| *** gnucode <gnucode!~gnucode@user/jab> has joined #libre-soc | 01:16 | |
| *** gnucode <gnucode!~gnucode@user/jab> has quit IRC | 02:45 | |
| *** lxo <lxo!~lxo@linux-libre.fsfla.org> has quit IRC | 05:33 | |
| *** lxo <lxo!~lxo@linux-libre.fsfla.org> has joined #libre-soc | 05:33 | |
| *** lxo <lxo!~lxo@linux-libre.fsfla.org> has quit IRC | 05:40 | |
| *** lxo <lxo!~lxo@linux-libre.fsfla.org> has joined #libre-soc | 05:40 | |
| lkcl | no problem. just remember always always always run budget-sync after changing/adding budgets/milestones/TOML fields, the report ends up looking like this once converted from mdwn to html https://libre-soc.org/task_db/report/ | 07:14 |
|---|---|---|
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@91.205.170.84> has quit IRC | 08:47 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@176.59.55.7> has joined #libre-soc | 08:47 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@176.59.55.7> has quit IRC | 08:50 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@91.205.170.84> has joined #libre-soc | 08:50 | |
| *** lxo <lxo!~lxo@linux-libre.fsfla.org> has quit IRC | 10:19 | |
| *** ghostmansd <ghostmansd!~ghostmans@91.205.170.84> has joined #libre-soc | 10:20 | |
| lkcl | ghostmansd, i pinged the mou team for adding you to 2021-02A-051. | 10:39 |
| ghostmansd | Thanks Luke! | 10:40 |
| ghostmansd | I've updated the milestones, now budget-sync seems to be happy. | 10:40 |
| ghostmansd | Is pi specifier stable enough to be picked and ported to insndb? | 10:43 |
| ghostmansd | Or it's WiP and this should be postponed? | 10:43 |
| lkcl | pi specifier? | 10:59 |
| lkcl | oh. pi specifier. 1 sec | 11:00 |
| lkcl | https://git.libre-soc.org/?p=openpower-isa.git;a=blob;f=src/openpower/decoder/isa/test_caller_svp64_ldst.py;h=647e7935d1aa9a77713c3a7af4838e16b5e4c028;hb=d7967c3c21fbf1d37f200b9284232aec15a7fadd#l52 | 11:01 |
| lkcl | it's part of the unit tests, so yes. | 11:01 |
| ghostmansd | OK, will add it soon | 11:01 |
| lkcl | ah.... https://libre-soc.org/openpower/sv/ldst/ | 11:02 |
| lkcl | i just realised that ffirst mode needs to go | 11:02 |
| lkcl | sorry it's been several weeks since i looked at this - i normally look at these pages 5-10 times a day | 11:03 |
| ghostmansd | lol, exactly after when we supported it in 4 places: binutils, disasm, asm and new asm :-) | 11:03 |
| lkcl | yyep, i know. | 11:03 |
| lkcl | it was a face-palm moment when i realised a couple months back that ffirst mode in LD/ST is not actually the original LD/ST "fault-first" of ARM SVE. | 11:04 |
| ghostmansd | OK, if you could update the docs, I could switch all these places to new mode | 11:04 |
| ghostmansd | Or maybe we can defer it | 11:05 |
| lkcl | i mean, it _could_ be left in - it's kinda "load this data, test it against the bit, and truncate VL based on that test" | 11:05 |
| lkcl | i mean, is that actually useful? | 11:05 |
| lkcl | data-dependent fail-first is supposed to be for applying to e.g. cmpi | 11:06 |
| ghostmansd | I don't see that many scenarios which could benefit, to be honest... | 11:06 |
| lkcl | "compare this data, if one of the CRfield bits is 1, truncate VL" | 11:06 |
| ghostmansd | but I'm by no means an expert in this area | 11:06 |
| lkcl | it's like combining a LD/ST with a cmpi-with-fail-first-mode into one instruction | 11:06 |
| lkcl | it's a bit much | 11:07 |
| ghostmansd | dropping ffirst would leave us two free modes, right? | 11:07 |
| ghostmansd | so these could be reused for something else | 11:07 |
| lkcl | the entire "01" block becomes free.. yes. | 11:07 |
| ghostmansd | well, practically one... | 11:07 |
| ghostmansd | because it depends on Rc IIRC | 11:07 |
| lkcl | it's CISC not RISC | 11:08 |
| ghostmansd | OK, I suggest I'll add /pi and concentrate on testing the new assembly; changing the modes will kinda now intervene the latter activity | 11:12 |
| ghostmansd | Once this is done, we can return to this topic and raise the relevant tasks: docs and code for Python and code for binutils | 11:12 |
| ghostmansd | Oh, nice, I see you already integrated this into disasm | 11:17 |
| ghostmansd | (I mean /pi specifier again, sorry) | 11:17 |
| ghostmansd | Hm. From what I see LF is specifier too. But there's no code for it in pysvp64asm. | 11:22 |
| ghostmansd | def specifiers(self, record): | 11:23 |
| ghostmansd | if self.pi: | 11:23 |
| ghostmansd | yield "pi" | 11:23 |
| ghostmansd | if self.lf: | 11:23 |
| ghostmansd | yield "lf" | 11:23 |
| *** ghostmansd <ghostmansd!~ghostmans@91.205.170.84> has quit IRC | 11:28 | |
| lkcl | correct, there isn't. it was part of the realisation a couple months ago that it's missing (conflated with ffirst) | 11:29 |
| lkcl | i'm currently mulling over: | 11:29 |
| lkcl | bit 0 - pi | 11:29 |
| lkcl | bit 1 - lf | 11:29 |
| lkcl | bit 2 - els | 11:30 |
| lkcl | bit 3 - sz | 11:30 |
| lkcl | bit 4 - dz | 11:30 |
| lkcl | or | 11:30 |
| lkcl | or | 11:31 |
| lkcl | yeah | 11:31 |
| *** lxo <lxo!~lxo@linux-libre.fsfla.org> has joined #libre-soc | 13:02 | |
| *** tplaten <tplaten!~isengaara@d5369b24.access.ecotel.net> has joined #libre-soc | 15:56 | |
| *** tplaten <tplaten!~isengaara@d5369b24.access.ecotel.net> has quit IRC | 18:31 | |
| *** tplaten <tplaten!~isengaara@d5369b24.access.ecotel.net> has joined #libre-soc | 18:45 | |
| *** tplaten <tplaten!~isengaara@d5369b24.access.ecotel.net> has quit IRC | 18:49 | |
| *** klys <klys!~mdasoh@show.op8.us> has joined #libre-soc | 20:16 | |
Generated by irclog2html.py 2.17.1 by Marius Gedminas - find it at https://mg.pov.lt/irclog2html/!