Re: PCIe MSI-X interrupts

Liste des GroupesRevenir à c arch 
Sujet : Re: PCIe MSI-X interrupts
De : mitchalsup (at) *nospam* aol.com (MitchAlsup1)
Groupes : comp.arch
Date : 27. Jun 2024, 19:37:12
Autres entêtes
Organisation : Rocksolid Light
Message-ID : <318fc7d548e853498b93337b1ca4acba@www.novabbs.org>
References : 1 2 3 4 5 6 7 8
User-Agent : Rocksolid Light
Scott Lurndal wrote:

mitchalsup@aol.com (MitchAlsup1) writes:
Scott Lurndal wrote:
>
mitchalsup@aol.com (MitchAlsup1) writes:
Scott,
>
Note that the ECAM must support 8, 16, 32-bit (optionally 64-bit)
single-copy atomic accesses to all configuration space registers.
>
MMI/O is sequentially consistent while Config is Strongly ordered.
>
Exactly what are you intending to mean from "single-copy atomic
accesses" ??

It's a term-of-art in the ARM architecture document (DDI0487).

    A memory access instruction that is single-copy atomic has the
following properties:

    1. For a pair of overlapping single-copy atomic store instructions,
all
        of the overlapping writes generated by one of the stores are
        Coherence-after the corresponding overlapping writes generated
        by the other store.
Writes to a small local do not pass each other in the interconnect.

    2. For a single-copy atomic load instruction L1 that overlaps a
single-copy
       atomic store instruction S2, if one of the overlapping reads
generated
       by L1 Reads-from one of the overlapping writes generated by S2,
then none
       of the overlapping writes generated by S2 are Coherence-after the
       corresponding overlapping reads generated
       by L1.
Because the LD saw the intermediate data state where some of the STs
were
complete while others pend.

Date Sujet#  Auteur
21 Jun 24 * PCIe MSI-X interrupts24MitchAlsup1
22 Jun 24 +* Re: PCIe MSI-X interrupts7MitchAlsup1
22 Jun 24 i+* Re: PCIe MSI-X interrupts3MitchAlsup1
22 Jun 24 ii`* Re: PCIe MSI-X interrupts2MitchAlsup1
23 Jun 24 ii `- Re: PCIe MSI-X interrupts1MitchAlsup1
22 Jun 24 i+* Re: PCIe MSI-X interrupts2MitchAlsup1
23 Jun 24 ii`- Re: PCIe MSI-X interrupts1MitchAlsup1
22 Jun 24 i`- Re: PCIe MSI-X interrupts1MitchAlsup1
25 Jun 24 `* Re: PCIe MSI-X interrupts16MitchAlsup1
25 Jun 24  +- Re: PCIe MSI-X interrupts1MitchAlsup1
27 Jun 24  `* Re: PCIe MSI-X interrupts14MitchAlsup1
27 Jun 24   +* Re: PCIe MSI-X interrupts12Michael S
27 Jun 24   i+* Re: PCIe MSI-X interrupts9MitchAlsup1
28 Jun 24   ii+* Re: PCIe MSI-X interrupts3MitchAlsup1
30 Jun 24   iii`* Re: PCIe MSI-X interrupts2George Neuner
30 Jun 24   iii `- Re: PCIe MSI-X interrupts1MitchAlsup1
28 Jun 24   ii+- Re: PCIe MSI-X interrupts1MitchAlsup1
10 Jul 24   ii`* Re: PCIe MSI-X interrupts4MitchAlsup1
10 Jul 24   ii +* Re: PCIe MSI-X interrupts2Kent Dickey
11 Jul 24   ii i`- Re: PCIe MSI-X interrupts1MitchAlsup1
29 Jul 24   ii `- Re: PCIe MSI-X interrupts1MitchAlsup1
1 Jul 24   i`* Re: PCIe MSI-X interrupts2aph
4 Jul 24   i `- Re: PCIe MSI-X interrupts1MitchAlsup1
27 Jun 24   `- Re: PCIe MSI-X interrupts1MitchAlsup1

Haut de la page

Les messages affichés proviennent d'usenet.

NewsPortal