Am 07.02.2014 15:21, schrieb James Harrison:
I remember the times when Redhat software releases (6.2, 7.3, 8, 9)
had a specific kernel for AMD and Intel CPUs.
times are changing
Now forward on to present day and Red Hat software has one kernel
build for AMD and Intel CPUs.
When was the decision to switch to an all in one encompassing kernel and is there a
performance hit.
What allows us to have one kernel build for two different CPUs?
The reason I ask these questions is that Ubuntu is still distinguishing between AMD and
Intel CPUs. Why,
and what is the difference between what they do and what Red Hat do to their Kernel
compiles.
Personally, I think that what Red Hat are doing makes maintaining kernels easier. There
is a layer of
abstraction that hides what the underlying technology is
for the relevant things the kernel has ASM code
on a modern SandyBridge as example it uses AVX if available
for most code there is no difference which can be easily tested by
mtune=corei7-avx and generic while often result in a identical binary
and if there is a difference you need to draw the line between
theory and real runtime differences compared to maintainance burden
if you have a IvyVdrige CPU which supports "rdrand" instructions
they are used and additionally thrown in the random pool. if not
the kernel does not care
_________________________________________
take a look at "lsmod", these are all intel-specific modules
if the CPU supports AES-NI for hw-accelerated crypto, a own
kernel optimized for Intel would not do anything different
in that context
crct10dif_pclmul 14289 0
crc32_pclmul 13113 0
crc32c_intel 22079 0
ghash_clmulni_intel 13259 0