Help with writing assembly..

Hi,
In my project I'm using LPC2378.
I Connect display to the IO ports. (DLC0283)
This display use a tft driver ILI9341

It has 8 bit data - I Connect it to P1.24-31
It has WR bit and CS bit.
The display data is arranged in 16bit per pixel.

To fill a full screen with data (To clear the screen)
(The color data - 16 bits - lower and upper bytes are not the same)

I create 2 integer that hold the upper & lower part of color (col_M32 & col_L32)

1. Set the frame addr (not shown here)
2. Set the CS bit to 0
3. Write the Most 8 bit of color
4. Set WR bit to 0 - then 1
5. Write the Least 8 bit of color
6. Set WR bit to 0 - then 1
7. Repeat lines 3-6 320*240 times.
8. Set the CS bit to 0

        ILI_CS_0;
        for (row=0;row<TFT_Y;row++){
                for (col=0;col<TFT_X;col++){

                        ILI_DAT_CLR=0xff000000;
                        ILI_DAT_SET=col_M32;
                        ILI_WR_0;
                        ILI_WR_1;

                        ILI_DAT_CLR=0xff000000;
                        ILI_DAT_SET=col_L32;
                        ILI_WR_0;
                        ILI_WR_1;

                }
        }
        ILI_CS_1;

The problem is that it works perfect - but it took about 1 second to finish and the effect of clear the screen is very bad.
In perfect world - the driver should have a command to do that - but thats life.

So - I need this code to run the fastest as it can.

When I look at the assembly code of the above code It seems to me that there are many assemblly commands that can be removed.
But I'm not good in assembly - I think that the above code can be created with less commands in assembly that I can insert in my code.

Here is the assembly part of the above code :

   467:         ILI_CS_0;
0x0003C908  E3A00701  MOV       R0,#0x00040000
0x0003C90C  E3A0190A  MOV       R1,#0x00028000
0x0003C910  E281120E  ADD       R1,R1,#WDMOD(0xE0000000)
0x0003C914  E581001C  STR       R0,[R1,#0x001C]
   468:         for (row=0;row<TFT_Y;row++){
0x0003C918  E3A05000  MOV       R5,#last_energy_valsH(0x00000000)
0x0003C91C  EA000019  B         0x0003C988
   469:                 for (col=0;col<TFT_X;col++){
   470:
0x0003C920  E3A04000  MOV       R4,#last_energy_valsH(0x00000000)
0x0003C924  EA000013  B         0x0003C978
   471:                         ILI_DAT_CLR=0xff000000;
0x0003C928  E3A004FF  MOV       R0,#0xFF000000
0x0003C92C  E3A0190A  MOV       R1,#0x00028000
0x0003C930  E281120E  ADD       R1,R1,#WDMOD(0xE0000000)
0x0003C934  E581001C  STR       R0,[R1,#0x001C]
   472:                         ILI_DAT_SET=col_M32;
0x0003C938  E59F006C  LDR       R0,[PC,#0x006C]
0x0003C93C  E5900000  LDR       R0,[R0]
0x0003C940  E5810014  STR       R0,[R1,#0x0014]
   473:                         ILI_WR_0;
0x0003C944  E3A00702  MOV       R0,#0x00080000
0x0003C948  E581001C  STR       R0,[R1,#0x001C]
   474:                         ILI_WR_1;
   475:
0x0003C94C  E5810014  STR       R0,[R1,#0x0014]
   476:                         ILI_DAT_CLR=0xff000000;
0x0003C950  E3A004FF  MOV       R0,#0xFF000000
0x0003C954  E581001C  STR       R0,[R1,#0x001C]
   477:                         ILI_DAT_SET=col_L32;
0x0003C958  E59F0048  LDR       R0,[PC,#0x0048]
0x0003C95C  E5900000  LDR       R0,[R0]
0x0003C960  E5810014  STR       R0,[R1,#0x0014]
   478:                         ILI_WR_0;
0x0003C964  E3A00702  MOV       R0,#0x00080000
0x0003C968  E581001C  STR       R0,[R1,#0x001C]
   479:                         ILI_WR_1;
   480:
   481:                 }
   483:         }
0x0003C96C  E5810014  STR       R0,[R1,#0x0014]

0x0003C970  E2840001  ADD       R0,R4,#0x00000001
0x0003C974  E3C04801  BIC       R4,R0,#0x00010000
0x0003C978  E3540D05  CMP       R4,#0x00000140
0x0003C97C  BAFFFFE9  BLT       0x0003C928

0x0003C980  E2850001  ADD       R0,R5,#0x00000001
0x0003C984  E3C05801  BIC       R5,R0,#0x00010000
0x0003C988  E35500F0  CMP       R5,#0x000000F0
0x0003C98C  BAFFFFE3  BLT       0x0003C920

   484:         ILI_CS_1;
   485:
   486: #endif
0x0003C990  E3A00701  MOV       R0,#0x00040000
0x0003C994  E3A0190A  MOV       R1,#0x00028000
0x0003C998  E281120E  ADD       R1,R1,#WDMOD(0xE0000000)
0x0003C99C  E5810014  STR       R0,[R1,#0x0014]
   487: }

Any help?
Thanks,
Doron