bsnes/snesreader/nall/ups.hpp
Tim Allen a59ecb3dd4 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.
2010-10-20 22:30:34 +11:00

190 lines
5 KiB
C++
Executable file

#ifndef NALL_UPS_HPP
#define NALL_UPS_HPP
#include <stdio.h>
#include <nall/algorithm.hpp>
#include <nall/crc32.hpp>
#include <nall/file.hpp>
#include <nall/stdint.hpp>
namespace nall {
class ups {
public:
enum result {
ok,
patch_unreadable,
patch_unwritable,
patch_invalid,
input_invalid,
output_invalid,
patch_crc32_invalid,
input_crc32_invalid,
output_crc32_invalid,
};
ups::result create(const char *patch_fn, const uint8_t *x_data, unsigned x_size, const uint8_t *y_data, unsigned y_size) {
if(!fp.open(patch_fn, file::mode_write)) return patch_unwritable;
crc32 = ~0;
uint32_t x_crc32 = crc32_calculate(x_data, x_size);
uint32_t y_crc32 = crc32_calculate(y_data, y_size);
//header
write('U');
write('P');
write('S');
write('1');
encptr(x_size);
encptr(y_size);
//body
unsigned max_size = max(x_size, y_size);
unsigned relative = 0;
for(unsigned i = 0; i < max_size;) {
uint8_t x = i < x_size ? x_data[i] : 0x00;
uint8_t y = i < y_size ? y_data[i] : 0x00;
if(x == y) {
i++;
continue;
}
encptr(i++ - relative);
write(x ^ y);
while(true) {
if(i >= max_size) {
write(0x00);
break;
}
x = i < x_size ? x_data[i] : 0x00;
y = i < y_size ? y_data[i] : 0x00;
i++;
write(x ^ y);
if(x == y) break;
}
relative = i;
}
//footer
for(unsigned i = 0; i < 4; i++) write(x_crc32 >> (i << 3));
for(unsigned i = 0; i < 4; i++) write(y_crc32 >> (i << 3));
uint32_t p_crc32 = ~crc32;
for(unsigned i = 0; i < 4; i++) write(p_crc32 >> (i << 3));
fp.close();
return ok;
}
ups::result apply(const uint8_t *p_data, unsigned p_size, const uint8_t *x_data, unsigned x_size, uint8_t *&y_data, unsigned &y_size) {
if(p_size < 18) return patch_invalid;
p_buffer = p_data;
crc32 = ~0;
//header
if(read() != 'U') return patch_invalid;
if(read() != 'P') return patch_invalid;
if(read() != 'S') return patch_invalid;
if(read() != '1') return patch_invalid;
unsigned px_size = decptr();
unsigned py_size = decptr();
//mirror
if(x_size != px_size && x_size != py_size) return input_invalid;
y_size = (x_size == px_size) ? py_size : px_size;
y_data = new uint8_t[y_size]();
for(unsigned i = 0; i < x_size && i < y_size; i++) y_data[i] = x_data[i];
for(unsigned i = x_size; i < y_size; i++) y_data[i] = 0x00;
//body
unsigned relative = 0;
while(p_buffer < p_data + p_size - 12) {
relative += decptr();
while(true) {
uint8_t x = read();
if(x && relative < y_size) {
uint8_t y = relative < x_size ? x_data[relative] : 0x00;
y_data[relative] = x ^ y;
}
relative++;
if(!x) break;
}
}
//footer
unsigned px_crc32 = 0, py_crc32 = 0, pp_crc32 = 0;
for(unsigned i = 0; i < 4; i++) px_crc32 |= read() << (i << 3);
for(unsigned i = 0; i < 4; i++) py_crc32 |= read() << (i << 3);
uint32_t p_crc32 = ~crc32;
for(unsigned i = 0; i < 4; i++) pp_crc32 |= read() << (i << 3);
uint32_t x_crc32 = crc32_calculate(x_data, x_size);
uint32_t y_crc32 = crc32_calculate(y_data, y_size);
if(px_size != py_size) {
if(x_size == px_size && x_crc32 != px_crc32) return input_crc32_invalid;
if(x_size == py_size && x_crc32 != py_crc32) return input_crc32_invalid;
if(y_size == px_size && y_crc32 != px_crc32) return output_crc32_invalid;
if(y_size == py_size && y_crc32 != py_crc32) return output_crc32_invalid;
} else {
if(x_crc32 != px_crc32 && x_crc32 != py_crc32) return input_crc32_invalid;
if(y_crc32 != px_crc32 && y_crc32 != py_crc32) return output_crc32_invalid;
if(x_crc32 == y_crc32 && px_crc32 != py_crc32) return output_crc32_invalid;
if(x_crc32 != y_crc32 && px_crc32 == py_crc32) return output_crc32_invalid;
}
if(p_crc32 != pp_crc32) return patch_crc32_invalid;
return ok;
}
private:
file fp;
uint32_t crc32;
const uint8_t *p_buffer;
uint8_t read() {
uint8_t n = *p_buffer++;
crc32 = crc32_adjust(crc32, n);
return n;
}
void write(uint8_t n) {
fp.write(n);
crc32 = crc32_adjust(crc32, n);
}
void encptr(uint64_t offset) {
while(true) {
uint64_t x = offset & 0x7f;
offset >>= 7;
if(offset == 0) {
write(0x80 | x);
break;
}
write(x);
offset--;
}
}
uint64_t decptr() {
uint64_t offset = 0, shift = 1;
while(true) {
uint8_t x = read();
offset += (x & 0x7f) * shift;
if(x & 0x80) break;
shift <<= 7;
offset += shift;
}
return offset;
}
};
}
#endif