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 * **Reworked memory subsystem.**
46 Memory subsystem has been reworked to support new functionality.
48 On Linux, support for reserving/unreserving hugepage memory at runtime was
49 added, so applications no longer need to pre-reserve memory at startup. Due to
50 reorganized internal workings of memory subsystem, any memory allocated
51 through ``rte_malloc()`` or ``rte_memzone_reserve()`` is no longer guaranteed
52 to be IOVA-contiguous.
54 This functionality has introduced the following changes:
56 * ``rte_eal_get_physmem_layout()`` was removed
57 * A new flag for memzone reservation (``RTE_MEMZONE_IOVA_CONTIG``) was added
58 to ensure reserved memory will be IOVA-contiguous, for use with device
59 drivers and other cases requiring such memory
60 * New callbacks for memory allocation/deallocation events, allowing user (or
61 drivers) to be notified of new memory being allocated or deallocated
62 * New callbacks for validating memory allocations above specified limit,
63 allowing user to permit or deny memory allocations
64 * A new command-line switch ``--legacy-mem`` to enable EAL behavior similar to
65 how older versions of DPDK worked (memory segments that are IOVA-contiguous,
66 but hugepages are reserved at startup only, and can never be released)
67 * A new command-line switch ``--single-file-segments`` to put all memory
68 segments within a segment list in a single file
69 * A set of convenience function calls to look up and iterate over allocated
71 * ``-m`` and ``--socket-mem`` command-line arguments now carry an additional
72 meaning and mark pre-reserved hugepages as "unfree-able", thereby acting as
73 a mechanism guaranteeing minimum availability of hugepage memory to the
76 Reserving/unreserving memory at runtime is not currently supported on FreeBSD.
78 * **Added bucket mempool driver.**
80 Added bucket mempool driver which provides a way to allocate contiguous
82 Number of objects in the block depends on how many objects fit in
83 RTE_DRIVER_MEMPOOL_BUCKET_SIZE_KB memory chunk which is build time option.
84 The number may be obtained using rte_mempool_ops_get_info() API.
85 Contiguous blocks may be allocated using rte_mempool_get_contig_blocks() API.
87 * **Added PMD-recommended Tx and Rx parameters**
89 Applications can now query drivers for device-tuned values of
90 ring sizes, burst sizes, and number of queues.
92 * **Added RSS hash and key update to CXGBE PMD.**
94 Support to update RSS hash and key has been added to CXGBE PMD.
96 * **Added CXGBE VF PMD.**
98 CXGBE VF Poll Mode Driver has been added to run DPDK over Chelsio
99 T5/T6 NIC VF instances.
101 * **Updated mlx5 driver.**
103 Updated the mlx5 driver including the following changes:
105 * Introduced Multi-packet Rx. With it, achieved 100Gb/sec with 64B frames.
106 * Supported to be run by non-root users given reduced set of capabilities
107 CAP_NET_ADMIN, CAP_NET_RAW and CAP_IPC_LOCK.
108 * Supported TSO and checksum for generic UDP and IP tunnels.
109 * Supported inner checksum and RSS for GRE, VXLAN-GPE, MPLSoGRE
110 and MPLSoUDP tunnels.
111 * Accommodate to the new memory hotplug model.
112 * Supported non virtually contiguous mempools.
113 * Supported MAC adding along with allmulti and promiscuous modes from VF.
114 * Supported Mellanox BlueField SoC device.
115 * Supported PMD defaults for queue number and depth to improve the out
116 of the box performance.
118 * **Updated mlx4 driver.**
120 Updated the mlx4 driver including the following changes:
122 * Supported to be run by non-root users given reduced set of capabilities
123 CAP_NET_ADMIN, CAP_NET_RAW and CAP_IPC_LOCK.
124 * Supported CRC strip toggling.
125 * Accommodate to the new memory hotplug model.
126 * Supported non virtually contiguous mempools.
127 * Dropped support in Mellanox OFED 4.2.
129 * **Updated Solarflare network PMD.**
131 Updated the sfc_efx driver including the following changes:
133 * Added support for Solarflare XtremeScale X2xxx family adapters.
134 * Added support for NVGRE, VXLAN and GENEVE filters in flow API.
135 * Added support for DROP action in flow API.
136 * Added support for equal stride super-buffer Rx mode (X2xxx only).
137 * Added support for MARK and FLAG actions in flow API (X2xxx only).
139 * **Added Ethernet poll mode driver for AMD XGBE devices.**
141 Added the new ``axgbe`` ethernet poll mode driver for AMD XGBE devices.
142 See the :doc:`../nics/axgbe` nic driver guide for more details on this
145 * **Updated szedata2 PMD.**
147 Added support for new NFB-200G2QL card.
148 New API was introduced in the libsze2 library which the szedata2 PMD depends
149 on thus the new version of the library was needed.
150 New versions of the packages are available and the minimum required version
153 * **Added support for Broadcom NetXtreme-S (BCM58800) family of controllers (aka Stingray)**
155 The BCM58800 devices feature a NetXtreme E-Series advanced network controller, a high-performance
156 ARM CPU block, PCI Express (PCIe) Gen3 interfaces, key accelerators for compute offload and a high-
157 speed memory subsystem including L3 cache and DDR4 interfaces, all interconnected by a coherent
158 Network-on-chip (NOC) fabric.
160 The ARM CPU subsystem features eight ARMv8 Cortex-A72 CPUs at 3.0 GHz, arranged in a multi-cluster
163 * **Added vDPA in vhost-user lib.**
165 Added support for selective datapath in vhost-user lib. vDPA stands for vhost
166 Data Path Acceleration. It supports virtio ring compatible devices to serve
167 virtio driver directly to enable datapath acceleration.
169 * **Added IFCVF vDPA driver.**
171 Added IFCVF vDPA driver to support Intel FPGA 100G VF device. IFCVF works
172 as a HW vhost data path accelerator, it supports live migration and is
173 compatible with virtio 0.95 and 1.0. This driver registers ifcvf vDPA driver
174 to vhost lib, when virtio connected, with the help of the registered vDPA
175 driver the assigned VF gets configured to Rx/Tx directly to VM's virtio
178 * **Added support for vhost dequeue interrupt mode.**
180 Added support for vhost dequeue interrupt mode to release cpus to others when
181 no data to transmit. Applications could register an epoll event fd to associate
182 Rx queues with interrupt vectors.
184 * **Added support for virtio-user server mode.**
185 In a container environment if the vhost-user backend restarts, there's no way
186 for it to reconnect to virtio-user. To address this, support for server mode
187 is added. In this mode the socket file is created by virtio-user, which the
188 backend connects to. This means that if the backend restarts, it can reconnect
189 to virtio-user and continue communications.
191 * **Added crypto workload support to vhost library.**
193 New APIs are introduced in vhost library to enable virtio crypto support
194 including session creation/deletion handling and translating virtio-crypto
195 request into DPDK crypto operations. A sample application is also introduced.
197 * **Added virtio crypto PMD.**
199 Added a new poll mode driver for virtio crypto devices, which provides
200 AES-CBC ciphering and AES-CBC with HMAC-SHA1 algorithm-chaining. See the
201 :doc:`../cryptodevs/virtio` crypto driver guide for more details on
204 * **Added AMD CCP Crypto PMD.**
206 Added the new ``ccp`` crypto driver for AMD CCP devices. See the
207 :doc:`../cryptodevs/ccp` crypto driver guide for more details on
210 * **Updated AESNI MB PMD.**
212 The AESNI MB PMD has been updated with additional support for:
214 * AES-CMAC (128-bit key).
216 * **Added Compressdev Library, a generic compression service library.**
218 The compressdev library provides an API for offload of compression and
219 decompression operations to hardware or software accelerator devices.
221 * **Added a new compression poll mode driver using Intels ISA-L.**
223 Added the new ``ISA-L`` compression driver, for compression and decompression
224 operations in software. See the :doc:`../compressdevs/isal` compression driver
225 guide for details on this new driver.
227 * **Added the Event Timer Adapter Library.**
229 The Event Timer Adapter Library extends the event-based model by introducing
230 APIs that allow applications to arm/cancel event timers that generate
231 timer expiry events. This new type of event is scheduled by an event device
232 along with existing types of events.
234 * **Added OcteonTx TIM Driver (Event timer adapter).**
236 The OcteonTx Timer block enables software to schedule events for a future
237 time, it is exposed to an application via Event timer adapter library.
239 See the :doc:`../eventdevs/octeontx` guide for more details
241 * **Added Event Crypto Adapter Library.**
243 Added the Event Crypto Adapter Library. This library extends the
244 event-based model by introducing APIs that allow applications to
245 enqueue/dequeue crypto operations to/from cryptodev as events scheduled
248 * **Added Ifpga Bus, a generic Intel FPGA Bus library.**
250 The Ifpga Bus library provides support for integrating any Intel FPGA device with
251 the DPDK framework. It provides Intel FPGA Partial Bit Stream AFU (Accelerated
252 Function Unit) scan and drivers probe.
254 * **Added IFPGA (Intel FPGA) Rawdev Driver.**
256 Added a new Rawdev driver called IFPGA(Intel FPGA) Rawdev Driver, which cooperates
257 with OPAE (Open Programmable Acceleration Engine) share code provides common FPGA
258 management ops for FPGA operation.
260 See the :doc:`../rawdevs/ifpga_rawdev` programmer's guide for more details.
262 * **Added DPAA2 QDMA Driver (in rawdev).**
264 The DPAA2 QDMA is an implementation of the rawdev API, that provide means
265 to initiate a DMA transaction from CPU. The initiated DMA is performed
266 without CPU being involved in the actual DMA transaction.
268 See the :doc:`../rawdevs/dpaa2_qdma` guide for more details.
270 * **Added DPAA2 Command Interface Driver (in rawdev).**
272 The DPAA2 CMDIF is an implementation of the rawdev API, that provides
273 communication between the GPP and NXP's QorIQ based AIOP Block (Firmware).
274 Advanced IO Processor i.e. AIOP is clusters of programmable RISC engines
275 optimised for flexible networking and I/O operations. The communication
276 between GPP and AIOP is achieved via using DPCI devices exposed by MC for
277 GPP <--> AIOP interaction.
279 See the :doc:`../rawdevs/dpaa2_cmdif` guide for more details.
281 * **Added device event monitor framework.**
283 Added a general device event monitor framework at EAL, for device dynamic management.
284 Such as device hotplug awareness and actions adopted accordingly. The list of new APIs:
286 * ``rte_dev_event_monitor_start`` and ``rte_dev_event_monitor_stop`` are for
287 the event monitor enable and disable.
288 * ``rte_dev_event_callback_register`` and ``rte_dev_event_callback_unregister``
289 are for the user's callbacks register and unregister.
291 Linux uevent is supported as backend of this device event notification framework.
293 * **Added support for procinfo and pdump on eth vdev.**
295 For ethernet virtual devices (like tap, pcap, etc), with this feature, we can get
296 stats/xstats on shared memory from secondary process, and also pdump packets on
297 those virtual devices.
299 * **Added the BPF Library.**
301 The BPF Library provides the ability to load and execute
302 Enhanced Berkeley Packet Filter (eBPF) within user-space dpdk application.
303 Also it introduces basic framework to load/unload BPF-based filters
304 on eth devices (right now only via SW RX/TX callbacks).
305 It also adds dependency on libelf.
311 .. This section should contain API changes. Sample format:
313 * Add a short 1-2 sentence description of the API change. Use fixed width
314 quotes for ``rte_function_names`` or ``rte_struct_names``. Use the past
317 This section is a comment. Do not overwrite or remove it.
318 Also, make sure to start the actual text at the margin.
319 =========================================================
321 * service cores: no longer marked as experimental.
323 The service cores functions are no longer marked as experimental, and have
324 become part of the normal DPDK API and ABI. Any future ABI changes will be
325 announced at least one release before the ABI change is made. There are no
326 ABI breaking changes planned.
328 * eal: ``rte_lcore_has_role()`` return value changed.
330 This function now returns true or false, respectively,
331 rather than 0 or <0 for success or failure.
332 It makes use of the function more intuitive.
334 * mempool: capability flags and related functions have been removed.
336 Flags ``MEMPOOL_F_CAPA_PHYS_CONTIG`` and
337 ``MEMPOOL_F_CAPA_BLK_ALIGNED_OBJECTS`` were used by octeontx mempool
338 driver to customize generic mempool library behaviour.
339 Now the new driver callbacks ``calc_mem_size`` and ``populate`` may be
340 used to achieve it without specific knowledge in the generic code.
342 * mempool: xmem functions have been deprecated:
344 - ``rte_mempool_xmem_create``
345 - ``rte_mempool_xmem_size``
346 - ``rte_mempool_xmem_usage``
347 - ``rte_mempool_populate_iova_tab``
349 * mbuf: The control mbuf API has been removed in v18.05. The impacted
350 functions and macros are:
352 - ``rte_ctrlmbuf_init()``
353 - ``rte_ctrlmbuf_alloc()``
354 - ``rte_ctrlmbuf_free()``
355 - ``rte_ctrlmbuf_data()``
356 - ``rte_ctrlmbuf_len()``
357 - ``rte_is_ctrlmbuf()``
360 The packet mbuf API should be used as a replacement.
362 * meter: updated to accommodate configuration profiles.
364 The meter API is changed to support meter configuration profiles. The
365 configuration profile represents the set of configuration parameters
366 for a given meter object, such as the rates and sizes for the token
367 buckets. These configuration parameters were previously the part of meter
368 object internal data strcuture. The separation of the configuration
369 parameters from meter object data structure results in reducing its
370 memory footprint which helps in better cache utilization when large number
371 of meter objects are used.
373 * ethdev: The function ``rte_eth_dev_count``, often mis-used to iterate
374 over ports, is deprecated and replaced by ``rte_eth_dev_count_avail``.
375 There is also a new function ``rte_eth_dev_count_total`` to get the
376 total number of allocated ports, available or not.
377 The hotplug-proof applications should use ``RTE_ETH_FOREACH_DEV`` or
378 ``RTE_ETH_FOREACH_DEV_OWNED_BY`` as port iterators.
380 * ethdev, in struct ``struct rte_eth_dev_info``, field ``rte_pci_device *pci_dev``
381 replaced with field ``struct rte_device *device``.
383 * **Changes to semantics of rte_eth_dev_configure() parameters.**
385 If both the ``nb_rx_q`` and ``nb_tx_q`` parameters are zero,
386 ``rte_eth_dev_configure`` will now use PMD-recommended queue sizes, or if
387 recommendations are not provided by the PMD the function will use ethdev
388 fall-back values. Previously setting both of the parameters to zero would
389 have resulted in ``-EINVAL`` being returned.
391 * **Changes to semantics of rte_eth_rx_queue_setup() parameters.**
393 If the ``nb_rx_desc`` parameter is zero, ``rte_eth_rx_queue_setup`` will
394 now use the PMD-recommended Rx ring size, or in the case where the PMD
395 does not provide a recommendation, will use an ethdev-provided
396 fall-back value. Previously, setting ``nb_rx_desc`` to zero would have
397 resulted in an error.
399 * **Changes to semantics of rte_eth_tx_queue_setup() parameters.**
401 If the ``nb_tx_desc`` parameter is zero, ``rte_eth_tx_queue_setup`` will
402 now use the PMD-recommended Tx ring size, or in the case where the PMD
403 does not provide a recoomendation, will use an ethdev-provided
404 fall-back value. Previously, setting ``nb_tx_desc`` to zero would have
405 resulted in an error.
407 * ethdev: several changes were made to the flow API.
409 * Unused DUP action was removed.
410 * Actions semantics in flow rules: list order now matters ("first
411 to last" instead of "all simultaneously"), repeated actions are now
412 all performed, and they do not individually have (non-)terminating
414 * Flow rules are now always terminating unless a PASSTHRU action is
416 * C99-style flexible arrays were replaced with standard pointers in RSS
417 action and in RAW pattern item structures due to compatibility issues.
418 * The RSS action was modified to not rely on external
419 ``struct rte_eth_rss_conf`` anymore to instead expose its own and more
420 appropriately named configuration fields directly
421 (``rss_conf->rss_key`` => ``key``,
422 ``rss_conf->rss_key_len`` => ``key_len``,
423 ``rss_conf->rss_hf`` => ``types``,
424 ``num`` => ``queue_num``), and the addition of missing RSS parameters
425 (``func`` for RSS hash function to apply and ``level`` for the
426 encapsulation level).
427 * The VLAN pattern item (``struct rte_flow_item_vlan``) was modified to
428 include inner EtherType instead of outer TPID. Its default mask was also
429 modified to cover the VID part (lower 12 bits) of TCI only.
430 * A new transfer attribute was added to ``struct rte_flow_attr`` in order
431 to clarify the behavior of some pattern items.
432 * PF and VF pattern items are now only accepted by PMDs that implement
433 them (bnxt and i40e) when the transfer attribute is also present for
435 * Pattern item PORT was renamed PHY_PORT to avoid confusion with DPDK port
437 * An action counterpart to the PHY_PORT pattern item was added in order to
438 redirect matching traffic to a specific physical port.
439 * PORT_ID pattern item and actions were added to match and target DPDK
440 port IDs at a higher level than PHY_PORT.
442 * ethdev: change flow APIs regarding count action:
443 * ``rte_flow_create()`` API count action now requires the ``struct rte_flow_action_count``.
444 * ``rte_flow_query()`` API parameter changed from action type to action structure.
446 * ethdev: changes to offload API
448 A pure per-port offloading isn't requested to be repeated in [rt]x_conf->offloads to
449 ``rte_eth_[rt]x_queue_setup()``. Now any offloading enabled in ``rte_eth_dev_configure()``
450 can't be disabled by ``rte_eth_[rt]x_queue_setup()``. Any new added offloading which has
451 not been enabled in ``rte_eth_dev_configure()`` and is requested to be enabled in
452 ``rte_eth_[rt]x_queue_setup()`` must be per-queue type, otherwise trigger an error log.
454 * ethdev: runtime queue setup:
456 ``rte_eth_rx_queue_setup`` and ``rte_eth_tx_queue_setup`` can be called after
457 ``rte_eth_dev_start`` if device support runtime queue setup. Device driver can
458 expose this capability through ``rte_eth_dev_info_get``. A Rx or Tx queue be
459 setup at runtime need to be started explicitly by ``rte_eth_dev_rx_queue_start``
460 or ``rte_eth_dev_tx_queue_start``.
466 .. This section should contain ABI changes. Sample format:
468 * Add a short 1-2 sentence description of the ABI change that was announced
469 in the previous releases and made in this release. Use fixed width quotes
470 for ``rte_function_names`` or ``rte_struct_names``. Use the past tense.
472 This section is a comment. Do not overwrite or remove it.
473 Also, make sure to start the actual text at the margin.
474 =========================================================
476 * ring: the alignment constraints on the ring structure has been relaxed
477 to one cache line instead of two, and an empty cache line padding is
478 added between the producer and consumer structures. The size of the
479 structure and the offset of the fields remains the same on platforms
480 with 64B cache line, but change on other platforms.
482 * mempool: ops have changed.
484 A new callback ``calc_mem_size`` has been added to ``rte_mempool_ops``
485 to allow to customize required memory size calculation.
486 A new callback ``populate`` has been added to ``rte_mempool_ops``
487 to allow to customize objects population.
488 Callback ``get_capabilities`` has been removed from ``rte_mempool_ops``
489 since its features are covered by ``calc_mem_size`` and ``populate``
491 Callback ``register_memory_area`` has been removed from ``rte_mempool_ops``
492 since the new callback ``populate`` may be used instead of it.
494 * **Additional fields in rte_eth_dev_info.**
496 The ``rte_eth_dev_info`` structure has had two extra entries appended to the
497 end of it: ``default_rxportconf`` and ``default_txportconf``. Each of these
498 in turn are ``rte_eth_dev_portconf`` structures containing three fields of
499 type ``uint16_t``: ``burst_size``, ``ring_size``, and ``nb_queues``. These
500 are parameter values recommended for use by the PMD.
502 * ethdev: ABI for all flow API functions was updated.
504 This includes functions ``rte_flow_copy``, ``rte_flow_create``,
505 ``rte_flow_destroy``, ``rte_flow_error_set``, ``rte_flow_flush``,
506 ``rte_flow_isolate``, ``rte_flow_query`` and ``rte_flow_validate``, due to
507 changes in error type definitions (``enum rte_flow_error_type``), removal
508 of the unused DUP action (``enum rte_flow_action_type``), modified
509 behavior for flow rule actions (see API changes), removal of C99 flexible
510 array from RAW pattern item (``struct rte_flow_item_raw``), complete
511 rework of the RSS action definition (``struct rte_flow_action_rss``),
512 sanity fix in the VLAN pattern item (``struct rte_flow_item_vlan``) and
513 new transfer attribute (``struct rte_flow_attr``).
515 **New parameter added to rte_bbdev_op_cap_turbo_dec.**
517 A new parameter ``max_llr_modulus`` has been added to
518 ``rte_bbdev_op_cap_turbo_dec`` structure to specify maximal LLR (likelihood
519 ratio) absolute value.
521 * **BBdev Queue Groups split into UL/DL Groups**
523 Queue Groups have been split into UL/DL Groups in Turbo Software Driver.
524 They are independent for Decode/Encode. ``rte_bbdev_driver_info`` reflects
531 .. This section should contain removed items in this release. Sample format:
533 * Add a short 1-2 sentence description of the removed item in the past
536 This section is a comment. Do not overwrite or remove it.
537 Also, make sure to start the actual text at the margin.
538 =========================================================
544 .. This section should contain new known issues in this release. Sample format:
546 * **Add title in present tense with full stop.**
548 Add a short 1-2 sentence description of the known issue in the present
549 tense. Add information on any known workarounds.
551 This section is a comment. Do not overwrite or remove it.
552 Also, make sure to start the actual text at the margin.
553 =========================================================
555 * **pdump is not compatible with old applications.**
557 As we changed to use generic multi-process communication for pdump negotiation
558 instead of previous dedicated unix socket way, pdump applications, including
559 dpdk-pdump example and any other applications using librte_pdump, cannot work
560 with older version DPDK primary applications.
563 Shared Library Versions
564 -----------------------
566 .. Update any library version updated in this release and prepend with a ``+``
570 + librte_cfgfile.so.2
573 This section is a comment. Do not overwrite or remove it.
574 =========================================================
577 The libraries prepended with a plus sign were incremented in this version.
583 librte_bitratestats.so.2
586 librte_bus_fslmc.so.1
591 + librte_common_octeontx.so.1
592 + librte_compressdev.so.1
593 librte_cryptodev.so.4
594 librte_distributor.so.1
597 + librte_eventdev.so.4
598 librte_flow_classify.so.1
606 librte_latencystats.so.1
609 + librte_mempool.so.4
619 librte_pmd_ixgbe.so.2
620 + librte_pmd_dpaa2_cmdif.so.1
621 + librte_pmd_dpaa2_qdma.so.1
623 librte_pmd_softnic.so.1
624 librte_pmd_vhost.so.2
640 .. This section should contain a list of platforms that were tested with this
645 * <vendor> platform with <vendor> <type of devices> combinations
650 * Other relevant details...
652 This section is a comment. Do not overwrite or remove it.
653 Also, make sure to start the actual text at the margin.
654 =========================================================
656 * Intel(R) platforms with Intel(R) NICs combinations
660 * Intel(R) Atom(TM) CPU C2758 @ 2.40GHz
661 * Intel(R) Xeon(R) CPU D-1541 @ 2.10GHz
662 * Intel(R) Xeon(R) CPU E5-4667 v3 @ 2.00GHz
663 * Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz
664 * Intel(R) Xeon(R) CPU E5-2699 v4 @ 2.20GHz
665 * Intel(R) Xeon(R) CPU E5-2695 v4 @ 2.10GHz
666 * Intel(R) Xeon(R) CPU E5-2658 v2 @ 2.40GHz
667 * Intel(R) Xeon(R) CPU E5-2658 v3 @ 2.20GHz
668 * Intel(R) Xeon(R) Platinum 8180 CPU @ 2.50GHz
677 * Red Hat Enterprise Linux Server release 7.3
678 * SUSE Enterprise Linux 12
687 * Intel(R) 82599ES 10 Gigabit Ethernet Controller
689 * Firmware version: 0x61bf0001
690 * Device id (pf/vf): 8086:10fb / 8086:10ed
691 * Driver version: 5.2.3 (ixgbe)
693 * Intel(R) Corporation Ethernet Connection X552/X557-AT 10GBASE-T
695 * Firmware version: 0x800003e7
696 * Device id (pf/vf): 8086:15ad / 8086:15a8
697 * Driver version: 4.4.6 (ixgbe)
699 * Intel(R) Ethernet Converged Network Adapter X710-DA4 (4x10G)
701 * Firmware version: 6.01 0x80003221
702 * Device id (pf/vf): 8086:1572 / 8086:154c
703 * Driver version: 2.4.6 (i40e)
705 * Intel Corporation Ethernet Connection X722 for 10GbE SFP+ (4x10G)
707 * Firmware version: 3.33 0x80000fd5 0.0.0
708 * Device id (pf/vf): 8086:37d0 / 8086:37cd
709 * Driver version: 2.4.3 (i40e)
711 * Intel(R) Ethernet Converged Network Adapter XXV710-DA2 (2x25G)
713 * Firmware version: 6.01 0x80003221
714 * Device id (pf/vf): 8086:158b / 8086:154c
715 * Driver version: 2.4.6 (i40e)
717 * Intel(R) Ethernet Converged Network Adapter XL710-QDA2 (2X40G)
719 * Firmware version: 6.01 0x8000321c
720 * Device id (pf/vf): 8086:1583 / 8086:154c
721 * Driver version: 2.4.6 (i40e)
723 * Intel(R) Corporation I350 Gigabit Network Connection
725 * Firmware version: 1.63, 0x80000dda
726 * Device id (pf/vf): 8086:1521 / 8086:1520
727 * Driver version: 5.4.0-k (igb)
729 * Intel(R) platforms with Mellanox(R) NICs combinations
733 * Intel(R) Xeon(R) Gold 6154 CPU @ 3.00GHz
734 * Intel(R) Xeon(R) CPU E5-2697A v4 @ 2.60GHz
735 * Intel(R) Xeon(R) CPU E5-2697 v3 @ 2.60GHz
736 * Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz
737 * Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20GHz
738 * Intel(R) Xeon(R) CPU E5-2640 @ 2.50GHz
739 * Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
743 * Red Hat Enterprise Linux Server release 7.5 (Maipo)
744 * Red Hat Enterprise Linux Server release 7.4 (Maipo)
745 * Red Hat Enterprise Linux Server release 7.3 (Maipo)
746 * Red Hat Enterprise Linux Server release 7.2 (Maipo)
751 * SUSE Linux Enterprise Server 15
753 * MLNX_OFED: 4.2-1.0.0.0
754 * MLNX_OFED: 4.3-2.0.2.0
758 * Mellanox(R) ConnectX(R)-3 Pro 40G MCX354A-FCC_Ax (2x40G)
760 * Host interface: PCI Express 3.0 x8
761 * Device ID: 15b3:1007
762 * Firmware version: 2.42.5000
764 * Mellanox(R) ConnectX(R)-4 10G MCX4111A-XCAT (1x10G)
766 * Host interface: PCI Express 3.0 x8
767 * Device ID: 15b3:1013
768 * Firmware version: 12.21.1000 and above
770 * Mellanox(R) ConnectX(R)-4 10G MCX4121A-XCAT (2x10G)
772 * Host interface: PCI Express 3.0 x8
773 * Device ID: 15b3:1013
774 * Firmware version: 12.21.1000 and above
776 * Mellanox(R) ConnectX(R)-4 25G MCX4111A-ACAT (1x25G)
778 * Host interface: PCI Express 3.0 x8
779 * Device ID: 15b3:1013
780 * Firmware version: 12.21.1000 and above
782 * Mellanox(R) ConnectX(R)-4 25G MCX4121A-ACAT (2x25G)
784 * Host interface: PCI Express 3.0 x8
785 * Device ID: 15b3:1013
786 * Firmware version: 12.21.1000 and above
788 * Mellanox(R) ConnectX(R)-4 40G MCX4131A-BCAT/MCX413A-BCAT (1x40G)
790 * Host interface: PCI Express 3.0 x8
791 * Device ID: 15b3:1013
792 * Firmware version: 12.21.1000 and above
794 * Mellanox(R) ConnectX(R)-4 40G MCX415A-BCAT (1x40G)
796 * Host interface: PCI Express 3.0 x16
797 * Device ID: 15b3:1013
798 * Firmware version: 12.21.1000 and above
800 * Mellanox(R) ConnectX(R)-4 50G MCX4131A-GCAT/MCX413A-GCAT (1x50G)
802 * Host interface: PCI Express 3.0 x8
803 * Device ID: 15b3:1013
804 * Firmware version: 12.21.1000 and above
806 * Mellanox(R) ConnectX(R)-4 50G MCX414A-BCAT (2x50G)
808 * Host interface: PCI Express 3.0 x8
809 * Device ID: 15b3:1013
810 * Firmware version: 12.21.1000 and above
812 * Mellanox(R) ConnectX(R)-4 50G MCX415A-GCAT/MCX416A-BCAT/MCX416A-GCAT (2x50G)
814 * Host interface: PCI Express 3.0 x16
815 * Device ID: 15b3:1013
816 * Firmware version: 12.21.1000 and above
817 * Firmware version: 12.21.1000 and above
819 * Mellanox(R) ConnectX(R)-4 50G MCX415A-CCAT (1x100G)
821 * Host interface: PCI Express 3.0 x16
822 * Device ID: 15b3:1013
823 * Firmware version: 12.21.1000 and above
825 * Mellanox(R) ConnectX(R)-4 100G MCX416A-CCAT (2x100G)
827 * Host interface: PCI Express 3.0 x16
828 * Device ID: 15b3:1013
829 * Firmware version: 12.21.1000 and above
831 * Mellanox(R) ConnectX(R)-4 Lx 10G MCX4121A-XCAT (2x10G)
833 * Host interface: PCI Express 3.0 x8
834 * Device ID: 15b3:1015
835 * Firmware version: 14.21.1000 and above
837 * Mellanox(R) ConnectX(R)-4 Lx 25G MCX4121A-ACAT (2x25G)
839 * Host interface: PCI Express 3.0 x8
840 * Device ID: 15b3:1015
841 * Firmware version: 14.21.1000 and above
843 * Mellanox(R) ConnectX(R)-5 100G MCX556A-ECAT (2x100G)
845 * Host interface: PCI Express 3.0 x16
846 * Device ID: 15b3:1017
847 * Firmware version: 16.21.1000 and above
849 * Mellanox(R) ConnectX-5 Ex EN 100G MCX516A-CDAT (2x100G)
851 * Host interface: PCI Express 4.0 x16
852 * Device ID: 15b3:1019
853 * Firmware version: 16.21.1000 and above
855 * ARM platforms with Mellanox(R) NICs combinations
859 * Qualcomm ARM 1.1 2500MHz
863 * Red Hat Enterprise Linux Server release 7.5 (Maipo)
867 * Mellanox(R) ConnectX(R)-4 Lx 25G MCX4121A-ACAT (2x25G)
869 * Host interface: PCI Express 3.0 x8
870 * Device ID: 15b3:1015
871 * Firmware version: 14.22.0428
873 * Mellanox(R) ConnectX(R)-5 100G MCX556A-ECAT (2x100G)
875 * Host interface: PCI Express 3.0 x16
876 * Device ID: 15b3:1017
877 * Firmware version: 16.22.0428
879 * ARM SoC combinations from Cavium (with integrated NICs)
888 * Ubuntu 16.04.2 LTS with Cavium SDK-6.2.0-Patch2 release support package.
890 * ARM SoC combinations from NXP (with integrated NICs)
894 * NXP/Freescale QorIQ LS1046A with ARM Cortex A72
895 * NXP/Freescale QorIQ LS2088A with ARM Cortex A72
899 * Ubuntu 16.04.3 LTS with NXP QorIQ LSDK 1803 support packages