDimensions = TransformedFeatureDimensions;
// Number of output dimensions for one side
static constexpr IndexType HalfDimensions = TransformedFeatureDimensions;
#ifdef VECTOR
static constexpr IndexType TileHeight = NumRegs * sizeof(vec_t) / 2;
static constexpr IndexType PsqtTileHeight = NumPsqtRegs * sizeof(psqt_vec_t) / 4;
#ifdef VECTOR
static constexpr IndexType TileHeight = NumRegs * sizeof(vec_t) / 2;
static constexpr IndexType PsqtTileHeight = NumPsqtRegs * sizeof(psqt_vec_t) / 4;
- std::pair<std::int32_t, bool> transform(const Position& pos, OutputType* output, int bucket) const {
+ std::pair<std::int32_t, bool> transform(const Position& pos, OutputType* output, int bucket, Value lazyThreshold) const {
update_accumulator(pos, WHITE);
update_accumulator(pos, BLACK);
update_accumulator(pos, WHITE);
update_accumulator(pos, BLACK);