Hi,

Thanks for the reply.

2011/8/4 Michel Dänzer <[email protected]>:
> On Don, 2011-08-04 at 14:46 +0800, Chen Jie wrote:
>>
>> We're running RS780E on a MIPS64 compatible platform, and encounter
>> screen corruption sometimes:
>>  * Do 'x11perf -compwinwin500' -- Window decoration and the background
>> corrupt 
>> (http://dev.lemote.com/files/upload/software/temp/x11perf-corrupt.png)
>>  * Hardware Accelerated video playback(video-pipe branch of mesa) --
>> both playback and the desktop:
>>   - 
>> http://dev.lemote.com/files/upload/software/temp/newmobcal1920-playback.png
>>   - 
>> http://dev.lemote.com/files/upload/software/temp/newmobcal1920-desktop-corrupt.png
>>   - Related thread:
>> http://lists.freedesktop.org/archives/mesa-dev/2011-August/010064.html
>
> The video decoding corruption may be due to the pipe-video code not
> working properly on all hardware yet.
>
> The rest looks like more or less random BO corruption.
The x11perf test causes the corruption each time.


>
>
>> Any idea? (BTW, don't know if related, but the bandwidth of separated
>> video ram is really low, about 14MB/s for write op)
>
> How do you measure it?
mmap the VRAM and write to it. Attachment is the test code.



Regards,
- Chen Jie
#include <sys/time.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/fcntl.h>
#include <sys/mman.h>
#include <stdio.h>
#include <string.h>

int main()
{
	void *fbmem;
	int fd;
	int fb_offset = 0x100000;
	struct timeval tv1, tv2;
	int i;
	
	fd = open("/dev/mem", O_RDWR);
	if(fd < 0) {
		printf("Open %s failed", "/dev/mem");
		return -1;
	}

	/* mmap 16M fbmem */
	fbmem = mmap(NULL, 16*1024*1024, PROT_WRITE, MAP_SHARED, fd, fb_offset);
	if(fbmem == NULL) {
		printf("mmap fbmem failed\n");
		return -1;
	}

	gettimeofday(&tv1, NULL);
	for(i=0; i<10; i++)
		memset(fbmem, 0x55, 16*1024*1024);
	gettimeofday(&tv2, NULL);

	printf("fbmem speed is %f\n", 
		16*10.0/((tv2.tv_sec+tv2.tv_usec/1000000)-(tv1.tv_sec+tv1.tv_usec/1000000)));

	return 0;
}
_______________________________________________
xorg-driver-ati mailing list
[email protected]
http://lists.x.org/mailman/listinfo/xorg-driver-ati

Reply via email to