| *** lxo <lxo!~lxo@gateway/tor-sasl/lxo> has joined #libre-soc | 00:03 | |
| *** gnucode <gnucode!~gnucode@user/jab> has quit IRC | 01:13 | |
| *** gnucode <gnucode!~gnucode@user/jab> has joined #libre-soc | 01:14 | |
| *** gnucode <gnucode!~gnucode@user/jab> has quit IRC | 01:51 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 02:19 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 02:54 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 03:05 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 03:32 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 03:58 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 04:00 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 04:11 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 04:14 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 04:26 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 05:00 | |
| lkcl | programmerjake, i've replied *very bluntly* to your comments on #1017. | 06:54 |
|---|---|---|
| lkcl | https://bugs.libre-soc.org/show_bug.cgi?id=1017#c16 | 06:54 |
| lkcl | please refrain from making premature judgement calls | 06:54 |
| lkcl | you've now forced me into a position of having to back-track and undo damage that you're doing, under pressure, because you've jumped to a premature and mis-informed conclusion and stated that as fact | 06:55 |
| lkcl | you *have* to stop doing that | 06:56 |
| lkcl | prefixing things with "imho" does not help if your "opinion" is not properly technically informed | 06:56 |
| lkcl | i have said it many times and i am getting fed up of saying it: if i say NO you HAVE to ask yourself "why has he said NO" | 06:57 |
| programmerjake | well, sorry, but you're likely wrong about power usage. we would need to measure to be sure. | 06:57 |
| lkcl | i referred you to comment 5 and i expect you to LISTEN | 06:57 |
| lkcl | then YOU need to work out WHY i have said that | 06:57 |
| lkcl | not go "well you're just plain wrong therefore i can just blithely smash through everything and jump to a conclusion" | 06:58 |
| programmerjake | to be blunt I think you said no because you don't want to make any changes now because it might slow down submission and you need money so want to finish tasks faster. | 06:58 |
| lkcl | no, there are plenty of other RFCs and i do not wish to damage the chances of getting RED Semiconductor its funding | 06:58 |
| programmerjake | also, I got tested and don't actually have Aspergers. | 06:58 |
| lkcl | if i were to do anything that fucking stupid it would be picked up by VCs during their Due Diligence and we would not receive USD 25 to 40 million being sought | 06:59 |
| programmerjake | and I am actually more technically informed than you apparently percieve me to be | 07:00 |
| lkcl | can you please watch Tim Forsyth's Larrabee talk, paying particular attention when he mentions about when they had to add predicate mask instructions | 07:02 |
| programmerjake | I do think we need to get our priorities straight and realize binlog has few use cases so far so we need to work on crternlogi/ternlogi which are actually obviously useful in lots of places and not bother with arguing over how to implement crbinlog for now. | 07:05 |
| programmerjake | yes, I'll rewatch it probably tomorrow | 07:05 |
| lkcl | let me think about it (but yes, i'm tending to agree) | 07:07 |
| lkcl | re-work / mistakes-detected like in https://bugs.libre-soc.org/show_bug.cgi?id=1023 tends to suggest they're just not ready | 07:08 |
| lkcl | and would delay the ternlog ones | 07:08 |
| lkcl | but crternlogi still needs adjustment down to 3in-1out (an overwrite) | 07:09 |
| lkcl | drat | 07:09 |
| programmerjake | if we mush msk into the holes left by BF/BFA being 3-bits, we can mostly use TLI-form unmodified -- iirc you basically proposed that | 07:09 |
| lkcl | yes. | 07:09 |
| lkcl | but also had to move 3 bits of TLI to other locations because the top-end needs to be dedicated to XO | 07:10 |
| programmerjake | and then skooch the 8-bit immediate over to fill the other holes to extend XO | 07:10 |
| programmerjake | oh, we typed the same thing at the same time :) | 07:10 |
| lkcl | :) | 07:11 |
| lkcl | apologies i need to go afk. | 07:11 |
| programmerjake | well, I think we just resolved all our recent arguments :) | 07:11 |
| programmerjake | ttyl | 07:11 |
| lkcl | thank you for listening jacob, sorry i'm... meh | 07:11 |
| programmerjake | ty too | 07:12 |
| programmerjake | turns out I forgot OE=1 for fcvttg when constructing the reduced instruction list so I added fcvttgo -- 5 instructions is still plenty small | 08:02 |
| programmerjake | fcvttg's pseudo-code is crazy long... | 08:41 |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 09:24 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 09:25 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 09:55 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 11:50 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 12:32 | |
| sadoon[m] | Incoming | 13:07 |
| sadoon[m] | https://soulserv.xyz/Screenshot_20230315_160805.png | 13:10 |
| sadoon[m] | This is qtwebengine actually working almost flawlessly on debian 12 power9 | 13:10 |
| sadoon[m] | The only missing dependency for KDE apps :D | 13:11 |
| sadoon[m] | Only missing features again, as with gentoo: sandboxing, JIT, and with debian specifically ffmpeg might be broken for some formats because qtwebengine uses ancient chromium builds | 13:16 |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 13:20 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 13:30 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@176.59.41.171> has joined #libre-soc | 13:31 | |
| *** openpowerbot_ <openpowerbot_!~openpower@94-226-187-44.access.telenet.be> has quit IRC | 13:39 | |
| *** openpowerbot_ <openpowerbot_!~openpower@94-226-187-44.access.telenet.be> has joined #libre-soc | 13:40 | |
| *** openpowerbot_ <openpowerbot_!~openpower@94-226-187-44.access.telenet.be> has quit IRC | 13:50 | |
| *** openpowerbot_ <openpowerbot_!~openpower@94-226-187-44.access.telenet.be> has joined #libre-soc | 13:51 | |
| lkcl | sadoon[m], wha-hey! | 14:03 |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@176.59.41.171> has quit IRC | 14:03 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@185.79.103.160> has joined #libre-soc | 14:04 | |
| lkcl | programmerjake, it's perfectly fine to call it as a separate function that's proposed to be added to... err... Appendix A Book I, i think it is. joining the SINGLE_TO_DOUBLE() functions and other rounding | 14:04 |
| lkcl | i think the "excessive" length is probably why none of the other FP-conversion-etc functions are listed in the actual pseudocode | 14:05 |
| lkcl | certainly there is a desire to keep the listing of instructions within a given section "compact" (i cannot say more on that) | 14:05 |
| markos | sadoon[m], nice! | 14:07 |
| sadoon[m] | I'll create the relevant patches when I'm free and host it on my server | 14:14 |
| sadoon[m] | :D | 14:14 |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@185.79.103.160> has quit IRC | 14:33 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@185.79.103.141> has joined #libre-soc | 14:34 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@185.79.103.141> has quit IRC | 14:42 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@176.59.41.167> has joined #libre-soc | 14:43 | |
| lkcl | toshywoshy, i'm putting together the "ongoing" grant, which is where implementation (and unit tests) occur, prior to OPF ISA WG submission. | 16:49 |
| lkcl | would you be interested in implementing the pseudocode for the CRweird set? https://libre-soc.org/openpower/sv/cr_int_predication/ | 16:49 |
| lkcl | it involves writing one of the markdown files https://git.libre-soc.org/?p=openpower-isa.git;a=tree;f=openpower/isa;hb=HEAD | 16:51 |
| lkcl | adding to the decoder csv files and the machine-readable version of Power ISA Section 1.6, and generally understanding what the hell is going on :) | 16:51 |
| markos | lkcl, on a related note, I'd be interested in the int butterfly instructions one, as I have exactly the code I would test it on | 16:54 |
| lkcl | it's been done enough times that there's sort-of a guide - by following relevant diffs for many *many* instructions already previously added | 16:55 |
| lkcl | https://libre-soc.org/docs/?updated | 16:55 |
| lkcl | markos, sure! | 16:55 |
| markos | I'd probably need your help in that though so we could do it together if you'd have time | 16:55 |
| lkcl | yes of course | 16:55 |
| markos | great | 16:55 |
| lkcl | although it really should be blindingly obvious from so many patches, ah you already did fmvis, remember? | 16:56 |
| lkcl | https://bugs.libre-soc.org/show_bug.cgi?id=887 | 16:56 |
| lkcl | and i insisted you put the diff-patch commit-links for exactly this reason: to be able to refer to it again and see what was done | 16:56 |
| lkcl | but yes (toshywoshy as well) i'm happy to walk you through the process | 16:57 |
| lkcl | someone really needs to finish the documentation as well https://libre-soc.org/docs/adding_instr/ | 16:57 |
| lkcl | which yes, all "paid" | 16:57 |
| lkcl | let me just put that on the list | 16:57 |
| markos | no, I mean what needs to be done in that regard, I remember I did fmvis, unless the process changed I don't expect many difficulties with the process itself :) | 16:59 |
| markos | is there a ticket for int butterfly instructions? | 16:59 |
| lkcl | no - any change would be so absolutely massive and disruptive it's highly unlikely to even take place - ever | 17:01 |
| lkcl | don't know yet - looking for it | 17:01 |
| lkcl | yes - 962 | 17:01 |
| lkcl | hm that's the *design* - not the implementation | 17:01 |
| markos | ok | 17:02 |
| lkcl | https://bugs.libre-soc.org/show_bug.cgi?id=1028 | 17:05 |
| *** adi_ <adi_!uid592526@id-592526.ilkley.irccloud.com> has quit IRC | 17:17 | |
| markos | great | 17:24 |
| sadoon[m] | markos you might be interested since you are running deb12 https://git.soulserv.xyz/sadoon/qtwebengine-5.15.12-lts | 17:26 |
| markos | I was a while ago, now my talos is running headless | 17:27 |
| toshywoshy | lkcl: yes, I can work on that | 17:33 |
| toshywoshy | given that markos already has that, it might be good as a first one, for me to do it with markos and have you assist us | 17:34 |
| markos | the int butterfly you mean? I agree it would be a great way for both of us to get acquainted with the internals | 17:35 |
| toshywoshy | yes, or any one instruction, this way we get to know more while it does not drain luke as much | 17:43 |
| toshywoshy | I also agree with your previous idea, that we should have internal get acquinten moments, in additional to the actual documentation | 17:43 |
| markos | oh you also meant the crweird as well? I have no objections, though I have no idea what this instruction does | 17:46 |
| markos | reg. the knowledge sharing I suggest we pick a convenient day/time and set up recurring events in the calendar | 17:46 |
| toshywoshy | well, we can see, I would like to start with one, where you and luke are working on, just to make it easier to start | 17:46 |
| toshywoshy | yes, that was the word I was looking for, correct | 17:47 |
| markos | I could start with showing and explaining the simpler algorithms first (eg libvpx variance) and moving on to more complicated (chacha20) | 17:53 |
| toshywoshy | yes, lets do that first | 18:05 |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@176.59.41.167> has quit IRC | 19:20 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 19:21 | |
| lkcl | CR ops are not powerful enough. they are one-bit-at-a-time. | 19:31 |
| lkcl | CRweird ops do up to *four* bits at once. [in the scalar versions] | 19:32 |
| lkcl | like, "copy this CR *field* to this other CR *field*" | 19:32 |
| lkcl | and | 19:32 |
| lkcl | "take a selection as specified by an immediate mask of any four of the CR *field* bits, then AND (or OR) them all together, and put the result into *this* bit of the CR" | 19:33 |
| lkcl | which when combined with SVP64 Predication is stunningly powerful | 19:33 |
| lkcl | toshywoshy, btw what's up with the domain named "openpower.foundation"? | 19:33 |
| lkcl | it appears to have gone walkies | 19:34 |
| lkcl | crops - crand cror crxor - are just not adequate. doing one bit at a time transfer between GPR and CR fields?? meh | 19:36 |
| markos | toshywoshy, do you remember what's the type of RAM the tyan board takes? | 20:07 |
| *** lxo <lxo!~lxo@gateway/tor-sasl/lxo> has quit IRC | 20:08 | |
| *** lxo <lxo!~lxo@gateway/tor-sasl/lxo> has joined #libre-soc | 20:08 | |
| toshywoshy | markos: RDIMM-DDR3L 1333 | 21:03 |
| toshywoshy | it has 32 dimm slots, of which a minimum of 8 must be populated to start the machine | 21:04 |
| markos | max capacity? | 21:05 |
| markos | I mean per dimm | 21:05 |
| toshywoshy | or 512GB per cpu, so if you have a dual socket 1TB | 21:06 |
| markos | it has 32 slots | 21:06 |
| markos | ECC I guess | 21:07 |
| toshywoshy | yes yes, standard ecc registered memory | 21:08 |
| markos | I find different types 10600R/10600U/10600E | 21:09 |
| toshywoshy | well, if you get devel boards, they might only have 16 slots and if you get the 'early developer board' those only had 8 slots with 1 cpu | 21:09 |
| toshywoshy | 10600R, the R stands for registered | 21:10 |
| toshywoshy | while the U standard for unbuffered and the E, I think, stands for enhanced, it has an extra buffer | 21:10 |
| markos | would these work: https://www.ebay.com/itm/371912732953 ? | 21:11 |
| markos | maybe I would buy 2 sets for 128GB | 21:11 |
| markos | price is cheap | 21:11 |
Generated by irclog2html.py 2.17.1 by Marius Gedminas - find it at https://mg.pov.lt/irclog2html/!
