andyc has quit [Quit: Connection closed for inactivity]
Andre_Z has joined #riscv
coldfeet has quit [Quit: Lost terminal]
<YangyuChen[m]>
<courmisch> "Yangyu Chen: did you test Zfh..." <- I confimed it has Zfh and Zvfh in both spacemit k1 and canaan k230. I have sent a k230 dt patch to add them.
coldfeet has joined #riscv
KREYREN has joined #riscv
<courmisch>
YangyuChen[m]: thanks. I had already xonfirmed k230, but my k1 is in cargon plane still
<courmisch>
cargo*
<courmisch>
post says delivery tomorrow but that sounds very optimistic to me
crabbedhaloablut has quit []
crabbedhaloablut has joined #riscv
wingsorc has quit [Ping timeout: 268 seconds]
Andre_Z has quit [Ping timeout: 255 seconds]
hightower4 has quit [Ping timeout: 268 seconds]
coldfeet has quit [Remote host closed the connection]
stolen has quit [Quit: Connection closed for inactivity]
billchenchina has joined #riscv
billchenchina has quit [Remote host closed the connection]
billchenchina has joined #riscv
billchenchina has quit [Read error: Connection reset by peer]
billchenchina has joined #riscv
<drewfustini>
YangyuChen[m]: thank you for the openssl pr link
hightower3 has joined #riscv
coldfeet has joined #riscv
hightower2 has quit [Ping timeout: 255 seconds]
BootLayer has quit [Quit: Leaving]
billchenchina- has joined #riscv
billchenchina has quit [Ping timeout: 268 seconds]
<palmer>
IIRC someone mentioning that some vector load/store instructions either trapped or were slow on the k230, is there anything documented about that?
<courmisch>
segmented loads and stores are a lot of slower than unit-segmented
<courmisch>
though AFAICT, it's not as dramatic as on LPi4a
billchenchina- has quit [Remote host closed the connection]
<palmer>
courmisch: thanks. Do you guys have a benchmark I can point at?
<courmisch>
seems I didn't keep any
<palmer>
OK, we'll try and dig up one of the chips...
<courmisch>
also strided loads and stores are slow, but that's to be expected
<bjdooks>
right, just registered for riscv-eu conf