mberenjk

## Details ___Do not mention proprietary info or link to internal work items in this PR.___ **Work item:** _"Internal", or link to GitHub issue (if applicable)._ **What were the changes?**...

Adding LatencyBench test to measure peer-to-peer latency between two GPUs

1

…GPUs ## Details ___Do not mention proprietary info or link to internal work items in this PR.___ **Work item:** LWPCOMMLIBS-143 **What were the changes?** adding LatencyBench test to measure peer-to-peer...

disabling AR_Bias for gfx90a

1

## Details ___Do not mention proprietary info or link to internal work items in this PR.___ **Work item:** LWPCLPAT-599 **What were the changes?** disabling AR_Bias for gfx90a **Why were the...

## Details ___Do not mention proprietary info or link to internal work items in this PR.___ **Work item:** SWDEV-546712 **What were the changes?** changing NCCL_LL128_SHMEM_ELEMS_PER_THREAD to 4 to avoid the...

Adding a barrier feature to highlight delays from preceding kernels in RCCL calls

3

## Details ___Do not mention proprietary info or link to internal work items in this PR.___ **Work item:**LWPCOMMLIBS-519 **What were the changes?** This commit implements a barrier to expose delays...