#include "tcg/tcg-gvec-desc.h"
-typedef uint8_t vec8;
-typedef uint16_t vec16;
-typedef uint32_t vec32;
-typedef uint64_t vec64;
-
-typedef int8_t svec8;
-typedef int16_t svec16;
-typedef int32_t svec32;
-typedef int64_t svec64;
-
#define DUP16(X) X
#define DUP8(X) X
#define DUP4(X) X
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec8)) {
- *(vec8 *)(d + i) = *(vec8 *)(a + i) + *(vec8 *)(b + i);
+ for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
+ *(uint8_t *)(d + i) = *(uint8_t *)(a + i) + *(uint8_t *)(b + i);
}
clear_high(d, oprsz, 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);
+ for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
+ *(uint16_t *)(d + i) = *(uint16_t *)(a + i) + *(uint16_t *)(b + i);
}
clear_high(d, oprsz, desc);
}
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec32)) {
- *(vec32 *)(d + i) = *(vec32 *)(a + i) + *(vec32 *)(b + i);
+ for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
+ *(uint32_t *)(d + i) = *(uint32_t *)(a + i) + *(uint32_t *)(b + i);
}
clear_high(d, oprsz, 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);
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) + *(uint64_t *)(b + 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);
+ uint8_t vecb = (uint8_t)DUP16(b);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec8)) {
- *(vec8 *)(d + i) = *(vec8 *)(a + i) + vecb;
+ for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
+ *(uint8_t *)(d + i) = *(uint8_t *)(a + i) + vecb;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_adds16)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- vec16 vecb = (vec16)DUP8(b);
+ uint16_t vecb = (uint16_t)DUP8(b);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec16)) {
- *(vec16 *)(d + i) = *(vec16 *)(a + i) + vecb;
+ for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
+ *(uint16_t *)(d + i) = *(uint16_t *)(a + i) + vecb;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_adds32)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- vec32 vecb = (vec32)DUP4(b);
+ uint32_t vecb = (uint32_t)DUP4(b);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec32)) {
- *(vec32 *)(d + i) = *(vec32 *)(a + i) + vecb;
+ for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
+ *(uint32_t *)(d + i) = *(uint32_t *)(a + i) + vecb;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_adds64)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- vec64 vecb = (vec64)DUP2(b);
+ uint64_t vecb = (uint64_t)DUP2(b);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec64)) {
- *(vec64 *)(d + i) = *(vec64 *)(a + i) + vecb;
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) + vecb;
}
clear_high(d, oprsz, desc);
}
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec8)) {
- *(vec8 *)(d + i) = *(vec8 *)(a + i) - *(vec8 *)(b + i);
+ for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
+ *(uint8_t *)(d + i) = *(uint8_t *)(a + i) - *(uint8_t *)(b + i);
}
clear_high(d, oprsz, 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);
+ for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
+ *(uint16_t *)(d + i) = *(uint16_t *)(a + i) - *(uint16_t *)(b + i);
}
clear_high(d, oprsz, desc);
}
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec32)) {
- *(vec32 *)(d + i) = *(vec32 *)(a + i) - *(vec32 *)(b + i);
+ for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
+ *(uint32_t *)(d + i) = *(uint32_t *)(a + i) - *(uint32_t *)(b + i);
}
clear_high(d, oprsz, 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);
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) - *(uint64_t *)(b + i);
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_subs8)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- vec8 vecb = (vec8)DUP16(b);
+ uint8_t vecb = (uint8_t)DUP16(b);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec8)) {
- *(vec8 *)(d + i) = *(vec8 *)(a + i) - vecb;
+ for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
+ *(uint8_t *)(d + i) = *(uint8_t *)(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);
+ uint16_t vecb = (uint16_t)DUP8(b);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec16)) {
- *(vec16 *)(d + i) = *(vec16 *)(a + i) - vecb;
+ for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
+ *(uint16_t *)(d + i) = *(uint16_t *)(a + i) - vecb;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_subs32)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- vec32 vecb = (vec32)DUP4(b);
+ uint32_t vecb = (uint32_t)DUP4(b);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec32)) {
- *(vec32 *)(d + i) = *(vec32 *)(a + i) - vecb;
+ for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
+ *(uint32_t *)(d + i) = *(uint32_t *)(a + i) - vecb;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_subs64)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- vec64 vecb = (vec64)DUP2(b);
+ uint64_t vecb = (uint64_t)DUP2(b);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec64)) {
- *(vec64 *)(d + i) = *(vec64 *)(a + i) - vecb;
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) - vecb;
}
clear_high(d, oprsz, desc);
}
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec8)) {
- *(vec8 *)(d + i) = *(vec8 *)(a + i) * *(vec8 *)(b + i);
+ for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
+ *(uint8_t *)(d + i) = *(uint8_t *)(a + i) * *(uint8_t *)(b + i);
}
clear_high(d, oprsz, 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);
+ for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
+ *(uint16_t *)(d + i) = *(uint16_t *)(a + i) * *(uint16_t *)(b + i);
}
clear_high(d, oprsz, desc);
}
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec32)) {
- *(vec32 *)(d + i) = *(vec32 *)(a + i) * *(vec32 *)(b + i);
+ for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
+ *(uint32_t *)(d + i) = *(uint32_t *)(a + i) * *(uint32_t *)(b + i);
}
clear_high(d, oprsz, 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);
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) * *(uint64_t *)(b + i);
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_muls8)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- vec8 vecb = (vec8)DUP16(b);
+ uint8_t vecb = (uint8_t)DUP16(b);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec8)) {
- *(vec8 *)(d + i) = *(vec8 *)(a + i) * vecb;
+ for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
+ *(uint8_t *)(d + i) = *(uint8_t *)(a + i) * vecb;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_muls16)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- vec16 vecb = (vec16)DUP8(b);
+ uint16_t vecb = (uint16_t)DUP8(b);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec16)) {
- *(vec16 *)(d + i) = *(vec16 *)(a + i) * vecb;
+ for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
+ *(uint16_t *)(d + i) = *(uint16_t *)(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);
+ uint32_t vecb = (uint32_t)DUP4(b);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec32)) {
- *(vec32 *)(d + i) = *(vec32 *)(a + i) * vecb;
+ for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
+ *(uint32_t *)(d + i) = *(uint32_t *)(a + i) * vecb;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_muls64)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- vec64 vecb = (vec64)DUP2(b);
+ uint64_t vecb = (uint64_t)DUP2(b);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec64)) {
- *(vec64 *)(d + i) = *(vec64 *)(a + i) * vecb;
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) * vecb;
}
clear_high(d, oprsz, desc);
}
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec8)) {
- *(vec8 *)(d + i) = -*(vec8 *)(a + i);
+ for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
+ *(uint8_t *)(d + i) = -*(uint8_t *)(a + i);
}
clear_high(d, oprsz, desc);
}
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec16)) {
- *(vec16 *)(d + i) = -*(vec16 *)(a + i);
+ for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
+ *(uint16_t *)(d + i) = -*(uint16_t *)(a + i);
}
clear_high(d, oprsz, desc);
}
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec32)) {
- *(vec32 *)(d + i) = -*(vec32 *)(a + i);
+ for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
+ *(uint32_t *)(d + i) = -*(uint32_t *)(a + i);
}
clear_high(d, oprsz, desc);
}
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec64)) {
- *(vec64 *)(d + i) = -*(vec64 *)(a + i);
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = -*(uint64_t *)(a + i);
}
clear_high(d, oprsz, desc);
}
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec64)) {
- *(vec64 *)(d + i) = ~*(vec64 *)(a + i);
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = ~*(uint64_t *)(a + i);
}
clear_high(d, oprsz, 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);
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) & *(uint64_t *)(b + i);
}
clear_high(d, oprsz, 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);
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) | *(uint64_t *)(b + i);
}
clear_high(d, oprsz, 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);
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) ^ *(uint64_t *)(b + i);
}
clear_high(d, oprsz, 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);
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) &~ *(uint64_t *)(b + i);
}
clear_high(d, oprsz, 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);
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) |~ *(uint64_t *)(b + i);
}
clear_high(d, oprsz, 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));
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = ~(*(uint64_t *)(a + i) & *(uint64_t *)(b + i));
}
clear_high(d, oprsz, 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));
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = ~(*(uint64_t *)(a + i) | *(uint64_t *)(b + i));
}
clear_high(d, oprsz, 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));
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = ~(*(uint64_t *)(a + i) ^ *(uint64_t *)(b + i));
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_ands)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- vec64 vecb = (vec64)DUP2(b);
+ uint64_t vecb = (uint64_t)DUP2(b);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec64)) {
- *(vec64 *)(d + i) = *(vec64 *)(a + i) & vecb;
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) & vecb;
}
clear_high(d, oprsz, desc);
}
void HELPER(gvec_xors)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- vec64 vecb = (vec64)DUP2(b);
+ uint64_t vecb = (uint64_t)DUP2(b);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec64)) {
- *(vec64 *)(d + i) = *(vec64 *)(a + i) ^ vecb;
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) ^ vecb;
}
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);
+ uint64_t vecb = (uint64_t)DUP2(b);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec64)) {
- *(vec64 *)(d + i) = *(vec64 *)(a + i) | vecb;
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) | vecb;
}
clear_high(d, oprsz, desc);
}
int shift = simd_data(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec8)) {
- *(vec8 *)(d + i) = *(vec8 *)(a + i) << shift;
+ for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
+ *(uint8_t *)(d + i) = *(uint8_t *)(a + i) << shift;
}
clear_high(d, oprsz, desc);
}
int shift = simd_data(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec16)) {
- *(vec16 *)(d + i) = *(vec16 *)(a + i) << shift;
+ for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
+ *(uint16_t *)(d + i) = *(uint16_t *)(a + i) << shift;
}
clear_high(d, 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;
+ for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
+ *(uint32_t *)(d + i) = *(uint32_t *)(a + i) << shift;
}
clear_high(d, oprsz, desc);
}
int shift = simd_data(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec64)) {
- *(vec64 *)(d + i) = *(vec64 *)(a + i) << shift;
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) << shift;
}
clear_high(d, oprsz, desc);
}
int shift = simd_data(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec8)) {
- *(vec8 *)(d + i) = *(vec8 *)(a + i) >> shift;
+ for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
+ *(uint8_t *)(d + i) = *(uint8_t *)(a + i) >> shift;
}
clear_high(d, oprsz, desc);
}
int shift = simd_data(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec16)) {
- *(vec16 *)(d + i) = *(vec16 *)(a + i) >> shift;
+ for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
+ *(uint16_t *)(d + i) = *(uint16_t *)(a + i) >> shift;
}
clear_high(d, 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;
+ for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
+ *(uint32_t *)(d + i) = *(uint32_t *)(a + i) >> shift;
}
clear_high(d, oprsz, desc);
}
int shift = simd_data(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec64)) {
- *(vec64 *)(d + i) = *(vec64 *)(a + i) >> shift;
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) >> shift;
}
clear_high(d, oprsz, desc);
}
int shift = simd_data(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec8)) {
- *(svec8 *)(d + i) = *(svec8 *)(a + i) >> shift;
+ for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
+ *(int8_t *)(d + i) = *(int8_t *)(a + i) >> shift;
}
clear_high(d, oprsz, desc);
}
int shift = simd_data(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec16)) {
- *(svec16 *)(d + i) = *(svec16 *)(a + i) >> shift;
+ for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
+ *(int16_t *)(d + i) = *(int16_t *)(a + i) >> shift;
}
clear_high(d, oprsz, desc);
}
int shift = simd_data(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec32)) {
- *(svec32 *)(d + i) = *(svec32 *)(a + i) >> shift;
+ for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
+ *(int32_t *)(d + i) = *(int32_t *)(a + i) >> shift;
}
clear_high(d, 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;
+ for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+ *(int64_t *)(d + i) = *(int64_t *)(a + i) >> shift;
}
clear_high(d, oprsz, desc);
}
}
#define DO_CMP2(SZ) \
- DO_CMP1(gvec_eq##SZ, vec##SZ, ==) \
- DO_CMP1(gvec_ne##SZ, vec##SZ, !=) \
- DO_CMP1(gvec_lt##SZ, svec##SZ, <) \
- DO_CMP1(gvec_le##SZ, svec##SZ, <=) \
- DO_CMP1(gvec_ltu##SZ, vec##SZ, <) \
- DO_CMP1(gvec_leu##SZ, vec##SZ, <=)
+ DO_CMP1(gvec_eq##SZ, uint##SZ##_t, ==) \
+ DO_CMP1(gvec_ne##SZ, uint##SZ##_t, !=) \
+ DO_CMP1(gvec_lt##SZ, int##SZ##_t, <) \
+ DO_CMP1(gvec_le##SZ, int##SZ##_t, <=) \
+ DO_CMP1(gvec_ltu##SZ, uint##SZ##_t, <) \
+ DO_CMP1(gvec_leu##SZ, uint##SZ##_t, <=)
DO_CMP2(8)
DO_CMP2(16)
intptr_t oprsz = simd_oprsz(desc);
intptr_t i;
- for (i = 0; i < oprsz; i += sizeof(vec64)) {
- vec64 aa = *(vec64 *)(a + i);
- vec64 bb = *(vec64 *)(b + i);
- vec64 cc = *(vec64 *)(c + i);
- *(vec64 *)(d + i) = (bb & aa) | (cc & ~aa);
+ 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 cc = *(uint64_t *)(c + i);
+ *(uint64_t *)(d + i) = (bb & aa) | (cc & ~aa);
}
clear_high(d, oprsz, desc);
}