Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
kstrauser
65 days ago
|
parent
|
context
|
favorite
| on:
Jemalloc Postmortem
Why is that? Couldn’t there be push_simd()/pop_simd() that the syscall itself uses around its SIMD calls?
If no syscalls use SIMD today, I’d think we’re starting from a safe position.
durrrrrrrrrrrrr
65 days ago
[–]
push_simd/pop_simd exist and are called kernel_fpu_begin/kernel_fpu_end. Their use is practically prohibited in most areas and iiuc not available on all archs, but it's available if needed.
kstrauser
65 days ago
|
parent
[–]
Today I learned. Thanks!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
If no syscalls use SIMD today, I’d think we’re starting from a safe position.