jim-wilson[m] has joined #fedora-riscv
<
davidlt[m]>
Probably fast communication, data movement, might be related to CXL maybe (?)
<
davidlt[m]>
Also maybe being Linux accelerator like Intel Xeon Phi (Linux box that used to plug into PCIe slot like a GPU)
jcajka has joined #fedora-riscv
nirik has quit [Ping timeout: 260 seconds]
nirik has joined #fedora-riscv
esv has quit [Ping timeout: 248 seconds]
<
davidlt[m]>
BTW, I am toying with GCC 13 outside of Koji right now trying to see if I can find all the issues locally.
<
davidlt[m]>
32 CPU 80G RAM VM + bootstrap disabled.
<
davidlt[m]>
Note, U-Boot patch to support more than 32-cores was never merged for some reason.
<
davidlt[m]>
So on larger things (like 64-core system) that would be a limitation.
zsun has joined #fedora-riscv
esv has joined #fedora-riscv
zsun has quit [Quit: Leaving.]
jcajka has quit [Quit: Leaving]
davidlt has joined #fedora-riscv
davidlt has quit [Ping timeout: 252 seconds]
davidlt has joined #fedora-riscv
<
djdelorie>
davidlt[m]: libffi 3.4.4 is in F37 (official build in progress)
<
davidlt[m]>
djdelorie: nice!
<
davidlt[m]>
EPYC + QEMU and GCC testsuite is still timing out.
davidlt_ has joined #fedora-riscv
davidlt has quit [Ping timeout: 260 seconds]
<
davidlt[m]>
Sadly I forgot to disable the test so I have to wait :(
<
davidlt[m]>
I only wanted to solve packaging issues on QEMU, not to run test suite.
<
davidlt[m]>
I never attempted 32 core 80GB RAM QEMU for riscv64 before.
davidlt_ has quit [Ping timeout: 248 seconds]
ahs3 has quit [Remote host closed the connection]