Why LFENCE, rather than CPUID? I guess LFENCE does not prevent
out-of-order execution for non-load instructions across it.
This link has detailed information on RDTSC, RDTSCP, and CPUID:
http://www.intel.com/content/dam/www/public/us/en/documents/white-papers/ia-32-ia-64-benchmark-code-execution-p
Yes, i will add a new function that includes the lfence;
for the performance penalty, we did not see noticable performance impact
on our full software, so we did not see any reason to use 2 functions,
but it's certainly because we make a very limited number of calls to
rdtsc and it's true that
24/01/2014 12:42, Fran?ois-Fr?d?ric Ozog:
> IMHO, adding the lfence for all cases is introducing an un-necessary
> performance penalty.
>
> What about adding rte_rdtsc_sync() or rte_rdtsc_serial() with the comment
> about the rdtsc instruction behavior so that developers can choose which
> form th
[mailto:dev-boun...@dpdk.org] On Behalf Of Fran?ois-Fr?d?ric Ozog
Sent: Friday, January 24, 2014 11:43 AM
To: 'Didier Pallard'; dev at dpdk.org
Subject: Re: [dpdk-dev] [PATCH] timer: add lfence before TSC read
Hi,
Most of the time rdtsc is used for timestamping and a few cycles incorrect ar
> Objet?: [dpdk-dev] [PATCH] timer: add lfence before TSC read
>
> According to Intel Developer's Manual:
>
> "The RDTSC instruction is not a serializing instruction. It does not
> necessarily wait until all previous instructions have been executed
before
> reading th
According to Intel Developer's Manual:
"The RDTSC instruction is not a serializing instruction. It does not
necessarily wait
until all previous instructions have been executed before reading the counter.
Simi-
larly, subsequent instructions may begin execution before the read operation is
per
6 matches
Mail list logo
