+* **Added write combining store APIs.**
+
+ Added ``rte_write32_wc`` and ``rte_write32_wc_relaxed`` APIs
+ that enable write combining stores (depending on architecture).
+ The functions are provided as a generic stub and
+ x86 specific implementation.
+
+* **Added prefetch with intention to write APIs.**
+
+ Added new prefetch function variants e.g. ``rte_prefetch0_write``,
+ which allow the programmer to prefetch a cache line and also indicate
+ the intention to write.
+
+* **Added the rte_cldemote API.**
+
+ Added a hardware hint CLDEMOTE, which is similar to prefetch in reverse.
+ CLDEMOTE moves the cache line to the more remote cache, where it expects
+ sharing to be efficient. Moving the cache line to a level more distant from
+ the processor helps to accelerate core-to-core communication.
+ This API is specific to x86 and implemented as a stub for other
+ architectures.
+
+* **Added support for limiting maximum SIMD bitwidth.**
+
+ Added a new EAL config setting ``max_simd_bitwidth`` to limit the vector
+ path selection at runtime. This value can be set by apps using the
+ ``rte_vect_set_max_simd_bitwidth`` function, or by the user with EAL flag
+ ``--force-max-simd-bitwidth``.
+
+* **Added zero copy APIs for rte_ring.**
+
+ For rings with producer/consumer in ``RTE_RING_SYNC_ST``, ``RTE_RING_SYNC_MT_HTS``
+ modes, these APIs split enqueue/dequeue operation into three phases
+ (enqueue/dequeue start, copy data to/from ring, enqueue/dequeue finish).
+ Along with the advantages of the peek APIs, these provide the ability to
+ copy the data to the ring memory directly without the need for temporary
+ storage.
+
+* **Updated CRC modules of the net library.**
+
+ * Added runtime selection of the optimal architecture-specific CRC path.
+ * Added optimized implementations of CRC32-Ethernet and CRC16-CCITT
+ using the AVX512 and VPCLMULQDQ instruction sets.
+
+* **Introduced extended buffer description for receiving.**
+
+ Added the extended Rx buffer description for Rx queue setup routine
+ providing the individual settings for each Rx segment with maximal size,
+ buffer offset and memory pool to allocate data buffers from.
+
+* **Added the FEC API, for a generic FEC query and config.**
+
+ Added the FEC API which provides functions for query FEC capabilities and
+ current FEC mode from device. An API for configuring FEC mode is also provided.
+
+* **Added thread safety to rte_flow functions.**
+
+ Added the ``RTE_ETH_DEV_FLOW_OPS_THREAD_SAFE`` device flag to indicate
+ whether a PMD supports thread safe operations. If the PMD doesn't set the flag,
+ the rte_flow API level functions will protect the flow operations with a mutex.
+
+* **Added flow-based traffic sampling support.**
+
+ Added a new action ``RTE_FLOW_ACTION_TYPE_SAMPLE`` that will sample the
+ incoming traffic and send a duplicated traffic with the specified ratio to
+ the application, while the original packet will continue to the target
+ destination.
+
+ The packets sampling is '1/ratio'. A ratio value set to 1 means that the
+ packets will be completely mirrored. The sample packet can be assigned with
+ a different set of actions than the original packet.
+
+* **Added support of shared action in flow API.**
+
+ Added shared action support to use single flow actions in multiple flow
+ rules. An update to the shared action configuration alters the behavior of all
+ flow rules using it.
+
+ * Added a new action: ``RTE_FLOW_ACTION_TYPE_SHARED`` to use shared action
+ as a flow action.
+ * Added new flow APIs to create/update/destroy/query shared actions.
+
+* **Added support to flow rules to allow private PMD items/actions.**
+
+ * Flow rule verification has been updated to accept private PMD
+ items and actions.
+
+* **Added a generic API to offload tunneled traffic and restore missed packets.**
+
+ * Added a new hardware independent helper to the flow API that
+ offloads tunneled traffic and restores missed packets.
+
+* **Updated the ethdev library to support hairpin between two ports.**
+
+ New APIs have been introduced to support binding / unbinding of 2 ports in a
+ hairpin configuration. The hairpin Tx part flow rules can be inserted
+ explicitly. A new API has been added to get the hairpin peer ports list.
+
+* **Updated the Amazon ena driver.**
+
+ Updated the ena PMD with new features and improvements, including:
+
+ * Added network interface metrics which can be read using xstats.
+
+* **Updated Broadcom bnxt driver.**
+
+ Updated the Broadcom bnxt driver with new features and improvements, including:
+
+ * Added support for 200G PAM4 link speed.
+ * Added support for RSS hash level selection.
+ * Updated HWRM structures to 1.10.1.70 version.
+ * Added TRUFLOW support for Stingray devices.
+ * Added support for representors on MAIA cores of SR.
+ * Added support for VXLAN decap offload using rte_flow.
+ * Added support to indicate native rte_flow API thread safety.
+
+* **Updated Cisco enic driver.**
+
+ * Added support for VF representors with single-queue Tx/Rx and flow API
+ * Added support for egress PORT_ID action
+ * Added support for non-zero priorities for group 0 flows
+ * Added support for VXLAN decap combined with VLAN pop
+
+* **Added hns3 FEC PMD, for supporting query and config FEC mode.**
+
+ Added the FEC PMD which provides functions for querying FEC capabilities and
+ current FEC mode from a device. A PMD for configuring FEC mode is also provided.
+
+* **Updated the Intel iavf driver.**
+
+ Updated the iavf PMD with new features and improvements, including:
+
+ * Added support for flexible descriptor metadata extraction.
+ * Added support for outer IP hash of GTPC and GTPU.
+ * Added support of AVX512 instructions in Rx and Tx path.
+ * Added support for up to 256 queue pairs per VF.
+
+* **Updated Intel ixgbe driver.**
+
+ Updated the Intel ixgbe driver to use write combining stores.
+
+* **Updated Intel i40e driver.**
+
+ Updated the Intel i40e driver to use write combining stores.
+
+* **Updated Intel ice driver.**
+
+ * Added support for write combining stores.
+ * Added ACL filter support for the Intel DCF.
+
+* **Updated Mellanox mlx5 driver.**
+
+ Updated the Mellanox mlx5 driver with new features and improvements, including:
+
+ * Added vectorized Multi-Packet Rx Queue burst.
+ * Added support for 2 new miniCQE formats: Flow Tag and L3/L4 header.
+ * Added support for PMD level multiple-thread flow insertion.
+ * Added support for matching on fragmented/non-fragmented IPv4/IPv6 packets.
+ * Added support for QinQ packets matching.
+ * Added support for the new VLAN fields ``has_vlan`` in the Ethernet item
+ and ``has_more_vlan`` in the VLAN item.
+ * Updated the supported timeout for Age action to the maximal value supported
+ by the rte_flow API.
+ * Added support for Age action query.
+ * Added support for multi-ports hairpin.
+ * Allow unknown link speed.
+
+ Updated Mellanox mlx5 vDPA driver:
+
+ * Added support of vDPA VirtQ error handling.
+
+* **Updated Solarflare network PMD.**
+
+ Updated the Solarflare ``sfc_efx`` driver with changes including:
+
+ * Added SR-IOV PF support
+ * Added Alveo SN1000 SmartNICs (EF100 architecture) support including
+ flow API transfer rules for switch HW offload
+ * Added ARMv8 support
+ * Claimed flow API native thread safety
+
+* **Added Wangxun txgbe PMD.**
+
+ Added a new PMD driver for Wangxun 10 Gigabit Ethernet NICs.
+
+ See the :doc:`../nics/txgbe` for more details.
+
+* **Updated Virtio driver.**
+
+ * Added support for Vhost-vDPA backend to the Virtio-user PMD.
+ * Changed default link speed to unknown.
+ * Added support for the 200G link speed.
+
+* **Updated Memif PMD.**
+
+ * Added support for abstract socket addresses.
+ * Changed default socket address type to abstract.
+
+* **Added UDP/IPv4 GRO support for VxLAN and non-VxLAN packets.**
+
+ For VxLAN packets, added inner UDP/IPv4 support.
+ For non-VxLAN packets, added UDP/IPv4 support.
+
+* **Extended the flow-perf application.**
+
+ * Added support for user order instead of bit mask.
+ Now the user can create any structure of rte_flow
+ using the flow performance application with any order.
+ Moreover the app also now starts to support inner
+ items matching as well.
+ * Added header modify actions.
+ * Added flag action.
+ * Added raw encap/decap actions.
+ * Added VXLAN encap/decap actions.
+ * Added ICMP (code/type/identifier/sequence number) and ICMP6 (code/type) matching items.
+ * Added option to set port mask for insertion/deletion:
+ ``--portmask=N``
+ where N represents the hexadecimal bitmask of the ports used.
+
+* **Added raw data-path APIs for cryptodev library.**
+
+ Added raw data-path APIs to Cryptodev to help accelerate external libraries
+ or applications which need to avail of fast cryptodev enqueue/dequeue
+ operations but which do not necessarily need to depend on mbufs and
+ cryptodev operation mempools.
+
+* **Updated the aesni_mb crypto PMD.**
+
+ * Added support for intel-ipsec-mb version 0.55.
+ * Added support for AES-ECB 128, 192 and 256.
+ * Added support for ZUC-EEA3/EIA3 algorithms.
+ * Added support for SNOW3G-UEA2/UIA2 algorithms.
+ * Added support for KASUMI-F8/F9 algorithms.
+ * Added support for Chacha20-Poly1305.
+ * Added support for AES-256 CCM algorithm.
+
+* **Updated the aesni_gcm crypto PMD.**
+
+ * Added SGL support for AES-GMAC.
+
+* **Added Broadcom BCMFS symmetric crypto PMD.**
+
+ Added a symmetric crypto PMD for Broadcom FlexSparc crypto units.
+ See :doc:`../cryptodevs/bcmfs` guide for more details on this new PMD.
+
+* **Updated NXP DPAA2_SEC crypto PMD.**
+
+ * Added DES-CBC support for cipher_only, chain and ipsec protocol.
+ * Added support for non-HMAC auth algorithms
+ (MD5, SHA1, SHA224, SHA256, SHA384, SHA512).
+
+* **Updated Marvell NITROX symmetric crypto PMD.**
+
+ * Added AES-GCM support.
+ * Added cipher only offload support.
+
+* **Updated Marvell OCTEON TX2 crypto PMD.**
+
+ * Updated the OCTEON TX2 crypto PMD lookaside protocol offload for IPsec with
+ IPv6 support.
+
+* **Updated Intel QAT PMD.**
+
+ * Added Raw Data-path APIs support.
+ * Added support for write combining stores.
+
+* **Added Intel ACC100 bbdev PMD.**
+
+ Added a new ``acc100`` bbdev driver for the Intel\ |reg| ACC100 accelerator
+ also known as Mount Bryce. See the
+ :doc:`../bbdevs/acc100` BBDEV guide for more details on this new driver.
+
+* **Updated rte_security library to support SDAP.**
+
+ ``rte_security_pdcp_xform`` in ``rte_security`` lib is updated to enable
+ 5G NR processing of SDAP headers in PMDs.
+
+* **Added Marvell OCTEON TX2 regex PMD.**
+
+ Added a new PMD driver for the hardware regex offload block for OCTEON TX2 SoC.
+
+ See the :doc:`../regexdevs/octeontx2` for more details.
+
+* **Updated Software Eventdev driver.**
+
+ Added performance tuning arguments to allow tuning the scheduler for
+ better throughput in high core count use cases.
+
+* **Added a new driver for the Intel Dynamic Load Balancer v1.0 device.**
+
+ Added the new ``dlb`` eventdev driver for the Intel DLB V1.0 device. See the
+ :doc:`../eventdevs/dlb` eventdev guide for more details on this new driver.
+
+* **Added a new driver for the Intel Dynamic Load Balancer v2.0 device.**
+
+ Added the new ``dlb2`` eventdev driver for the Intel DLB V2.0 device. See the
+ :doc:`../eventdevs/dlb2` eventdev guide for more details on this new driver.
+
+* **Added Ice Lake (Gen4) support for Intel NTB.**
+
+ Added NTB device support (4th generation) for the Intel Ice Lake platform.
+
+* **Updated ioat rawdev driver.**
+
+ The ioat rawdev driver has been updated and enhanced. Changes include:
+
+ * Added support for Intel\ |reg| Data Streaming Accelerator hardware. For
+ more information, see `Introducing the Intel Data Streaming Accelerator
+ (Intel DSA)
+ <https://01.org/blogs/2019/introducing-intel-data-streaming-accelerator>`_.
+ * Added support for the fill operation via the API ``rte_ioat_enqueue_fill()``,
+ where the hardware fills an area of memory with a repeating pattern.
+ * Added a per-device configuration flag to disable management
+ of user-provided completion handles.
+ * Renamed the ``rte_ioat_do_copies()`` API to ``rte_ioat_perform_ops()``,
+ and renamed the ``rte_ioat_completed_copies()`` API to ``rte_ioat_completed_ops()``
+ to better reflect the APIs' purposes, and remove the implication that
+ they are limited to copy operations only.
+ Note: The old API is still provided but marked as deprecated in the code.
+ * Added a new API ``rte_ioat_fence()`` to add a fence between operations.
+ This API replaces the ``fence`` flag parameter in the ``rte_ioat_enqueue_copies()`` function,
+ and is clearer as there is no ambiguity as to whether the flag should be
+ set on the last operation before the fence or the first operation after it.
+
+* **Updated the pipeline library for alignment with the P4 language.**
+
+ Added a new Software Switch (SWX) pipeline type that provides more
+ flexibility through APIs and feature alignment with the P4 language.
+ Some enhancements are:
+
+ * The packet headers, meta-data, actions, tables and pipelines are
+ dynamically defined instead of selected from a pre-defined set.
+ * The actions and the pipeline are defined with instructions.
+ * Extern objects and functions can be plugged into the pipeline.
+ * Transaction-oriented table updates.
+
+* **Added new AVX512 specific classify algorithms for ACL library.**
+
+ * Added new ``RTE_ACL_CLASSIFY_AVX512X16`` vector implementation,
+ which can process up to 16 flows in parallel. Requires AVX512 support.
+
+ * Added new ``RTE_ACL_CLASSIFY_AVX512X32`` vector implementation,
+ which can process up to 32 flows in parallel. Requires AVX512 support.
+
+* **Added AVX512 lookup implementation for FIB.**
+
+ Added a AVX512 lookup functions implementation into FIB and FIB6 libraries.
+
+* **Added support to update subport bandwidth dynamically.**
+
+ * Added new API ``rte_sched_port_subport_profile_add`` to add new
+ subport bandwidth profiles to the subport profile table at runtime.
+
+ * Added support to update the subport rate dynamically.
+
+* **Updated FIPS validation sample application.**
+
+ * Added scatter gather support.
+ * Added NIST GCMVS complaint GMAC test method support.
+
+* **Updated l3wfd-acl sample application.**
+
+ * Added new optional parameter ``--eth-dest`` for the ``l3fwd-acl`` to allow
+ the user to specify the destination mac address for each ethernet port
+ used.
+ * Replaced ``--scalar`` command-line option with ``--alg=<value>``, to allow
+ the user to select the desired classify method.
+
+* **Updated vhost sample application.**
+
+ Added vhost asynchronous APIs support, which demonstrates how the application
+ can leverage IOAT DMA channels with vhost asynchronous APIs.
+ See the :doc:`../sample_app_ug/vhost` for more details.
+