And associated cleanup.
On most compilers these days, it'll either inline the memset with vector
fills or rep stosq, or outline with a call to memset.
I trust the compiler is probably going to make a better decision here,
than manual SSE intrinsics.
Ends up a couple of percent faster in FMV decoding.
Works around an LTO bug which seems to occur in clang 15, but not in
clang 12. The entire else branch in the 0 case in get_non_intra_block()
was being removed...
Fixes Burnout 3 crashing in clang builds.
These have no meaning in x64 (apart from throwing compiler warnings),
and we don't do 32-bit anymore. Also saves needing to include
`Pcsx2Defs.h` in files which don't otherwise need it.
Pcsx2 now has a gifUnit class which acts like the ps2's gif and executes a single gif transfer at a time (and performs path arbitration according to priority and path3 slicing).
This new code is generally a speedup for most games. Particularly VU heavy games like GoW.
This revision breaks old saved state compatibility so don't update if you wish to keep playing with your old saved states.
Leave comments if this revision fixes or breaks anything...
Message to GS Plugin authors:
This new code now uses only 1 gif callback to transfer data to the gs plugin (GSgifTransfer).
pcsx2 also is garaunteed to send full GS primitives to the plugin. So you don't have to account for partial-transfers anymore.
Thanks goes out to shadowlady who tested around 500 games for me :D
Note 1: The old gif code is still in this revision, and can be enabled by the USE_OLD_GIF macro. The old code will be deleted soon.
Note 2: This revision also enables assertion dialogs in devel builds, and changed a lot of assume cases into assertions.
git-svn-id: http://pcsx2.googlecode.com/svn/trunk@4821 96395faa-99c1-11dd-bbfe-3dabce05a288
Note: This is technically still a hack, but it shouldnt break anything like the existing hack does, also it's closer to how it should be than anything we've done previous.
git-svn-id: http://pcsx2.googlecode.com/svn/trunk@4058 96395faa-99c1-11dd-bbfe-3dabce05a288
* Fix a potentially obscure bug in ipuCSC (color space conversion) which would have caused PCSX2 to hang on certain types of rare partial transfers.
* Remove some more dead code and structure data from the mpeg library.
git-svn-id: http://pcsx2.googlecode.com/svn/trunk@3833 96395faa-99c1-11dd-bbfe-3dabce05a288
* Writes via 16 and 8 bit ops now use 32-bit read/modify/write operations by default; which should enable nearly complete support for all such operations (instead of the formerly spotty coverage before).
* Eliminated almost all former 8/16-bit specific register operations. All code shares the same 32 bit handlers now.
* Completely revamped the developer trace logs for hardware registers! *ALL* registers are logged now, complete with address, name, and value being read/written (and nicely formatted!).
* Handlers are now fully page-based using templated functions (minor speedup)
git-svn-id: http://pcsx2.googlecode.com/svn/trunk@3704 96395faa-99c1-11dd-bbfe-3dabce05a288
* Now using SSE for all hardware register reads and writes (mainly MFIFO stuff) [don't expect a speedup, really -- its more of a code simplification in this case].
* [refactoring] Changed the EE Memory (vtlb) to use the u128 type instead of u64 for the 128-bit loads/stores (see mem128_t typedef)
git-svn-id: http://pcsx2.googlecode.com/svn/trunk@3626 96395faa-99c1-11dd-bbfe-3dabce05a288
* Added __fi and __ri, which are abbreviations for __forceinline and __releaseinline.
* Added some static qualifiers to functions in mVU, MMI ops, and others where appropriate.
* Removed some unnecessary __fastcall qualifiers (since GCC gets funny sometimes when you combine __fastcall and inlining).
* Made _1mb, _16mb, _1gb values common to all emulation code (moved from newVif/mvu to Common.h) -- they're useful! :)
git-svn-id: http://pcsx2.googlecode.com/svn/trunk@3624 96395faa-99c1-11dd-bbfe-3dabce05a288
* Savestate mega-fix! Removed all the old direct pointer types from decoder_t, which should fix the oddball random savestate crashes when IPU is active.
* Moved iq/niq into decoder_t.
* Moved all macroblocks into decoder_t (mb8, mb16, rgb16, rgb32).
* Turned decoder.stride into a constant, since IPU can only decode in strides of 16 bytes only.
* Added sanity checking to the ipu0_fifo stuff (was formerly g_nIPU0Data, etc).
* Added some SSE moves to the Idct (very minor optimization). There's a completely SSE from-ground-up implementation provided by newer versions of libmpeg2 that we should probably look into later, rather than rolling our own.
git-svn-id: http://pcsx2.googlecode.com/svn/trunk@3587 96395faa-99c1-11dd-bbfe-3dabce05a288
-Fixed a Bitstream bug which was annoying me.
-Modified a silly long if check with multiple bit shifts, should be a tiny bit quicker.
-Various other IPU changes
git-svn-id: http://pcsx2.googlecode.com/svn/trunk@2926 96395faa-99c1-11dd-bbfe-3dabce05a288
-Improved DMA Queuing slightly, less "all over the place" code.
-Jiggled some IPU bits around to clean up some clutter.
-Added the FFX and Digital Devil Saga video fixes as a Gamefix for now. Due to the delay involved, this causes other videos to terminate early, so now disabled by default.
-Added a load of logging for hardware in dev builds (also now label more correctly) and some bits for debugging IPU easier. Some are commented out, but can be enabled for testing.
-Made a small clarification in VIF
git-svn-id: http://pcsx2.googlecode.com/svn/trunk@2875 96395faa-99c1-11dd-bbfe-3dabce05a288
