[dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over memcpy

[Li, Xiaoyun]

> -----Original Message-----
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Li, Xiaoyun
> Sent: Wednesday, October 18, 2017 10:22
> To: Thomas Monjalon <thomas at monjalon.net>; Ananyev, Konstantin
> <konstantin.ananyev at intel.com>; Richardson, Bruce
> <bruce.richardson at intel.com>
> Cc: dev at dpdk.org; Lu, Wenzhuo <wenzhuo.lu at intel.com>; Zhang, Helin
> <helin.zhang at intel.com>; ophirmu at mellanox.com
> Subject: Re: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over
> memcpy
> 
> Hi
> 
> > -----Original Message-----
> > From: Thomas Monjalon [mailto:thomas at monjalon.net]
> > Sent: Wednesday, October 18, 2017 05:24
> > To: Li, Xiaoyun <xiaoyun.li at intel.com>; Ananyev, Konstantin
> > <konstantin.ananyev at intel.com>; Richardson, Bruce
> > <bruce.richardson at intel.com>
> > Cc: dev at dpdk.org; Lu, Wenzhuo <wenzhuo.lu at intel.com>; Zhang, Helin
> > <helin.zhang at intel.com>; ophirmu at mellanox.com
> > Subject: Re: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over
> > memcpy
> >
> > Hi,
> >
> > 13/10/2017 11:01, Xiaoyun Li:
> > > 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.li at intel.com>
> > > ---
> > Keeping only the major changes of the patch for later discussions:
> > [...]
> > >  static inline void *
> > >  rte_memcpy(void *dst, const void *src, size_t n)  {
> > > -	if (!(((uintptr_t)dst | (uintptr_t)src) & ALIGNMENT_MASK))
> > > -		return rte_memcpy_aligned(dst, src, n);
> > > +	if (n <= RTE_X86_MEMCPY_THRESH)
> > > +		return rte_memcpy_internal(dst, src, n);
> > >  	else
> > > -		return rte_memcpy_generic(dst, src, n);
> > > +		return (*rte_memcpy_ptr)(dst, src, n);
> > >  }
> > [...]
> > > +static inline void *
> > > +rte_memcpy_internal(void *dst, const void *src, size_t n) {
> > > +	if (!(((uintptr_t)dst | (uintptr_t)src) & ALIGNMENT_MASK))
> > > +		return rte_memcpy_aligned(dst, src, n);
> > > +	else
> > > +		return rte_memcpy_generic(dst, src, n); }
> >
> > The significant change of this patch is to call a function pointer for
> > packet size > 128 (RTE_X86_MEMCPY_THRESH).
> The perf drop is due to function call replacing inline.
> 
> > Please could you provide some benchmark numbers?
> I ran memcpy_perf_test which would show the time cost of memcpy. I ran it
> on broadwell with sse and avx2.
> But I just draw pictures and looked at the trend not computed the exact
> percentage. Sorry about that.
> The picture shows results of copy size of 2, 4, 6, 8, 9, 12, 16, 32, 64, 128, 192,
> 256, 320, 384, 448, 512, 768, 1024, 1518, 1522, 1536, 1600, 2048, 2560, 3072,
> 3584, 4096, 4608, 5120, 5632, 6144, 6656, 7168, 7680, 8192.
> In my test, the size grows, the drop degrades. (Using copy time indicates the
> perf.) From the trend picture, when the size is smaller than 128 bytes, the
> perf drops a lot, almost 50%. And above 128 bytes, it approaches the original
> dpdk.
> I computed it right now, it shows that when greater than 128 bytes and
> smaller than 1024 bytes, the perf drops about 15%. When above 1024 bytes,
> the perf drops about 4%.
> 
> > From a test done at Mellanox, there might be a performance degradation
> > of about 15% in testpmd txonly with AVX2.

Another thing, I will test testpmd txonly with intel nics and mellanox these days.
And try adjusting the RTE_X86_MEMCPY_THRESH to see if there is any improvement.

> > Is there someone else seeing a performance degradation?