Re: Tonights Tradeoff - Background Execution Buffers

Liste des GroupesRevenir à c arch 
Sujet : Re: Tonights Tradeoff - Background Execution Buffers
De : anton (at) *nospam* mips.complang.tuwien.ac.at (Anton Ertl)
Groupes : comp.arch
Date : 13. Oct 2024, 17:43:53
Autres entêtes
Organisation : Institut fuer Computersprachen, Technische Universitaet Wien
Message-ID : <2024Oct13.184353@mips.complang.tuwien.ac.at>
References : 1 2 3 4 5 6 7 8 9 10 11 12 13
User-Agent : xrn 10.11
Robert Finch <robfi680@gmail.com> writes:

[Context: carry and overflow in GPRs
 <https://www.complang.tuwien.ac.at/anton/tmp/carry.pdf>]

Been thinking some about the carry and overflow and what to do about
register spills and reloads during expression processing. My thought was
that on the machine with 256 registers, simply allocate a ridiculous
number of registers for expression processing, for example 25 or even
50. Then if the expression is too complex, have the compiler spit out an
error message to the programmer to simplify the expression. Remnants of
the ‘expression too complex’ error in BASIC. So, there are no spills or
reloads during expression processing.

The first question is how carry and overflow are represented in the
programming language.

Currently there are programming languages with growable integers, and
overflow is needed short-term for that, so spilling the overflow bit
is probably not necessary for that (and indeed, the one overflow bit
of AMD64 or ARM A64 that is not preserved across calls is good enough
for that).

For dealing with multiple-precision integers (e.g., when the growable
integers actually grow to more than one word), typically library
routines are used, but sure, one could also have a programming
language that computes with multi-precision integers and then is
compiled into either loops over the individual words of these numbers,
or it unrolls these loops (if the length is known in advance).  Yes,
if you run out of registers there, you may want to spill and refill a
register, including its carry bit.  But that should be rare, so if
it's an expensive operation, we can live with it.

What we have now is things like the GNU C extension

bool __builtin_add_overflow (type1 a, type2 b, type3 *res);

This produces two different results, the return value, and res.  With
the kind of architecture I have in mind, these two results could be
allocated into the same register.  If at some point the register has
to be spilled, the two results can be stored into different memory
locations, and on refill they will land in different GPRs unless the
compiler writer really puts a lot more work in than is merited (I
don't expect many spills and refills).

I think the storextra / loadextra
registers used during context switching would work okay. But in Q+ there
are 256 regs which require eight storextra / loadextra registers. I
think the store extra / load extra registers could be hidden in the
context save and restore hardware. Not even requiring access via CSRs or
whatever.

Yes.  In my paper I wanted to spell out an implementation that does
not look like I am ignoring some hard problems and shove it over to
the implementor.  If a computer architect wants to pick my idea up,
they are welcome to implement context-switching in any way they deem
appropriate.

I suppose context loads and stores could be done in blocks of
32 registers. An issue is that the load extra needs to be done before
registers are loaded.

Maybe, with 256 GPRs, you would use 8 storeextra and 8 loadextra
registers, each on associated with 32 registers.  This avoids having
to make the whole process a sequential operation working on 32-GPR
blocks.  Just store all 256 GPRs, sync (to get the storeextra
registers up-to-date, then store the 8 storeextra registers.  For
context load, load the 8 loadextra registers, sync (so the loads of
the loadextra registers are finished), then the 256 GPRs.

Or alternatively just have 8 extra registers that are used for both
context stores and context loads.  Then you cannot use the same sync
for both storing and loading, but you may prefer a little more
context-switch overhead to needing 16 extra registers.

Another thought is to store additional info such as a CRC check of the
register file on context save and restore.

Typically ECC memory and something similar in bus protocols achieve
what I guess you want to achieve with the CRC checks.

- anton
--
'Anyone trying for "industrial quality" ISA should avoid undefined behavior.'
  Mitch Alsup, <c17fcd89-f024-40e7-a594-88a85ac10d20o@googlegroups.com>

Date Sujet#  Auteur
7 Sep 24 * Tonights Tradeoff99Robert Finch
7 Sep 24 `* Re: Tonights Tradeoff98MitchAlsup1
8 Sep 24  `* Re: Tonights Tradeoff97Robert Finch
8 Sep 24   `* Re: Tonights Tradeoff96MitchAlsup1
10 Sep 24    `* Re: Tonights Tradeoff95Robert Finch
10 Sep 24     +* Re: Tonights Tradeoff17BGB
10 Sep 24     i+* Re: Tonights Tradeoff12Robert Finch
10 Sep 24     ii+* Re: Tonights Tradeoff10BGB
11 Sep 24     iii`* Re: Tonights Tradeoff9Robert Finch
11 Sep 24     iii +* Re: Tonights Tradeoff7Stephen Fuld
11 Sep 24     iii i+- Re: Tonights Tradeoff1MitchAlsup1
12 Sep 24     iii i`* Re: Tonights Tradeoff5Robert Finch
12 Sep 24     iii i `* Re: Tonights Tradeoff4MitchAlsup1
12 Sep 24     iii i  `* Re: Tonights Tradeoff3Robert Finch
12 Sep 24     iii i   `* Re: Tonights Tradeoff2MitchAlsup1
13 Sep 24     iii i    `- Re: Tonights Tradeoff1MitchAlsup1
12 Sep 24     iii `- Re: Tonights Tradeoff1BGB
11 Sep 24     ii`- Re: Tonights Tradeoff1MitchAlsup1
11 Sep 24     i`* Re: Tonights Tradeoff4MitchAlsup1
12 Sep 24     i `* Re: Tonights Tradeoff3Thomas Koenig
12 Sep 24     i  `* Re: Tonights Tradeoff2BGB
12 Sep 24     i   `- Re: Tonights Tradeoff1Robert Finch
11 Sep 24     `* Re: Tonights Tradeoff77MitchAlsup1
15 Sep 24      `* Re: Tonights Tradeoff76Robert Finch
16 Sep 24       `* Re: Tonights Tradeoff75Robert Finch
24 Sep 24        `* Re: Tonights Tradeoff - Background Execution Buffers74Robert Finch
24 Sep 24         `* Re: Tonights Tradeoff - Background Execution Buffers73MitchAlsup1
26 Sep 24          `* Re: Tonights Tradeoff - Background Execution Buffers72Robert Finch
26 Sep 24           `* Re: Tonights Tradeoff - Background Execution Buffers71MitchAlsup1
27 Sep 24            `* Re: Tonights Tradeoff - Background Execution Buffers70Robert Finch
4 Oct 24             `* Re: Tonights Tradeoff - Background Execution Buffers69Robert Finch
4 Oct 24              +* Re: Tonights Tradeoff - Background Execution Buffers66Anton Ertl
4 Oct 24              i`* Re: Tonights Tradeoff - Background Execution Buffers65Robert Finch
5 Oct 24              i `* Re: Tonights Tradeoff - Background Execution Buffers64Anton Ertl
9 Oct 24              i  `* Re: Tonights Tradeoff - Background Execution Buffers63Robert Finch
9 Oct 24              i   +* Re: Tonights Tradeoff - Background Execution Buffers3MitchAlsup1
9 Oct 24              i   i+- Re: Tonights Tradeoff - Background Execution Buffers1Robert Finch
12 Oct 24              i   i`- Re: Tonights Tradeoff - Background Execution Buffers1BGB
12 Oct 24              i   +* Re: Tonights Tradeoff - Carry and Overflow58Robert Finch
12 Oct 24              i   i`* Re: Tonights Tradeoff - Carry and Overflow57MitchAlsup1
12 Oct 24              i   i `* Re: Tonights Tradeoff - Carry and Overflow56BGB
12 Oct 24              i   i  `* Re: Tonights Tradeoff - Carry and Overflow55Robert Finch
13 Oct 24              i   i   +* Re: Tonights Tradeoff - Carry and Overflow3MitchAlsup1
13 Oct 24              i   i   i`* Re: Tonights Tradeoff - ATOM2Robert Finch
13 Oct 24              i   i   i `- Re: Tonights Tradeoff - ATOM1MitchAlsup1
13 Oct 24              i   i   +- Re: Tonights Tradeoff - Carry and Overflow1BGB
31 Oct 24              i   i   `* Page fetching cache controller50Robert Finch
31 Oct 24              i   i    +- Re: Page fetching cache controller1MitchAlsup1
6 Nov 24              i   i    `* Re: Q+ Fibonacci48Robert Finch
17 Apr 25              i   i     `* Re: register sets47Robert Finch
17 Apr 25              i   i      `* Re: register sets46Stephen Fuld
17 Apr 25              i   i       +- Re: register sets1Robert Finch
17 Apr 25              i   i       `* Re: register sets44MitchAlsup1
18 Apr 25              i   i        `* Re: register sets43Robert Finch
18 Apr 25              i   i         `* Re: register sets42MitchAlsup1
20 Apr 25              i   i          `* Re: register sets41Robert Finch
21 Apr 25              i   i           `* Re: auto predicating branches40Robert Finch
21 Apr 25              i   i            `* Re: auto predicating branches39Anton Ertl
21 Apr 25              i   i             +- Is an instruction on the critical path? (was: auto predicating branches)1Anton Ertl
21 Apr 25              i   i             `* Re: auto predicating branches37MitchAlsup1
22 Apr 25              i   i              `* Re: auto predicating branches36Anton Ertl
22 Apr 25              i   i               +- Re: auto predicating branches1MitchAlsup1
22 Apr 25              i   i               `* Re: auto predicating branches34Anton Ertl
22 Apr 25              i   i                `* Re: auto predicating branches33MitchAlsup1
23 Apr 25              i   i                 +* Re: auto predicating branches3Stefan Monnier
23 Apr 25              i   i                 i`* Re: auto predicating branches2Anton Ertl
25 Apr 25              i   i                 i `- Re: auto predicating branches1MitchAlsup1
23 Apr 25              i   i                 `* Re: auto predicating branches29Anton Ertl
23 Apr 25              i   i                  `* Re: auto predicating branches28MitchAlsup1
24 Apr 25              i   i                   `* Re: asynch register rename27Robert Finch
27 Apr 25              i   i                    `* Re: fractional PCs26Robert Finch
27 Apr 25              i   i                     `* Re: fractional PCs25MitchAlsup1
28 Apr 25              i   i                      `* Re: fractional PCs24Robert Finch
28 Apr 25              i   i                       +* Re: fractional PCs13MitchAlsup1
29 Apr 25              i   i                       i`* Re: fractional PCs12Robert Finch
5 May 25              i   i                       i `* Re: control co-processor11Robert Finch
5 May 25              i   i                       i  `* Re: control co-processor10Al Kossow
5 May 25              i   i                       i   `* Re: control co-processor9Stefan Monnier
6 May 25              i   i                       i    +* Re: control co-processor2MitchAlsup1
7 May 25              i   i                       i    i`- Re: control co-processor1MitchAlsup1
7 May 25              i   i                       i    `* Scan chains (was: control co-processor)6Stefan Monnier
7 May 25              i   i                       i     +* Re: Scan chains (was: control co-processor)2Al Kossow
7 May 25              i   i                       i     i`- Re: Scan chains1Stefan Monnier
7 May 25              i   i                       i     `* Re: Scan chains3MitchAlsup1
7 May 25              i   i                       i      `* Re: Scan chains2Stefan Monnier
8 May 25              i   i                       i       `- Re: Scan chains1MitchAlsup1
29 Apr 25              i   i                       `* Re: fractional PCs10Robert Finch
29 Apr 25              i   i                        `* Re: fractional PCs9MitchAlsup1
30 Apr 25              i   i                         `* Re: fractional PCs8Robert Finch
30 Apr 25              i   i                          +* Re: fractional PCs6Thomas Koenig
1 May 25              i   i                          i+- Re: fractional PCs1Robert Finch
2 May 25              i   i                          i`* Re: fractional PCs4moi
2 May 25              i   i                          i +* Re: millicode, extracode, fractional PCs2John Levine
2 May 25              i   i                          i i`- Re: millicode, extracode, fractional PCs1moi
2 May 25              i   i                          i `- Re: fractional PCs1moi
30 Apr 25              i   i                          `- Re: fractional PCs1MitchAlsup1
13 Oct 24              i   `- Re: Tonights Tradeoff - Background Execution Buffers1Anton Ertl
4 Oct 24              +- Re: Tonights Tradeoff - Background Execution Buffers1BGB
6 Oct 24              `- Re: Tonights Tradeoff - Background Execution Buffers1MitchAlsup1

Haut de la page

Les messages affichés proviennent d'usenet.

NewsPortal