void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm,
void *vfpst, uint32_t desc)
{
uintptr_t opr_sz = simd_oprsz(desc);
float64 *d = vd;
float64 *n = vn;
float64 *m = vm;
float_status *fpst = vfpst;
intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1);
uint64_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1);
uint64_t neg_real = flip ^ neg_imag;
uintptr_t i;
/* Shift boolean to the sign bit so we can xor to negate. */
neg_real <<= 63;
neg_imag <<= 63;
for (i = 0; i < opr_sz / 8; i += 2) {
float64 e2 = n[i + flip];
float64 e1 = m[i + flip] ^ neg_real;
float64 e4 = e2;
float64 e3 = m[i + 1 - flip] ^ neg_imag;
d[i] = float64_muladd(e2, e1, d[i], 0, fpst);
d[i + 1] = float64_muladd(e4, e3, d[i + 1], 0, fpst);
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
void HELPER(gvec_fcaddd)(void *vd, void *vn, void *vm,
void *vfpst, uint32_t desc)
{
uintptr_t opr_sz = simd_oprsz(desc);
float64 *d = vd;
float64 *n = vn;
float64 *m = vm;
float_status *fpst = vfpst;
uint64_t neg_real = extract64(desc, SIMD_DATA_SHIFT, 1);
uint64_t neg_imag = neg_real ^ 1;
uintptr_t i;
/* Shift boolean to the sign bit so we can xor to negate. */
neg_real <<= 63;
neg_imag <<= 63;
for (i = 0; i < opr_sz / 8; i += 2) {
float64 e0 = n[i];
float64 e1 = m[i + 1] ^ neg_imag;
float64 e2 = n[i + 1];
float64 e3 = m[i] ^ neg_real;
d[i] = float64_add(e0, e1, fpst);
d[i + 1] = float64_add(e2, e3, fpst);
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
void HELPER(gvec_fcadds)(void *vd, void *vn, void *vm,
void *vfpst, uint32_t desc)
{
uintptr_t opr_sz = simd_oprsz(desc);
float32 *d = vd;
float32 *n = vn;
float32 *m = vm;
float_status *fpst = vfpst;
uint32_t neg_real = extract32(desc, SIMD_DATA_SHIFT, 1);
uint32_t neg_imag = neg_real ^ 1;
uintptr_t i;
/* Shift boolean to the sign bit so we can xor to negate. */
neg_real <<= 31;
neg_imag <<= 31;
for (i = 0; i < opr_sz / 4; i += 2) {
float32 e0 = n[H4(i)];
float32 e1 = m[H4(i + 1)] ^ neg_imag;
float32 e2 = n[H4(i + 1)];
float32 e3 = m[H4(i)] ^ neg_real;
d[H4(i)] = float32_add(e0, e1, fpst);
d[H4(i + 1)] = float32_add(e2, e3, fpst);
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm,
void *vfpst, uint32_t desc)
{
uintptr_t opr_sz = simd_oprsz(desc);
float32 *d = vd;
float32 *n = vn;
float32 *m = vm;
float_status *fpst = vfpst;
intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1);
uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1);
uint32_t neg_real = flip ^ neg_imag;
uintptr_t i;
float32 e1 = m[H4(flip)];
float32 e3 = m[H4(1 - flip)];
/* Shift boolean to the sign bit so we can xor to negate. */
neg_real <<= 31;
neg_imag <<= 31;
e1 ^= neg_real;
e3 ^= neg_imag;
for (i = 0; i < opr_sz / 4; i += 2) {
float32 e2 = n[H4(i + flip)];
float32 e4 = e2;
d[H4(i)] = float32_muladd(e2, e1, d[H4(i)], 0, fpst);
d[H4(i + 1)] = float32_muladd(e4, e3, d[H4(i + 1)], 0, fpst);
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
void HELPER(gvec_mov)(void *d, void *a, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
memcpy(d, a, oprsz);
clear_high(d, oprsz, desc);
}
void HELPER(gvec_add16)(void *d, void *a, void *b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(vec16)) {
*(vec16 *)(d + i) = *(vec16 *)(a + i) + *(vec16 *)(b + i);
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_eqv)(void *d, void *a, void *b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(vec64)) {
*(vec64 *)(d + i) = ~(*(vec64 *)(a + i) ^ *(vec64 *)(b + i));
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_neg64)(void *d, void *a, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(vec64)) {
*(vec64 *)(d + i) = -*(vec64 *)(a + i);
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_adds8)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
vec8 vecb = (vec8)DUP16(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(vec8)) {
*(vec8 *)(d + i) = *(vec8 *)(a + i) + vecb;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_sar64i)(void *d, void *a, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
int shift = simd_data(desc);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(vec64)) {
*(svec64 *)(d + i) = *(svec64 *)(a + i) >> shift;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_ors)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
vec64 vecb = (vec64)DUP2(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(vec64)) {
*(vec64 *)(d + i) = *(vec64 *)(a + i) | vecb;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_muls32)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
vec32 vecb = (vec32)DUP4(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(vec32)) {
*(vec32 *)(d + i) = *(vec32 *)(a + i) * vecb;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_subs16)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
vec16 vecb = (vec16)DUP8(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(vec16)) {
*(vec16 *)(d + i) = *(vec16 *)(a + i) - vecb;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_shl32i)(void *d, void *a, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
int shift = simd_data(desc);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(vec32)) {
*(vec32 *)(d + i) = *(vec32 *)(a + i) << shift;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_umax64)(void *d, void *a, void *b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
uint64_t aa = *(uint64_t *)(a + i);
uint64_t bb = *(uint64_t *)(b + i);
uint64_t dd = aa > bb ? aa : bb;
*(uint64_t *)(d + i) = dd;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_smin16)(void *d, void *a, void *b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(int16_t)) {
int16_t aa = *(int16_t *)(a + i);
int16_t bb = *(int16_t *)(b + i);
int16_t dd = aa < bb ? aa : bb;
*(int16_t *)(d + i) = dd;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_ussub16)(void *d, void *a, void *b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
int r = *(uint16_t *)(a + i) - *(uint16_t *)(b + i);
if (r < 0) {
r = 0;
}
*(uint16_t *)(d + i) = r;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_dup32)(void *d, uint32_t desc, uint32_t c)
{
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
if (c == 0) {
oprsz = 0;
} else {
for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
*(uint32_t *)(d + i) = c;
}
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_usadd16)(void *d, void *a, void *b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
unsigned r = *(uint16_t *)(a + i) + *(uint16_t *)(b + i);
if (r > UINT16_MAX) {
r = UINT16_MAX;
}
*(uint16_t *)(d + i) = r;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_qrdmlsh_s32)(void *vd, void *vn, void *vm,
void *ve, uint32_t desc)
{
uintptr_t opr_sz = simd_oprsz(desc);
int32_t *d = vd;
int32_t *n = vn;
int32_t *m = vm;
CPUARMState *env = ve;
uintptr_t i;
for (i = 0; i < opr_sz / 4; ++i) {
d[i] = helper_neon_qrdmlsh_s32(env, n[i], m[i], d[i]);
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
void HELPER(gvec_qrdmlah_s16)(void *vd, void *vn, void *vm,
void *ve, uint32_t desc)
{
uintptr_t opr_sz = simd_oprsz(desc);
int16_t *d = vd;
int16_t *n = vn;
int16_t *m = vm;
CPUARMState *env = ve;
uintptr_t i;
for (i = 0; i < opr_sz / 2; ++i) {
d[i] = inl_qrdmlah_s16(env, n[i], m[i], d[i]);
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
void HELPER(gvec_sssub16)(void *d, void *a, void *b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(int16_t)) {
int r = *(int16_t *)(a + i) - *(int16_t *)(b + i);
if (r > INT16_MAX) {
r = INT16_MAX;
} else if (r < INT16_MIN) {
r = INT16_MIN;
}
*(int16_t *)(d + i) = r;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_usadd64)(void *d, void *a, void *b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
uint64_t ai = *(uint64_t *)(a + i);
uint64_t bi = *(uint64_t *)(b + i);
uint64_t di = ai + bi;
if (di < ai) {
di = UINT64_MAX;
}
*(uint64_t *)(d + i) = di;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_ussub32)(void *d, void *a, void *b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
uint32_t ai = *(uint32_t *)(a + i);
uint32_t bi = *(uint32_t *)(b + i);
uint32_t di = ai - bi;
if (ai < bi) {
di = 0;
}
*(uint32_t *)(d + i) = di;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_sssub64)(void *d, void *a, void *b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(int64_t)) {
int64_t ai = *(int64_t *)(a + i);
int64_t bi = *(int64_t *)(b + i);
int64_t di = ai - bi;
if (((di ^ ai) & (ai ^ bi)) < 0) {
/* Signed overflow. */
di = (di < 0 ? INT64_MAX : INT64_MIN);
}
*(int64_t *)(d + i) = di;
}
clear_high(d, oprsz, desc);
}
