Basic GDI functions should always be optimized for speed rather than size. The entire windowing system and other components rely on these functions, any bottleneck in these functions results in a bottleneck in everything else. If your code generator is just as fast as current implementations, or can be made just as fast if not faster, then i'd say go for it. Otherwise, i'd say don't.
Richard
Ge van Geldorp wrote:
One of the things which has bothered me a bit is the code duplication we have in our DIB engine (subsys/win32k/dib). Most of the BitBlt routines in there are very similar. With the recent interest in optimizations a bunch of new (almost identical) routines were added. Don't get me wrong, I'm not saying that adding those optimizations was a bad idea, I'm just pointing out that we have a lot of code duplication.
There are 256 possible ROP codes, we support 1bpp, 4bpp, 8bpp, 16bpp, 24bpp and 32bpp, so in theory there could be 1536 routines with basically the same structure. I've been playing around with the idea to write a code generator which would generate the source code for those routines. That would cut down on the duplicated source code and associated maintenance problems (you only need to change the code generator) while still allowing optimized code for each individual ROP code.
Just to give you an idea what such a code generator would look like, I've attached my first attempt. Please note that it doesn't really try to optimize the generated code yet, it's just to give an impression. The code generated (16bpp only atm) is rather large, you can get it from ftp://ftp.geldorp.nl/pub/ReactOS/dib16gen.c if you like (or compile the code generator ("gcc -o gendib gendib.c") and run it).
A possible problem is that the generated code is quite large. When using the generated 16bpp code, size of win32k.sys increases by about 350kb. Extrapolating this for all bpps, it would mean that win32k.sys would triple in size.
So, I'm wondering what you guys are thinking. Should we basically trade memory for speed? Problem is that I can't quantify the speed increase at the moment.
Gé van Geldorp.
#include <stdio.h>
#define USES_DEST(RopCode) ((((RopCode) & 0xaa) >> 1) != ((RopCode) & 0x55)) #define USES_SOURCE(RopCode) ((((RopCode) & 0xcc) >> 2) != ((RopCode) & 0x33)) #define USES_PATTERN(RopCode) ((((RopCode) & 0xf0) >> 4) != ((RopCode) & 0x0f))
static void PrintRoutineName(FILE *Out, unsigned Bpp, unsigned RopCode) { static struct { unsigned RopCode; char *Name; } KnownCodes[] = { { 0x00, "BLACKNESS" }, { 0x11, "NOTSRCERASE" }, { 0x33, "NOTSRCCOPY" }, { 0x44, "SRCERASE" }, { 0x55, "DSTINVERT" }, { 0x5a, "PATINVERT" }, { 0x66, "SRCINVERT" }, { 0x88, "SRCAND" }, { 0xbb, "MERGEPAINT" }, { 0xc0, "MERGECOPY" }, { 0xcc, "SRCCOPY" }, { 0xee, "SRCPAINT" }, { 0xf0, "PATCOPY" }, { 0xfb, "PATPAINT" }, { 0xff, "WHITENESS" } }; unsigned Index;
for (Index = 0; Index < sizeof(KnownCodes) / sizeof(KnownCodes[0]); Index++) { if (RopCode == KnownCodes[Index].RopCode) { fprintf(Out, "DIB_%uBPP_BitBlt_%s", Bpp, KnownCodes[Index].Name); return; } } fprintf(Out, "DIB_%uBPP_BitBlt_%02x", Bpp, RopCode); }
static void CreatePrimitive(FILE *Out, unsigned Bpp, unsigned RopCode) { int UsesSource; int UsesPattern; int UsesDest;
UsesSource = USES_SOURCE(RopCode); UsesPattern = USES_PATTERN(RopCode); UsesDest = USES_DEST(RopCode);
fprintf(Out, "\n"); fprintf(Out, "static void\n"); PrintRoutineName(Out, Bpp, RopCode); fprintf(Out, "(PBLTINFO BltInfo)\n"); fprintf(Out, "{\n"); fprintf(Out, " ULONG DestX, DestY;\n"); if (UsesSource) { fprintf(Out, " ULONG SourceX, SourceY;\n"); } if (UsesPattern) { fprintf(Out, " ULONG PatternY = 0;\n"); } fprintf(Out, " ULONG Dest = 0, Source = 0, Pattern = 0;\n"); fprintf(Out, " PULONG DestBits;\n"); fprintf(Out, " ULONG RoundedRight;\n"); fprintf(Out, "\n"); fprintf(Out, " RoundedRight = BltInfo->DestRect.right -\n"); fprintf(Out, " ((BltInfo->DestRect.right - BltInfo->DestRect.left) & 0x1);\n"); if (UsesSource) { fprintf(Out, " SourceY = BltInfo->SourcePoint.y;\n"); } fprintf(Out, " DestBits = (PULONG)(\n"); fprintf(Out, " BltInfo->DestSurface->pvScan0 +\n"); fprintf(Out, " (BltInfo->DestRect.left << 1) +\n"); fprintf(Out, " BltInfo->DestRect.top * BltInfo->DestSurface->lDelta);\n"); fprintf(Out, "\n"); if (UsesPattern) { fprintf(Out, " if (BltInfo->PatternSurface)\n"); fprintf(Out, " {\n"); fprintf(Out, " PatternY = (BltInfo->DestRect.top + BltInfo->BrushOrigin.y) %\n"); fprintf(Out, " BltInfo->PatternSurface->sizlBitmap.cy;\n"); fprintf(Out, " }\n"); fprintf(Out, " else\n"); fprintf(Out, " {\n"); fprintf(Out, " Pattern = BltInfo->Brush->iSolidColor |\n"); fprintf(Out, " (BltInfo->Brush->iSolidColor << 16);\n"); fprintf(Out, " }\n"); } fprintf(Out, "\n"); fprintf(Out, " for (DestY = BltInfo->DestRect.top; DestY < BltInfo->DestRect.bottom; DestY++)\n"); fprintf(Out, " {\n"); if (UsesSource) { fprintf(Out, " SourceX = BltInfo->SourcePoint.x;\n"); fprintf(Out, "\n"); } fprintf(Out, " for (DestX = BltInfo->DestRect.left; DestX < RoundedRight; DestX += 2, DestBits++"); if (UsesSource) { fprintf(Out, ", SourceX += 2"); } fprintf(Out, ")\n"); fprintf(Out, " {\n"); if (UsesDest) { fprintf(Out, " Dest = *DestBits;\n"); fprintf(Out, "\n"); } if (UsesSource) { fprintf(Out, " Source = DIB_GetSource(BltInfo->SourceSurface, SourceX, SourceY, BltInfo->XlateSourceToDest);\n"); fprintf(Out, " Source |= DIB_GetSource(BltInfo->SourceSurface, SourceX + 1, SourceY, BltInfo->XlateSourceToDest) << 16;\n"); fprintf(Out, "\n"); } if (UsesPattern) { fprintf(Out, " if (BltInfo->PatternSurface)\n"); fprintf(Out, " {\n"); fprintf(Out, " Pattern = DIB_GetSource(BltInfo->PatternSurface, (DestX + BltInfo->BrushOrigin.x) % BltInfo->PatternSurface->sizlBitmap.cx, PatternY, BltInfo->XlatePatternToDest);\n"); fprintf(Out, " Pattern |= DIB_GetSource(BltInfo->PatternSurface, (DestX + BltInfo->BrushOrigin.x + 1) % BltInfo->PatternSurface->sizlBitmap.cx, PatternY, BltInfo->XlatePatternToDest) << 16;\n"); fprintf(Out, " }\n"); fprintf(Out, "\n"); } fprintf(Out, " *DestBits = DIB_DoRop(BltInfo->Rop4, Dest, Source, Pattern);\n"); fprintf(Out, " }\n"); fprintf(Out, "\n"); fprintf(Out, " if (DestX < BltInfo->DestRect.right)\n"); fprintf(Out, " {\n"); if (UsesDest) { fprintf(Out, " Dest = *((PUSHORT)DestBits);\n"); fprintf(Out, "\n"); } if (UsesSource) { fprintf(Out, " Source = DIB_GetSource(BltInfo->SourceSurface, SourceX, SourceY, BltInfo->XlateSourceToDest);\n"); } if (UsesPattern) { fprintf(Out, " if (BltInfo->PatternSurface)\n"); fprintf(Out, " {\n"); fprintf(Out, " Pattern = DIB_GetSource(BltInfo->PatternSurface, (DestX + BltInfo->BrushOrigin.x) % BltInfo->PatternSurface->sizlBitmap.cx, PatternY, BltInfo->XlatePatternToDest);\n"); fprintf(Out, " }\n"); fprintf(Out, "\n"); } fprintf(Out, " DIB_16BPP_PutPixel(BltInfo->DestSurface, DestX, DestY, DIB_DoRop(BltInfo->Rop4, Dest, Source, Pattern) & 0xFFFF);\n"); fprintf(Out, " DestBits = (PULONG)((ULONG_PTR)DestBits + 2);\n"); fprintf(Out, " }\n"); fprintf(Out, "\n"); if (UsesSource) { fprintf(Out, " SourceY++;\n"); } if (UsesPattern) { fprintf(Out, " if (BltInfo->PatternSurface)\n"); fprintf(Out, " {\n"); fprintf(Out, " PatternY++;\n"); fprintf(Out, " PatternY %= BltInfo->PatternSurface->sizlBitmap.cy;\n"); fprintf(Out, " }\n"); } fprintf(Out, " DestBits = (PULONG)(\n"); fprintf(Out, " (ULONG_PTR)DestBits -\n"); fprintf(Out, " ((BltInfo->DestRect.right - BltInfo->DestRect.left) << 1) +\n"); fprintf(Out, " BltInfo->DestSurface->lDelta);\n"); fprintf(Out, " }\n"); fprintf(Out, "}\n"); }
static void CreateTable(FILE *Out, unsigned Bpp) { unsigned RopCode;
fprintf(Out, "\n"); fprintf(Out, "static void (*PrimitivesTable[256])(PBLTINFO) =\n"); fprintf(Out, " {\n"); for (RopCode = 0; RopCode < 256; RopCode++) { fprintf(Out, " "); PrintRoutineName(Out, Bpp, RopCode); if (RopCode < 255) { putc(',', Out); } putc('\n', Out); } fprintf(Out, " };\n"); }
static void CreateBitBlt(FILE *Out, unsigned Bpp) { fprintf(Out, "\n"); fprintf(Out, "BOOLEAN\n"); fprintf(Out, "DIB_%uBPP_BitBlt(PBLTINFO BltInfo)\n", Bpp); fprintf(Out, "{\n"); fprintf(Out, " PrimitivesTable[BltInfo->Rop4 & 0xff](BltInfo);\n"); fprintf(Out, "\n"); fprintf(Out, " return TRUE;\n"); fprintf(Out, "}\n"); }
int main(int argc, char *argv[]) { FILE *Out; unsigned RopCode; unsigned Bpp;
Bpp = 16; Out = fopen("dib16gen.c", "w"); if (NULL == Out) { perror("Error opening output file"); exit(1); }
fprintf(Out, "/* This is a generated file. Please do not edit */\n"); fprintf(Out, "\n"); fprintf(Out, "#include "w32k.h"\n");
for (RopCode = 0; RopCode < 256; RopCode++) { CreatePrimitive(Out, Bpp, RopCode); } CreateTable(Out, Bpp); CreateBitBlt(Out, Bpp);
fclose(Out);
return 0; }
Ros-dev mailing list Ros-dev@reactos.com http://reactos.com:8080/mailman/listinfo/ros-dev