On Mon, 9 Apr 2001, Michel Lanners wrote:
On 6 Apr, this message from Peter Cordes echoed through cyberspace:
BTW, I've
found that compiling kernels isn't nearly as fast as I hoped it would be
with 4 PPC604 CPUs at 150MHz. I think the problem is that they share the L2
cache, and it
My very subjective impression is that compiling (kernels, or anything
else, for that matter) _is_ slower on PPC than on i386. No hard figures
here; but that has been my impression all the time during the 4 years
I'm following PPC Linux.
Reasons might be many and various: memory bandwidth being
On 6 Apr, this message from Peter Cordes echoed through cyberspace:
BTW, I've
found that compiling kernels isn't nearly as fast as I hoped it would be
with 4 PPC604 CPUs at 150MHz. I think the problem is that they share the L2
cache, and it isn't big enough to keep 4 gcc processes happy.
On 7 Apr, this message from Peter Cordes echoed through cyberspace:
Now that I think about it again, maybe the problem is just that the L2
cache is on the mobo, as well as being shared, so the CPUs have to go
through the bottleneck bus to get to it.
Yeah, nothing like a backside cache,
On Sat, Apr 07, 2001 at 03:17:24PM -0700, Taro Fukunaga wrote:
I don't have the technical background to follow a lot of this thread,
but I've been studying pthreads, and it seems that whether a certain
process gets executed more quickly on a multiprocessor computer depends
on how well the
I'm afraid it's even worse than that. I haven't looked up the
design specs on the web or anything, but I believe the Daystar
design is quite poor in a number of ways, some of them not really in
their control. First, it's not SMP, it's really AMP, or Asymetric
MP: only processor 0 gets
I am trying to get Debian 2.2 on a 9600/200MP.
When I reboot I get the Disk with the X in it. Which means I
need to configure My boot loader. I can't get into OF I get a
black screen.
I boot with the floppies and go to a shell I mount my root
partion (/dev/sda3) to /target and run ybin -b
On Sat, Apr 07, 2001 at 04:26:02AM -0700, Andrew Sharp wrote:
I'm afraid it's even worse than that. I haven't looked up the
design specs on the web or anything, but I believe the Daystar
design is quite poor in a number of ways, some of them not really in
their control. First, it's not SMP,
I don't have the technical background to follow a lot of this thread,
but I've been studying pthreads, and it seems that whether a certain
process gets executed more quickly on a multiprocessor computer depends
on how well the process uses threads for concurrency. So in a
compilation
9 matches
Mail list logo
