For older versions history, please refer to their dedicated Release Notes.
|
Category |
Description |
|
Version 27.2010.6102 |
|
|
General |
See Bug Fixes. |
|
Version 27.2010.6064 |
|
|
Counters: Unhealthy Link |
Added BER Monitor counters for unhealthy link. |
|
Additional Status in Each MAD |
Added support of AdditionalStatus in MAD packets. |
|
Mirroring Congested Packets Towards UFM |
Added support for mirroring of congested packets towards UFM entity (collector) in the network. |
|
General |
See Bug Fixes. |
|
Version 27.2010.5108 |
|
|
General |
Stability improvements. |
|
Version 27.2010.5002 |
|
|
General |
Stability improvements. |
|
Version 27.2010.4102 |
|
|
General |
Stability improvements. |
|
Version 27.2010.4010 |
|
|
pFRN Collector |
Added support for mirroring of PFRN packets towards UFM entity (collector) in the subnet. |
|
PKEY Filter for Multicast |
Added support for MulticastPKeyTrapSuppression (PKEY mismatch filtering). |
|
SL to VL Mapping |
Added switch support for port mask optimization of SL to VL Mapping Table configuration. |
|
Version 27.2010.3118 |
|
|
Temperature Drift Tolerance |
Improved HDR InfiniBand temperature drift tolerance on Quantum systems. Improved the algorithm for periodic link maintenance which is performed by NVIDIA IC during normal link operation in order to compensate for changes in link environment that might influence the analog behavior of the SerDes blocks in order to prevent a degradation in link performance. |
|
Version 27.2010.3004 |
|
|
pFRN |
Added support for pFRN (Proactive Fault Routing Notification) which allows for dynamic link failure detection and route correction for topologies based on Adaptive Routing. |
|
Counters |
Added support for PortXmitWaitVLExtended counters. |
|
Fans |
Enlarged fans' PRM registers to support up to 16 fans. |
|
General |
See Bug Fixes. |
|
Version 27.2010.2246 |
|
|
General |
Stability improvements. |
|
Version 27.2010.2110 |
|
|
General |
Stability improvements. |
|
Version 27.2010.2036 |
|
|
General |
Stability improvements. |
|
Version 27.2010.1404 |
|
|
General |
Stability improvements. |
|
Version 27.2010.1310 |
|
|
Congestion Control |
Added ES-level support for congestion control class key. |
|
Vendor Key |
Added ES-level support for vendor class key. |
|
Version 27.2010.1202 |
|
|
Counters |
Added support for PortVLXmitFlowCtlUpdateErrors counters. |
|
Version 27.2008.3328 |
|
|
Cables |
Added GA-level support for AOC splitter cables MFS1S50-H0xxE-LL. *Note that the cables above are HDR-only and are supported up to 30 meters. |
|
LinkX Cable Upgrade |
Added GA-level support, on supported cables, for direct firmware burning from the internal flash storage to reduce the bandwidth and accelerate the burning process, including burning several modules at a time. |
|
PKEY |
Added support for PKEY traps. |
|
Bug Fixes |
|
|
Version 27.2008.2500 |
|
|
Cables |
Added support for cable MMS1W50-HM NVIDIA transceiver, IB HDR, up to 200Gb/s, QSFP56, MPO, 1310nm, FR4 on MQM8700-HS2R and MQM8790-HS2R systems. |
|
Cables |
Added GA-level support for Active Optical Cables MFS1S00-H0xx-LL . *Note that the cables above are HDR-only and are supported up to 30 meters. |
|
Version 27.2008.2402 |
|
|
Bug Fixes |
See Bug Fixes. |
|
Version 27.2008.2300 |
|
|
Bug Fixes |
See Bug Fixes. |
|
Version 27.2008.2202 |
|
|
LinkX Cable Upgrade |
Added beta-level support on supported cables for direct firmware burning from the internal flash storage to reduce the bandwidth and accelerate the burning process, including burning several modules at a time. |
|
Version 27.2008.2102 |
|
|
BER |
100Gb/s speed BER improvements. con |
|
Cables |
Added support for the following Active Fiber HDR cables: MFS1S00-H130E and MFS1S00-H150E. |
|
Counters |
Added support for "Maximum PLR Counts per second (cps)" counter. |
|
IBdiagnet |
Updated the PPNCT group/DiagnosticData to use SymbolBER counters instead of Effective BER counters. |
|
Telemetry |
Added support for performance analysis using histogram-based traffic models to obtain the queue length distribution. |
|
Version 27.2008.1904 |
|
|
SHARP |
Added support for SHARP SAT performance counters. |
|
Adaptive Routing |
Added support for a new Adaptive Router counter (PortARTrials) as part of the PortRNCounters group. PortARTrials is used to indicate the number of times the AR decision mechanism is used per port |
|
Version 27.2008.1604 |
|
|
SHARP |
Added support for MAD security policy for SHARP. |
|
Cables |
Enabled PLR with Low-Latency (LL)-FEC mode in optical cables up to 30m. |
|
Version 27.2008.1300 |
|
|
EDR Link in ConnectX-6 100Gb/s cards |
EDR link speed is now supported when using ConnectX-6 100Gb/s HCA and connecting with HDR optical cables. |
|
Version 27.2008.0232 |
|
|
Link Speed |
Added support for FDR link speed when connecting a ConnectX-3 HCA with an HDR Quantum switch. |
|
SHARP |
SHARP stability improvements. |
|
SHARP |
Added support for legacy SHARP port and performance counters. |
|
Cables |
Enabled KP4RS FEC on Active Fiber cables (OPN: MFS1S00-V0xxE). |
|
Cables |
Disabled PLR on Active Fiber cables. |
|
Bug Fixes |
See Bug Fixes. |
|
Version 27.2007.1124 |
|
|
Bug Fixes |
See Bug Fixes. |
|
Version 27.2007.0618 |
|
|
Bug Fixes |
See Bug Fixes. |
|
Version 27.2007.0300 |
|
|
Performance |
Added support for link-negotiated credit size. |
|
General |
Added support for DCQCN Congestion Control. |
|
Version 27.2000.3276 |
|
|
NVIDIA Scalable Hierarchical Aggregation and Reduction Protocol (SHARP)™ |
SHARP (SAT) is at GA level. *SAT: Streaming Aggregation Tree |
|
Version 27.2000.2708 |
|
|
SHARP |
SHARP now supports running 2 flows in parallel. |
|
Version 27.2000.2626 |
|
|
Speed Link |
SDR link speed on InfiniBand systems is now available for all cables, including cables that do not advertise InfiniBand speed in their memory map. |
|
NVIDIA Scalable Hierarchical Aggregation and Reduction Protocol (SHARP) |
SHARP (LLT) is at GA level, whereas SHARP (SAT) is at Beta level. *LLT: Local Latency Tree *SAT: Streaming Aggregation Tree |
|
General |
Added support for Error Injection with PTER register. |
|
General |
See Bug Fixes. |
|
Version 27.2000.2306 |
|
|
General |
See Bug Fixes. |
|
Version 27.2000.2182 |
|
|
General |
See Bug Fixes. |
|
Version 27.2000.2046 |
|
|
NVIDIA Scalable Hierarchical Aggregation and Reduction Protocol (SHARP) |
[Beta] NVIDIA Scalable Hierarchical Aggregation and Reduction Protocol (SHARP) technology improves the performance of MPI operations by offloading collective operations from the CPU to the switch network, and by eliminating the need to send data multiple times between endpoints. |
|
Link Speed |
Added QDR/FDR support in Quantum switch systems when using optical cables of up to 30m. Note: QDR speed is only supported when using the FDR cables. See Validated and Supported FDR Cables |
|
Cables |
Removed PLR from active cables longer than 30m. |
|
Version 27.2000.1886 |
|
|
Physical Layer Retransmission (PLR) |
Added support to the Physical Layer Retransmission (PLR) functionality for HDR speed. |
|
Link Speed |
Link-up time improvements. The link up time is up to 60 sec |
|
Version 27.2000.1600 |
|
|
General |
See Bug Fixes. |
|
Version 27.2000.1400 |
|
|
Link Speed |
HDR speed rate is at GA level. |
|
Cables |
Added support for Break-Out Cable auto-sensing. |
|
Version 27.2000.1142 |
|
|
Link Speed |
HDR link stability enhancements. Note: HDR is at beta level. |
|
Version 27.2000.1012 |
|
|
Link Speed |
HDR speed rate is currently at beta level. |
|
Version 27.2000.1004 |
|
|
Link Speed |
Stability improvements for HDR link. |
|
Subnet Manager (Adaptive Routing) |
Added support for Adaptive Routing. Adaptive routing (AR) allows optimizing data traffic flow. The InfiniBand protocol uses multiple paths between any two points. Thus, when unexpected traffic patterns cause some paths to be overloaded, AR can automatically move traffic to less congested paths according to the current temporal state of the network. |
|
Adaptive Routing |
Added support for Private Linear Forwarding Tables (PLFT). This capability helps SM to optimize traffic. |