![]() |
|
|
#1 |
|
Dec 2002
881 Posts |
I installed 4GB in a machine and configured mprime to use 3072 of it. I then replaced the 4GB with 2GB and forgot to reconfigure mprime. Oddly mprime keeps on running and does not seem to notice the total amount has changed. It starts the second stage of P-1 work with the parameters that you would expect for 4GB, and does not protest along the way.
|
|
|
|
|
|
#2 |
|
If I May
"Chris Halsall"
Sep 2002
Barbados
2C6E16 Posts |
|
|
|
|
|
|
#3 |
|
Serpentine Vermin Jar
Jul 2014
65168 Posts |
Although, it depends on the work being done and how much actual RAM mprime needs.
I'd want to know what exponent and what bounds were being used, then see exactly how much memory that process is snarfing up. If it is more than the free RAM, yeah, thrashing is an understatement. Seems like it would beat your system within an inch of it's life.
|
|
|
|
|
|
#4 |
|
P90 years forever!
Aug 2002
Yeehaw, FL
17·487 Posts |
Looking at the source code: mprime will ask the OS for the amount of physical ram. If your day or night mem settings are greater than the amount of physical RAM, then that setting is reduced to "physical RAM - 8MB".
Of course, I imagine this would still thrash. I cannot explain why the P-1 stage 2 bounds would be unaffected. |
|
|
|
|
|
#5 |
|
"Forget I exist"
Jul 2009
Dartmouth NS
846110 Posts |
the only thought that came to my mind is that with multiple channels 2GB could equate to more than 4GB.
|
|
|
|
|
|
#6 |
|
Basketry That Evening!
"Bunslow the Bold"
Jun 2011
40<A<43 -89<O<-88
1C3516 Posts |
|
|
|
|
|
|
#7 |
|
"Forget I exist"
Jul 2009
Dartmouth NS
210D16 Posts |
|
|
|
|
|
|
#8 |
|
Dec 2015
1 Posts |
I think you have to test the performance of your computer ...
|
|
|
|
![]() |
Similar Threads
|
||||
| Thread | Thread Starter | Forum | Replies | Last Post |
| Round Off Checking and Sum (Inputs) Error Checking | Forceman | Software | 2 | 2013-01-30 17:32 |
| "Hybrid Memory Cube" offers 1 Tb/s memory bandwith at just 1.4 mW/Gb/s | ixfd64 | Hardware | 4 | 2011-12-14 21:24 |
| Large memory bugfix for mprime 24.14.2 | S00113 | Software | 7 | 2006-03-24 02:56 |
| Problem with mprime (Fixed with mprime -d) | antiroach | Software | 2 | 2004-07-19 04:07 |
| Cache, dual channel memory and Mprime performance | optim | Hardware | 4 | 2004-06-25 03:20 |