4 .. **Read this first.**
6 The text in the sections below explains how to update the release notes.
8 Use proper spelling, capitalization and punctuation in all sections.
10 Variable and config names should be quoted as fixed width text:
13 Build the docs and view the output file to ensure the changes are correct::
17 xdg-open build/doc/html/guides/rel_notes/release_18_05.html
23 .. This section should contain new features added in this release. Sample
26 * **Add a title in the past tense with a full stop.**
28 Add a short 1-2 sentence description in the past tense. The description
29 should be enough to allow someone scanning the release notes to
30 understand the new feature.
32 If the feature adds a lot of sub-features you can use a bullet list like
35 * Added feature foo to do something.
36 * Enhanced feature bar to do something else.
38 Refer to the previous release notes for examples.
40 This section is a comment. Do not overwrite or remove it.
41 Also, make sure to start the actual text at the margin.
42 =========================================================
44 * **Added bucket mempool driver.**
46 Added bucket mempool driver which provides a way to allocate contiguous
48 Number of objects in the block depends on how many objects fit in
49 RTE_DRIVER_MEMPOOL_BUCKET_SIZE_KB memory chunk which is build time option.
50 The number may be obtained using rte_mempool_ops_get_info() API.
51 Contiguous blocks may be allocated using rte_mempool_get_contig_blocks() API.
53 * **Added PMD-recommended Tx and Rx parameters**
55 Applications can now query drivers for device-tuned values of
56 ring sizes, burst sizes, and number of queues.
58 * **Added RSS hash and key update to CXGBE PMD.**
60 Support to update RSS hash and key has been added to CXGBE PMD.
62 * **Added CXGBE VF PMD.**
64 CXGBE VF Poll Mode Driver has been added to run DPDK over Chelsio
65 T5/T6 NIC VF instances.
67 * **Updated mlx5 driver.**
69 Updated the mlx5 driver including the following changes:
71 * Introduced Multi-packet Rx. With it, achieved 100Gb/sec with 64B frames.
72 * Supported to be run by non-root users given reduced set of capabilities
73 CAP_NET_ADMIN, CAP_NET_RAW and CAP_IPC_LOCK.
74 * Supported TSO and checksum for generic UDP and IP tunnels.
75 * Supported inner checksum and RSS for GRE, VXLAN-GPE, MPLSoGRE
77 * Accommodate to the new memory hotplug model.
78 * Supported non virtually contiguous mempools.
79 * Supported MAC adding along with allmulti and promiscuous modes from VF.
80 * Supported Mellanox BlueField SoC device.
81 * Supported PMD defaults for queue number and depth to improve the out
82 of the box performance.
84 * **Updated mlx4 driver.**
86 Updated the mlx4 driver including the following changes:
88 * Supported to be run by non-root users given reduced set of capabilities
89 CAP_NET_ADMIN, CAP_NET_RAW and CAP_IPC_LOCK.
90 * Supported CRC strip toggling.
91 * Accommodate to the new memory hotplug model.
92 * Supported non virtually contiguous mempools.
93 * Dropped support in Mellanox OFED 4.2.
95 * **Updated Solarflare network PMD.**
97 Updated the sfc_efx driver including the following changes:
99 * Added support for Solarflare XtremeScale X2xxx family adapters.
100 * Added support for NVGRE, VXLAN and GENEVE filters in flow API.
101 * Added support for DROP action in flow API.
102 * Added support for equal stride super-buffer Rx mode (X2xxx only).
103 * Added support for MARK and FLAG actions in flow API (X2xxx only).
105 * **Added Ethernet poll mode driver for AMD XGBE devices.**
107 Added the new ``axgbe`` ethernet poll mode driver for AMD XGBE devices.
108 See the :doc:`../nics/axgbe` nic driver guide for more details on this
111 * **Updated szedata2 PMD.**
113 Added support for new NFB-200G2QL card.
114 New API was introduced in the libsze2 library which the szedata2 PMD depends
115 on thus the new version of the library was needed.
116 New versions of the packages are available and the minimum required version
119 * **Added support for Broadcom NetXtreme-S (BCM58800) family of controllers (aka Stingray)**
121 The BCM58800 devices feature a NetXtreme E-Series advanced network controller, a high-performance
122 ARM CPU block, PCI Express (PCIe) Gen3 interfaces, key accelerators for compute offload and a high-
123 speed memory subsystem including L3 cache and DDR4 interfaces, all interconnected by a coherent
124 Network-on-chip (NOC) fabric.
126 The ARM CPU subsystem features eight ARMv8 Cortex-A72 CPUs at 3.0 GHz, arranged in a multi-cluster
129 * **Added vDPA in vhost-user lib.**
131 Added support for selective datapath in vhost-user lib. vDPA stands for vhost
132 Data Path Acceleration. It supports virtio ring compatible devices to serve
133 virtio driver directly to enable datapath acceleration.
135 * **Added IFCVF vDPA driver.**
137 Added IFCVF vDPA driver to support Intel FPGA 100G VF device. IFCVF works
138 as a HW vhost data path accelerator, it supports live migration and is
139 compatible with virtio 0.95 and 1.0. This driver registers ifcvf vDPA driver
140 to vhost lib, when virtio connected, with the help of the registered vDPA
141 driver the assigned VF gets configured to Rx/Tx directly to VM's virtio
144 * **Added support for vhost dequeue interrupt mode.**
146 Added support for vhost dequeue interrupt mode to release cpus to others when
147 no data to transmit. Applications could register an epoll event fd to associate
148 Rx queues with interrupt vectors.
150 * **Added support for virtio-user server mode.**
151 In a container environment if the vhost-user backend restarts, there's no way
152 for it to reconnect to virtio-user. To address this, support for server mode
153 is added. In this mode the socket file is created by virtio-user, which the
154 backend connects to. This means that if the backend restarts, it can reconnect
155 to virtio-user and continue communications.
157 * **Added crypto workload support to vhost library.**
159 New APIs are introduced in vhost library to enable virtio crypto support
160 including session creation/deletion handling and translating virtio-crypto
161 request into DPDK crypto operations. A sample application is also introduced.
163 * **Added virtio crypto PMD.**
165 Added a new poll mode driver for virtio crypto devices, which provides
166 AES-CBC ciphering and AES-CBC with HMAC-SHA1 algorithm-chaining. See the
167 :doc:`../cryptodevs/virtio` crypto driver guide for more details on
170 * **Added AMD CCP Crypto PMD.**
172 Added the new ``ccp`` crypto driver for AMD CCP devices. See the
173 :doc:`../cryptodevs/ccp` crypto driver guide for more details on
176 * **Updated AESNI MB PMD.**
178 The AESNI MB PMD has been updated with additional support for:
180 * AES-CMAC (128-bit key).
182 * **Added Compressdev Library, a generic compression service library.**
184 The compressdev library provides an API for offload of compression and
185 decompression operations to hardware or software accelerator devices.
187 * **Added a new compression poll mode driver using Intels ISA-L.**
189 Added the new ``ISA-L`` compression driver, for compression and decompression
190 operations in software. See the :doc:`../compressdevs/isal` compression driver
191 guide for details on this new driver.
193 * **Added the Event Timer Adapter Library.**
195 The Event Timer Adapter Library extends the event-based model by introducing
196 APIs that allow applications to arm/cancel event timers that generate
197 timer expiry events. This new type of event is scheduled by an event device
198 along with existing types of events.
200 * **Added OcteonTx TIM Driver (Event timer adapter).**
202 The OcteonTx Timer block enables software to schedule events for a future
203 time, it is exposed to an application via Event timer adapter library.
205 See the :doc:`../eventdevs/octeontx` guide for more details
207 * **Added Event Crypto Adapter Library.**
209 Added the Event Crypto Adapter Library. This library extends the
210 event-based model by introducing APIs that allow applications to
211 enqueue/dequeue crypto operations to/from cryptodev as events scheduled
214 * **Added Ifpga Bus, a generic Intel FPGA Bus library.**
216 The Ifpga Bus library provides support for integrating any Intel FPGA device with
217 the DPDK framework. It provides Intel FPGA Partial Bit Stream AFU (Accelerated
218 Function Unit) scan and drivers probe.
220 * **Added IFPGA (Intel FPGA) Rawdev Driver.**
222 Added a new Rawdev driver called IFPGA(Intel FPGA) Rawdev Driver, which cooperates
223 with OPAE (Open Programmable Acceleration Engine) share code provides common FPGA
224 management ops for FPGA operation.
226 See the :doc:`../rawdevs/ifpga_rawdev` programmer's guide for more details.
228 * **Added DPAA2 QDMA Driver (in rawdev).**
230 The DPAA2 QDMA is an implementation of the rawdev API, that provide means
231 to initiate a DMA transaction from CPU. The initiated DMA is performed
232 without CPU being involved in the actual DMA transaction.
234 See the :doc:`../rawdevs/dpaa2_qdma` guide for more details.
236 * **Added DPAA2 Command Interface Driver (in rawdev).**
238 The DPAA2 CMDIF is an implementation of the rawdev API, that provides
239 communication between the GPP and NXP's QorIQ based AIOP Block (Firmware).
240 Advanced IO Processor i.e. AIOP is clusters of programmable RISC engines
241 optimised for flexible networking and I/O operations. The communication
242 between GPP and AIOP is achieved via using DPCI devices exposed by MC for
243 GPP <--> AIOP interaction.
245 See the :doc:`../rawdevs/dpaa2_cmdif` guide for more details.
247 * **Added device event monitor framework.**
249 Added a general device event monitor framework at EAL, for device dynamic management.
250 Such as device hotplug awareness and actions adopted accordingly. The list of new APIs:
252 * ``rte_dev_event_monitor_start`` and ``rte_dev_event_monitor_stop`` are for
253 the event monitor enable and disable.
254 * ``rte_dev_event_callback_register`` and ``rte_dev_event_callback_unregister``
255 are for the user's callbacks register and unregister.
257 Linux uevent is supported as backend of this device event notification framework.
259 * **Added support for procinfo and pdump on eth vdev.**
261 For ethernet virtual devices (like tap, pcap, etc), with this feature, we can get
262 stats/xstats on shared memory from secondary process, and also pdump packets on
263 those virtual devices.
265 * **Added the BPF Library.**
267 The BPF Library provides the ability to load and execute
268 Enhanced Berkeley Packet Filter (eBPF) within user-space dpdk application.
269 Also it introduces basic framework to load/unload BPF-based filters
270 on eth devices (right now only via SW RX/TX callbacks).
271 It also adds dependency on libelf.
277 .. This section should contain API changes. Sample format:
279 * Add a short 1-2 sentence description of the API change. Use fixed width
280 quotes for ``rte_function_names`` or ``rte_struct_names``. Use the past
283 This section is a comment. Do not overwrite or remove it.
284 Also, make sure to start the actual text at the margin.
285 =========================================================
287 * service cores: no longer marked as experimental.
289 The service cores functions are no longer marked as experimental, and have
290 become part of the normal DPDK API and ABI. Any future ABI changes will be
291 announced at least one release before the ABI change is made. There are no
292 ABI breaking changes planned.
294 * eal: ``rte_lcore_has_role()`` return value changed.
296 This function now returns true or false, respectively,
297 rather than 0 or <0 for success or failure.
298 It makes use of the function more intuitive.
300 * mempool: capability flags and related functions have been removed.
302 Flags ``MEMPOOL_F_CAPA_PHYS_CONTIG`` and
303 ``MEMPOOL_F_CAPA_BLK_ALIGNED_OBJECTS`` were used by octeontx mempool
304 driver to customize generic mempool library behaviour.
305 Now the new driver callbacks ``calc_mem_size`` and ``populate`` may be
306 used to achieve it without specific knowledge in the generic code.
308 * mempool: xmem functions have been deprecated:
310 - ``rte_mempool_xmem_create``
311 - ``rte_mempool_xmem_size``
312 - ``rte_mempool_xmem_usage``
313 - ``rte_mempool_populate_iova_tab``
315 * mbuf: The control mbuf API has been removed in v18.05. The impacted
316 functions and macros are:
318 - ``rte_ctrlmbuf_init()``
319 - ``rte_ctrlmbuf_alloc()``
320 - ``rte_ctrlmbuf_free()``
321 - ``rte_ctrlmbuf_data()``
322 - ``rte_ctrlmbuf_len()``
323 - ``rte_is_ctrlmbuf()``
326 The packet mbuf API should be used as a replacement.
328 * meter: updated to accommodate configuration profiles.
330 The meter API is changed to support meter configuration profiles. The
331 configuration profile represents the set of configuration parameters
332 for a given meter object, such as the rates and sizes for the token
333 buckets. These configuration parameters were previously the part of meter
334 object internal data strcuture. The separation of the configuration
335 parameters from meter object data structure results in reducing its
336 memory footprint which helps in better cache utilization when large number
337 of meter objects are used.
339 * ethdev: The function ``rte_eth_dev_count``, often mis-used to iterate
340 over ports, is deprecated and replaced by ``rte_eth_dev_count_avail``.
341 There is also a new function ``rte_eth_dev_count_total`` to get the
342 total number of allocated ports, available or not.
343 The hotplug-proof applications should use ``RTE_ETH_FOREACH_DEV`` or
344 ``RTE_ETH_FOREACH_DEV_OWNED_BY`` as port iterators.
346 * ethdev, in struct ``struct rte_eth_dev_info``, field ``rte_pci_device *pci_dev``
347 replaced with field ``struct rte_device *device``.
349 * **Changes to semantics of rte_eth_dev_configure() parameters.**
351 If both the ``nb_rx_q`` and ``nb_tx_q`` parameters are zero,
352 ``rte_eth_dev_configure`` will now use PMD-recommended queue sizes, or if
353 recommendations are not provided by the PMD the function will use ethdev
354 fall-back values. Previously setting both of the parameters to zero would
355 have resulted in ``-EINVAL`` being returned.
357 * **Changes to semantics of rte_eth_rx_queue_setup() parameters.**
359 If the ``nb_rx_desc`` parameter is zero, ``rte_eth_rx_queue_setup`` will
360 now use the PMD-recommended Rx ring size, or in the case where the PMD
361 does not provide a recommendation, will use an ethdev-provided
362 fall-back value. Previously, setting ``nb_rx_desc`` to zero would have
363 resulted in an error.
365 * **Changes to semantics of rte_eth_tx_queue_setup() parameters.**
367 If the ``nb_tx_desc`` parameter is zero, ``rte_eth_tx_queue_setup`` will
368 now use the PMD-recommended Tx ring size, or in the case where the PMD
369 does not provide a recoomendation, will use an ethdev-provided
370 fall-back value. Previously, setting ``nb_tx_desc`` to zero would have
371 resulted in an error.
373 * ethdev: several changes were made to the flow API.
375 * Unused DUP action was removed.
376 * Actions semantics in flow rules: list order now matters ("first
377 to last" instead of "all simultaneously"), repeated actions are now
378 all performed, and they do not individually have (non-)terminating
380 * Flow rules are now always terminating unless a PASSTHRU action is
382 * C99-style flexible arrays were replaced with standard pointers in RSS
383 action and in RAW pattern item structures due to compatibility issues.
384 * The RSS action was modified to not rely on external
385 ``struct rte_eth_rss_conf`` anymore to instead expose its own and more
386 appropriately named configuration fields directly
387 (``rss_conf->rss_key`` => ``key``,
388 ``rss_conf->rss_key_len`` => ``key_len``,
389 ``rss_conf->rss_hf`` => ``types``,
390 ``num`` => ``queue_num``), and the addition of missing RSS parameters
391 (``func`` for RSS hash function to apply and ``level`` for the
392 encapsulation level).
393 * The VLAN pattern item (``struct rte_flow_item_vlan``) was modified to
394 include inner EtherType instead of outer TPID. Its default mask was also
395 modified to cover the VID part (lower 12 bits) of TCI only.
396 * A new transfer attribute was added to ``struct rte_flow_attr`` in order
397 to clarify the behavior of some pattern items.
398 * PF and VF pattern items are now only accepted by PMDs that implement
399 them (bnxt and i40e) when the transfer attribute is also present for
401 * Pattern item PORT was renamed PHY_PORT to avoid confusion with DPDK port
403 * An action counterpart to the PHY_PORT pattern item was added in order to
404 redirect matching traffic to a specific physical port.
405 * PORT_ID pattern item and actions were added to match and target DPDK
406 port IDs at a higher level than PHY_PORT.
408 * ethdev: change flow APIs regarding count action:
409 * ``rte_flow_create()`` API count action now requires the ``struct rte_flow_action_count``.
410 * ``rte_flow_query()`` API parameter changed from action type to action structure.
412 * ethdev: changes to offload API
414 A pure per-port offloading isn't requested to be repeated in [rt]x_conf->offloads to
415 ``rte_eth_[rt]x_queue_setup()``. Now any offloading enabled in ``rte_eth_dev_configure()``
416 can't be disabled by ``rte_eth_[rt]x_queue_setup()``. Any new added offloading which has
417 not been enabled in ``rte_eth_dev_configure()`` and is requested to be enabled in
418 ``rte_eth_[rt]x_queue_setup()`` must be per-queue type, otherwise trigger an error log.
420 * ethdev: runtime queue setup:
422 ``rte_eth_rx_queue_setup`` and ``rte_eth_tx_queue_setup`` can be called after
423 ``rte_eth_dev_start`` if device support runtime queue setup. Device driver can
424 expose this capability through ``rte_eth_dev_info_get``. A Rx or Tx queue be
425 setup at runtime need to be started explicitly by ``rte_eth_dev_rx_queue_start``
426 or ``rte_eth_dev_tx_queue_start``.
432 .. This section should contain ABI changes. Sample format:
434 * Add a short 1-2 sentence description of the ABI change that was announced
435 in the previous releases and made in this release. Use fixed width quotes
436 for ``rte_function_names`` or ``rte_struct_names``. Use the past tense.
438 This section is a comment. Do not overwrite or remove it.
439 Also, make sure to start the actual text at the margin.
440 =========================================================
442 * ring: the alignment constraints on the ring structure has been relaxed
443 to one cache line instead of two, and an empty cache line padding is
444 added between the producer and consumer structures. The size of the
445 structure and the offset of the fields remains the same on platforms
446 with 64B cache line, but change on other platforms.
448 * mempool: ops have changed.
450 A new callback ``calc_mem_size`` has been added to ``rte_mempool_ops``
451 to allow to customize required memory size calculation.
452 A new callback ``populate`` has been added to ``rte_mempool_ops``
453 to allow to customize objects population.
454 Callback ``get_capabilities`` has been removed from ``rte_mempool_ops``
455 since its features are covered by ``calc_mem_size`` and ``populate``
457 Callback ``register_memory_area`` has been removed from ``rte_mempool_ops``
458 since the new callback ``populate`` may be used instead of it.
460 * **Additional fields in rte_eth_dev_info.**
462 The ``rte_eth_dev_info`` structure has had two extra entries appended to the
463 end of it: ``default_rxportconf`` and ``default_txportconf``. Each of these
464 in turn are ``rte_eth_dev_portconf`` structures containing three fields of
465 type ``uint16_t``: ``burst_size``, ``ring_size``, and ``nb_queues``. These
466 are parameter values recommended for use by the PMD.
468 * ethdev: ABI for all flow API functions was updated.
470 This includes functions ``rte_flow_copy``, ``rte_flow_create``,
471 ``rte_flow_destroy``, ``rte_flow_error_set``, ``rte_flow_flush``,
472 ``rte_flow_isolate``, ``rte_flow_query`` and ``rte_flow_validate``, due to
473 changes in error type definitions (``enum rte_flow_error_type``), removal
474 of the unused DUP action (``enum rte_flow_action_type``), modified
475 behavior for flow rule actions (see API changes), removal of C99 flexible
476 array from RAW pattern item (``struct rte_flow_item_raw``), complete
477 rework of the RSS action definition (``struct rte_flow_action_rss``),
478 sanity fix in the VLAN pattern item (``struct rte_flow_item_vlan``) and
479 new transfer attribute (``struct rte_flow_attr``).
481 **New parameter added to rte_bbdev_op_cap_turbo_dec.**
483 A new parameter ``max_llr_modulus`` has been added to
484 ``rte_bbdev_op_cap_turbo_dec`` structure to specify maximal LLR (likelihood
485 ratio) absolute value.
487 * **BBdev Queue Groups split into UL/DL Groups**
489 Queue Groups have been split into UL/DL Groups in Turbo Software Driver.
490 They are independent for Decode/Encode. ``rte_bbdev_driver_info`` reflects
497 .. This section should contain removed items in this release. Sample format:
499 * Add a short 1-2 sentence description of the removed item in the past
502 This section is a comment. Do not overwrite or remove it.
503 Also, make sure to start the actual text at the margin.
504 =========================================================
510 .. This section should contain new known issues in this release. Sample format:
512 * **Add title in present tense with full stop.**
514 Add a short 1-2 sentence description of the known issue in the present
515 tense. Add information on any known workarounds.
517 This section is a comment. Do not overwrite or remove it.
518 Also, make sure to start the actual text at the margin.
519 =========================================================
521 * **pdump is not compatible with old applications.**
523 As we changed to use generic multi-process communication for pdump negotiation
524 instead of previous dedicated unix socket way, pdump applications, including
525 dpdk-pdump example and any other applications using librte_pdump, cannot work
526 with older version DPDK primary applications.
529 Shared Library Versions
530 -----------------------
532 .. Update any library version updated in this release and prepend with a ``+``
536 + librte_cfgfile.so.2
539 This section is a comment. Do not overwrite or remove it.
540 =========================================================
543 The libraries prepended with a plus sign were incremented in this version.
549 librte_bitratestats.so.2
552 librte_bus_fslmc.so.1
557 + librte_common_octeontx.so.1
558 + librte_compressdev.so.1
559 librte_cryptodev.so.4
560 librte_distributor.so.1
563 + librte_eventdev.so.4
564 librte_flow_classify.so.1
572 librte_latencystats.so.1
575 + librte_mempool.so.4
585 librte_pmd_ixgbe.so.2
586 + librte_pmd_dpaa2_cmdif.so.1
587 + librte_pmd_dpaa2_qdma.so.1
589 librte_pmd_softnic.so.1
590 librte_pmd_vhost.so.2
606 .. This section should contain a list of platforms that were tested with this
611 * <vendor> platform with <vendor> <type of devices> combinations
616 * Other relevant details...
618 This section is a comment. Do not overwrite or remove it.
619 Also, make sure to start the actual text at the margin.
620 =========================================================
622 * Intel(R) platforms with Intel(R) NICs combinations
626 * Intel(R) Atom(TM) CPU C2758 @ 2.40GHz
627 * Intel(R) Xeon(R) CPU D-1541 @ 2.10GHz
628 * Intel(R) Xeon(R) CPU E5-4667 v3 @ 2.00GHz
629 * Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz
630 * Intel(R) Xeon(R) CPU E5-2699 v4 @ 2.20GHz
631 * Intel(R) Xeon(R) CPU E5-2695 v4 @ 2.10GHz
632 * Intel(R) Xeon(R) CPU E5-2658 v2 @ 2.40GHz
633 * Intel(R) Xeon(R) CPU E5-2658 v3 @ 2.20GHz
634 * Intel(R) Xeon(R) Platinum 8180 CPU @ 2.50GHz
643 * Red Hat Enterprise Linux Server release 7.3
644 * SUSE Enterprise Linux 12
653 * Intel(R) 82599ES 10 Gigabit Ethernet Controller
655 * Firmware version: 0x61bf0001
656 * Device id (pf/vf): 8086:10fb / 8086:10ed
657 * Driver version: 5.2.3 (ixgbe)
659 * Intel(R) Corporation Ethernet Connection X552/X557-AT 10GBASE-T
661 * Firmware version: 0x800003e7
662 * Device id (pf/vf): 8086:15ad / 8086:15a8
663 * Driver version: 4.4.6 (ixgbe)
665 * Intel(R) Ethernet Converged Network Adapter X710-DA4 (4x10G)
667 * Firmware version: 6.01 0x80003221
668 * Device id (pf/vf): 8086:1572 / 8086:154c
669 * Driver version: 2.4.6 (i40e)
671 * Intel Corporation Ethernet Connection X722 for 10GbE SFP+ (4x10G)
673 * Firmware version: 3.33 0x80000fd5 0.0.0
674 * Device id (pf/vf): 8086:37d0 / 8086:37cd
675 * Driver version: 2.4.3 (i40e)
677 * Intel(R) Ethernet Converged Network Adapter XXV710-DA2 (2x25G)
679 * Firmware version: 6.01 0x80003221
680 * Device id (pf/vf): 8086:158b / 8086:154c
681 * Driver version: 2.4.6 (i40e)
683 * Intel(R) Ethernet Converged Network Adapter XL710-QDA2 (2X40G)
685 * Firmware version: 6.01 0x8000321c
686 * Device id (pf/vf): 8086:1583 / 8086:154c
687 * Driver version: 2.4.6 (i40e)
689 * Intel(R) Corporation I350 Gigabit Network Connection
691 * Firmware version: 1.63, 0x80000dda
692 * Device id (pf/vf): 8086:1521 / 8086:1520
693 * Driver version: 5.4.0-k (igb)
695 * Intel(R) platforms with Mellanox(R) NICs combinations
699 * Intel(R) Xeon(R) Gold 6154 CPU @ 3.00GHz
700 * Intel(R) Xeon(R) CPU E5-2697A v4 @ 2.60GHz
701 * Intel(R) Xeon(R) CPU E5-2697 v3 @ 2.60GHz
702 * Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz
703 * Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20GHz
704 * Intel(R) Xeon(R) CPU E5-2640 @ 2.50GHz
705 * Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
709 * Red Hat Enterprise Linux Server release 7.5 (Maipo)
710 * Red Hat Enterprise Linux Server release 7.4 (Maipo)
711 * Red Hat Enterprise Linux Server release 7.3 (Maipo)
712 * Red Hat Enterprise Linux Server release 7.2 (Maipo)
717 * SUSE Linux Enterprise Server 15
719 * MLNX_OFED: 4.2-1.0.0.0
720 * MLNX_OFED: 4.3-2.0.2.0
724 * Mellanox(R) ConnectX(R)-3 Pro 40G MCX354A-FCC_Ax (2x40G)
726 * Host interface: PCI Express 3.0 x8
727 * Device ID: 15b3:1007
728 * Firmware version: 2.42.5000
730 * Mellanox(R) ConnectX(R)-4 10G MCX4111A-XCAT (1x10G)
732 * Host interface: PCI Express 3.0 x8
733 * Device ID: 15b3:1013
734 * Firmware version: 12.21.1000 and above
736 * Mellanox(R) ConnectX(R)-4 10G MCX4121A-XCAT (2x10G)
738 * Host interface: PCI Express 3.0 x8
739 * Device ID: 15b3:1013
740 * Firmware version: 12.21.1000 and above
742 * Mellanox(R) ConnectX(R)-4 25G MCX4111A-ACAT (1x25G)
744 * Host interface: PCI Express 3.0 x8
745 * Device ID: 15b3:1013
746 * Firmware version: 12.21.1000 and above
748 * Mellanox(R) ConnectX(R)-4 25G MCX4121A-ACAT (2x25G)
750 * Host interface: PCI Express 3.0 x8
751 * Device ID: 15b3:1013
752 * Firmware version: 12.21.1000 and above
754 * Mellanox(R) ConnectX(R)-4 40G MCX4131A-BCAT/MCX413A-BCAT (1x40G)
756 * Host interface: PCI Express 3.0 x8
757 * Device ID: 15b3:1013
758 * Firmware version: 12.21.1000 and above
760 * Mellanox(R) ConnectX(R)-4 40G MCX415A-BCAT (1x40G)
762 * Host interface: PCI Express 3.0 x16
763 * Device ID: 15b3:1013
764 * Firmware version: 12.21.1000 and above
766 * Mellanox(R) ConnectX(R)-4 50G MCX4131A-GCAT/MCX413A-GCAT (1x50G)
768 * Host interface: PCI Express 3.0 x8
769 * Device ID: 15b3:1013
770 * Firmware version: 12.21.1000 and above
772 * Mellanox(R) ConnectX(R)-4 50G MCX414A-BCAT (2x50G)
774 * Host interface: PCI Express 3.0 x8
775 * Device ID: 15b3:1013
776 * Firmware version: 12.21.1000 and above
778 * Mellanox(R) ConnectX(R)-4 50G MCX415A-GCAT/MCX416A-BCAT/MCX416A-GCAT (2x50G)
780 * Host interface: PCI Express 3.0 x16
781 * Device ID: 15b3:1013
782 * Firmware version: 12.21.1000 and above
783 * Firmware version: 12.21.1000 and above
785 * Mellanox(R) ConnectX(R)-4 50G MCX415A-CCAT (1x100G)
787 * Host interface: PCI Express 3.0 x16
788 * Device ID: 15b3:1013
789 * Firmware version: 12.21.1000 and above
791 * Mellanox(R) ConnectX(R)-4 100G MCX416A-CCAT (2x100G)
793 * Host interface: PCI Express 3.0 x16
794 * Device ID: 15b3:1013
795 * Firmware version: 12.21.1000 and above
797 * Mellanox(R) ConnectX(R)-4 Lx 10G MCX4121A-XCAT (2x10G)
799 * Host interface: PCI Express 3.0 x8
800 * Device ID: 15b3:1015
801 * Firmware version: 14.21.1000 and above
803 * Mellanox(R) ConnectX(R)-4 Lx 25G MCX4121A-ACAT (2x25G)
805 * Host interface: PCI Express 3.0 x8
806 * Device ID: 15b3:1015
807 * Firmware version: 14.21.1000 and above
809 * Mellanox(R) ConnectX(R)-5 100G MCX556A-ECAT (2x100G)
811 * Host interface: PCI Express 3.0 x16
812 * Device ID: 15b3:1017
813 * Firmware version: 16.21.1000 and above
815 * Mellanox(R) ConnectX-5 Ex EN 100G MCX516A-CDAT (2x100G)
817 * Host interface: PCI Express 4.0 x16
818 * Device ID: 15b3:1019
819 * Firmware version: 16.21.1000 and above
821 * ARM platforms with Mellanox(R) NICs combinations
825 * Qualcomm ARM 1.1 2500MHz
829 * Red Hat Enterprise Linux Server release 7.5 (Maipo)
833 * Mellanox(R) ConnectX(R)-4 Lx 25G MCX4121A-ACAT (2x25G)
835 * Host interface: PCI Express 3.0 x8
836 * Device ID: 15b3:1015
837 * Firmware version: 14.22.0428
839 * Mellanox(R) ConnectX(R)-5 100G MCX556A-ECAT (2x100G)
841 * Host interface: PCI Express 3.0 x16
842 * Device ID: 15b3:1017
843 * Firmware version: 16.22.0428
845 * ARM SoC combinations from Cavium (with integrated NICs)
854 * Ubuntu 16.04.2 LTS with Cavium SDK-6.2.0-Patch2 release support package.
856 * ARM SoC combinations from NXP (with integrated NICs)
860 * NXP/Freescale QorIQ LS1046A with ARM Cortex A72
861 * NXP/Freescale QorIQ LS2088A with ARM Cortex A72
865 * Ubuntu 16.04.3 LTS with NXP QorIQ LSDK 1803 support packages