mlw has quit [Read error: Connection reset by peer]
mlw has joined #riscv
naoki has joined #riscv
naoki has quit [Client Quit]
naoki has joined #riscv
ldevulder has joined #riscv
fuwei has quit [Remote host closed the connection]
fuwei has joined #riscv
Stat_headcrabbed has joined #riscv
alperak has joined #riscv
X-Scale24 has quit [Ping timeout: 256 seconds]
naoki has quit [Quit: naoki]
prabhakalad has quit [Quit: Konversation terminated!]
prabhakalad has joined #riscv
danilogondolfo has joined #riscv
naoki has joined #riscv
jjido has joined #riscv
jacklsw has joined #riscv
coldfeet has joined #riscv
damian101 has quit [Ping timeout: 252 seconds]
zukunf has joined #riscv
<zukunf>
greets
<zukunf>
I am reading over armv9 specs
<zukunf>
I was wondering whether riscv got something similar to avx512
<zukunf>
'With Armv9’s SVE2 upgrade, chip designers can choose a vector length in multiples of 128, up to 2048 bits.'
<zukunf>
wow
hwspeedy has joined #riscv
jacklsw has quit [Ping timeout: 265 seconds]
<gurki>
did any vendor actually implement > 512 bit?
jacklsw has joined #riscv
levitating__ has joined #riscv
X-Scale has joined #riscv
X-Scale has quit [Ping timeout: 256 seconds]
jacklsw has quit [Quit: Back to the real world]
levitating__ has quit [Ping timeout: 252 seconds]
jobol has joined #riscv
naoki has quit [Quit: naoki]
naoki has joined #riscv
BootLayer has quit [Quit: Leaving]
naoki has quit [Quit: naoki]
bsFFFFFF has joined #riscv
coldfeet has quit [Remote host closed the connection]
damian101 has joined #riscv
zBeeble24 has joined #riscv
zBeeble42 has quit [Remote host closed the connection]
jjido has quit [Quit: My laptop has gone to sleep. ZZZzzz…]
BootLayer has joined #riscv
jjido has joined #riscv
Armand|X13s has joined #riscv
levitating__ has joined #riscv
Tenkawa has joined #riscv
impomatic has joined #riscv
jacklsw has joined #riscv
armand_ has joined #riscv
Armand|X13s has quit [Killed (NickServ (GHOST command used by armand_))]
armand_ is now known as Armand|X13s
hwspeedy has quit [Read error: Connection reset by peer]
levitating__ has quit [Ping timeout: 248 seconds]
Armand|X13s has quit [Ping timeout: 244 seconds]
levitating__ has joined #riscv
___nick___ has joined #riscv
___nick___ has quit [Client Quit]
___nick___ has joined #riscv
ldevulder has quit [Quit: Leaving]
impomatic has quit [Ping timeout: 256 seconds]
<palmer>
smaeul_: Alex is saying you think the -ffixed register stuff is broken in LLVM?
<Tenkawa>
palmer: I saw that mainline: 6.12-rc1 2024-09-29 came out... You heard any rumblings on better Mars support at all? (I know its way too early to ask about the Spacemit-K1 heh)
TMM has quit [Remote host closed the connection]
<palmer>
I think the StarFive stuff is basically just stuck on getting a description of those PCIe quirks so we can figure out what to do with them, right now it's just "we put some slowdowns in and it stops crashing" which isn't going to fly upstream
<palmer>
Spacemit also didn't make it, but there's active work going on so hopefully it'll get sorted out eventually
TMM has joined #riscv
<Tenkawa>
palmer: I would be happy to test/dug the K1 stuff on a BPI-F3 if needed..
<Tenkawa>
er debug
<palmer>
I think right now it's blocked on a missing driver (pinmux or clock controller or something)
<Tenkawa>
yeah... pinmux is a mess right now
<Tenkawa>
even on vendor
<Tenkawa>
and remoteproc causes a mass spin
<Tenkawa>
but without it the unit isn't stable.. so ots either high load or crashing... pick your problem....
<la_mettrie>
why did starfive write those drivers (and even device tree) twice instead of just adjusting them for mainline or something?
levitating__ has quit [Ping timeout: 260 seconds]
<palmer>
SOC vendors do crazy stuff, this isn't even that bad ;)
<Tenkawa>
haahaa touche indeed
<Tenkawa>
I have seen things that make me just go "huh"???
levitating__ has joined #riscv
smaeul_ is now known as smaeul
<smaeul>
palmer: yeah, due to fastcall calling convention you can't do -ffixed-x28 through -ffixed-x31 which would be most efficient
zBeeble24 is now known as zBeeble
levitating__ has quit [Ping timeout: 244 seconds]
coldfeet has joined #riscv
levitating__ has joined #riscv
levitating_ has joined #riscv
<la_mettrie>
vendor kernel's PCIE driver works at least to some extent. at which point problems begin (from user's perspective)?
levitating__ has quit [Ping timeout: 265 seconds]
<palmer>
la_mettrie: for the StarFive one I think it's just a worry that the arbitrary slowdowns aren't sufficient to make the thing robust, and if they are we need some reason for why
levitating_ has quit [Remote host closed the connection]
levitating_ has joined #riscv
impomatic has joined #riscv
jacklsw has quit [Quit: Back to the real world]
levitating_ has quit [Ping timeout: 252 seconds]
heat_ has joined #riscv
zukunf has quit [Remote host closed the connection]
Finde_ is now known as Finde
Finde has quit [Quit: WeeChat 3.8]
Finde has joined #riscv
___nick___ has quit [Ping timeout: 276 seconds]
fayr has quit [Ping timeout: 252 seconds]
fayr has joined #riscv
coldfeet has quit [Remote host closed the connection]
Stat_headcrabbed has quit [Quit: Stat_headcrabbed]