bsnes/snesreader/zlib/adler32.c

150 lines
4.5 KiB
C
Raw Normal View History

Include all the code from the bsnes v068 tarball. byuu describes the changes since v067: This release officially introduces the accuracy and performance cores, alongside the previously-existing compatibility core. The accuracy core allows the most accurate SNES emulation ever seen, with every last processor running at the lowest possible clock synchronization level. The performance core allows slower computers the chance to finally use bsnes. It is capable of attaining 60fps in standard games even on an entry-level Intel Atom processor, commonly found in netbooks. The accuracy core is absolutely not meant for casual gaming at all. It is meant solely for getting as close to 100% perfection as possible, no matter the cost to speed. It should only be used for testing, development or debugging. The compatibility core is identical to bsnes v067 and earlier, but is now roughly 10% faster. This is the default and recommended core for casual gaming. The performance core contains an entirely new S-CPU core, with range-tested IRQs; and uses blargg's heavily-optimized S-DSP core directly. Although there are very minor accuracy tradeoffs to increase speed, I am confident that the performance core is still more accurate and compatible than any other SNES emulator. The S-CPU, S-SMP, S-DSP, SuperFX and SA-1 processors are all clock-based, just as in the accuracy and compatibility cores; and as always, there are zero game-specific hacks. Its compatibility is still well above 99%, running even the most challenging games flawlessly. If you have held off from using bsnes in the past due to its system requirements, please give the performance core a try. I think you will be impressed. I'm also not finished: I believe performance can be increased even further. I would also strongly suggest Windows Vista and Windows 7 users to take advantage of the new XAudio2 driver by OV2. Not only does it give you a performance boost, it also lowers latency and provides better sound by way of skipping an API emulation layer. Changelog: - Split core into three profiles: accuracy, compatibility and performance - Accuracy core now takes advantage of variable-bitlength integers (eg uint24_t) - Performance core uses a new S-CPU core, written from scratch for speed - Performance core uses blargg's snes_dsp library for S-DSP emulation - Binaries are now compiled using GCC 4.5 - Added a workaround in the SA-1 core for a bug in GCC 4.5+ - The clock-based S-PPU renderer has greatly improved OAM emulation; fixing Winter Gold and Megalomania rendering issues - Corrected pseudo-hires color math in the clock-based S-PPU renderer; fixing Super Buster Bros backgrounds - Fixed a clamping bug in the Cx4 16-bit triangle operation [Jonas Quinn]; fixing Mega Man X2 "gained weapon" star background effect - Updated video renderer to properly handle mixed-resolution screens with interlace enabled; fixing Air Strike Patrol level briefing screen - Added mightymo's 2010-08-19 cheat code pack - Windows port: added XAudio2 output support [OV2] - Source: major code restructuring; virtual base classes for processor - cores removed, build system heavily modified, etc.
2010-08-22 01:02:42 +00:00
/* adler32.c -- compute the Adler-32 checksum of a data stream
* Copyright (C) 1995-2004 Mark Adler
* For conditions of distribution and use, see copyright notice in zlib.h
*/
/* @(#) $Id$ */
#define ZLIB_INTERNAL
#include "zlib.h"
#define BASE 65521UL /* largest prime smaller than 65536 */
#define NMAX 5552
/* NMAX is the largest n such that 255n(n+1)/2 + (n+1)(BASE-1) <= 2^32-1 */
#define DO1(buf,i) {adler += (buf)[i]; sum2 += adler;}
#define DO2(buf,i) DO1(buf,i); DO1(buf,i+1);
#define DO4(buf,i) DO2(buf,i); DO2(buf,i+2);
#define DO8(buf,i) DO4(buf,i); DO4(buf,i+4);
#define DO16(buf) DO8(buf,0); DO8(buf,8);
/* use NO_DIVIDE if your processor does not do division in hardware */
#ifdef NO_DIVIDE
# define MOD(a) \
do { \
if (a >= (BASE << 16)) a -= (BASE << 16); \
if (a >= (BASE << 15)) a -= (BASE << 15); \
if (a >= (BASE << 14)) a -= (BASE << 14); \
if (a >= (BASE << 13)) a -= (BASE << 13); \
if (a >= (BASE << 12)) a -= (BASE << 12); \
if (a >= (BASE << 11)) a -= (BASE << 11); \
if (a >= (BASE << 10)) a -= (BASE << 10); \
if (a >= (BASE << 9)) a -= (BASE << 9); \
if (a >= (BASE << 8)) a -= (BASE << 8); \
if (a >= (BASE << 7)) a -= (BASE << 7); \
if (a >= (BASE << 6)) a -= (BASE << 6); \
if (a >= (BASE << 5)) a -= (BASE << 5); \
if (a >= (BASE << 4)) a -= (BASE << 4); \
if (a >= (BASE << 3)) a -= (BASE << 3); \
if (a >= (BASE << 2)) a -= (BASE << 2); \
if (a >= (BASE << 1)) a -= (BASE << 1); \
if (a >= BASE) a -= BASE; \
} while (0)
# define MOD4(a) \
do { \
if (a >= (BASE << 4)) a -= (BASE << 4); \
if (a >= (BASE << 3)) a -= (BASE << 3); \
if (a >= (BASE << 2)) a -= (BASE << 2); \
if (a >= (BASE << 1)) a -= (BASE << 1); \
if (a >= BASE) a -= BASE; \
} while (0)
#else
# define MOD(a) a %= BASE
# define MOD4(a) a %= BASE
#endif
/* ========================================================================= */
uLong ZEXPORT adler32(adler, buf, len)
uLong adler;
const Bytef *buf;
uInt len;
{
unsigned long sum2;
unsigned n;
/* split Adler-32 into component sums */
sum2 = (adler >> 16) & 0xffff;
adler &= 0xffff;
/* in case user likes doing a byte at a time, keep it fast */
if (len == 1) {
adler += buf[0];
if (adler >= BASE)
adler -= BASE;
sum2 += adler;
if (sum2 >= BASE)
sum2 -= BASE;
return adler | (sum2 << 16);
}
/* initial Adler-32 value (deferred check for len == 1 speed) */
if (buf == Z_NULL)
return 1L;
/* in case short lengths are provided, keep it somewhat fast */
if (len < 16) {
while (len--) {
adler += *buf++;
sum2 += adler;
}
if (adler >= BASE)
adler -= BASE;
MOD4(sum2); /* only added so many BASE's */
return adler | (sum2 << 16);
}
/* do length NMAX blocks -- requires just one modulo operation */
while (len >= NMAX) {
len -= NMAX;
n = NMAX / 16; /* NMAX is divisible by 16 */
do {
DO16(buf); /* 16 sums unrolled */
buf += 16;
} while (--n);
MOD(adler);
MOD(sum2);
}
/* do remaining bytes (less than NMAX, still just one modulo) */
if (len) { /* avoid modulos if none remaining */
while (len >= 16) {
len -= 16;
DO16(buf);
buf += 16;
}
while (len--) {
adler += *buf++;
sum2 += adler;
}
MOD(adler);
MOD(sum2);
}
/* return recombined sums */
return adler | (sum2 << 16);
}
/* ========================================================================= */
uLong ZEXPORT adler32_combine(adler1, adler2, len2)
uLong adler1;
uLong adler2;
z_off_t len2;
{
unsigned long sum1;
unsigned long sum2;
unsigned rem;
/* the derivation of this formula is left as an exercise for the reader */
rem = (unsigned)(len2 % BASE);
sum1 = adler1 & 0xffff;
sum2 = rem * sum1;
MOD(sum2);
sum1 += (adler2 & 0xffff) + BASE - 1;
sum2 += ((adler1 >> 16) & 0xffff) + ((adler2 >> 16) & 0xffff) + BASE - rem;
if (sum1 > BASE) sum1 -= BASE;
if (sum1 > BASE) sum1 -= BASE;
if (sum2 > (BASE << 1)) sum2 -= (BASE << 1);
if (sum2 > BASE) sum2 -= BASE;
return sum1 | (sum2 << 16);
}