[RndTbl] new ECC computer options

Hartmut W Sager hwsager at marityme.net
Sat Jan 28 17:09:05 CST 2017


Ah, so the original PC did simple parity checking only.  And I believe that
the PC AT did the same (definitely not less).  However, very many PC clones
right from the beginning never did even simple parity checking (and often
had no DMA either, which the PC and PC AT had), and that set the trend
toward no checking at all in the whole realm of consumer computers.  By the
time laptops came along, this was the norm, and only a few really high-end
laptops ever did even simple parity checking (let alone ECC).

By the way, ECC in the PC realm uses the same 9-bit RAM as for simple
parity checking, but uses the parity bits over a whole block of bytes to do
ECC.  Doing ECC on a per byte basis would require 11-bit RAM.

Hartmut W Sager - Tel +1-204-339-8331, +1-204-515-1701, +1-204-515-1700,
+1-810-471-4600


On 28 January 2017 at 08:00, Kevin McGregor <kevin.a.mcgregor at gmail.com>
wrote:

> The original PC had parity checking only. I don't know how long ago that
> stopped. Or did it?
>
> Kevin
>
> On Sat, Jan 28, 2017 at 1:36 AM, Hartmut W Sager <hwsager at marityme.net>
> wrote:
>
>> Just for the record here (i.e., moral support for you, Trevor), I too
>> have always been a strong believer in ECC.  And heck, the original IBM PC
>> had ECC (or did it just do parity checking, and crash if parity error?).
>>
>> Hartmut W Sager - Tel +1-204-339-8331 <%28204%29%20339-8331>
>>
>>
>> On 28 January 2017 at 00:46, Trevor Cordes <trevor at tecnopolis.ca> wrote:
>>
>>> I'm looking for input from anyone in the club who may be knowledgable,
>>> eyeballing, or has purchased a "workstation" system recently with ECC
>>> memory.  (Note, ECC is imperative!)  I don't need dual-socket, crazy
>>> speed, just something like a mid-range modern i7 with modern RAM, slots,
>>> etc.  (i3 speeds won't cut it.)
>>>
>>>
>>
>> _______________________________________________
>> Roundtable mailing list
>> Roundtable at muug.ca
>> https://muug.ca/mailman/listinfo/roundtable
>>
>>
>
> _______________________________________________
> Roundtable mailing list
> Roundtable at muug.ca
> https://muug.ca/mailman/listinfo/roundtable
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://muug.ca/pipermail/roundtable/attachments/20170128/c710a116/attachment-0001.html>


More information about the Roundtable mailing list