There can still be a problem if there is an outstanding write to the
block you're reading from because the request will see the new updated
write data, but the cache doesn't have the rest of the block yet so it
can't be satisfied. The only easy solution is to write in smaller
chunks. A more difficult solution is to have a valid bit for each byte
of the packet or maybe some kind of nested functional access, where
the functional access would try to continue down the hierarchy looking
for the fullest chunk of data and recombined itself on the way up.
Trouble is most memory devices would have a problem with this because
there is no way to check the next place in the cache for example.
Ali
On Dec 1, 2007, at 8:17 PM, Steve Reinhardt wrote:
Just to clarify: it's using BaseBufferArg::copyIn() and not
VirtualPort::CopyIn(), right? I just noticed that these are two
different functions with totally opposite semantics (explaining Ali's
earlier confusion).
Can you print the values of 'size' and 'getSize()' at the point in
Packet::checkFunctional() where you get this assertion failure? One
solution is probably to do the readFunctional() in smaller chunks, but
I don't know what size chunks it's already using. If it's trying to
do the whole buffer and we need to do it in cache-block chunks, that's
reasonable. If it's already doing cache-block chunks and still
failing, then that's a little more puzzling.
Steve
On Nov 30, 2007 3:54 PM, Jiayuan Meng <[EMAIL PROTECTED]> wrote:
Hey all,
I'm adding my own benchmarks which spawns multiple threads each
printing out
a string.
Things are fine at beginning but when I scale the number of threads
to 100,
a panic takes place:
"Memory value only partially satisfies the functional request. Now
what?"
This panic takes place in Packet::checkFunctional(Addr addr, int
size,
uint8_t* data) (mem/packet.cc). A backtrace with gdb reveals that
it is
triggered by the writeFunc( ) system call (sim/syscall_emul.cc),
which is
trying to use CopyIn to emulate printing to the screen. The CopyIn
sends a
functional read request which in turn caused the panic.
I appreciate your help.
Thanks!
Jiayuan
p.s. patch is available, just let me know how to send it to you.
_______________________________________________
m5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
_______________________________________________
m5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
_______________________________________________
m5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
