From 115fb093774a06d2ed9264903fd88fc9572f9aac Mon Sep 17 00:00:00 2001
From: David Addison <daddison@nvidia.com>
Date: Fri, 6 Mar 2026 17:45:03 -0800
Subject: [PATCH] Add new unalign flag to README.md and update help text

---
 README.md     | 5 +++--
 src/common.cu | 2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index a9071c4..61cfe11 100644
--- a/README.md
+++ b/README.md
@@ -83,7 +83,8 @@ All tests support the same set of arguments :
   * `-S,--report_timestamps <0/1>` Add timestamp (`"%Y-%m-%d %H:%M:%S"`) to each performance report line. Default : 0.
   * `-J,--output_file <file>` Write [JSON] output to filepath. Infer type from suffix (only `json` supported presently).
   * `-T,--timeout <time in seconds>` timeout each test after specified number of seconds. Default : disabled.
-  * `-M,--memory_report <0/1>` enable memory usage report. Default : 0
+  * `-M,--memory_report <0/1>` enable memory usage report. Default : 0.
+  * `-u,--unalign <index of first element>` Misalign source and destination buffers. Default : 0.
 
 ### Running multiple operations in parallel
 
@@ -107,4 +108,4 @@ Note that the reported bandwidth is per group, hence to get the total bandwidth
 
 ## Copyright
 
-NCCL tests are provided under the BSD license. All source code and accompanying documentation is copyright (c) 2016-2025, NVIDIA CORPORATION. All rights reserved.
+NCCL tests are provided under the BSD license. All source code and accompanying documentation is copyright (c) 2016-2026, NVIDIA CORPORATION. All rights reserved.
diff --git a/src/common.cu b/src/common.cu
index aa4e988..566b13b 100644
--- a/src/common.cu
+++ b/src/common.cu
@@ -1170,7 +1170,7 @@ int main(int argc, char* argv[], char **envp) {
             "[-D,--device_implementation <implementation number> enable device implementation (default: 0, use NCCL implementation; requires -R 2 if > 0)] \n\t"
             "[-V,--device_cta_count <number> set number of CTAs for device implementation (default: 16)] \n\t"
             "[-M,--memory_report <0/1> enable memory usage report (default: 0)] \n\t"
-            "[-u,--unalign <index of first element>] \n\t"
+            "[-u,--unalign <index of first element> Misalign source and destination buffers (default: 0)] \n\t"
             "[-h,--help]\n",
           basename(argv[0]));
         return 0;