view mercurial/bitmanipulation.h @ 35599:af25237be091

perf: add threading capability to perfbdiff

Since we are releasing the GIL during diffing, it is interesting to see how a
thread pool would perform on diffing. We add a new `--threads` argument to
commands. Synchronizing the thread pool is a bit complex because we want to be
able to reuse it from one run to another.

On my computer (i7 with 4 cores + hyperthreading), I get the following data for
about 12000 revisions:
threads wall        comb    wall gain   comb overhead
none    31.596715   31.59    0.00%       0.00%
1       31.621228   31.62   -0.08%       0.09%
2       16.406202   32.8    48.08%       3.83%
3       11.598334   34.76   63.29%      10.03%
4        9.205421   36.77   70.87%      16.40%
5        8.517604   42.51   73.04%      34.57%
6        7.94645    47.58   74.85%      50.62%
7        7.434972   51.92   76.47%      64.36%
8        7.070638   55.34   77.62%      75.18%

Compared to the feature disabled (threads=0), the overhead is negligible with
the threading code (threads=1), and the gain is already 48% with two threads.

#ifndef _HG_BITMANIPULATION_H_
#define _HG_BITMANIPULATION_H_

#include <string.h>

#include "compat.h"

static inline uint32_t getbe32(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;

	return ((d[0] << 24) | (d[1] << 16) | (d[2] << 8) | (d[3]));
}

static inline int16_t getbeint16(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;

	return ((d[0] << 8) | (d[1]));
}

static inline uint16_t getbeuint16(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;

	return ((d[0] << 8) | (d[1]));
}

static inline void putbe32(uint32_t x, char *c)
{
	c[0] = (x >> 24) & 0xff;
	c[1] = (x >> 16) & 0xff;
	c[2] = (x >> 8) & 0xff;
	c[3] = (x)&0xff;
}

static inline double getbefloat64(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;
	double ret;
	int i;
	uint64_t t = 0;
	for (i = 0; i < 8; i++) {
		t = (t << 8) + d[i];
	}
	memcpy(&ret, &t, sizeof(t));
	return ret;
}

#endif