net/ice: add AVX512BW flag check both in build and runtime
Checks
Commit Message
Intrinsic function __mm512_bsrli_epi128 should be used in
the environment which supports AVX512BW, so adds check for
this flag.
Fixes: 5dd3b8f3af34 ("net/ice: add AVX512 vector path")
Signed-off-by: Leyi Rong <leyi.rong@intel.com>
---
drivers/net/ice/ice_rxtx.c | 12 ++++++++++--
drivers/net/ice/meson.build | 13 +++++++++++--
2 files changed, 21 insertions(+), 4 deletions(-)
Comments
On 10/27/2020 10:19 AM, Leyi Rong wrote:
> Intrinsic function __mm512_bsrli_epi128 should be used in
> the environment which supports AVX512BW, so adds check for
> this flag.
>
> Fixes: 5dd3b8f3af34 ("net/ice: add AVX512 vector path")
>
> Signed-off-by: Leyi Rong <leyi.rong@intel.com>
Squashed into relevant commit in next-net, thanks.
Andrew, Ali, David,
Can you please confirm the issue is solved in the next-net/main?
Thanks,
ferruh
On 10/27/20 2:57 PM, Ferruh Yigit wrote:
> On 10/27/2020 10:19 AM, Leyi Rong wrote:
>> Intrinsic function __mm512_bsrli_epi128 should be used in
>> the environment which supports AVX512BW, so adds check for
>> this flag.
>>
>> Fixes: 5dd3b8f3af34 ("net/ice: add AVX512 vector path")
>>
>> Signed-off-by: Leyi Rong <leyi.rong@intel.com>
>
> Squashed into relevant commit in next-net, thanks.
>
>
> Andrew, Ali, David,
>
> Can you please confirm the issue is solved in the next-net/main?
Yes, it solved build issues which I observed.
Andrew.
Hi,
> -----Original Message-----
> From: Ferruh Yigit <ferruh.yigit@intel.com>
> Sent: Tuesday, October 27, 2020 1:57 PM
> To: Leyi Rong <leyi.rong@intel.com>; qi.z.zhang@intel.com;
> bruce.richardson@intel.com; wenzhuo.lu@intel.com; Ali Alnubani
> <alialnu@nvidia.com>; Andrew Rybchenko <arybchenko@solarflare.com>;
> David Marchand <david.marchand@redhat.com>
> Cc: dev@dpdk.org
> Subject: Re: [PATCH] net/ice: add AVX512BW flag check both in build and
> runtime
>
> On 10/27/2020 10:19 AM, Leyi Rong wrote:
> > Intrinsic function __mm512_bsrli_epi128 should be used in the
> > environment which supports AVX512BW, so adds check for this flag.
> >
> > Fixes: 5dd3b8f3af34 ("net/ice: add AVX512 vector path")
> >
> > Signed-off-by: Leyi Rong <leyi.rong@intel.com>
>
> Squashed into relevant commit in next-net, thanks.
>
>
> Andrew, Ali, David,
>
> Can you please confirm the issue is solved in the next-net/main?
>
The build failures in CentOS 7, Ubuntu 18.04 and in OpenSUSE Leap 15.2 no longer reproduce. But we just noticed that Ubuntu 16.04.7 (gcc 5.4.0) is also failing with a different error:
"""
drivers/net/ice/ice_rxtx_vec_avx512.c:1:0: error: bad value (skylake-avx512) for -march= switch
/* SPDX-License-Identifier: BSD-3-Clause
"""
Which is also caused by "net/ice: add AVX512 vector path".
Regards,
Ali
On Tue, Oct 27, 2020 at 12:57 PM Ferruh Yigit <ferruh.yigit@intel.com> wrote:
>
> On 10/27/2020 10:19 AM, Leyi Rong wrote:
> > Intrinsic function __mm512_bsrli_epi128 should be used in
> > the environment which supports AVX512BW, so adds check for
> > this flag.
> >
> > Fixes: 5dd3b8f3af34 ("net/ice: add AVX512 vector path")
> >
> > Signed-off-by: Leyi Rong <leyi.rong@intel.com>
>
> Squashed into relevant commit in next-net, thanks.
>
>
> Andrew, Ali, David,
>
> Can you please confirm the issue is solved in the next-net/main?
Tree with HEAD at 5e12432f4be4 ("net/ice: fix Rx offload flags in SSE
path") looks good to me.
Thanks.
On Tue, Oct 27, 2020 at 01:12:20PM +0000, Ali Alnubani wrote:
> Hi,
>
> > -----Original Message-----
> > From: Ferruh Yigit <ferruh.yigit@intel.com>
> > Sent: Tuesday, October 27, 2020 1:57 PM
> > To: Leyi Rong <leyi.rong@intel.com>; qi.z.zhang@intel.com;
> > bruce.richardson@intel.com; wenzhuo.lu@intel.com; Ali Alnubani
> > <alialnu@nvidia.com>; Andrew Rybchenko <arybchenko@solarflare.com>;
> > David Marchand <david.marchand@redhat.com>
> > Cc: dev@dpdk.org
> > Subject: Re: [PATCH] net/ice: add AVX512BW flag check both in build and
> > runtime
> >
> > On 10/27/2020 10:19 AM, Leyi Rong wrote:
> > > Intrinsic function __mm512_bsrli_epi128 should be used in the
> > > environment which supports AVX512BW, so adds check for this flag.
> > >
> > > Fixes: 5dd3b8f3af34 ("net/ice: add AVX512 vector path")
> > >
> > > Signed-off-by: Leyi Rong <leyi.rong@intel.com>
> >
> > Squashed into relevant commit in next-net, thanks.
> >
> >
> > Andrew, Ali, David,
> >
> > Can you please confirm the issue is solved in the next-net/main?
> >
>
> The build failures in CentOS 7, Ubuntu 18.04 and in OpenSUSE Leap 15.2 no longer reproduce. But we just noticed that Ubuntu 16.04.7 (gcc 5.4.0) is also failing with a different error:
>
> """
> drivers/net/ice/ice_rxtx_vec_avx512.c:1:0: error: bad value (skylake-avx512) for -march= switch
> /* SPDX-License-Identifier: BSD-3-Clause
> """
> Which is also caused by "net/ice: add AVX512 vector path".
>
I think we can drop the -march=skylake-avx512 flag in the build command for
the avx512 file, since specifying the -mavx512f and -mavx512bw should be
enough. Testing in an ubuntu 16.04 VM (which has 5.5 rather than 5.4
compiler, but should be ok), shows that the avx512 instruction set flags
are recognised and enable the isntructions, which the -march one is not.
/Bruce
bruce@ubuntu-1604-vm:~$ gcc -mavx512f -mavx512bw -dM -E - < /dev/null | grep AVX
#define __AVX512F__ 1
#define __AVX512BW__ 1
#define __AVX__ 1
#define __AVX2__ 1
bruce@ubuntu-1604-vm:~$ gcc -march=skylake-avx512 -dM -E - < /dev/null | grep AVX
cc1: error: bad value (skylake-avx512) for -march= switch
> -----Original Message-----
> From: Bruce Richardson <bruce.richardson@intel.com>
> Sent: Tuesday, October 27, 2020 9:28 PM
> To: Ali Alnubani <alialnu@nvidia.com>
> Cc: Yigit, Ferruh <ferruh.yigit@intel.com>; Rong, Leyi <leyi.rong@intel.com>;
> Zhang, Qi Z <qi.z.zhang@intel.com>; Lu, Wenzhuo <wenzhuo.lu@intel.com>;
> Andrew Rybchenko <arybchenko@solarflare.com>; David Marchand
> <david.marchand@redhat.com>; Raslan Darawsheh <rasland@nvidia.com>;
> dev@dpdk.org
> Subject: Re: [PATCH] net/ice: add AVX512BW flag check both in build and
> runtime
>
> On Tue, Oct 27, 2020 at 01:12:20PM +0000, Ali Alnubani wrote:
> > Hi,
> >
> > > -----Original Message-----
> > > From: Ferruh Yigit <ferruh.yigit@intel.com>
> > > Sent: Tuesday, October 27, 2020 1:57 PM
> > > To: Leyi Rong <leyi.rong@intel.com>; qi.z.zhang@intel.com;
> > > bruce.richardson@intel.com; wenzhuo.lu@intel.com; Ali Alnubani
> > > <alialnu@nvidia.com>; Andrew Rybchenko
> <arybchenko@solarflare.com>;
> > > David Marchand <david.marchand@redhat.com>
> > > Cc: dev@dpdk.org
> > > Subject: Re: [PATCH] net/ice: add AVX512BW flag check both in build
> > > and runtime
> > >
> > > On 10/27/2020 10:19 AM, Leyi Rong wrote:
> > > > Intrinsic function __mm512_bsrli_epi128 should be used in the
> > > > environment which supports AVX512BW, so adds check for this flag.
> > > >
> > > > Fixes: 5dd3b8f3af34 ("net/ice: add AVX512 vector path")
> > > >
> > > > Signed-off-by: Leyi Rong <leyi.rong@intel.com>
> > >
> > > Squashed into relevant commit in next-net, thanks.
> > >
> > >
> > > Andrew, Ali, David,
> > >
> > > Can you please confirm the issue is solved in the next-net/main?
> > >
> >
> > The build failures in CentOS 7, Ubuntu 18.04 and in OpenSUSE Leap 15.2 no
> longer reproduce. But we just noticed that Ubuntu 16.04.7 (gcc 5.4.0) is also
> failing with a different error:
> >
> > """
> > drivers/net/ice/ice_rxtx_vec_avx512.c:1:0: error: bad value
> > (skylake-avx512) for -march= switch
> > /* SPDX-License-Identifier: BSD-3-Clause """
> > Which is also caused by "net/ice: add AVX512 vector path".
> >
>
> I think we can drop the -march=skylake-avx512 flag in the build command for
> the avx512 file, since specifying the -mavx512f and -mavx512bw should be
> enough. Testing in an ubuntu 16.04 VM (which has 5.5 rather than 5.4
> compiler, but should be ok), shows that the avx512 instruction set flags are
> recognised and enable the isntructions, which the -march one is not.
>
> /Bruce
>
> bruce@ubuntu-1604-vm:~$ gcc -mavx512f -mavx512bw -dM -E - < /dev/null
> | grep AVX #define __AVX512F__ 1 #define __AVX512BW__ 1 #define
> __AVX__ 1 #define __AVX2__ 1 bruce@ubuntu-1604-vm:~$ gcc -
> march=skylake-avx512 -dM -E - < /dev/null | grep AVX
> cc1: error: bad value (skylake-avx512) for -march= switch
Hi Bruce,
Drop -march=skylake-avx512 really impact the throughput performance in my test, although -avx512f and -avx512bw are set meanwhile.
Could we add a judgement before setting -march=skylake-avx512, the judgement can just like
if (toolchain == 'gcc' and cc.version().version_compare('>=7.0.0'))
Leyi
On Tue, Oct 27, 2020 at 03:36:58PM +0000, Rong, Leyi wrote:
>
> > -----Original Message-----
> > From: Bruce Richardson <bruce.richardson@intel.com>
> > Sent: Tuesday, October 27, 2020 9:28 PM
> > To: Ali Alnubani <alialnu@nvidia.com>
> > Cc: Yigit, Ferruh <ferruh.yigit@intel.com>; Rong, Leyi <leyi.rong@intel.com>;
> > Zhang, Qi Z <qi.z.zhang@intel.com>; Lu, Wenzhuo <wenzhuo.lu@intel.com>;
> > Andrew Rybchenko <arybchenko@solarflare.com>; David Marchand
> > <david.marchand@redhat.com>; Raslan Darawsheh <rasland@nvidia.com>;
> > dev@dpdk.org
> > Subject: Re: [PATCH] net/ice: add AVX512BW flag check both in build and
> > runtime
> >
> > On Tue, Oct 27, 2020 at 01:12:20PM +0000, Ali Alnubani wrote:
> > > Hi,
> > >
> > > > -----Original Message-----
> > > > From: Ferruh Yigit <ferruh.yigit@intel.com>
> > > > Sent: Tuesday, October 27, 2020 1:57 PM
> > > > To: Leyi Rong <leyi.rong@intel.com>; qi.z.zhang@intel.com;
> > > > bruce.richardson@intel.com; wenzhuo.lu@intel.com; Ali Alnubani
> > > > <alialnu@nvidia.com>; Andrew Rybchenko
> > <arybchenko@solarflare.com>;
> > > > David Marchand <david.marchand@redhat.com>
> > > > Cc: dev@dpdk.org
> > > > Subject: Re: [PATCH] net/ice: add AVX512BW flag check both in build
> > > > and runtime
> > > >
> > > > On 10/27/2020 10:19 AM, Leyi Rong wrote:
> > > > > Intrinsic function __mm512_bsrli_epi128 should be used in the
> > > > > environment which supports AVX512BW, so adds check for this flag.
> > > > >
> > > > > Fixes: 5dd3b8f3af34 ("net/ice: add AVX512 vector path")
> > > > >
> > > > > Signed-off-by: Leyi Rong <leyi.rong@intel.com>
> > > >
> > > > Squashed into relevant commit in next-net, thanks.
> > > >
> > > >
> > > > Andrew, Ali, David,
> > > >
> > > > Can you please confirm the issue is solved in the next-net/main?
> > > >
> > >
> > > The build failures in CentOS 7, Ubuntu 18.04 and in OpenSUSE Leap 15.2 no
> > longer reproduce. But we just noticed that Ubuntu 16.04.7 (gcc 5.4.0) is also
> > failing with a different error:
> > >
> > > """
> > > drivers/net/ice/ice_rxtx_vec_avx512.c:1:0: error: bad value
> > > (skylake-avx512) for -march= switch
> > > /* SPDX-License-Identifier: BSD-3-Clause """
> > > Which is also caused by "net/ice: add AVX512 vector path".
> > >
> >
> > I think we can drop the -march=skylake-avx512 flag in the build command for
> > the avx512 file, since specifying the -mavx512f and -mavx512bw should be
> > enough. Testing in an ubuntu 16.04 VM (which has 5.5 rather than 5.4
> > compiler, but should be ok), shows that the avx512 instruction set flags are
> > recognised and enable the isntructions, which the -march one is not.
> >
> > /Bruce
> >
> > bruce@ubuntu-1604-vm:~$ gcc -mavx512f -mavx512bw -dM -E - < /dev/null
> > | grep AVX #define __AVX512F__ 1 #define __AVX512BW__ 1 #define
> > __AVX__ 1 #define __AVX2__ 1 bruce@ubuntu-1604-vm:~$ gcc -
> > march=skylake-avx512 -dM -E - < /dev/null | grep AVX
> > cc1: error: bad value (skylake-avx512) for -march= switch
>
> Hi Bruce,
>
> Drop -march=skylake-avx512 really impact the throughput performance in my test, although -avx512f and -avx512bw are set meanwhile.
We need to find out why this is, since it really should not matter? We
should be used the instruction set flags to turn on features rather than
relying on a particular CPU architecture. Can you try turning on the other
features present in "skylake-avx512" and see if that makes a difference.
For reference, they are avx512vl, avx512cd and avx512dq.
gcc -march=skylake-avx512 -dM -E - < /dev/null | grep AVX5
#define __AVX512F__ 1
#define __AVX512BW__ 1
#define __AVX512VL__ 1
#define __AVX512CD__ 1
#define __AVX512DQ__ 1
> Could we add a judgement before setting -march=skylake-avx512, the judgement can just like
> if (toolchain == 'gcc' and cc.version().version_compare('>=7.0.0'))
>
We should never check for a specific compiler. Instead check for the
compiler flag directly.
/Bruce
Hi,
> -----Original Message-----
> From: David Marchand <david.marchand@redhat.com>
> Sent: Tuesday, October 27, 2020 3:17 PM
> To: Ferruh Yigit <ferruh.yigit@intel.com>
> Cc: Leyi Rong <leyi.rong@intel.com>; Qi Zhang <qi.z.zhang@intel.com>;
> Bruce Richardson <bruce.richardson@intel.com>; Wenzhuo Lu
> <wenzhuo.lu@intel.com>; Ali Alnubani <alialnu@nvidia.com>; Andrew
> Rybchenko <arybchenko@solarflare.com>; dev <dev@dpdk.org>
> Subject: Re: [PATCH] net/ice: add AVX512BW flag check both in build and
> runtime
>
> On Tue, Oct 27, 2020 at 12:57 PM Ferruh Yigit <ferruh.yigit@intel.com>
> wrote:
> >
> > On 10/27/2020 10:19 AM, Leyi Rong wrote:
> > > Intrinsic function __mm512_bsrli_epi128 should be used in the
> > > environment which supports AVX512BW, so adds check for this flag.
> > >
> > > Fixes: 5dd3b8f3af34 ("net/ice: add AVX512 vector path")
> > >
> > > Signed-off-by: Leyi Rong <leyi.rong@intel.com>
> >
> > Squashed into relevant commit in next-net, thanks.
> >
> >
> > Andrew, Ali, David,
> >
> > Can you please confirm the issue is solved in the next-net/main?
>
> Tree with HEAD at 5e12432f4be4 ("net/ice: fix Rx offload flags in SSE
> path") looks good to me.
> Thanks.
>
> --
> David Marchand
I can reproduce right now in net/iavf on latest next-net/main "3197a1371 net/octeontx2: avoid per packet barrier with multi segment":
"""
drivers/net/iavf/iavf_rxtx_vec_avx512.c:1:0: error: bad value (skylake-avx512) for -march= switch
/* SPDX-License-Identifier: BSD-3-Clause
"""
- Ali
@@ -3007,7 +3007,8 @@ ice_set_rx_function(struct rte_eth_dev *dev)
}
if (rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_512 &&
- rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) == 1)
+ rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) == 1 &&
+ rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512BW) == 1)
#ifdef CC_AVX512_SUPPORT
use_avx512 = true;
#else
@@ -3028,11 +3029,13 @@ ice_set_rx_function(struct rte_eth_dev *dev)
if (ad->rx_vec_allowed) {
if (dev->data->scattered_rx) {
if (use_avx512) {
+#ifdef CC_AVX512_SUPPORT
PMD_DRV_LOG(NOTICE,
"Using AVX512 Vector Scattered Rx (port %d).",
dev->data->port_id);
dev->rx_pkt_burst =
ice_recv_scattered_pkts_vec_avx512;
+#endif
} else {
PMD_DRV_LOG(DEBUG,
"Using %sVector Scattered Rx (port %d).",
@@ -3044,11 +3047,13 @@ ice_set_rx_function(struct rte_eth_dev *dev)
}
} else {
if (use_avx512) {
+#ifdef CC_AVX512_SUPPORT
PMD_DRV_LOG(NOTICE,
"Using AVX512 Vector Rx (port %d).",
dev->data->port_id);
dev->rx_pkt_burst =
ice_recv_pkts_vec_avx512;
+#endif
} else {
PMD_DRV_LOG(DEBUG,
"Using %sVector Rx (port %d).",
@@ -3218,7 +3223,8 @@ ice_set_tx_function(struct rte_eth_dev *dev)
}
if (rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_512 &&
- rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) == 1)
+ rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) == 1 &&
+ rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512BW) == 1)
#ifdef CC_AVX512_SUPPORT
use_avx512 = true;
#else
@@ -3238,9 +3244,11 @@ ice_set_tx_function(struct rte_eth_dev *dev)
if (ad->tx_vec_allowed) {
if (use_avx512) {
+#ifdef CC_AVX512_SUPPORT
PMD_DRV_LOG(NOTICE, "Using AVX512 Vector Tx (port %d).",
dev->data->port_id);
dev->tx_pkt_burst = ice_xmit_pkts_vec_avx512;
+#endif
} else {
PMD_DRV_LOG(DEBUG, "Using %sVector Tx (port %d).",
use_avx2 ? "avx2 " : "",
@@ -35,14 +35,23 @@ if arch_subdir == 'x86'
objs += ice_avx2_lib.extract_objects('ice_rxtx_vec_avx2.c')
endif
- if dpdk_conf.has('RTE_MACHINE_CPUFLAG_AVX512F') or (not machine_args.contains('-mno-avx512f') and cc.has_argument('-mavx512f'))
+ ice_avx512_cpu_support = (
+ cc.get_define('__AVX512F__', args: machine_args) != '' and
+ cc.get_define('__AVX512BW__', args: machine_args) != '')
+
+ ice_avx512_cc_support = (
+ not machine_args.contains('-mno-avx512f') and
+ cc.has_argument('-mavx512f') and
+ cc.has_argument('-mavx512bw'))
+
+ if ice_avx512_cpu_support == true or ice_avx512_cc_support == true
cflags += ['-DCC_AVX512_SUPPORT']
ice_avx512_lib = static_library('ice_avx512_lib',
'ice_rxtx_vec_avx512.c',
dependencies: [static_rte_ethdev,
static_rte_kvargs, static_rte_hash],
include_directories: includes,
- c_args: [cflags, '-march=skylake-avx512', '-mavx512f'])
+ c_args: [cflags, '-march=skylake-avx512', '-mavx512f', '-mavx512bw'])
objs += ice_avx512_lib.extract_objects('ice_rxtx_vec_avx512.c')
endif
endif