1 .. SPDX-License-Identifier: BSD-3-Clause
2 Copyright 2017 The DPDK contributors
7 .. **Read this first.**
9 The text in the sections below explains how to update the release notes.
11 Use proper spelling, capitalization and punctuation in all sections.
13 Variable and config names should be quoted as fixed width text:
16 Build the docs and view the output file to ensure the changes are correct::
20 xdg-open build/doc/html/guides/rel_notes/release_17_11.html
26 .. This section should contain new features added in this release. Sample
29 * **Add a title in the past tense with a full stop.**
31 Add a short 1-2 sentence description in the past tense. The description
32 should be enough to allow someone scanning the release notes to
33 understand the new feature.
35 If the feature adds a lot of sub-features you can use a bullet list like
38 * Added feature foo to do something.
39 * Enhanced feature bar to do something else.
41 Refer to the previous release notes for examples.
43 This section is a comment. do not overwrite or remove it.
44 Also, make sure to start the actual text at the margin.
45 =========================================================
47 * **Extended port_id range from uint8_t to uint16_t.**
49 Increased the ``port_id`` range from 8 bits to 16 bits in order to support
50 more than 256 ports in DPDK. All ethdev APIs which have ``port_id`` as
51 parameter have been changed.
53 * **Modified the return type of rte_eth_stats_reset.**
55 Changed return type of ``rte_eth_stats_reset`` from ``void`` to ``int`` so
56 that the caller can determine whether a device supports the operation or not
57 and if the operation was carried out.
59 * **Added a new driver for Marvell Armada 7k/8k devices.**
61 Added the new ``mrvl`` net driver for Marvell Armada 7k/8k devices. See the
62 :doc:`../nics/mvpp2` NIC guide for more details on this new driver.
64 * **Updated mlx4 driver.**
66 Updated the mlx4 driver including the following changes:
68 * Isolated mode (rte_flow) can now be enabled anytime, not only during
69 initial device configuration.
70 * Flow rules now support up to 4096 priority levels usable at will by
72 * Enhanced error message to help debugging invalid/unsupported flow rules.
73 * Flow rules matching all multicast and promiscuous traffic are now allowed.
74 * No more software restrictions on flow rules with the RSS action, their
75 configuration is much more flexible.
76 * Significantly reduced memory footprint for Rx and Tx queue objects.
77 * While supported, UDP RSS is temporarily disabled due to a remaining issue
78 with its support in the Linux kernel.
79 * The new RSS implementation does not automatically spread traffic according
80 to the inner packet of VXLAN frames anymore, only the outer one (like
82 * Partial (Tx only) support for secondary processes was broken and had to be
84 * Refactored driver to get rid of dependency on the components provided by
85 Mellanox OFED and instead rely on the current and public rdma-core
86 package and Linux version from now on.
87 * Removed compile-time limitation on number of device instances the PMD
90 * **Updated mlx5 driver.**
92 Updated the mlx5 driver including the following changes:
94 * Enabled the PMD to run on top of upstream Linux kernel and rdma-core
95 libs, removing the dependency on specific Mellanox OFED libraries.
96 * Improved PMD latency performance.
97 * Improved PMD memory footprint.
98 * Added support for vectorized Rx/Tx burst for ARMv8.
99 * Added support for secondary process.
100 * Added support for flow counters.
101 * Added support for Rx hardware timestamp offload.
102 * Added support for device removal event.
104 * **Added SoftNIC PMD.**
106 Added a new SoftNIC PMD. This virtual device provides applications with
107 software fallback support for traffic management.
109 * **Added support for NXP DPAA Devices.**
111 Added support for NXP's DPAA devices - LS104x series. This includes:
114 * DPAA Mempool driver for supporting offloaded packet memory pool
115 * DPAA PMD for DPAA devices
117 See the :doc:`../nics/dpaa` document for more details of this new driver.
119 * **Updated support for Cavium OCTEONTX Device.**
121 Updated support for Cavium's OCTEONTX device (CN83xx). This includes:
123 * OCTEONTX Mempool driver for supporting offloaded packet memory pool
124 * OCTEONTX Ethdev PMD
125 * OCTEONTX Eventdev-Ethdev Rx adapter
127 See the :doc:`../nics/octeontx` document for more details of this new driver.
129 * **Added PF support to the Netronome NFP PMD.**
131 Added PF support to the Netronome NFP PMD. Previously the NFP PMD only
132 supported VFs. PF support is just as a basic DPDK port and has no VF
135 PF support comes with firmware upload support which allows the PMD to
136 independently work from kernel netdev NFP drivers.
138 NFP 4000 devices are also now supported along with previous 6000 devices.
140 * **Updated bnxt PMD.**
142 Major enhancements include:
144 * Support for Flow API
145 * Support for Tx and Rx descriptor status functions
147 * **Added bus agnostic functions to cryptodev for PMD initialization**
149 Added new PMD assist, bus independent, functions
150 ``rte_cryptodev_pmd_parse_input_args()``, ``rte_cryptodev_pmd_create()`` and
151 ``rte_cryptodev_pmd_destroy()`` for drivers to manage creation and
152 destruction of new device instances.
154 * **Updated QAT crypto PMD.**
156 Added several performance enhancements:
158 * Removed atomics from the internal queue pair structure.
159 * Added coalesce writes to HEAD CSR on response processing.
160 * Added coalesce writes to TAIL CSR on request processing.
162 In addition support was added for the AES CCM algorithm.
164 * **Updated the AESNI MB PMD.**
166 The AESNI MB PMD has been updated with additional support for:
168 * The DES CBC algorithm.
169 * The DES DOCSIS BPI algorithm.
171 This change requires version 0.47 of the IPsec Multi-buffer library. For
172 more details see the :doc:`../cryptodevs/aesni_mb` documentation.
174 * **Updated the OpenSSL PMD.**
176 The OpenSSL PMD has been updated with additional support for:
178 * The DES CBC algorithm.
179 * The AES CCM algorithm.
181 * **Added NXP DPAA SEC crypto PMD.**
183 A new ``dpaa_sec`` hardware based crypto PMD for NXP DPAA devices has been
184 added. See the :doc:`../cryptodevs/dpaa_sec` document for more details.
186 * **Added MRVL crypto PMD.**
188 A new crypto PMD has been added, which provides several ciphering and hashing
189 algorithms. All cryptography operations use the MUSDK library crypto API.
190 See the :doc:`../cryptodevs/mvsam` document for more details.
192 * **Add new benchmarking mode to dpdk-test-crypto-perf application.**
194 Added a new "PMD cyclecount" benchmark mode to the ``dpdk-test-crypto-perf``
195 application to display a detailed breakdown of CPU cycles used by hardware
198 * **Added the Security Offload Library.**
200 Added an experimental library - ``rte_security``. This provide security APIs
201 for protocols like IPsec using inline ipsec offload to ethernet devices or
202 full protocol offload with lookaside crypto devices.
204 See the :doc:`../prog_guide/rte_security` section of the DPDK Programmers
205 Guide document for more information.
207 * **Updated the DPAA2_SEC crypto driver to support rte_security.**
209 Updated the ``dpaa2_sec`` crypto PMD to support ``rte_security`` lookaside
210 protocol offload for IPsec.
212 * **Updated the IXGBE ethernet driver to support rte_security.**
214 Updated ixgbe ethernet PMD to support ``rte_security`` inline IPsec offload.
216 * **Updated i40e driver to support GTP-C/GTP-U.**
218 Updated i40e PMD to support GTP-C/GTP-U with GTP-C/GTP-U supporting
219 profiles which can be programmed by dynamic device personalization (DDP)
222 * **Added the i40e ethernet driver to support queue region feature.**
224 This feature enable queue regions configuration for RSS in PF,
225 so that different traffic classes or different packet
226 classification types can be separated into different queues in
227 different queue regions.
229 * **Updated ipsec-secgw application to support rte_security.**
231 Updated the ``ipsec-secgw`` sample application to support ``rte_security``
232 actions for ipsec inline and full protocol offload using lookaside crypto
235 * **Added IOMMU support to libvhost-user**
237 Implemented device IOTLB in the Vhost-user backend, and enabled Virtio's
238 IOMMU feature. The feature is disabled by default, and can be enabled by
239 setting ``RTE_VHOST_USER_IOMMU_SUPPORT`` flag at vhost device registration
242 * **Added the Event Ethernet Adapter Library.**
244 Added the Event Ethernet Adapter library. This library provides APIs for
245 eventdev applications to configure the ethdev for eventdev packet flow.
247 * **Updated DPAA2 Event PMD for the Event Ethernet Adapter.**
249 Added support for the eventdev ethernet adapter for DPAA2.
251 * **Added Membership library (rte_member).**
253 Added a new data structure library called the Membership Library.
255 The Membership Library is an extension and generalization of a traditional
256 filter (for example Bloom Filter) structure that has multiple usages in a
257 wide variety of workloads and applications. In general, the Membership
258 Library is a data structure that provides a "set-summary" and responds to
259 set-membership queries whether a certain member belongs to a set(s).
261 The library provides APIs for DPDK applications to insert a new member,
262 delete an existing member, and query the existence of a member in a given
263 set, or a group of sets. For the case of a group of sets the library will
264 return not only whether the element has been inserted in one of the sets but
265 also which set it belongs to.
267 See the :doc:`../prog_guide/member_lib` documentation in the Programmers
268 Guide, for more information.
270 * **Added the Generic Segmentation Offload Library.**
272 Added the Generic Segmentation Offload (GSO) library to enable
273 applications to split large packets (e.g. MTU is 64KB) into small
274 ones (e.g. MTU is 1500B). Supported packet types are:
277 * VxLAN packets, which must have an outer IPv4 header, and contain
278 an inner TCP/IPv4 packet.
279 * GRE packets, which must contain an outer IPv4 header, and inner
282 The GSO library doesn't check if the input packets have correct
283 checksums, and doesn't update checksums for output packets.
284 Additionally, the GSO library doesn't process IP fragmented packets.
286 * **Added the Flow Classification Library.**
288 Added an experimental Flow Classification library to provide APIs for DPDK
289 applications to classify an input packet by matching it against a set of
290 flow rules. It uses the ``librte_table`` API to manage the flow rules.
296 .. This section should contain bug fixes added to the relevant
297 sections. Sample format:
299 * **code/section Fixed issue in the past tense with a full stop.**
301 Add a short 1-2 sentence description of the resolved issue in the past
304 The title should contain the code/lib section like a commit message.
306 Add the entries in alphabetic order in the relevant sections below.
308 This section is a comment. do not overwrite or remove it.
309 Also, make sure to start the actual text at the margin.
310 =========================================================
313 * **Service core fails to call service callback due to atomic lock**
315 In a specific configuration of multi-thread unsafe services and service
316 cores, a service core previously did not correctly release the atomic lock
317 on the service. This would result in the cores polling the service, but it
318 looked like another thread was executing the service callback. The logic for
319 atomic locking of the services has been fixed and refactored for readability.
325 .. This section should contain API changes. Sample format:
327 * Add a short 1-2 sentence description of the API change. Use fixed width
328 quotes for ``rte_function_names`` or ``rte_struct_names``. Use the past
331 This section is a comment. do not overwrite or remove it.
332 Also, make sure to start the actual text at the margin.
333 =========================================================
335 * **Ethdev device name length increased.**
337 The size of internal device name has been increased to 64 characters
338 to allow for storing longer bus specific names.
340 * **Removed the Ethdev RTE_ETH_DEV_DETACHABLE flag.**
342 Removed the Ethdev ``RTE_ETH_DEV_DETACHABLE`` flag. This flag is not
343 required anymore, with the new hotplug implementation. It has been removed
344 from the ether library. Its semantics are now expressed at the bus and PMD
347 * **Service cores API updated for usability**
349 The service cores API has been changed, removing pointers from the API where
350 possible, and instead using integer IDs to identify each service. This
351 simplifies application code, aids debugging, and provides better
352 encapsulation. A summary of the main changes made is as follows:
354 * Services identified by ID not by ``rte_service_spec`` pointer
355 * Reduced API surface by using ``set`` functions instead of enable/disable
356 * Reworked ``rte_service_register`` to provide the service ID to registrar
357 * Reworked start and stop APIs into ``rte_service_runstate_set``
358 * Added API to set runstate of service implementation to indicate readiness
360 * **The following changes have been made in the mempool library**
362 * Moved ``flags`` datatype from ``int`` to ``unsigned int`` for
364 * Removed ``__rte_unused int flag`` param from ``rte_mempool_generic_put``
365 and ``rte_mempool_generic_get`` API.
366 * Added ``flags`` param in ``rte_mempool_xmem_size`` and
367 ``rte_mempool_xmem_usage``.
368 * ``rte_mem_phy2mch`` was used in Xen dom0 to obtain the physical address;
369 remove this API as Xen dom0 support was removed.
371 * **Added IOVA aliases related to physical address handling.**
373 Some data types, structure members and functions related to physical address
374 handling are deprecated and have new aliases with IOVA wording. For example:
376 * ``phys_addr_t`` can be often replaced by ``rte_iova_t`` of same size.
377 * ``RTE_BAD_PHYS_ADDR`` is often replaced by ``RTE_BAD_IOVA`` of same value.
378 * ``rte_memseg.phys_addr`` is aliased with ``rte_memseg.iova_addr``.
379 * ``rte_mem_virt2phy()`` can often be replaced by ``rte_mem_virt2iova``.
380 * ``rte_malloc_virt2phy`` is aliased with ``rte_malloc_virt2iova``.
381 * ``rte_memzone.phys_addr`` is aliased with ``rte_memzone.iova``.
382 * ``rte_mempool_objhdr.physaddr`` is aliased with
383 ``rte_mempool_objhdr.iova``.
384 * ``rte_mempool_memhdr.phys_addr`` is aliased with
385 ``rte_mempool_memhdr.iova``.
386 * ``rte_mempool_virt2phy()`` can be replaced by ``rte_mempool_virt2iova()``.
387 * ``rte_mempool_populate_phys*()`` are aliased with
388 ``rte_mempool_populate_iova*()``
389 * ``rte_mbuf.buf_physaddr`` is aliased with ``rte_mbuf.buf_iova``.
390 * ``rte_mbuf_data_dma_addr*()`` are aliased with ``rte_mbuf_data_iova*()``.
391 * ``rte_pktmbuf_mtophys*`` are aliased with ``rte_pktmbuf_iova*()``.
393 * **PCI bus API moved outside of the EAL**
395 The PCI bus previously implemented within the EAL has been moved.
396 A first part has been added as an RTE library providing PCI helpers to
397 parse device locations or other such utilities.
398 A second part consisting of the actual bus driver has been moved to its
399 proper subdirectory, without changing its functionalities.
401 As such, several PCI-related functions are not exposed by the EAL anymore:
405 * ``rte_pci_ioport_map``
406 * ``rte_pci_ioport_read``
407 * ``rte_pci_ioport_unmap``
408 * ``rte_pci_ioport_write``
409 * ``rte_pci_map_device``
411 * ``rte_pci_probe_one``
412 * ``rte_pci_read_config``
413 * ``rte_pci_register``
415 * ``rte_pci_unmap_device``
416 * ``rte_pci_unregister``
417 * ``rte_pci_write_config``
419 These functions are made available either as part of ``librte_pci`` or
422 * **Moved vdev bus APIs outside of the EAL**
424 Moved the following APIs from ``librte_eal`` to ``librte_bus_vdev``:
427 * ``rte_vdev_register``
428 * ``rte_vdev_uninit``
429 * ``rte_vdev_unregister``
431 * **Add return value to stats_get dev op API**
433 The ``stats_get`` dev op API return value has been changed to be int.
434 In this way PMDs can return an error value in case of failure at stats
435 getting process time.
437 * **Modified the rte_cryptodev_allocate_driver function.**
439 Modified the ``rte_cryptodev_allocate_driver()`` function in the cryptodev
440 library. An extra parameter ``struct cryptodev_driver *crypto_drv`` has been
443 * **Removed virtual device bus specific functions from librte_cryptodev.**
445 The functions ``rte_cryptodev_vdev_parse_init_params()`` and
446 ``rte_cryptodev_vdev_pmd_init()`` have been removed from librte_cryptodev
447 and have been replaced by non bus specific functions
448 ``rte_cryptodev_pmd_parse_input_args()`` and ``rte_cryptodev_pmd_create()``.
450 The ``rte_cryptodev_create_vdev()`` function was removed to avoid the
451 dependency on vdev in librte_cryptodev; instead, users can call
452 ``rte_vdev_init()`` directly.
454 * **Removed PCI device bus specific functions from librte_cryptodev.**
456 The functions ``rte_cryptodev_pci_generic_probe()`` and
457 ``rte_cryptodev_pci_generic_remove()`` have been removed from librte_cryptodev
458 and have been replaced by non bus specific functions
459 ``rte_cryptodev_pmd_create()`` and ``rte_cryptodev_pmd_destroy()``.
461 * **Removed deprecated functions to manage log level or type.**
463 The functions ``rte_set_log_level()``, ``rte_get_log_level()``,
464 ``rte_set_log_type()`` and ``rte_get_log_type()`` have been removed.
466 They are respectively replaced by ``rte_log_set_global_level()``,
467 ``rte_log_get_global_level()``, ``rte_log_set_level()`` and
468 ``rte_log_get_level()``.
470 * **Removed mbuf flags PKT_RX_VLAN_PKT and PKT_RX_QINQ_PKT.**
472 The ``mbuf`` flags ``PKT_RX_VLAN_PKT`` and ``PKT_RX_QINQ_PKT`` have
473 been removed since their behavior was not properly described.
475 * **Added mbuf flags PKT_RX_VLAN and PKT_RX_QINQ.**
477 Two ``mbuf`` flags have been added to indicate that the VLAN
478 identifier has been saved in the ``mbuf`` structure. For instance:
480 - If VLAN is not stripped and TCI is saved: ``PKT_RX_VLAN``
481 - If VLAN is stripped and TCI is saved: ``PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED``
483 * **Modified the vlan_offload_set_t function prototype in the ethdev library.**
485 Modified the ``vlan_offload_set_t`` function prototype in the ethdev
486 library. The return value has been changed from ``void`` to ``int`` so the
487 caller can determine whether the backing device supports the operation or if
488 the operation was successfully performed.
494 .. This section should contain ABI changes. Sample format:
496 * Add a short 1-2 sentence description of the ABI change that was announced
497 in the previous releases and made in this release. Use fixed width quotes
498 for ``rte_function_names`` or ``rte_struct_names``. Use the past tense.
500 This section is a comment. do not overwrite or remove it.
501 Also, make sure to start the actual text at the margin.
502 =========================================================
504 * **Extended port_id range.**
506 The size of the field ``port_id`` in the ``rte_eth_dev_data`` structure
507 has changed, as described in the `New Features` section above.
509 * **New parameter added to rte_eth_dev.**
511 A new parameter ``security_ctx`` has been added to ``rte_eth_dev`` to
512 support security operations like IPsec inline.
514 * **New parameter added to rte_cryptodev.**
516 A new parameter ``security_ctx`` has been added to ``rte_cryptodev`` to
517 support security operations like lookaside crypto.
523 .. This section should contain removed items in this release. Sample format:
525 * Add a short 1-2 sentence description of the removed item in the past
528 This section is a comment. do not overwrite or remove it.
529 Also, make sure to start the actual text at the margin.
530 =========================================================
532 * Xen dom0 in EAL has been removed, as well as the xenvirt PMD and vhost_xen.
534 * The crypto performance unit tests have been removed,
535 replaced by the ``dpdk-test-crypto-perf`` application.
538 Shared Library Versions
539 -----------------------
541 .. Update any library version updated in this release and prepend with a ``+``
545 + librte_cfgfile.so.2
548 This section is a comment. do not overwrite or remove it.
549 =========================================================
552 The libraries prepended with a plus sign were incremented in this version.
557 + librte_bitratestats.so.2
558 + librte_bus_dpaa.so.1
559 + librte_bus_fslmc.so.1
560 + librte_bus_pci.so.1
561 + librte_bus_vdev.so.1
564 + librte_cryptodev.so.4
565 librte_distributor.so.1
568 + librte_eventdev.so.3
569 + librte_flow_classify.so.1
577 librte_latencystats.so.1
580 + librte_mempool.so.3
587 + librte_pmd_bnxt.so.2
588 + librte_pmd_bond.so.2
589 + librte_pmd_i40e.so.2
590 + librte_pmd_ixgbe.so.2
592 + librte_pmd_softnic.so.1
593 + librte_pmd_vhost.so.2
599 + librte_security.so.1
608 .. This section should contain a list of platforms that were tested with this
613 * <vendor> platform with <vendor> <type of devices> combinations
618 * Other relevant details...
620 This section is a comment. do not overwrite or remove it.
621 Also, make sure to start the actual text at the margin.
622 =========================================================
624 * Intel(R) platforms with Intel(R) NICs combinations
628 * Intel(R) Atom(TM) CPU C2758 @ 2.40GHz
629 * Intel(R) Xeon(R) CPU D-1540 @ 2.00GHz
630 * Intel(R) Xeon(R) CPU D-1541 @ 2.10GHz
631 * Intel(R) Xeon(R) CPU E5-4667 v3 @ 2.00GHz
632 * Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz
633 * Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz
634 * Intel(R) Xeon(R) CPU E5-2695 v4 @ 2.10GHz
635 * Intel(R) Xeon(R) CPU E5-2658 v2 @ 2.40GHz
636 * Intel(R) Xeon(R) CPU E5-2658 v3 @ 2.20GHz
644 * Red Hat Enterprise Linux Server release 7.3
645 * SUSE Enterprise Linux 12
652 * Intel(R) 82599ES 10 Gigabit Ethernet Controller
654 * Firmware version: 0x61bf0001
655 * Device id (pf/vf): 8086:10fb / 8086:10ed
656 * Driver version: 5.2.3 (ixgbe)
658 * Intel(R) Corporation Ethernet Connection X552/X557-AT 10GBASE-T
660 * Firmware version: 0x800003e7
661 * Device id (pf/vf): 8086:15ad / 8086:15a8
662 * Driver version: 4.4.6 (ixgbe)
664 * Intel(R) Ethernet Converged Network Adapter X710-DA4 (4x10G)
666 * Firmware version: 6.01 0x80003205
667 * Device id (pf/vf): 8086:1572 / 8086:154c
668 * Driver version: 2.1.26 (i40e)
670 * Intel(R) Ethernet Converged Network Adapter X710-DA2 (2x10G)
672 * Firmware version: 6.01 0x80003204
673 * Device id (pf/vf): 8086:1572 / 8086:154c
674 * Driver version: 2.1.26 (i40e)
676 * Intel(R) Ethernet Converged Network Adapter XXV710-DA2 (2x25G)
678 * Firmware version: 6.01 0x80003221
679 * Device id (pf/vf): 8086:158b
680 * Driver version: 2.1.26 (i40e)
682 * Intel(R) Ethernet Converged Network Adapter XL710-QDA2 (2X40G)
684 * Firmware version: 6.01 0x8000321c
685 * Device id (pf/vf): 8086:1583 / 8086:154c
686 * Driver version: 2.1.26 (i40e)
688 * Intel(R) Corporation I350 Gigabit Network Connection
690 * Firmware version: 1.63, 0x80000dda
691 * Device id (pf/vf): 8086:1521 / 8086:1520
692 * Driver version: 5.3.0-k (igb)
694 * Intel(R) platforms with Mellanox(R) NICs combinations
698 * Intel(R) Xeon(R) CPU E5-2697A v4 @ 2.60GHz
699 * Intel(R) Xeon(R) CPU E5-2697 v3 @ 2.60GHz
700 * Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz
701 * Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20GHz
702 * Intel(R) Xeon(R) CPU E5-2640 @ 2.50GHz
703 * Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
707 * Red Hat Enterprise Linux Server release 7.3 (Maipo)
708 * Red Hat Enterprise Linux Server release 7.2 (Maipo)
713 * MLNX_OFED: 4.2-1.0.0.0
717 * Mellanox(R) ConnectX(R)-3 Pro 40G MCX354A-FCC_Ax (2x40G)
719 * Host interface: PCI Express 3.0 x8
720 * Device ID: 15b3:1007
721 * Firmware version: 2.42.5000
723 * Mellanox(R) ConnectX(R)-4 10G MCX4111A-XCAT (1x10G)
725 * Host interface: PCI Express 3.0 x8
726 * Device ID: 15b3:1013
727 * Firmware version: 12.21.1000
729 * Mellanox(R) ConnectX(R)-4 10G MCX4121A-XCAT (2x10G)
731 * Host interface: PCI Express 3.0 x8
732 * Device ID: 15b3:1013
733 * Firmware version: 12.21.1000
735 * Mellanox(R) ConnectX(R)-4 25G MCX4111A-ACAT (1x25G)
737 * Host interface: PCI Express 3.0 x8
738 * Device ID: 15b3:1013
739 * Firmware version: 12.21.1000
741 * Mellanox(R) ConnectX(R)-4 25G MCX4121A-ACAT (2x25G)
743 * Host interface: PCI Express 3.0 x8
744 * Device ID: 15b3:1013
745 * Firmware version: 12.21.1000
747 * Mellanox(R) ConnectX(R)-4 40G MCX4131A-BCAT/MCX413A-BCAT (1x40G)
749 * Host interface: PCI Express 3.0 x8
750 * Device ID: 15b3:1013
751 * Firmware version: 12.21.1000
753 * Mellanox(R) ConnectX(R)-4 40G MCX415A-BCAT (1x40G)
755 * Host interface: PCI Express 3.0 x16
756 * Device ID: 15b3:1013
757 * Firmware version: 12.21.1000
759 * Mellanox(R) ConnectX(R)-4 50G MCX4131A-GCAT/MCX413A-GCAT (1x50G)
761 * Host interface: PCI Express 3.0 x8
762 * Device ID: 15b3:1013
763 * Firmware version: 12.21.1000
765 * Mellanox(R) ConnectX(R)-4 50G MCX414A-BCAT (2x50G)
767 * Host interface: PCI Express 3.0 x8
768 * Device ID: 15b3:1013
769 * Firmware version: 12.21.1000
771 * Mellanox(R) ConnectX(R)-4 50G MCX415A-GCAT/MCX416A-BCAT/MCX416A-GCAT
774 * Host interface: PCI Express 3.0 x16
775 * Device ID: 15b3:1013
776 * Firmware version: 12.21.1000
778 * Mellanox(R) ConnectX(R)-4 50G MCX415A-CCAT (1x100G)
780 * Host interface: PCI Express 3.0 x16
781 * Device ID: 15b3:1013
782 * Firmware version: 12.21.1000
784 * Mellanox(R) ConnectX(R)-4 100G MCX416A-CCAT (2x100G)
786 * Host interface: PCI Express 3.0 x16
787 * Device ID: 15b3:1013
788 * Firmware version: 12.21.1000
790 * Mellanox(R) ConnectX(R)-4 Lx 10G MCX4121A-XCAT (2x10G)
792 * Host interface: PCI Express 3.0 x8
793 * Device ID: 15b3:1015
794 * Firmware version: 14.21.1000
796 * Mellanox(R) ConnectX(R)-4 Lx 25G MCX4121A-ACAT (2x25G)
798 * Host interface: PCI Express 3.0 x8
799 * Device ID: 15b3:1015
800 * Firmware version: 14.21.1000
802 * Mellanox(R) ConnectX(R)-5 100G MCX556A-ECAT (2x100G)
804 * Host interface: PCI Express 3.0 x16
805 * Device ID: 15b3:1017
806 * Firmware version: 16.21.1000
808 * Mellanox(R) ConnectX-5 Ex EN 100G MCX516A-CDAT (2x100G)
810 * Host interface: PCI Express 4.0 x16
811 * Device ID: 15b3:1019
812 * Firmware version: 16.21.1000
814 * ARM platforms with Mellanox(R) NICs combinations
818 * Qualcomm ARM 1.1 2500MHz
824 * MLNX_OFED: 4.2-1.0.0.0
828 * Mellanox(R) ConnectX(R)-4 Lx 25G MCX4121A-ACAT (2x25G)
830 * Host interface: PCI Express 3.0 x8
831 * Device ID: 15b3:1015
832 * Firmware version: 14.21.1000
834 * Mellanox(R) ConnectX(R)-5 100G MCX556A-ECAT (2x100G)
836 * Host interface: PCI Express 3.0 x16
837 * Device ID: 15b3:1017
838 * Firmware version: 16.21.1000