|
Interview with Qbix on DOSBox online This interview with "Qbix" goes into more depth on how DOSBox works: http://www.classicdosgames.com/interviews/peterveenstra.html As I've mentioned previously, DOSBox with SDL could be used as an OS: http://groups.google.com/group/alt.os.development/msg/fec484c7a0c0b4af With modifications, it could be use... 7 May 2008 12:24
Wanna do a WriteLongwordBits contest ? Skybuck Flying wrote: "MitchAlsup" <MitchAlsup(a)aol.com> wrote in message news:cb20dc12-415b-4a0c-8bd9-4985a7c04946(a)w74g2000hsh.googlegroups.com... Lets do this in an instruction set that it makes it easy, and use C; void WriteLongwordBits( unsigned long Value, unsignedint BitCount, unsigned long ... 7 May 2008 07:31
Parallel execution of carry dependent instructions ? Hello, Suppose I write x86 code like so: bt eax, 0 adc [edx], 0 bt eax, 1 adc [edx + 4], 0 bt eax, 2 adc [edx + 8], 0 The bt (bit test) instruction sets the carry flag if the bit position is set, otherwise the carry flag is cleared. The adc instruction adds the carry flag. Then this ... 7 May 2008 00:08
begginer question On 3 maio, 17:11, Robert Redelmeier <red...(a)ev1.net.invalid> wrote: Prime Mover <eple...(a)hotmail.com> wrote in part: You asked about what type of numbers I want. Well, let's start with integers only. Assuming 32 bit unsigned, the code Frank posted is good: mov eax, 7 mov ecx, 4 a... 6 May 2008 22:24
How many branches in a loop can be predicted successfully ? What is a branch ? Classic sense like a tree: if (True) then <- node/evaluation/condition. /\ / \ / \ / \ / \ / \ True Branch False Branch (does not exist) Since there is only one ... 6 May 2008 22:24
Wanna do a WriteLongwordBits contest ? (Skybuck's SimInt64 C/C++ version) Ok, I ported my simulated-int64-Delphi-2007-version to Visual Studio 2008, to compare assembler outputs, Here is the Visual Studio 2008 C/C++ version and it's output: // *** Begin of C/C++ Code *** #include <stdio.h> #include <windows.h> /* Skybuck's WriteLongword (simulated int64 version) ported t... 6 May 2008 22:24
Wanna do a WriteLongwordBits contest ? (Skybuck's Fiveth Entry: Better Lightning Fast A1B1) Algorithm included. Hello, Skybuck's Super Fast WriteBits Algorithm (32 bits): Assumptions: Buffer is cleared. Trailing garbage bits in buffer not a problem. Buffer is large enough. Value bits: Initial Value pointer | | Secondary Value pointer | | | | 01234567 89012345 67890123 45678901 ???????? ... 6 May 2008 22:24
AMD X2 3800+ processor has bottleneck in integer multiplier ? Hello, I noticed how one of my applications performed an insane ammount of 32 bit multiplies, and at the same time the app was kinda slow. Now that I am reading the AMD documentation again it says something like: Multiplier on AMD processor is attached to pipeline 0, and such. So to me it looks like this ... 6 May 2008 22:24
How many branches in a loop can be predicted successfully ? Hello, Suppose I have code like so: Condition1 := True or False; // determined here Condition2 := True or False; // determined here Condition3 := True or False; // determined here for Y := 0 to Height-1 do begin for X := 0 to Width-1 do begin // ... inner loop ... if Conditio... 6 May 2008 22:24
Wanna do a WriteLongwordBits contest ? (Skybuck's Second Entry) Hello, Here is my second entry for the contest. I was hoping that by using assembler instructions, the instruction count could be reduced. But the opposite has happened. This version is even worse: 105 instructions ! And it's using slower instructions too, like shld and a branch ! However the kee... 6 May 2008 21:20
Wanna do a WriteLongwordBits contest ? (Skybuck's Third Entry) Ok, This version 2 uses 85 instructions. Still 2 more instructions than the simulated-int64 version ;) // Optimizations applied: // + KeepLowBits function inlined. // + Variables reduced by re-using stack space via absolute directive // Instructions re-ordered to make that possible. // + DestBitIndex shr ... 6 May 2008 21:20
Calling libraries from assembler. SoLo2 wrote: Hello! I have tried how simple it is to use system calls in Linux from assembler. Setting parameters in the registers eax/edx and then "int 0x80". I would like to know it there is a similar, easy way of calling other libraries (specially X windows). I don't know how "simi... 6 May 2008 21:20
Skybuck presents FastGetBit ( Value, BitPosition ) (latency 3) Hello, Here is my fast (latency 3) get bit routine: Enjoy ! ;) =D // *** Begin of Code *** program Project1; {$APPTYPE CONSOLE} { Skybuck presents FastGetBit version 0.01 created on 4 may 2008 by Skybuck Flying. This routine has just 3 latency on AMD X2 3800+. Ofcourse it also has some cal... 6 May 2008 21:20
Patching of a divide overflow error ? "Wolfgang Kern" <nowhere(a)never.at> ha scritto Many old programs weren't aware of 'huge' RAM, VRAM and speed values, so they in fact often stumble into DIV overflow, my workaround for DOS-based programs is a tiny TSR which hooks DIV-exceptions and skips the my "workaround" it is never to do that error (... 6 May 2008 21:20
Fast way of splitting an image into bit planes ? On May 2, 12:06 am, Terence <tbwri...(a)cantv.net> wrote: On Apr 28, 5:07 pm, "Skybuck Flying" <BloodySh...(a)hotmail.com> wrote: Idea was to: Take 1 bit from the first pixel. Take 1 bit from the second pixel. Take 1 bit from the third pixel. Take 1 bit from the fourth pixel. ... 6 May 2008 21:20
Skybuck presents RotateLeft and RotateRight routines. Hello, "If Skybuck can do it then so can you !" I wonder why high level languages like Delphi and FreePascal do not have ror and rol support ? Which processors targetted by FreePascal do not have ror and rol support me wonders ? I suspect I need these routines to be able to easily, flawlessly, and bra... 6 May 2008 21:20
Skybuck presents KeepLowBits and KeepHighBits Hello, Skybuck presents: KeepLowBits and KeepHighBits functions. Visual inspection/verification program included ! ;) // *** Begin of Code *** program Project1; {$APPTYPE CONSOLE} { Skybuck presents KeepLowBits and KeepHighBits Version 0.01 created on 5 may 2008 by Skybuck Flying Correct i... 6 May 2008 21:20
Fastest way to get rid of accessive bits (chop off bits) There it's done. See the other thread: "Skybuck presents KeepLowBits and KeepHighBits" For good code and test program. Bye, Skybuck. ... 6 May 2008 21:20
Wanna do a WriteLongwordBits contest ? (Skybuck's Fourth Entry: Lightning Fast A1B1) Ok, I wasn't statisfied with all the slow routines. I probably need something faster. Maybe if I clear the buffer up front and then simply place everything sequentially it will go faster and fast enough for my purposes. Actually this is all I really need at the moment. But if I do need something special... 6 May 2008 21:20 |