What is the most efficient algorithm to achieve the following:
0010 0000 => 0000 0100
The conversion is from MSB->LSB to LSB->MSB. All bits must be reversed; that is, this is not endianness-swapping.
This question is related to
c
algorithm
bit-manipulation
You might want to use the standard template library. It might be slower than the above mentioned code. However, it seems to me clearer and easier to understand.
#include<bitset>
#include<iostream>
template<size_t N>
const std::bitset<N> reverse(const std::bitset<N>& ordered)
{
std::bitset<N> reversed;
for(size_t i = 0, j = N - 1; i < N; ++i, --j)
reversed[j] = ordered[i];
return reversed;
};
// test the function
int main()
{
unsigned long num;
const size_t N = sizeof(num)*8;
std::cin >> num;
std::cout << std::showbase << std::hex;
std::cout << "ordered = " << num << std::endl;
std::cout << "reversed = " << reverse<N>(num).to_ulong() << std::endl;
std::cout << "double_reversed = " << reverse<N>(reverse<N>(num)).to_ulong() << std::endl;
}
unsigned char ReverseBits(unsigned char data)
{
unsigned char k = 0, rev = 0;
unsigned char n = data;
while(n)
{
k = n & (~(n - 1));
n &= (n - 1);
rev |= (128 / k);
}
return rev;
}
Native ARM instruction "rbit" can do it with 1 cpu cycle and 1 extra cpu register, impossible to beat.
This is for 32 bit, we need to change the size if we consider 8 bits.
void bitReverse(int num)
{
int num_reverse = 0;
int size = (sizeof(int)*8) -1;
int i=0,j=0;
for(i=0,j=size;i<=size,j>=0;i++,j--)
{
if((num >> i)&1)
{
num_reverse = (num_reverse | (1<<j));
}
}
printf("\n rev num = %d\n",num_reverse);
}
Reading the input integer "num" in LSB->MSB order and storing in num_reverse in MSB->LSB order.
Another loop-based solution that exits quickly when the number is low (in C++ for multiple types)
template<class T>
T reverse_bits(T in) {
T bit = static_cast<T>(1) << (sizeof(T) * 8 - 1);
T out;
for (out = 0; bit && in; bit >>= 1, in >>= 1) {
if (in & 1) {
out |= bit;
}
}
return out;
}
or in C for an unsigned int
unsigned int reverse_bits(unsigned int in) {
unsigned int bit = 1u << (sizeof(T) * 8 - 1);
unsigned int out;
for (out = 0; bit && in; bit >>= 1, in >>= 1) {
if (in & 1)
out |= bit;
}
return out;
}
Efficient can mean throughput or latency.
For throughout, see the answer by Anders Cedronius, it’s a good one.
For lower latency, I would recommend this code:
uint32_t reverseBits( uint32_t x )
{
#if defined(__arm__) || defined(__aarch64__)
__asm__( "rbit %0, %1" : "=r" ( x ) : "r" ( x ) );
return x;
#endif
// Flip pairwise
x = ( ( x & 0x55555555 ) << 1 ) | ( ( x & 0xAAAAAAAA ) >> 1 );
// Flip pairs
x = ( ( x & 0x33333333 ) << 2 ) | ( ( x & 0xCCCCCCCC ) >> 2 );
// Flip nibbles
x = ( ( x & 0x0F0F0F0F ) << 4 ) | ( ( x & 0xF0F0F0F0 ) >> 4 );
// Flip bytes. CPUs have an instruction for that, pretty fast one.
#ifdef _MSC_VER
return _byteswap_ulong( x );
#elif defined(__INTEL_COMPILER)
return (uint32_t)_bswap( (int)x );
#else
// Assuming gcc or clang
return __builtin_bswap32( x );
#endif
}
Compilers output: https://godbolt.org/z/5ehd89
I thought this is one of the simplest way to reverse the bit. please let me know if there is any flaw in this logic. basically in this logic, we check the value of the bit in position. set the bit if value is 1 on reversed position.
void bit_reverse(ui32 *data)
{
ui32 temp = 0;
ui32 i, bit_len;
{
for(i = 0, bit_len = 31; i <= bit_len; i++)
{
temp |= (*data & 1 << i)? (1 << bit_len-i) : 0;
}
*data = temp;
}
return;
}
My simple solution
BitReverse(IN)
OUT = 0x00;
R = 1; // Right mask ...0000.0001
L = 0; // Left mask 1000.0000...
L = ~0;
L = ~(i >> 1);
int size = sizeof(IN) * 4; // bit size
while(size--){
if(IN & L) OUT = OUT | R; // start from MSB 1000.xxxx
if(IN & R) OUT = OUT | L; // start from LSB xxxx.0001
L = L >> 1;
R = R << 1;
}
return OUT;
I was curious how fast would be the obvious raw rotation.
On my machine (i7@2600), the average for 1,500,150,000 iterations was 27.28 ns (over a a random set of 131,071 64-bit integers).
Advantages: the amount of memory needed is little and the code is simple. I would say it is not that large, either. The time required is predictable and constant for any input (128 arithmetic SHIFT operations + 64 logical AND operations + 64 logical OR operations).
I compared to the best time obtained by @Matt J - who has the accepted answer. If I read his answer correctly, the best he has got was 0.631739 seconds for 1,000,000 iterations, which leads to an average of 631 ns per rotation.
The code snippet I used is this one below:
unsigned long long reverse_long(unsigned long long x)
{
return (((x >> 0) & 1) << 63) |
(((x >> 1) & 1) << 62) |
(((x >> 2) & 1) << 61) |
(((x >> 3) & 1) << 60) |
(((x >> 4) & 1) << 59) |
(((x >> 5) & 1) << 58) |
(((x >> 6) & 1) << 57) |
(((x >> 7) & 1) << 56) |
(((x >> 8) & 1) << 55) |
(((x >> 9) & 1) << 54) |
(((x >> 10) & 1) << 53) |
(((x >> 11) & 1) << 52) |
(((x >> 12) & 1) << 51) |
(((x >> 13) & 1) << 50) |
(((x >> 14) & 1) << 49) |
(((x >> 15) & 1) << 48) |
(((x >> 16) & 1) << 47) |
(((x >> 17) & 1) << 46) |
(((x >> 18) & 1) << 45) |
(((x >> 19) & 1) << 44) |
(((x >> 20) & 1) << 43) |
(((x >> 21) & 1) << 42) |
(((x >> 22) & 1) << 41) |
(((x >> 23) & 1) << 40) |
(((x >> 24) & 1) << 39) |
(((x >> 25) & 1) << 38) |
(((x >> 26) & 1) << 37) |
(((x >> 27) & 1) << 36) |
(((x >> 28) & 1) << 35) |
(((x >> 29) & 1) << 34) |
(((x >> 30) & 1) << 33) |
(((x >> 31) & 1) << 32) |
(((x >> 32) & 1) << 31) |
(((x >> 33) & 1) << 30) |
(((x >> 34) & 1) << 29) |
(((x >> 35) & 1) << 28) |
(((x >> 36) & 1) << 27) |
(((x >> 37) & 1) << 26) |
(((x >> 38) & 1) << 25) |
(((x >> 39) & 1) << 24) |
(((x >> 40) & 1) << 23) |
(((x >> 41) & 1) << 22) |
(((x >> 42) & 1) << 21) |
(((x >> 43) & 1) << 20) |
(((x >> 44) & 1) << 19) |
(((x >> 45) & 1) << 18) |
(((x >> 46) & 1) << 17) |
(((x >> 47) & 1) << 16) |
(((x >> 48) & 1) << 15) |
(((x >> 49) & 1) << 14) |
(((x >> 50) & 1) << 13) |
(((x >> 51) & 1) << 12) |
(((x >> 52) & 1) << 11) |
(((x >> 53) & 1) << 10) |
(((x >> 54) & 1) << 9) |
(((x >> 55) & 1) << 8) |
(((x >> 56) & 1) << 7) |
(((x >> 57) & 1) << 6) |
(((x >> 58) & 1) << 5) |
(((x >> 59) & 1) << 4) |
(((x >> 60) & 1) << 3) |
(((x >> 61) & 1) << 2) |
(((x >> 62) & 1) << 1) |
(((x >> 63) & 1) << 0);
}
Implementation with low memory and fastest.
private Byte BitReverse(Byte bData)
{
Byte[] lookup = { 0, 8, 4, 12,
2, 10, 6, 14 ,
1, 9, 5, 13,
3, 11, 7, 15 };
Byte ret_val = (Byte)(((lookup[(bData & 0x0F)]) << 4) + lookup[((bData & 0xF0) >> 4)]);
return ret_val;
}
I know it isn't C but asm:
var1 dw 0f0f0
clc
push ax
push cx
mov cx 16
loop1:
shl var1
shr ax
loop loop1
pop ax
pop cx
This works with the carry bit, so you may save flags too
I think the simplest method I know follows. MSB is input and LSB is 'reversed' output:
unsigned char rev(char MSB) {
unsigned char LSB=0; // for output
_FOR(i,0,8) {
LSB= LSB << 1;
if(MSB&1) LSB = LSB | 1;
MSB= MSB >> 1;
}
return LSB;
}
// It works by rotating bytes in opposite directions.
// Just repeat for each byte.
Of course the obvious source of bit-twiddling hacks is here: http://graphics.stanford.edu/~seander/bithacks.html#BitReverseObvious
Presuming that you have an array of bits, how about this: 1. Starting from MSB, push bits into a stack one by one. 2. Pop bits from this stack into another array (or the same array if you want to save space), placing the first popped bit into MSB and going on to less significant bits from there.
Stack stack = new Stack();
Bit[] bits = new Bit[] { 0, 0, 1, 0, 0, 0, 0, 0 };
for (int i = 0; i < bits.Length; i++)
{
stack.push(bits[i]);
}
for (int i = 0; i < bits.Length; i++)
{
bits[i] = stack.pop();
}
This is another solution for folks who love recursion.
The idea is simple. Divide up input by half and swap the two halves, continue until it reaches single bit.
Illustrated in the example below.
Ex : If Input is 00101010 ==> Expected output is 01010100
1. Divide the input into 2 halves
0010 --- 1010
2. Swap the 2 Halves
1010 0010
3. Repeat the same for each half.
10 -- 10 --- 00 -- 10
10 10 10 00
1-0 -- 1-0 --- 1-0 -- 0-0
0 1 0 1 0 1 0 0
Done! Output is 01010100
Here is a recursive function to solve it. (Note I have used unsigned ints, so it can work for inputs up to sizeof(unsigned int)*8 bits.
The recursive function takes 2 parameters - The value whose bits need to be reversed and the number of bits in the value.
int reverse_bits_recursive(unsigned int num, unsigned int numBits)
{
unsigned int reversedNum;;
unsigned int mask = 0;
mask = (0x1 << (numBits/2)) - 1;
if (numBits == 1) return num;
reversedNum = reverse_bits_recursive(num >> numBits/2, numBits/2) |
reverse_bits_recursive((num & mask), numBits/2) << numBits/2;
return reversedNum;
}
int main()
{
unsigned int reversedNum;
unsigned int num;
num = 0x55;
reversedNum = reverse_bits_recursive(num, 8);
printf ("Bit Reversal Input = 0x%x Output = 0x%x\n", num, reversedNum);
num = 0xabcd;
reversedNum = reverse_bits_recursive(num, 16);
printf ("Bit Reversal Input = 0x%x Output = 0x%x\n", num, reversedNum);
num = 0x123456;
reversedNum = reverse_bits_recursive(num, 24);
printf ("Bit Reversal Input = 0x%x Output = 0x%x\n", num, reversedNum);
num = 0x11223344;
reversedNum = reverse_bits_recursive(num,32);
printf ("Bit Reversal Input = 0x%x Output = 0x%x\n", num, reversedNum);
}
This is the output:
Bit Reversal Input = 0x55 Output = 0xaa
Bit Reversal Input = 0xabcd Output = 0xb3d5
Bit Reversal Input = 0x123456 Output = 0x651690
Bit Reversal Input = 0x11223344 Output = 0x22cc4488
How about the following:
uint reverseMSBToLSB32ui(uint input)
{
uint output = 0x00000000;
uint toANDVar = 0;
int places = 0;
for (int i = 1; i < 32; i++)
{
places = (32 - i);
toANDVar = (uint)(1 << places);
output |= (uint)(input & (toANDVar)) >> places;
}
return output;
}
Small and easy (though, 32 bit only).
Well, this is basically the same as the first "reverse()" but it is 64 bit and only needs one immediate mask to be loaded from the instruction stream. GCC creates code without jumps, so this should be pretty fast.
#include <stdio.h>
static unsigned long long swap64(unsigned long long val)
{
#define ZZZZ(x,s,m) (((x) >>(s)) & (m)) | (((x) & (m))<<(s));
/* val = (((val) >>16) & 0xFFFF0000FFFF) | (((val) & 0xFFFF0000FFFF)<<16); */
val = ZZZZ(val,32, 0x00000000FFFFFFFFull );
val = ZZZZ(val,16, 0x0000FFFF0000FFFFull );
val = ZZZZ(val,8, 0x00FF00FF00FF00FFull );
val = ZZZZ(val,4, 0x0F0F0F0F0F0F0F0Full );
val = ZZZZ(val,2, 0x3333333333333333ull );
val = ZZZZ(val,1, 0x5555555555555555ull );
return val;
#undef ZZZZ
}
int main(void)
{
unsigned long long val, aaaa[16] =
{ 0xfedcba9876543210,0xedcba9876543210f,0xdcba9876543210fe,0xcba9876543210fed
, 0xba9876543210fedc,0xa9876543210fedcb,0x9876543210fedcba,0x876543210fedcba9
, 0x76543210fedcba98,0x6543210fedcba987,0x543210fedcba9876,0x43210fedcba98765
, 0x3210fedcba987654,0x210fedcba9876543,0x10fedcba98765432,0x0fedcba987654321
};
unsigned iii;
for (iii=0; iii < 16; iii++) {
val = swap64 (aaaa[iii]);
printf("A[]=%016llX Sw=%016llx\n", aaaa[iii], val);
}
return 0;
}
// Purpose: to reverse bits in an unsigned short integer
// Input: an unsigned short integer whose bits are to be reversed
// Output: an unsigned short integer with the reversed bits of the input one
unsigned short ReverseBits( unsigned short a )
{
// declare and initialize number of bits in the unsigned short integer
const char num_bits = sizeof(a) * CHAR_BIT;
// declare and initialize bitset representation of integer a
bitset<num_bits> bitset_a(a);
// declare and initialize bitset representation of integer b (0000000000000000)
bitset<num_bits> bitset_b(0);
// declare and initialize bitset representation of mask (0000000000000001)
bitset<num_bits> mask(1);
for ( char i = 0; i < num_bits; ++i )
{
bitset_b = (bitset_b << 1) | bitset_a & mask;
bitset_a >>= 1;
}
return (unsigned short) bitset_b.to_ulong();
}
void PrintBits( unsigned short a )
{
// declare and initialize bitset representation of a
bitset<sizeof(a) * CHAR_BIT> bitset(a);
// print out bits
cout << bitset << endl;
}
// Testing the functionality of the code
int main ()
{
unsigned short a = 17, b;
cout << "Original: ";
PrintBits(a);
b = ReverseBits( a );
cout << "Reversed: ";
PrintBits(b);
}
// Output:
Original: 0000000000010001
Reversed: 1000100000000000
Anders Cedronius's answer provides a great solution for people that have an x86 CPU with AVX2 support. For x86 platforms without AVX support or non-x86 platforms, either of the following implementations should work well.
The first code is a variant of the classic binary partitioning method, coded to maximize the use of the shift-plus-logic idiom useful on various ARM processors. In addition, it uses on-the-fly mask generation which could be beneficial for RISC processors that otherwise require multiple instructions to load each 32-bit mask value. Compilers for x86 platforms should use constant propagation to compute all masks at compile time rather than run time.
/* Classic binary partitioning algorithm */
inline uint32_t brev_classic (uint32_t a)
{
uint32_t m;
a = (a >> 16) | (a << 16); // swap halfwords
m = 0x00ff00ff; a = ((a >> 8) & m) | ((a << 8) & ~m); // swap bytes
m = m^(m << 4); a = ((a >> 4) & m) | ((a << 4) & ~m); // swap nibbles
m = m^(m << 2); a = ((a >> 2) & m) | ((a << 2) & ~m);
m = m^(m << 1); a = ((a >> 1) & m) | ((a << 1) & ~m);
return a;
}
In volume 4A of "The Art of Computer Programming", D. Knuth shows clever ways of reversing bits that somewhat surprisingly require fewer operations than the classical binary partitioning algorithms. One such algorithm for 32-bit operands, that I cannot find in TAOCP, is shown in this document on the Hacker's Delight website.
/* Knuth's algorithm from http://www.hackersdelight.org/revisions.pdf. Retrieved 8/19/2015 */
inline uint32_t brev_knuth (uint32_t a)
{
uint32_t t;
a = (a << 15) | (a >> 17);
t = (a ^ (a >> 10)) & 0x003f801f;
a = (t + (t << 10)) ^ a;
t = (a ^ (a >> 4)) & 0x0e038421;
a = (t + (t << 4)) ^ a;
t = (a ^ (a >> 2)) & 0x22488842;
a = (t + (t << 2)) ^ a;
return a;
}
Using the Intel compiler C/C++ compiler 13.1.3.198, both of the above functions auto-vectorize nicely targetting XMM registers. They could also be vectorized manually without a lot of effort.
On my IvyBridge Xeon E3 1270v2, using the auto-vectorized code, 100 million uint32_t words were bit-reversed in 0.070 seconds using brev_classic(), and 0.068 seconds using brev_knuth(). I took care to ensure that my benchmark was not limited by system memory bandwidth.
This thread caught my attention since it deals with a simple problem that requires a lot of work (CPU cycles) even for a modern CPU. And one day I also stood there with the same ¤#%"#" problem. I had to flip millions of bytes. However I know all my target systems are modern Intel-based so let's start optimizing to the extreme!!!
So I used Matt J's lookup code as the base. the system I'm benchmarking on is a i7 haswell 4700eq.
Matt J's lookup bitflipping 400 000 000 bytes: Around 0.272 seconds.
I then went ahead and tried to see if Intel's ISPC compiler could vectorise the arithmetics in the reverse.c.
I'm not going to bore you with my findings here since I tried a lot to help the compiler find stuff, anyhow I ended up with performance of around 0.15 seconds to bitflip 400 000 000 bytes. It's a great reduction but for my application that's still way way too slow..
So people let me present the fastest Intel based bitflipper in the world. Clocked at:
Time to bitflip 400000000 bytes: 0.050082 seconds !!!!!
// Bitflip using AVX2 - The fastest Intel based bitflip in the world!!
// Made by Anders Cedronius 2014 (anders.cedronius (you know what) gmail.com)
#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <omp.h>
using namespace std;
#define DISPLAY_HEIGHT 4
#define DISPLAY_WIDTH 32
#define NUM_DATA_BYTES 400000000
// Constants (first we got the mask, then the high order nibble look up table and last we got the low order nibble lookup table)
__attribute__ ((aligned(32))) static unsigned char k1[32*3]={
0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,
0x00,0x08,0x04,0x0c,0x02,0x0a,0x06,0x0e,0x01,0x09,0x05,0x0d,0x03,0x0b,0x07,0x0f,0x00,0x08,0x04,0x0c,0x02,0x0a,0x06,0x0e,0x01,0x09,0x05,0x0d,0x03,0x0b,0x07,0x0f,
0x00,0x80,0x40,0xc0,0x20,0xa0,0x60,0xe0,0x10,0x90,0x50,0xd0,0x30,0xb0,0x70,0xf0,0x00,0x80,0x40,0xc0,0x20,0xa0,0x60,0xe0,0x10,0x90,0x50,0xd0,0x30,0xb0,0x70,0xf0
};
// The data to be bitflipped (+32 to avoid the quantization out of memory problem)
__attribute__ ((aligned(32))) static unsigned char data[NUM_DATA_BYTES+32]={};
extern "C" {
void bitflipbyte(unsigned char[],unsigned int,unsigned char[]);
}
int main()
{
for(unsigned int i = 0; i < NUM_DATA_BYTES; i++)
{
data[i] = rand();
}
printf ("\r\nData in(start):\r\n");
for (unsigned int j = 0; j < 4; j++)
{
for (unsigned int i = 0; i < DISPLAY_WIDTH; i++)
{
printf ("0x%02x,",data[i+(j*DISPLAY_WIDTH)]);
}
printf ("\r\n");
}
printf ("\r\nNumber of 32-byte chunks to convert: %d\r\n",(unsigned int)ceil(NUM_DATA_BYTES/32.0));
double start_time = omp_get_wtime();
bitflipbyte(data,(unsigned int)ceil(NUM_DATA_BYTES/32.0),k1);
double end_time = omp_get_wtime();
printf ("\r\nData out:\r\n");
for (unsigned int j = 0; j < 4; j++)
{
for (unsigned int i = 0; i < DISPLAY_WIDTH; i++)
{
printf ("0x%02x,",data[i+(j*DISPLAY_WIDTH)]);
}
printf ("\r\n");
}
printf("\r\n\r\nTime to bitflip %d bytes: %f seconds\r\n\r\n",NUM_DATA_BYTES, end_time-start_time);
// return with no errors
return 0;
}
The printf's are for debugging..
Here is the workhorse:
bits 64
global bitflipbyte
bitflipbyte:
vmovdqa ymm2, [rdx]
add rdx, 20h
vmovdqa ymm3, [rdx]
add rdx, 20h
vmovdqa ymm4, [rdx]
bitflipp_loop:
vmovdqa ymm0, [rdi]
vpand ymm1, ymm2, ymm0
vpandn ymm0, ymm2, ymm0
vpsrld ymm0, ymm0, 4h
vpshufb ymm1, ymm4, ymm1
vpshufb ymm0, ymm3, ymm0
vpor ymm0, ymm0, ymm1
vmovdqa [rdi], ymm0
add rdi, 20h
dec rsi
jnz bitflipp_loop
ret
The code takes 32 bytes then masks out the nibbles. The high nibble gets shifted right by 4. Then I use vpshufb and ymm4 / ymm3 as lookup tables. I could use a single lookup table but then I would have to shift left before ORing the nibbles together again.
There are even faster ways of flipping the bits. But I'm bound to single thread and CPU so this was the fastest I could achieve. Can you make a faster version?
Please make no comments about using the Intel C/C++ Compiler Intrinsic Equivalent commands...
This ain't no job for a human! ... but perfect for a machine
This is 2015, 6 years from when this question was first asked. Compilers have since become our masters, and our job as humans is only to help them. So what's the best way to give our intentions to the machine?
Bit-reversal is so common that you have to wonder why the x86's ever growing ISA doesn't include an instruction to do it one go.
The reason: if you give your true concise intent to the compiler, bit reversal should only take ~20 CPU cycles. Let me show you how to craft reverse() and use it:
#include <inttypes.h>
#include <stdio.h>
uint64_t reverse(const uint64_t n,
const uint64_t k)
{
uint64_t r, i;
for (r = 0, i = 0; i < k; ++i)
r |= ((n >> i) & 1) << (k - i - 1);
return r;
}
int main()
{
const uint64_t size = 64;
uint64_t sum = 0;
uint64_t a;
for (a = 0; a < (uint64_t)1 << 30; ++a)
sum += reverse(a, size);
printf("%" PRIu64 "\n", sum);
return 0;
}
Compiling this sample program with Clang version >= 3.6, -O3, -march=native (tested with Haswell), gives artwork-quality code using the new AVX2 instructions, with a runtime of 11 seconds processing ~1 billion reverse()s. That's ~10 ns per reverse(), with .5 ns CPU cycle assuming 2 GHz puts us at the sweet 20 CPU cycles.
Caveat: this sample code should hold as a decent benchmark for a few years, but it will eventually start to show its age once compilers are smart enough to optimize main() to just printf the final result instead of really computing anything. But for now it works in showcasing reverse().
Well this certainly won't be an answer like Matt J's but hopefully it will still be useful.
size_t reverse(size_t n, unsigned int bytes)
{
__asm__("BSWAP %0" : "=r"(n) : "0"(n));
n >>= ((sizeof(size_t) - bytes) * 8);
n = ((n & 0xaaaaaaaaaaaaaaaa) >> 1) | ((n & 0x5555555555555555) << 1);
n = ((n & 0xcccccccccccccccc) >> 2) | ((n & 0x3333333333333333) << 2);
n = ((n & 0xf0f0f0f0f0f0f0f0) >> 4) | ((n & 0x0f0f0f0f0f0f0f0f) << 4);
return n;
}
This is exactly the same idea as Matt's best algorithm except that there's this little instruction called BSWAP which swaps the bytes (not the bits) of a 64-bit number. So b7,b6,b5,b4,b3,b2,b1,b0 becomes b0,b1,b2,b3,b4,b5,b6,b7. Since we are working with a 32-bit number we need to shift our byte-swapped number down 32 bits. This just leaves us with the task of swapping the 8 bits of each byte which is done and voila! we're done.
Timing: on my machine, Matt's algorithm ran in ~0.52 seconds per trial. Mine ran in about 0.42 seconds per trial. 20% faster is not bad I think.
If you're worried about the availability of the instruction BSWAP Wikipedia lists the instruction BSWAP as being added with 80846 which came out in 1989. It should be noted that Wikipedia also states that this instruction only works on 32 bit registers which is clearly not the case on my machine, it very much works only on 64-bit registers.
This method will work equally well for any integral datatype so the method can be generalized trivially by passing the number of bytes desired:
size_t reverse(size_t n, unsigned int bytes)
{
__asm__("BSWAP %0" : "=r"(n) : "0"(n));
n >>= ((sizeof(size_t) - bytes) * 8);
n = ((n & 0xaaaaaaaaaaaaaaaa) >> 1) | ((n & 0x5555555555555555) << 1);
n = ((n & 0xcccccccccccccccc) >> 2) | ((n & 0x3333333333333333) << 2);
n = ((n & 0xf0f0f0f0f0f0f0f0) >> 4) | ((n & 0x0f0f0f0f0f0f0f0f) << 4);
return n;
}
which can then be called like:
n = reverse(n, sizeof(char));//only reverse 8 bits
n = reverse(n, sizeof(short));//reverse 16 bits
n = reverse(n, sizeof(int));//reverse 32 bits
n = reverse(n, sizeof(size_t));//reverse 64 bits
The compiler should be able to optimize the extra parameter away (assuming the compiler inlines the function) and for the sizeof(size_t) case the right-shift would be removed completely. Note that GCC at least is not able to remove the BSWAP and right-shift if passed sizeof(char).
It seems that many other posts are concerned about speed (i.e best = fastest). What about simplicity? Consider:
char ReverseBits(char character) {
char reversed_character = 0;
for (int i = 0; i < 8; i++) {
char ith_bit = (c >> i) & 1;
reversed_character |= (ith_bit << (sizeof(char) - 1 - i));
}
return reversed_character;
}
and hope that clever compiler will optimise for you.
If you want to reverse a longer list of bits (containing sizeof(char) * n bits), you can use this function to get:
void ReverseNumber(char* number, int bit_count_in_number) {
int bytes_occupied = bit_count_in_number / sizeof(char);
// first reverse bytes
for (int i = 0; i <= (bytes_occupied / 2); i++) {
swap(long_number[i], long_number[n - i]);
}
// then reverse bits of each individual byte
for (int i = 0; i < bytes_occupied; i++) {
long_number[i] = ReverseBits(long_number[i]);
}
}
This would reverse [10000000, 10101010] into [01010101, 00000001].
Bit reversal in pseudo code
source -> byte to be reversed b00101100 destination -> reversed, also needs to be of unsigned type so sign bit is not propogated down
copy into temp so original is unaffected, also needs to be of unsigned type so that sign bit is not shifted in automaticaly
bytecopy = b0010110
LOOP8: //do this 8 times test if bytecopy is < 0 (negative)
set bit8 (msb) of reversed = reversed | b10000000
else do not set bit8
shift bytecopy left 1 place
bytecopy = bytecopy << 1 = b0101100 result
shift result right 1 place
reversed = reversed >> 1 = b00000000
8 times no then up^ LOOP8
8 times yes then done.
Generic
C code. Using 1 byte input data num as example.
unsigned char num = 0xaa; // 1010 1010 (aa) -> 0101 0101 (55)
int s = sizeof(num) * 8; // get number of bits
int i, x, y, p;
int var = 0; // make var data type to be equal or larger than num
for (i = 0; i < (s / 2); i++) {
// extract bit on the left, from MSB
p = s - i - 1;
x = num & (1 << p);
x = x >> p;
printf("x: %d\n", x);
// extract bit on the right, from LSB
y = num & (1 << i);
y = y >> i;
printf("y: %d\n", y);
var = var | (x << i); // apply x
var = var | (y << p); // apply y
}
printf("new: 0x%x\n", new);
Source: Stackoverflow.com