// Mixing ARM and/or Thumb Assembly Code with C when using GCC
// by Jeff Frohwein
// Some contributions from Dennis Ranke (exoticorn/icebird)
//   v1.0225 - Original Release
//   v1.0311 - Bug fix. Replaced STMED & LDMED with STMFD & LDMFD.
//   v1.0314 - No longer saving R14 on stack. Not needed.

//  The first half of this document describes including assembly
// code inside of your .c files. The second half describes linking
// a stand-alone .s assembly file in with your project. These examples
// only apply for GCC and NOT the arm SDT compiler.

//  The normal code used in GBA games is Thumb asm. Thumb code tends
// to be smaller and slower than ARM code. If you plan to mix Thumb
// and ARM code then you need to use the following compiler option:

//  First, make sure that you add '-mthumb-interwork' to your compile
// options for both the compiler (GCC) and the assembler (AS).
//
//  -mthumb-interwork
//       Generate code which supports calling between the ARM
//      and THUMB instruction sets. Without this option the two
//      instruction sets cannot be reliably used inside one program.
//      The default is `-mno-thumb-interwork', since slightly larger
//      code is generated when `-mthumb-interwork' is specified.

//
// *********** Mixing Assembly IN c code examples ************

// Draw pixel in GBA graphics modes 3/5 in Thumb asm (slow)
// Entry: px = pixel X coordinate
//        py = pixel Y coordinate
//      colr = pixel color
void PutPixel16 (u32 px, u32 py, u32 colr)
   {
   // r0 = px
   // r1 = py
   // r2 = colr
   // Since input parameters are stored in the lower registers,
   //  it's more efficient to use the upper registers for
   //  your asm code whenever possible.
   // For less routine overhead, use 'u32' function parameters
   //  instead of 'u8' or 'u16'. These smaller types automatically
   //  perform the following additional overhead: u8: v=v&0xff; u16: v=v&0xffff;
   asm ("
      mov    r3,%0

      mov    r5, #240
      lsl    r5, r5, #1          @ r2 = 480

      mul    r5,r5,r3
      mov    r4,%1
      add    r5,r5,r4
      add    r5,r5,r4

      mov    r3,#192
      lsl    r3, r3, #19         @ r0 = 0x6000000

      add    r3,r3,r5
      mov    r4,%2
      strh   r4,[r3]
      " :
      /* No output */ :                 // No output is returned from this routine.
      "r" (py), "r" (px), "r" (colr) :  // Define the routine inputs (%0,%1,%2).
      "r3", "r4", "r5" );               // Specific which registers we destroy.
                                        // For more info on 'asm' read the GCC docs at gnu.org
   }

// Draw pixel in GBA graphics modes 3/5 in ARM asm (fast)
// Entry: px = pixel X coordinate
//        py = pixel Y coordinate
//      colr = pixel color
void PutPixel32 (u32 px, u32 py, u32 colr)
   {
   // r0 = px
   // r1 = py
   // r2 = colr
   // Since input parameters are stored in the lower registers,
   //  it's more efficient to use the upper registers for
   //  your asm code whenever possible.
   // For less routine overhead, use 'u32' function parameters
   //  instead of 'u8' or 'u16'. These smaller values automatically
   //  perform the following additional overhead: u8: v=v&0xff; u16: v=v&0xffff;
   asm ("
@ Enter ARM Mode
      adr    r3,2f             @ Get address of label 2 (f means the label
                               @  is below[f=forward] instead of above[b=backward])
      bx     r3

      .ALIGN                   @ This is required before all ARM code.
                               @ ..or you can use .CODE 32 here
      .ARM

2:
      mov    r4,#480
      mul    r5,r4,r1
      movs   r4,r0,lsl #1
      add    r5,r5,r4

      mov    r3,#0x6000000     @ MOV Rx,#x attempts to shift an 8-bit value to
                               @  to implement your request. Any other format will
                               @  generate an error. Use LDR Rx,=x for other values.
      add    r3,r3,r5
      strh   r2,[r3]

@ Enter Thumb mode
      adr    r3,3f + 1
      bx     r3

      .THUMB                   @ ..or you can use .CODE 16 here
3:
      " :
      /* No output */ :               // No output is returned from this routine
      "r" (px), "r" (py), "r" (colr): // Define the routine inputs (%0,%1,%2) even if we don't use them
      "r3", "r4", "r5" );             // Specific which registers we destroy
   }

//*****************************************************************

// *********** Linking to assembly code (.s) from C code ************

//  Both of the following routines my be in the same .s file.
// One is written in Thumb (slow) amd the other is in ARM (fast).
// Add the following to your .c file:
//   extern void DrawPixel16 (u32 px, u32 py, u32 colr);
//   extern void DrawPixel32 (u32 px, u32 py, u32 colr, u32 scrnadr);
// Add this .s file to your makefile and you are all setup.
// (For an example of that, check out gfxLib on http://www/devrs.com/gba/ )
//
//  Note that in DrawPixel16 below, the compiler stays in native Thumb
// mode. In DrawPixel32, the C calling routine switches to ARM mode
// when calling DrawPixel32 because no .THUMB_FUNC is used. The
// C calling routine expects you to switch back to Thumb mode before
// returning. This is accomplished by the 'bx r14' here.

@ Draw pixel in GBA graphics modes 3/5 in Thumb asm (slow)
@ (void) DrawPixel16 (u32 x, u32 y, u32 color);
        .THUMB
        .ALIGN  2
        .GLOBL  DrawPixel16
        .THUMB_FUNC

DrawPixel16:
        push    {r3, r4, r5, lr}

        mov     r5, #240
        lsl     r5, r5,#1           @ r5 = 480
        mul     r5,r5,r1 @r3
        mov     r4,r0
        add     r5,r5,r4
        add     r5,r5,r4
        mov     r3,#192
        lsl     r3, r3, #19         @ r3 = 0x6000000
        add     r3,r3,r5
        mov     r4,r2
        strh    r4,[r3]

        pop     {r3, r4, r5}
        pop     {r0}
        bx      r0

@ Draw pixel in GBA graphics modes 3/5 in ARM asm (fast)
@ Entry: px = pixel X coordinate
@        py = pixel Y coordinate
@     color = pixel color
@   scrnadr = base screen address
@ (void) DrawPixel32 (u32 x, u32 y, u32 color, u32 scrnadr);

        .ARM
        .ALIGN
        .GLOBL  DrawPixel32

DrawPixel32:
        stmfd   sp!,{r4-r5}

        mov     r4,#480
        mul     r5,r4,r1
        add     r5,r5,r0,lsl #1
        add     r4,r5,r3
        strh    r2,[r4]

        ldmfd   sp!,{r4-r5}
        bx      lr

*EOF*