mirror of https://github.com/PCSX2/pcsx2.git
2dcee32079
git-svn-id: http://pcsx2.googlecode.com/svn/trunk@1037 96395faa-99c1-11dd-bbfe-3dabce05a288 |
||
|---|---|---|
| .. | ||
| ix86 | ||
| ix86-32 | ||
| BaseblockEx.cpp | ||
| BaseblockEx.h | ||
| Makefile.am | ||
| README | ||
| aMicroVU.S | ||
| aR3000A.S | ||
| aVUzerorec.S | ||
| aVif.S | ||
| aVif.asm | ||
| fast_routines.S | ||
| fast_routines.cpp | ||
| iCOP0.cpp | ||
| iCOP0.h | ||
| iCOP2.cpp | ||
| iCore.cpp | ||
| iCore.h | ||
| iFPU.cpp | ||
| iFPU.h | ||
| iFPUd.cpp | ||
| iMMI.cpp | ||
| iMMI.h | ||
| iPsxMem.cpp | ||
| iR3000A.cpp | ||
| iR3000A.h | ||
| iR3000Atables.cpp | ||
| iR5900.h | ||
| iR5900Arit.h | ||
| iR5900AritImm.h | ||
| iR5900Branch.h | ||
| iR5900Jump.h | ||
| iR5900LoadStore.h | ||
| iR5900Misc.cpp | ||
| iR5900Move.h | ||
| iR5900MultDiv.h | ||
| iR5900Shift.h | ||
| iVU0micro.cpp | ||
| iVU1micro.cpp | ||
| iVUmicro.cpp | ||
| iVUmicro.h | ||
| iVUmicroLower.cpp | ||
| iVUmicroUpper.cpp | ||
| iVUops.h | ||
| iVUzerorec.cpp | ||
| iVUzerorec.h | ||
| iVif.cpp | ||
| ir5900tables.cpp | ||
| microVU.cpp | ||
| microVU.h | ||
| microVU_Alloc.h | ||
| microVU_Alloc.inl | ||
| microVU_Analyze.inl | ||
| microVU_Compile.inl | ||
| microVU_Execute.inl | ||
| microVU_Log.inl | ||
| microVU_Lower.inl | ||
| microVU_Misc.h | ||
| microVU_Misc.inl | ||
| microVU_Tables.inl | ||
| microVU_Upper.inl | ||
README
PCSX2 x86 Recompilers - zerofrog(@gmail.com)
There are two types of x86 recompilers: x86-32 and x86-64. The code that both of them share is in the x86/ directory. Code for x86-32 is in the ix86-32/ and same goes for x86-64. The ix86/ dirctory contains the low level translation of x86 instructions to actual code, it is written to be used for both architectures. There are a lot of places where it was hard to separate 32bit from 64bit recompilers, so a lot of functions are surrounded by "#if(n)def __x86_64__" statements.
It would be simple if the story ended here, but hte x86 recompilers use a lot of low level assembly routines, meaning that assembly has to be compiled for both windows x32/x64 versions and linux x32/x64 versions.
For windows, the masm assembler is used (*.asm files)
For linux, gcc is used (*.S files)
Both assemblers use very different syntax, also some routines in x86-64 differ a lot from their 32bit counterparts. Therefore, you might see the same function implemented up to 4 times in assembly.
(no, it's not fun maintaining 4 versions of the same thing... and it might be easier to use nasm, but that probably has its own unforseeable problems)