About a week's worth of changes here. As a heads-up, I wouldn't be
surprised if this doesn't build in Linux right now. The CMakeLists.txt
were checked with MinGW and NMake, but how they fair under Linux is an
unknown to me at this time.
- Converted most sprintf (and all wsprintf) calls to either mysnprintf or
FStrings, depending on the situation.
- Changed the strings in the wbstartstruct to be FStrings.
- Changed myvsnprintf() to output nothing if count is greater than INT_MAX.
This is so that I can use a series of mysnprintf() calls and advance the
pointer for each one. Once the pointer goes beyond the end of the buffer,
the count will go negative, but since it's an unsigned type it will be
seen as excessively huge instead. This should not be a problem, as there's
no reason for ZDoom to be using text buffers larger than 2 GB anywhere.
- Ripped out the disabled bit from FGameConfigFile::MigrateOldConfig().
- Changed CalcMapName() to return an FString instead of a pointer to a static
buffer.
- Changed startmap in d_main.cpp into an FString.
- Changed CheckWarpTransMap() to take an FString& as the first argument.
- Changed d_mapname in g_level.cpp into an FString.
- Changed DoSubstitution() in ct_chat.cpp to place the substitutions in an
FString.
- Fixed: The MAPINFO parser wrote into the string buffer to construct a map
name when given a Hexen map number. This was fine with the old scanner
code, but only a happy coincidence prevents it from crashing with the new
code
- Added the 'B' conversion specifier to StringFormat::VWorker() for printing
binary numbers.
- Added CMake support for building with MinGW, MSYS, and NMake. Linux support
is probably broken until I get around to booting into Linux again. Niceties
provided over the existing Makefiles they're replacing:
* All command-line builds can use the same build system, rather than having
a separate one for MinGW and another for Linux.
* Microsoft's NMake tool is supported as a target.
* Progress meters.
* Parallel makes work from a fresh checkout without needing to be primed
first with a single-threaded make.
* Porting to other architectures should be simplified, whenever that day
comes.
- Replaced the makewad tool with zipdir. This handles the dependency tracking
itself instead of generating an external makefile to do it, since I couldn't
figure out how to generate a makefile with an external tool and include it
with a CMake-generated makefile. Where makewad used a master list of files
to generate the package file, zipdir just zips the entire contents of one or
more directories.
- Added the gdtoa package from netlib's fp library so that ZDoom's printf-style
formatting can be entirely independant of the CRT.
SVN r1082 (trunk)
2008-07-23 04:57:26 +00:00
|
|
|
%include "valgrind.inc"
|
2008-06-08 02:31:30 +00:00
|
|
|
|
2006-02-24 04:48:15 +00:00
|
|
|
%ifdef M_TARGET_WATCOM
|
|
|
|
|
SEGMENT DATA PUBLIC ALIGN=16 CLASS=DATA USE32
|
|
|
|
|
SEGMENT DATA
|
|
|
|
|
%else
|
|
|
|
|
SECTION .data
|
|
|
|
|
%endif
|
|
|
|
|
|
|
|
|
|
%ifndef M_TARGET_LINUX
|
|
|
|
|
%define ylookup _ylookup
|
|
|
|
|
%define vplce _vplce
|
|
|
|
|
%define vince _vince
|
|
|
|
|
%define palookupoffse _palookupoffse
|
|
|
|
|
%define bufplce _bufplce
|
|
|
|
|
%define dc_iscale _dc_iscale
|
|
|
|
|
%define dc_colormap _dc_colormap
|
|
|
|
|
%define dc_count _dc_count
|
|
|
|
|
%define dc_dest _dc_dest
|
|
|
|
|
%define dc_source _dc_source
|
|
|
|
|
%define dc_texturefrac _dc_texturefrac
|
|
|
|
|
%define dc_pitch _dc_pitch
|
|
|
|
|
|
|
|
|
|
%define setupvlinetallasm _setupvlinetallasm
|
|
|
|
|
%define vlinetallasm4 _vlinetallasm4
|
|
|
|
|
%define vlinetallasmathlon4 _vlinetallasmathlon4
|
|
|
|
|
%define vlinetallasm1 _vlinetallasm1
|
|
|
|
|
%define prevlinetallasm1 _prevlinetallasm1
|
|
|
|
|
%endif
|
|
|
|
|
|
|
|
|
|
EXTERN vplce
|
|
|
|
|
EXTERN vince
|
|
|
|
|
EXTERN palookupoffse
|
|
|
|
|
EXTERN bufplce
|
|
|
|
|
|
|
|
|
|
EXTERN ylookup
|
|
|
|
|
EXTERN dc_iscale
|
|
|
|
|
EXTERN dc_colormap
|
|
|
|
|
EXTERN dc_count
|
|
|
|
|
EXTERN dc_dest
|
|
|
|
|
EXTERN dc_source
|
|
|
|
|
EXTERN dc_texturefrac
|
|
|
|
|
EXTERN dc_pitch
|
|
|
|
|
|
|
|
|
|
GLOBAL vlt4pitch
|
|
|
|
|
GLOBAL vlt1pitch
|
|
|
|
|
|
|
|
|
|
%ifdef M_TARGET_WATCOM
|
|
|
|
|
SEGMENT CODE PUBLIC ALIGN=16 CLASS=CODE USE32
|
|
|
|
|
SEGMENT CODE
|
|
|
|
|
%else
|
|
|
|
|
SECTION .text
|
|
|
|
|
%endif
|
|
|
|
|
|
|
|
|
|
ALIGN 16
|
|
|
|
|
GLOBAL setpitch3
|
|
|
|
|
setpitch3:
|
|
|
|
|
mov [vltpitch+2], eax
|
|
|
|
|
mov [vltpitcha+2],eax
|
|
|
|
|
mov [vlt1pitch1+2], eax
|
|
|
|
|
mov [vlt1pitch2+2], eax
|
2008-06-08 02:31:30 +00:00
|
|
|
selfmod vltpitch, vlt1pitch2+6
|
2006-02-24 04:48:15 +00:00
|
|
|
ret
|
|
|
|
|
|
|
|
|
|
ALIGN 16
|
|
|
|
|
GLOBAL setupvlinetallasm
|
|
|
|
|
setupvlinetallasm:
|
|
|
|
|
mov ecx, [esp+4]
|
|
|
|
|
mov [shifter1+2], cl
|
|
|
|
|
mov [shifter2+2], cl
|
|
|
|
|
mov [shifter3+2], cl
|
|
|
|
|
mov [shifter4+2], cl
|
|
|
|
|
mov [shifter1a+2], cl
|
|
|
|
|
mov [shifter2a+2], cl
|
|
|
|
|
mov [shifter3a+2], cl
|
|
|
|
|
mov [shifter4a+2], cl
|
|
|
|
|
mov [preshift+2], cl
|
|
|
|
|
mov [shift11+2], cl
|
|
|
|
|
mov [shift12+2], cl
|
2008-06-08 02:31:30 +00:00
|
|
|
selfmod shifter1, shift12+6
|
2006-02-24 04:48:15 +00:00
|
|
|
ret
|
|
|
|
|
|
|
|
|
|
SECTION .rtext progbits alloc exec write align=64
|
|
|
|
|
|
|
|
|
|
ALIGN 16
|
|
|
|
|
|
|
|
|
|
GLOBAL vlinetallasm4
|
|
|
|
|
vlinetallasm4:
|
|
|
|
|
push ebx
|
|
|
|
|
mov eax, [bufplce+0]
|
|
|
|
|
mov ebx, [bufplce+4]
|
|
|
|
|
mov ecx, [bufplce+8]
|
|
|
|
|
mov edx, [bufplce+12]
|
|
|
|
|
mov [source1+3], eax
|
|
|
|
|
mov [source2+3], ebx
|
|
|
|
|
mov [source3+3], ecx
|
|
|
|
|
mov [source4+3], edx
|
|
|
|
|
mov eax, [palookupoffse+0]
|
|
|
|
|
mov ebx, [palookupoffse+4]
|
|
|
|
|
mov ecx, [palookupoffse+8]
|
|
|
|
|
mov edx, [palookupoffse+12]
|
|
|
|
|
mov [lookup1+2], eax
|
|
|
|
|
mov [lookup2+2], ebx
|
|
|
|
|
mov [lookup3+2], ecx
|
|
|
|
|
mov [lookup4+2], edx
|
|
|
|
|
mov eax, [vince+0]
|
|
|
|
|
mov ebx, [vince+4]
|
|
|
|
|
mov ecx, [vince+8]
|
|
|
|
|
mov edx, [vince+12]
|
|
|
|
|
mov [step1+2], eax
|
|
|
|
|
mov [step2+2], ebx
|
|
|
|
|
mov [step3+2], ecx
|
|
|
|
|
mov [step4+1], edx
|
|
|
|
|
push ebp
|
|
|
|
|
push esi
|
|
|
|
|
push edi
|
|
|
|
|
mov ecx, [dc_count]
|
|
|
|
|
mov edi, [dc_dest]
|
|
|
|
|
mov eax, dword [ylookup+ecx*4-4]
|
|
|
|
|
add eax, edi
|
|
|
|
|
sub edi, eax
|
|
|
|
|
mov [write1+2],eax
|
|
|
|
|
inc eax
|
|
|
|
|
mov [write2+2],eax
|
|
|
|
|
inc eax
|
|
|
|
|
mov [write3+2],eax
|
|
|
|
|
inc eax
|
|
|
|
|
mov [write4+2],eax
|
|
|
|
|
mov ebx, [vplce]
|
|
|
|
|
mov ecx, [vplce+4]
|
|
|
|
|
mov esi, [vplce+8]
|
|
|
|
|
mov eax, [vplce+12]
|
2008-06-08 02:31:30 +00:00
|
|
|
selfmod loopit, vltpitch
|
2006-02-24 04:48:15 +00:00
|
|
|
jmp loopit
|
|
|
|
|
|
|
|
|
|
ALIGN 16
|
|
|
|
|
loopit:
|
|
|
|
|
mov edx, ebx
|
|
|
|
|
shifter1: shr edx, 24
|
|
|
|
|
source1: movzx edx, BYTE [edx+0x88888888]
|
|
|
|
|
lookup1: mov dl, [edx+0x88888888]
|
|
|
|
|
write1: mov [edi+0x88888880], dl
|
|
|
|
|
step1: add ebx, 0x88888888
|
|
|
|
|
mov edx, ecx
|
|
|
|
|
shifter2: shr edx, 24
|
|
|
|
|
source2: movzx edx, BYTE [edx+0x88888888]
|
|
|
|
|
lookup2: mov dl, [edx+0x88888888]
|
|
|
|
|
write2: mov [edi+0x88888881], dl
|
|
|
|
|
step2: add ecx, 0x88888888
|
|
|
|
|
mov edx, esi
|
|
|
|
|
shifter3: shr edx, 24
|
|
|
|
|
source3: movzx edx, BYTE [edx+0x88888888]
|
|
|
|
|
lookup3: mov dl, BYTE [edx+0x88888888]
|
|
|
|
|
write3: mov [edi+0x88888882], dl
|
|
|
|
|
step3: add esi, 0x88888888
|
|
|
|
|
mov edx, eax
|
|
|
|
|
shifter4: shr edx, 24
|
|
|
|
|
source4: movzx edx, BYTE [edx+0x88888888]
|
|
|
|
|
lookup4: mov dl, [edx+0x88888888]
|
|
|
|
|
write4: mov [edi+0x88888883], dl
|
|
|
|
|
step4: add eax, 0x88888888
|
|
|
|
|
vltpitch: add edi, 320
|
|
|
|
|
jle near loopit
|
|
|
|
|
|
|
|
|
|
mov [vplce], ebx
|
|
|
|
|
mov [vplce+4], ecx
|
|
|
|
|
mov [vplce+8], esi
|
|
|
|
|
mov [vplce+12], eax
|
|
|
|
|
|
|
|
|
|
pop edi
|
|
|
|
|
pop esi
|
|
|
|
|
pop ebp
|
|
|
|
|
pop ebx
|
|
|
|
|
|
|
|
|
|
ret
|
|
|
|
|
|
|
|
|
|
ALIGN 16
|
|
|
|
|
|
|
|
|
|
GLOBAL vlinetallasmathlon4
|
|
|
|
|
vlinetallasmathlon4:
|
|
|
|
|
push ebx
|
|
|
|
|
mov eax, [bufplce+0]
|
|
|
|
|
mov ebx, [bufplce+4]
|
|
|
|
|
mov ecx, [bufplce+8]
|
|
|
|
|
mov edx, [bufplce+12]
|
|
|
|
|
mov [source1a+3], eax
|
|
|
|
|
mov [source2a+3], ebx
|
|
|
|
|
mov [source3a+3], ecx
|
|
|
|
|
mov [source4a+3], edx
|
|
|
|
|
mov eax, [palookupoffse+0]
|
|
|
|
|
mov ebx, [palookupoffse+4]
|
|
|
|
|
mov ecx, [palookupoffse+8]
|
|
|
|
|
mov edx, [palookupoffse+12]
|
|
|
|
|
mov [lookup1a+2], eax
|
|
|
|
|
mov [lookup2a+2], ebx
|
|
|
|
|
mov [lookup3a+2], ecx
|
|
|
|
|
mov [lookup4a+2], edx
|
|
|
|
|
mov eax, [vince+0]
|
|
|
|
|
mov ebx, [vince+4]
|
|
|
|
|
mov ecx, [vince+8]
|
|
|
|
|
mov edx, [vince+12]
|
|
|
|
|
mov [step1a+2], eax
|
|
|
|
|
mov [step2a+2], ebx
|
|
|
|
|
mov [step3a+2], ecx
|
|
|
|
|
mov [step4a+1], edx
|
|
|
|
|
push ebp
|
|
|
|
|
push esi
|
|
|
|
|
push edi
|
|
|
|
|
mov ecx, [dc_count]
|
|
|
|
|
mov edi, [dc_dest]
|
|
|
|
|
mov eax, dword [ylookup+ecx*4-4]
|
|
|
|
|
add eax, edi
|
|
|
|
|
sub edi, eax
|
|
|
|
|
mov [write1a+2],eax
|
|
|
|
|
inc eax
|
|
|
|
|
mov [write2a+2],eax
|
|
|
|
|
inc eax
|
|
|
|
|
mov [write3a+2],eax
|
|
|
|
|
inc eax
|
|
|
|
|
mov [write4a+2],eax
|
|
|
|
|
mov ebp, [vplce]
|
|
|
|
|
mov ecx, [vplce+4]
|
|
|
|
|
mov esi, [vplce+8]
|
|
|
|
|
mov eax, [vplce+12]
|
2008-06-08 02:31:30 +00:00
|
|
|
selfmod loopita, vltpitcha
|
2006-02-24 04:48:15 +00:00
|
|
|
jmp loopita
|
|
|
|
|
|
|
|
|
|
; Unfortunately, this code has not been carefully analyzed to determine
|
|
|
|
|
; how well it utilizes the processor's instruction units. Instead, I just
|
|
|
|
|
; kept rearranging code, seeing what sped it up and what slowed it down
|
|
|
|
|
; until I arrived at this. The is the fastest version I was able to
|
|
|
|
|
; manage, but that does not mean it cannot be made faster with careful
|
|
|
|
|
; instructing shuffling.
|
|
|
|
|
|
|
|
|
|
ALIGN 64
|
|
|
|
|
|
|
|
|
|
loopita: mov edx, ebp
|
|
|
|
|
mov ebx, ecx
|
|
|
|
|
shifter1a: shr edx, 24
|
|
|
|
|
shifter2a: shr ebx, 24
|
|
|
|
|
source1a: movzx edx, BYTE [edx+0x88888888]
|
|
|
|
|
source2a: movzx ebx, BYTE [ebx+0x88888888]
|
|
|
|
|
step1a: add ebp, 0x88888888
|
|
|
|
|
step2a: add ecx, 0x88888888
|
|
|
|
|
lookup1a: mov dl, [edx+0x88888888]
|
|
|
|
|
lookup2a: mov dh, [ebx+0x88888888]
|
|
|
|
|
mov ebx, esi
|
|
|
|
|
write1a: mov [edi+0x88888880], dl
|
|
|
|
|
write2a: mov [edi+0x88888881], dh
|
|
|
|
|
shifter3a: shr ebx, 24
|
|
|
|
|
mov edx, eax
|
|
|
|
|
source3a: movzx ebx, BYTE [ebx+0x88888888]
|
|
|
|
|
shifter4a: shr edx, 24
|
|
|
|
|
step3a: add esi, 0x88888888
|
|
|
|
|
source4a: movzx edx, BYTE [edx+0x88888888]
|
|
|
|
|
step4a: add eax, 0x88888888
|
|
|
|
|
lookup3a: mov bl, [ebx+0x88888888]
|
|
|
|
|
lookup4a: mov dl, [edx+0x88888888]
|
|
|
|
|
write3a: mov [edi+0x88888882], bl
|
|
|
|
|
write4a: mov [edi+0x88888883], dl
|
|
|
|
|
vltpitcha: add edi, 320
|
|
|
|
|
jle near loopita
|
|
|
|
|
|
|
|
|
|
mov [vplce], ebp
|
|
|
|
|
mov [vplce+4], ecx
|
|
|
|
|
mov [vplce+8], esi
|
|
|
|
|
mov [vplce+12], eax
|
|
|
|
|
|
|
|
|
|
pop edi
|
|
|
|
|
pop esi
|
|
|
|
|
pop ebp
|
|
|
|
|
pop ebx
|
|
|
|
|
|
|
|
|
|
ret
|
|
|
|
|
|
|
|
|
|
ALIGN 16
|
|
|
|
|
GLOBAL prevlinetallasm1
|
|
|
|
|
prevlinetallasm1:
|
|
|
|
|
mov ecx, [dc_count]
|
|
|
|
|
cmp ecx, 1
|
|
|
|
|
ja vlinetallasm1
|
|
|
|
|
|
|
|
|
|
mov eax, [dc_iscale]
|
|
|
|
|
mov edx, [dc_texturefrac]
|
|
|
|
|
add eax, edx
|
|
|
|
|
mov ecx, [dc_source]
|
|
|
|
|
preshift: shr edx, 16
|
|
|
|
|
push ebx
|
|
|
|
|
push edi
|
|
|
|
|
mov edi, [dc_colormap]
|
|
|
|
|
movzx ebx, byte [ecx+edx]
|
|
|
|
|
mov ecx, [dc_dest]
|
|
|
|
|
mov bl, byte [edi+ebx]
|
|
|
|
|
pop edi
|
|
|
|
|
mov byte [ecx], bl
|
|
|
|
|
pop ebx
|
|
|
|
|
ret
|
|
|
|
|
|
|
|
|
|
ALIGN 16
|
|
|
|
|
GLOBAL vlinetallasm1
|
|
|
|
|
vlinetallasm1:
|
|
|
|
|
push ebp
|
|
|
|
|
push ebx
|
|
|
|
|
push edi
|
|
|
|
|
push esi
|
|
|
|
|
|
|
|
|
|
mov ebp, [dc_count]
|
|
|
|
|
mov ebx, [dc_texturefrac] ; ebx = frac
|
|
|
|
|
mov edi, [dc_dest]
|
|
|
|
|
mov ecx, ebx
|
|
|
|
|
shift11: shr ecx, 16
|
|
|
|
|
mov esi, [dc_source]
|
|
|
|
|
mov edx, [dc_iscale]
|
|
|
|
|
vlt1pitch1: sub edi, 0x88888888
|
|
|
|
|
mov eax, [dc_colormap]
|
|
|
|
|
|
|
|
|
|
loop2:
|
|
|
|
|
movzx ecx, BYTE [esi+ecx]
|
|
|
|
|
add ebx, edx
|
|
|
|
|
vlt1pitch2: add edi, 0x88888888
|
|
|
|
|
mov cl,[eax+ecx]
|
|
|
|
|
mov [edi],cl
|
|
|
|
|
mov ecx,ebx
|
|
|
|
|
shift12: shr ecx,16
|
|
|
|
|
dec ebp
|
|
|
|
|
jnz loop2
|
|
|
|
|
|
|
|
|
|
mov eax,ebx
|
|
|
|
|
pop esi
|
|
|
|
|
pop edi
|
|
|
|
|
pop ebx
|
|
|
|
|
pop ebp
|
|
|
|
|
ret
|