crabbedhaloablut has quit [Remote host closed the connection]
marcj has quit [Ping timeout: 256 seconds]
crabbedhaloablut has joined #riscv
marcj has joined #riscv
aerkiaga has quit [Remote host closed the connection]
jacklsw has joined #riscv
ntwk has quit [Ping timeout: 256 seconds]
ntwk has joined #riscv
kailo has joined #riscv
jimwilson has joined #riscv
winterflaw has joined #riscv
davidlt has joined #riscv
PyroPeter has quit [Ping timeout: 240 seconds]
PyroPeter has joined #riscv
adjtm has quit [Read error: Connection reset by peer]
adjtm has joined #riscv
frost has joined #riscv
davidlt has quit [Ping timeout: 268 seconds]
jimwilson has quit [*.net *.split]
TMM_ has quit [*.net *.split]
riff-IRC has quit [*.net *.split]
pabs3 has quit [*.net *.split]
gdd has quit [*.net *.split]
elastic_dog has quit [*.net *.split]
avoidr has quit [*.net *.split]
FL4SHK has quit [*.net *.split]
nun has quit [*.net *.split]
drewfustini has quit [*.net *.split]
drmpeg has quit [*.net *.split]
JSharp has quit [*.net *.split]
khilman has quit [*.net *.split]
moto-timo has quit [*.net *.split]
frost has quit [*.net *.split]
adjtm has quit [*.net *.split]
ntwk has quit [*.net *.split]
jonasbits has quit [*.net *.split]
djdelorie has quit [*.net *.split]
shicz2 has quit [*.net *.split]
fabs has quit [*.net *.split]
balrog has quit [*.net *.split]
edf0_ has quit [*.net *.split]
ln5 has quit [*.net *.split]
derelict has quit [*.net *.split]
dionysos has quit [*.net *.split]
s1b1 has quit [*.net *.split]
sauce has quit [*.net *.split]
sm2n has quit [*.net *.split]
rah has quit [*.net *.split]
guerby has quit [*.net *.split]
connojd has quit [*.net *.split]
Esmil has quit [*.net *.split]
DynamiteDan has quit [*.net *.split]
somlo has quit [*.net *.split]
tgamblin has quit [*.net *.split]
olofj has quit [*.net *.split]
elms has quit [*.net *.split]
abelvesa has quit [*.net *.split]
kido_ has quit [*.net *.split]
zv has quit [*.net *.split]
Forty-Bot has quit [*.net *.split]
ornxka has quit [*.net *.split]
leah2 has quit [*.net *.split]
smaeul has quit [*.net *.split]
mort has quit [*.net *.split]
koolazer has quit [*.net *.split]
geist2 has quit [*.net *.split]
pavelow_ has quit [*.net *.split]
raghavgururajan has quit [*.net *.split]
laanwj has quit [*.net *.split]
jemarch has quit [*.net *.split]
hl has quit [*.net *.split]
il has quit [*.net *.split]
danielinux has quit [*.net *.split]
adjtm has joined #riscv
frost has joined #riscv
jimwilson has joined #riscv
drewfustini has joined #riscv
ntwk has joined #riscv
sauce has joined #riscv
shicz2 has joined #riscv
rah has joined #riscv
balrog has joined #riscv
sm2n has joined #riscv
fabs has joined #riscv
DynamiteDan has joined #riscv
guerby has joined #riscv
Esmil has joined #riscv
ln5 has joined #riscv
edf0_ has joined #riscv
connojd has joined #riscv
pavelow_ has joined #riscv
Forty-Bot has joined #riscv
danielinux has joined #riscv
khilman has joined #riscv
jonasbits has joined #riscv
djdelorie has joined #riscv
TMM_ has joined #riscv
riff-IRC has joined #riscv
elastic_dog has joined #riscv
pabs3 has joined #riscv
avoidr has joined #riscv
gdd has joined #riscv
nun has joined #riscv
drmpeg has joined #riscv
FL4SHK has joined #riscv
dionysos has joined #riscv
jemarch has joined #riscv
mort has joined #riscv
derelict has joined #riscv
leah2 has joined #riscv
koolazer has joined #riscv
smaeul has joined #riscv
geist2 has joined #riscv
laanwj has joined #riscv
raghavgururajan has joined #riscv
hl has joined #riscv
il has joined #riscv
tgamblin has joined #riscv
s1b1 has joined #riscv
kido_ has joined #riscv
zv has joined #riscv
moto-timo has joined #riscv
JSharp has joined #riscv
abelvesa has joined #riscv
ornxka has joined #riscv
olofj has joined #riscv
somlo has joined #riscv
elms has joined #riscv
wolfshappen has quit [Max SendQ exceeded]
koolazer has quit [Max SendQ exceeded]
koolazer has joined #riscv
nmeum has quit [Remote host closed the connection]
nmeum has joined #riscv
wolfshappen has joined #riscv
ChengjunXie has quit [*.net *.split]
stefanct has quit [*.net *.split]
cp- has quit [*.net *.split]
meowray has quit [*.net *.split]
tux3 has quit [*.net *.split]
klys_ has quit [*.net *.split]
Haise0 has quit [*.net *.split]
meowray has joined #riscv
ChengjunXie has joined #riscv
klys has joined #riscv
stefanct has joined #riscv
cp- has joined #riscv
tux3 has joined #riscv
haise01 has joined #riscv
tux3 has quit [Changing host]
tux3 has joined #riscv
_whitelogger has joined #riscv
adomas has joined #riscv
seds has joined #riscv
Gravis has joined #riscv
jrjsmrtn has joined #riscv
mrus has joined #riscv
ZipCPU has joined #riscv
Xark has joined #riscv
CarlosEDP has joined #riscv
riff-IRC has quit [Remote host closed the connection]
riff-IRC has joined #riscv
BOKALDO has joined #riscv
davidlt has joined #riscv
jjido has joined #riscv
pecastro has joined #riscv
riff-IRC has quit [Read error: Connection reset by peer]
riff-IRC has joined #riscv
<enthusi>
how absurd would it be to have extensions that emulate legacy CPUs? i.e. directly execute 8bit 6502 binary?
<geertu>
Or x86, oh the horror
bauruine has joined #riscv
<geist>
enthusi: well, i guess if there's an architecture to do it on, riscv would be the easiest to extend
jacklsw has quit [Ping timeout: 245 seconds]
aburgess has joined #riscv
EchelonX has quit [Quit: Leaving]
Ivii has joined #riscv
davidlt has quit [Ping timeout: 240 seconds]
<adjtm>
enthusi, as any modern CPU emulating legacy CPUs would be faster than the original ones, I don't see much of a point of extensions for native execution of the instructions
<adjtm>
maybe some extensions that accelerates emulation in general?
<adjtm>
fast emulation of x86 and arm would be the most used cases in my opinion
jjido has quit [Quit: My MacBook Air has gone to sleep. ZZZzzz…]
kailo has quit [Ping timeout: 252 seconds]
Sofia has quit [Ping timeout: 276 seconds]
Sofia has joined #riscv
<mort>
I thought I heard something somewhere about apple already having some custom stuff in their chips to help with emulating tricky x86 things
<mort>
quickly executing an x86 instruction stream requires so much work just in the front-end, not to mention the legal issues with getting a license from both Intel and AMD to essentially manufacture your own x86-compatible CPUs, that I think running an x86 instruction stream in hardware as a risc-v extension would be basically impossible
<mort>
or, well, impractical
<The_Decryptor>
I think their chips have TSO support for x86 emulation
<sorear>
there are at least two bits, one of them gives you TSO, the other enables Intel-compatible floating point arithmetic
<mort>
I wonder how the licensing situation is with x86 emulation, does Apple have an x86 license? Or is anyone allowed to implement x86 in software, just not in hardware? How would that even be possible, legally speaking?
Sofia has quit [Remote host closed the connection]
<sorear>
well intel won't stop you from downloading qemui
Sofia has joined #riscv
<sorear>
AFAIK the issue of whether software emulators can infringe CPU patents has never been tested
<mort>
fun
<mort>
I feel like, unless the license is specifically for patents which are only relevant when implementing it in hardware, there should be no difference, legally speaking, between a hardware implementation or a software implementation
<sorear>
IBM successfully got a commercial s390 emulator to shut down years ago (google Super-Hercules); there was a bit of saber rattling between Intel and Microsoft/Qualcomm more recently but I don't think anything came of it
<sorear>
Intel got NVidia to drop their plans for firmware x86 compatibility in what became Denver by threatening to revoke _unrelated_ patents that NVidia was using on the hardware manufacturing side
<mort>
patent warfare is so destructive
<sorear>
enthusi: loongson did a MIPS extension to make translated x86 code more efficient, without trying to do an x86 decoder, https://sci-hub.se/10.1109/MM.2009.30 "GODSON-3: A SCALABLE MULTICORE RISC PROCESSOR WITH X86 EMULATION" has some details
<sorear>
sorry, TurboHercules, not Super
<sorear>
tbh I think the focus on binary translation that Apple and Loongson have is less a matter of "an x86 decoder would be unfeasibly difficult to implement" and more a matter of "we want to be able to fix bugs in our x86 decoder"
aerkiaga has joined #riscv
<sorear>
(Crusoe/Denver was a different situation, those were *in order* chips which used binary translation to perform much of the prediction and speculation that other high perf designs do in hardware)
kehvo has joined #riscv
Ivii has quit [Remote host closed the connection]
Ivii has joined #riscv
<geertu>
sorear: Indeed, Super-Hercules is not the system you're looking for ;-)
Ivii has quit [Remote host closed the connection]
Ivii has joined #riscv
crabbedhaloablut has quit [Remote host closed the connection]
freakazoid12345 has quit [Read error: Connection reset by peer]
freakazoid12345 has joined #riscv
crabbedhaloablut has joined #riscv
cousteau_ has joined #riscv
jjido has joined #riscv
BOKALDO has quit [Quit: Leaving]
Ivii has quit [Remote host closed the connection]
Ivii has joined #riscv
kehvo has joined #riscv
kehvo has quit [Changing host]
jacklsw has joined #riscv
frost has quit [Ping timeout: 256 seconds]
cousteau_ has quit [Read error: Connection reset by peer]
cousteau_ has joined #riscv
<pierce>
SuperHercules sounds like a good name for a sh4 emulator
<geertu>
pierce: hehe
elastic_dog has quit [Ping timeout: 252 seconds]
elastic_dog has joined #riscv
BOKALDO has joined #riscv
cousteau_ has quit [Quit: ♫ I can't forget the day I shot that network down ♫]
bauruine has quit [Remote host closed the connection]
jacklsw has quit [Read error: Connection reset by peer]
mahmutov has joined #riscv
indy has quit [Read error: Connection reset by peer]
indy has joined #riscv
shicz2 has quit [Ping timeout: 256 seconds]
shicz2 has joined #riscv
shicz2 has quit [Ping timeout: 265 seconds]
shicz2 has joined #riscv
voltron has joined #riscv
voltron has quit [Remote host closed the connection]
jjido has quit [Quit: My MacBook Air has gone to sleep. ZZZzzz…]
___nick___ has joined #riscv
___nick___ has quit [Client Quit]
___nick___ has joined #riscv
___nick___ has quit [Client Quit]
___nick___ has joined #riscv
shicz2 has quit [Ping timeout: 240 seconds]
shicz2 has joined #riscv
jellydonut has quit [Quit: jellydonut]
vagrantc has joined #riscv
winterflaw has quit [Remote host closed the connection]
jellydonut has joined #riscv
shicz2 has quit [Ping timeout: 240 seconds]
shicz2 has joined #riscv
jellydonut has quit [Quit: jellydonut]
jellydonut has joined #riscv
shicz2 has quit [Ping timeout: 252 seconds]
shicz2 has joined #riscv
BOKALDO has quit [Read error: Connection reset by peer]
Andre_H has joined #riscv
___nick___ has quit [Ping timeout: 252 seconds]
shicz2 has quit [Ping timeout: 265 seconds]
shicz2 has joined #riscv
winterflaw has joined #riscv
winterflaw has quit [Ping timeout: 276 seconds]
shicz2 has quit [Ping timeout: 240 seconds]
shicz2 has joined #riscv
sirn- has joined #riscv
sirn has quit [Ping timeout: 265 seconds]
sirn- is now known as sirn
Andre_H has quit [Quit: Leaving.]
NishanthMenon has quit [Ping timeout: 245 seconds]
NishanthMenon has joined #riscv
<enthusi>
sorear: and others: thanks ;)
<Esmil>
I just tried building Linux with LTO_CLANG. Since ARCH_SUPPORTS_LTO_CLANG is not enabled for risc-v I guess this is to be expected: http://sprunge.us/sDdlGY
kailo has joined #riscv
KombuchaKip has quit [Quit: Leaving.]
KombuchaKip has joined #riscv
jjido has joined #riscv
<jrtc27>
Esmil: LLVM LTO on RISC-V is a long-standing problem
<jrtc27>
nobody seems to care enough to fix it
<jrtc27>
there are various stalled patches filed by someone who didn't really understand the way things were meant to work
<Esmil>
i see, thanks
mahmutov has quit [Ping timeout: 265 seconds]
kailo has quit [Ping timeout: 256 seconds]
aerkiaga has quit [Remote host closed the connection]
shicz2 has quit [Ping timeout: 256 seconds]
shicz2 has joined #riscv
cwebber has joined #riscv
EchelonX has joined #riscv
jjido has quit [Quit: My MacBook Air has gone to sleep. ZZZzzz…]
shicz2 has quit [Ping timeout: 240 seconds]
shicz2 has joined #riscv
<muurkha>
adjtm: depends on the obsolete CPU; surely, for fuzzing, a fast 6502 emulator would be useful if you care about 6502 security
<sorear>
it might help to ask exactly what y'all are hoping to achive
<muurkha>
I was just playing with the idea. a 6502 or Z80 is about the smallest address space where it makes sense to do things like CAD and HLL compilers