嗯，这是最好的一点摆弄。用一个字节数组做它比用更大的元素更复杂，因为一个 14 位的数量可以跨越 3 个字节，其中 uint16_t 或更大的任何东西都需要不超过两个。但我会相信你的话，这就是你想要的（不是双关语）。此代码实际上将使用设置为 8 或更大的常量（但不会超过 int 的大小；为此，需要额外的类型转换）。当然如果大于 16 则需要调整值类型。
#include <stdio.h>
#include <stdint.h>
#include <stdlib.h>
#define W 14
uint16_t arr_get(unsigned char* arr, size_t index) {
size_t bit_index = W * index;
size_t byte_index = bit_index / 8;
unsigned bit_in_byte_index = bit_index % 8;
uint16_t result = arr[byte_index] >> bit_in_byte_index;
for (unsigned n_bits = 8 - bit_in_byte_index; n_bits < W; n_bits += 8)
result |= arr[++byte_index] << n_bits;
return result & ~(~0u << W);
}
void arr_set(unsigned char* arr, size_t index, uint16_t value) {
size_t bit_index = W * index;
size_t byte_index = bit_index / 8;
unsigned bit_in_byte_index = bit_index % 8;
arr[byte_index] &= ~(0xff << bit_in_byte_index);
arr[byte_index++] |= value << bit_in_byte_index;
unsigned n_bits = 8 - bit_in_byte_index;
value >>= n_bits;
while (n_bits < W - 8) {
arr[byte_index++] = value;
value >>= 8;
n_bits += 8;
}
arr[byte_index] &= 0xff << (W - n_bits);
arr[byte_index] |= value;
}
int main(void) {
int mod = 1 << W;
int n = 50000;
unsigned x[n];
unsigned char b[2 * n];
for (int tries = 0; tries < 10000; tries++) {
for (int i = 0; i < n; i++) {
x[i] = rand() % mod;
arr_set(b, i, x[i]);
}
for (int i = 0; i < n; i++)
if (arr_get(b, i) != x[i])
printf("Err @%d: %d should be %d\n", i, arr_get(b, i), x[i]);
}
return 0;
}
更快的版本 既然您在 cmets 中说过性能是一个问题：在原始版本中包含的小测试驱动程序上，开放编码循环使我的机器的速度提高了大约 10%。这包括随机数生成和测试，因此原语可能快 20%。我相信 16 位或 32 位数组元素会提供进一步的改进，因为字节访问很昂贵：
uint16_t arr_get(unsigned char* a, size_t i) {
size_t ib = 14 * i;
size_t iy = ib / 8;
switch (ib % 8) {
case 0:
return (a[iy] | (a[iy+1] << 8)) & 0x3fff;
case 2:
return ((a[iy] >> 2) | (a[iy+1] << 6)) & 0x3fff;
case 4:
return ((a[iy] >> 4) | (a[iy+1] << 4) | (a[iy+2] << 12)) & 0x3fff;
}
return ((a[iy] >> 6) | (a[iy+1] << 2) | (a[iy+2] << 10)) & 0x3fff;
}
#define M(IB) (~0u << (IB))
#define SETLO(IY, IB, V) a[IY] = (a[IY] & M(IB)) | ((V) >> (14 - (IB)))
#define SETHI(IY, IB, V) a[IY] = (a[IY] & ~M(IB)) | ((V) << (IB))
void arr_set(unsigned char* a, size_t i, uint16_t val) {
size_t ib = 14 * i;
size_t iy = ib / 8;
switch (ib % 8) {
case 0:
a[iy] = val;
SETLO(iy+1, 6, val);
return;
case 2:
SETHI(iy, 2, val);
a[iy+1] = val >> 6;
return;
case 4:
SETHI(iy, 4, val);
a[iy+1] = val >> 4;
SETLO(iy+2, 2, val);
return;
}
SETHI(iy, 6, val);
a[iy+1] = val >> 2;
SETLO(iy+2, 4, val);
}
另一种变体
这在我的机器上要快得多，比上面的要快 20%：
uint16_t arr_get2(unsigned char* a, size_t i) {
size_t ib = i * 14;
size_t iy = ib / 8;
unsigned buf = a[iy] | (a[iy+1] << 8) | (a[iy+2] << 16);
return (buf >> (ib % 8)) & 0x3fff;
}
void arr_set2(unsigned char* a, size_t i, unsigned val) {
size_t ib = i * 14;
size_t iy = ib / 8;
unsigned buf = a[iy] | (a[iy+1] << 8) | (a[iy+2] << 16);
unsigned io = ib % 8;
buf = (buf & ~(0x3fff << io)) | (val << io);
a[iy] = buf;
a[iy+1] = buf >> 8;
a[iy+2] = buf >> 16;
}
请注意，为了安全起见，您应该在打包数组的末尾分配一个额外的字节。即使所需的 14 位在前 2 位中，它也始终读取和写入 3 个字节。
另一种变体 最后，它的运行速度比上面的慢一点（同样在我的机器上；YMMV），但您不需要额外的字节。每个操作使用一个比较：
uint16_t arr_get2(unsigned char* a, size_t i) {
size_t ib = i * 14;
size_t iy = ib / 8;
unsigned io = ib % 8;
unsigned buf = ib % 8 <= 2
? a[iy] | (a[iy+1] << 8)
: a[iy] | (a[iy+1] << 8) | (a[iy+2] << 16);
return (buf >> io) & 0x3fff;
}
void arr_set2(unsigned char* a, size_t i, unsigned val) {
size_t ib = i * 14;
size_t iy = ib / 8;
unsigned io = ib % 8;
if (io <= 2) {
unsigned buf = a[iy] | (a[iy+1] << 8);
buf = (buf & ~(0x3fff << io)) | (val << io);
a[iy] = buf;
a[iy+1] = buf >> 8;
} else {
unsigned buf = a[iy] | (a[iy+1] << 8) | (a[iy+2] << 16);
buf = (buf & ~(0x3fff << io)) | (val << io);
a[iy] = buf;
a[iy+1] = buf >> 8;
a[iy+2] = buf >> 16;
}
}