>
> Hi
> You mean just use rte_memcpy_internal in rte_memcpy_avx2, rte_memcpy_avx512?
Yes, exactly and for rte_memcpy_sse() too.
Basically we for rte_memcpy_avx512() we force compiler to use AVX512F path
inside rte_memcpy_iternal(),
for rte_memcpy_avx2() we use AVX2 path inside rte_memcpy_internal(), etc.
To do that we setup:
CFLAGS_rte_memcpy_avx512f.o += -mavx512f
CFLAGS_rte_memcpy_avx512f.o += -DRTE_MACHINE_CPUFLAG_AVX512F
inside the Makefile.
For rte_memcpy_avx2() we force compiler to use AVX2 path inside
rte_memcpy_internal(), etc.
> But if RTE_MACHINE_CPUFLAGS_AVX2 means only whether the compiler supports
> avx2, then internal would only compiled
> With avx2 codes, then cannot choose other code path. What if the HW cannot
> support avx2?
If the HW can't support AVX2 then rte_memcpy_init() just wouldn't select
rte_memcpy_avx2(),
it would select rte_memcpy_sse() instead:
if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2)) {...} -
that is a runtime check that underlying HW does support AVX2.
Konstantin
> If RTE_MACHINE_CPUFLAGS_AVX2 means as before, suggests whether both compiler
> and HW supports avx2. Then the function
> has no difference right now.
> The mocro is determined at compilation time. But selection is hoped to be at
> runtime.
> Did I consider something wrong?
>
> Best Regards,
> Xiaoyun Li
>
>
>
>
> > -----Original Message-----
> > From: Ananyev, Konstantin
> > Sent: Tuesday, October 3, 2017 19:16
> > To: Li, Xiaoyun <xiaoyun...@intel.com>; Richardson, Bruce
> > <bruce.richard...@intel.com>
> > Cc: Lu, Wenzhuo <wenzhuo...@intel.com>; Zhang, Helin
> > <helin.zh...@intel.com>; dev@dpdk.org
> > Subject: RE: [PATCH v4 1/3] eal/x86: run-time dispatch over memcpy
> >
> > Hi,
> >
> > >
> > > Hi
> > >
> > > > -----Original Message-----
> > > > From: Ananyev, Konstantin
> > > > Sent: Tuesday, October 3, 2017 00:39
> > > > To: Li, Xiaoyun <xiaoyun...@intel.com>; Richardson, Bruce
> > > > <bruce.richard...@intel.com>
> > > > Cc: Lu, Wenzhuo <wenzhuo...@intel.com>; Zhang, Helin
> > > > <helin.zh...@intel.com>; dev@dpdk.org
> > > > Subject: RE: [PATCH v4 1/3] eal/x86: run-time dispatch over memcpy
> > > >
> > > >
> > > >
> > > > > -----Original Message-----
> > > > > From: Li, Xiaoyun
> > > > > Sent: Monday, October 2, 2017 5:13 PM
> > > > > To: Ananyev, Konstantin <konstantin.anan...@intel.com>;
> > > > > Richardson,
> > > > Bruce <bruce.richard...@intel.com>
> > > > > Cc: Lu, Wenzhuo <wenzhuo...@intel.com>; Zhang, Helin
> > > > <helin.zh...@intel.com>; dev@dpdk.org; Li, Xiaoyun
> > > > <xiaoyun...@intel.com>
> > > > > Subject: [PATCH v4 1/3] eal/x86: run-time dispatch over memcpy
> > > > >
> > > > > This patch dynamically selects functions of memcpy at run-time
> > > > > based on CPU flags that current machine supports. This patch uses
> > > > > function pointers which are bind to the relative functions at
> > > > > constrctor
> > time.
> > > > > In addition, AVX512 instructions set would be compiled only if
> > > > > users config it enabled and the compiler supports it.
> > > > >
> > > > > Signed-off-by: Xiaoyun Li <xiaoyun...@intel.com>
> > > > > ---
> > > > > v2
> > > > > * Use gcc function multi-versioning to avoid compilation issues.
> > > > > * Add macros for AVX512 and AVX2. Only if users enable AVX512 and
> > > > > the compiler supports it, the AVX512 codes would be compiled. Only
> > > > > if the compiler supports AVX2, the AVX2 codes would be compiled.
> > > > >
> > > > > v3
> > > > > * Reduce function calls via only keep rte_memcpy_xxx.
> > > > > * Add conditions that when copy size is small, use inline code path.
> > > > > Otherwise, use dynamic code path.
> > > > > * To support attribute target, clang version must be greater than 3.7.
> > > > > Otherwise, would choose SSE/AVX code path, the same as before.
> > > > > * Move two mocro functions to the top of the code since they would
> > > > > be used in inline SSE/AVX and dynamic SSE/AVX codes.
> > > > >
> > > > > v4
> > > > > * Modify rte_memcpy.h to several .c files and modify makefiles to
> > > > > compile
> > > > > AVX2 and AVX512 files.
> > > >
> > > > Could you explain to me why instead of reusing existing rte_memcpy()
> > > > code to generate _sse/_avx2/ax512f flavors you keep pushing changes
> > > > with 3 separate implementations?
> > > > Obviously that is much more expensive in terms of maintenance and
> > > > doesn't look like feasible solution to me.
> > > > Is existing rte_memcpy() implementation is not good enough in terms
> > > > of functionality and/or performance?
> > > > If so, can you outline these problems and try to fix them first.
> > > > Konstantin
> > > >
> > >
> > > I just change many small functions to one function in those 3 separate
> > functions.
> >
> > Yes, so with what you suggest we'll have 4 implementations for rte_memcpy
> > to support.
> > That's very expensive terms of maintenance and I believe totally
> > unnecessary.
> >
> > > Because the existing codes are totally inline, including rte_memcpy()
> > > itself. So the compilation will change all rte_memcpy() calls into the
> > > basic
> > codes like xmm0=xxx.
> > >
> > > The existing codes in this way are OK.
> >
> > Good.
> >
> > >But when run-time, it will bring lots of function calls and cause perf
> > >drop.
> >
> > I believe it wouldn't if we do it properly.
> > All internal functions (mov16, mov32, etc.) will still be unlined by the
> > compiler for each flavor (sse/avx2/etc.) - have a look at the patch I sent.
> >
> > Konstantin
