Re: 4gb (4 memory sticks) at 400Mhz on socket 939 MB -- JEDEC specifications ... | |
| [Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] | |
On Sun, 2006-07-09 at 01:40 -0400, hahn@xxxxxxxxxxxxxxxxxxx wrote: > I believe this ignores another relevant factor: > how many chip-selects the dimm uses. I was purposely not trying to get into memory controller design. Not only have I ripped out the AMD and Intel engineering specification sheets on various chipsets to verify the _exact_ IC technology, width and number/banking before -- but I've designed memory controllers myself. But yes, if you have a total of 128-bit IC width in a 64-bit DIMM, that's also an issue. But that's just the tip-of-the-iceberg. > my understanding is that if a dimm is "double-sided", it means that > it uses 2 CS's. There are a lot of "double sided" or "double stacked" or "low density" or "double rank" or "low rank" or countless other, non-standard, non-uniform descriptions out there. I _refuse_ to use them, as they are not standardized and often confusing. E.g., does "low density" mean less total width/fewer chips? Or does it mean the lower density in the IC, meaning more total width/more chips? The *ONLY* way to *ACCURATELY* describe this is to sit down and break out each DIMM into the *RAW* number of 32-bit "banks" -- and that means you take the bit-width of the *INDIVIDUAL* ICs on every DIMM and multiply by number (except for parity/ECC chips). So, if you want to get really details, we *CAN* do that! ;-> Furthermore, some chipsets just do _not_ support certain IC technologies, bit-widths and other sizing. The chronic issue was the PC100 256MB DIMM for i440BX versus i810/815 -- they used completely _difference_ DIMMs. The i440BX only supported a 4-bit with in 32-chip (36-chip for ECC) configuration -- clearly a "double sided" registered DIMM. The i810/815 used a 8-bit or 16-bit in a 8 or 4 chip configuration, respectively. And even that is a mega-oversimplification! ;-> > table 46 on p 182 of AMD's bios guide (doc 26094) appears to allow up > to 6 ranks for ddr400/2T operation. afaikt, a double-rank dimm is AKA > double-sided. unfortunatley AMD also adds some weaselish text about > how MB vendors should validate, etc... I only listed the JEDEC specifications and recommendations. If you want to go outside of those, which some vendors may do, by all means, do! Also remember that AMD _might_ be talking about "banks" and not merely "DIMMs." "Banks" are 32-bit (like old SIMMs). "DIMMs" are 64-bit. BTW, I've seen the term "rank" used 3 different ways. Everyone seems to want to simply things with a term or two. Impossible. Especially when it comes to DDR333 v. DDR400 performance. Even reporting 3 or 4 timings is woefully incomplete. -- Bryan J. Smith Professional, technical annoyance mailto:b.j.smith@xxxxxxxx http://thebs413.blogspot.com ---------------------------------------------------------- The existence of Linux has far more to do with the breakup of AT&T's monopoly than anything Microsoft has ever done. -- amd64-list@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/amd64-list
[Search] [Home] [Kernel List] [Linux ia64] [Linux X86_64] [Red Hat Install] [Red Hat Migration] [Red Hat Development] [Red Hat 9 Bible] [Red Hat 9 Mailing List] [Fedora Legacy] [Yosemite News]