What's New:

• Optimizations on key-value store support to scale up to 3000 nodes
• New APIs for Allgather, Broadcast and group API calls
• Performance Optimizations for scaleup for Allgather, Allreduce, and Reduce-scatter for scaleup and scaleout
• Performance Optimizations for CPU single node
• Optimizations to reuse Level Zero events.
• Change of the default mechanism for IPC exchange to pidfd

What's new:

• Bug fixes

What's New:

• Optimizations to limit the memory consumed by oneCCL
• Optimizations to limit the number of file descriptors maintained opened by oneCCL.
• Align the support for in-place for the Allgatherv and Reduce-scatter collectives to follow the same behavior as NCCL.
• In particular, the Allgatherv collective is in place when:
• send_buff == recv_buff rank_offset, where rank_offset = sum (recv_counts[i]), for all I<rank.
• Reduce-scatter is in-place when recv_buff == send_buff rank *recv_count.
• When using the environment variable CCL_WORKER_AFFINITY, oneCCL enforces the requirement that the length of the list should be equal to the number of workers.
• Bug fixes.

What's New

• Performance improvements for scaleup for all message sizes for AllReduce, Allgather, and Reduce_Scatter.
• Optimizations also include small message sizes that appear in inference apps.
• Performance improvements for scaleout for Allreduce, Reduce, Allgather, and Reduce_Scatter.
• Optimized memory usage of oneCCL.
• Support for PMIx 4.2.6.
• Bug fixes.

Removals

• oneCCL 2021.12 removes support for PMIx 4.2.2

This update provides bug fixes to maintain driver compatibility for Intel® Data Center GPU Max Series.

This update addresses stability issues with distributed Training and Inference workloads on Intel® Data Center GPU Max Series.

• Added point to point blocking communication operations for send and receive.

• Performance optimizations for Reduce-Scatter.

• Improved profiling with Intel® Instrumentation and Tracing Technology (ITT) profiling level.

• Improved scaling efficiency of the Scaleup algorithms for ReduceScatter
• Optimized performance of oneCCL scaleup collectives by utilizing the new embedded Data Streaming Accelerator in Intel® 4th Generation Xeon Scalable Processors (formerly code-named Sapphire Rapids)

• Optimizations across the board including improved scaling efficiency of the Scaleup algorithms for Alltoall and Allgather
• Add collective selection for scaleout algorithm for device (GPU) buffers

• Provides optimized performance for Intel® Data Center GPU Max Series utilizing oneCCL.
• Enables support for Allreduce, Allgather, Reduce, and Alltoall connectivity for GPUs on the same node.