>
>On Fri, 18 Dec 1998, Andrea Arcangeli wrote:
>
>> Since we just waste 64*4 byte in the struct, we could waste 16 more bytes
>> to be completly aligned I think...
>
>this we'd have to make it a runtime pointer. Even if we could fix it up
>compile-time, the .section solution i suggested is better because we will
>not waste 'partial buffers', we will tightly pack cache-aligned structures
>into a continuous chunk.
Ah OK, that way we will waste 32byte/2 in mean only one time even if there
will be many structures that want to be cache aligned in the kernel.
Andrea Arcangeli
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/