Question on large amounts of RAM and memory training.
Question on large amounts of RAM and memory training.
Total that got cut of there was £3,309. Which to be fair given what it allows me to do now will mean it should pay for itself within a couple of years worst case.
Hey all, thanks for all your replies to my previous post about the beefy machine for test renders, i am delighted to say i have gone ahead and ordered the machine after switching the gpu to a 4080 super, and getting a slighty better power supply.
I have also decided to go ahead and double the RAM to 192GB while they are still builing it. But i am getting concerned about cold boots and memory training.
How often does memory training happen? Is it every cold boot? Every manual reset?
The machine will be crashing alot, its just the nature of pushing them hard, and i dont want to be stuck waiting with that horrible feeling of if it will ever even boot at all, the next time i push the render quality a little too high in 3DSMax.
Would greatly appreciate some feedback on this from someone with experience of machines that have alot of RAM.
I get ya want to overclock, buy why on a rendering machine? Are those seconds saved worth loosing an entire render and having to restart / clear CMOS
The more ram the less stable overclocking will get. Hence why most rendering machines stick with JDEC timings
Feel free to ignore me as the most ram I've OC'd if 64gb
Hey thanks for your reply, are you saying memory training is only related to overclocking?
As no, i dont intend to overlock the machine. I dont know much about PC building and had seen some videos with people talking about memory training, i just assumed it was a part of the build/boot process for all machines.
I guess my question really is then, does having a very large amount of RAM have a negative effect on boot times, and is there any variation in that depending on the type of boot, cold/soft etc.
Ok, I may have misunderstood what you ment.
The more ram you have in a system the longer training can take. DDR5 is the worse offender. Don't be surprised if it takes 10 min or more to train 192gb.
Memory training happens after every cold boot (from off state). Every PC will do this it is normal.
If you're not overclocking and you have instabilities there is something wrong. Need to use something like OCCT to find the problem.
I see you have 14th gen Intel, I would recommend getting a contact plate as Intel's mechanism sucks ass.
Large amounts of RAM should not significantly impact boot times unless you have a bios / efi that is doing a full memory check every boot like old computers used to do 30-40 years ago.
Memory Training? I assume is when the mobo tries overclock settings until it finds something that works. For a renderfarm, that's not good.
In the EFI you can choose XMP profile or DOCP profile for your RAM, but beware that just because the RAM supports that speed, the mobo and CPU might not. Example, I have DDR4-4600 RAM that I can only run at 3000 speeds because my CPU can't handle 4600 speeds.
It will take some tweaking and testing and benchmarking to find the optimal setting that doesn't crash the system during a render.
does having a very large amount of RAM have a negative effect on boot times
My 64GB rig takes a good 1-2 minutes to memory train. You can skip it on most boots by enabling
Memory Context Restoreon Asus motherboards, but starting after being unplugged from power or a hardware change (and seemingly randomly) will still require training. I also believe XMP plays a heavy part in training, so leaving it at the default JDEC speeds should speed up the boot process.
Maybe a stupid question, but since when are memory chips no longer a power of 2 size?
Probably 64gb chips that failed QC and had some registers disabled. Similar to how CPUs that fail QC have cores disabled and are sold as lower-tier skus