PCI bus access method

• Next message: Alexander Viro: "[PATCH] raid kdev_t cleanups (part 1)"
• Previous message: Alexander Viro: "[PATCH] kdev_t crapectomy"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Hi!

I'm curious about which one of the following code
segments is executed faster. They are in an interrupt
handler, the readings and writings are done on the PCI bus.

__u32 tmp;
int i;
for (i=0;i<128;i++) {
        tmp=readb(dev->dpmem+i);
        if (!tmp) continue;
        writeb(0,dev->dpmem+i);
        some_code;
}

256 PCI bus access in the worst case, but fewer code

or

__u32 tmp;
int i,j;
char *p=&tmp;
for (i=0;i<128;i+=4) {
        tmp=readl(dev->dpmem+i);
        if (!tmp) continue;
        writel(0, dev->dpmem+i);
        for (j=0;j<4;j++)
                if (*(p+j)) {
                        some_code;
                }
}

64 PCI bus access in the worst case but more code

Thanks,

Gabor

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

• Next message: Alexander Viro: "[PATCH] raid kdev_t cleanups (part 1)"
• Previous message: Alexander Viro: "[PATCH] kdev_t crapectomy"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

This archive was generated by hypermail 2b29 : Sun Jul 07 2002 - 22:00:14 EST