diff --git a/README.md b/README.md
index ad51eb1..caf690f 100644
--- a/README.md
+++ b/README.md
@@ -71,7 +71,7 @@ After build, you can find libcustom_tpc_perf_lib.so in build/src directory, whic
 For more details about TPC kernel writing, please refer to the [TPC User Guide](https://docs.habana.ai/en/latest/TPC_User_Guide/TPC_User_Guide.html) for more information.
 
 ## Kernels Performance Measure
-The new test core feature can be used to measure the custom kernels performance when set env variables TPC_RUNNER=1 (make sure hardware and driver are installed correctly) and HABANA_PROFILE=1. A hltv file will be created after running the test, make sure only run one kernel test at a time, for example, `tpc_kernel_tests -t FilterFwd2DBF16Test`. You can load the hltv file to https://hltv.habana.ai/ and visually check the performance.  Please check the [Habana Profiler](https://docs.habana.ai/en/latest/Profiling/index.html) to find more details.
+The new test core feature can be used to measure a custom kernel's performance when environment variables `TPC_RUNNER=1` and `HABANA_PROFILE=1`. (Make sure hardware and driver are installed correctly.) A `.hltv` file will be created after running the test. Be sure to run only one kernel test at a time. For example, `tpc_kernel_tests -t FilterFwd2DBF16Test`. You can load the `.hltv` file at https://perfetto.habana-labs.com/ and visually check the performance.  Please check the [Intel Gaudi Profiler User Guide](https://docs.habana.ai/en/latest/Profiling/index.html) for more details.
 
 ## Custom Ops for Tensorflow and PyTorch
 The user also can develop their own Tensorflow and PyTorch custom ops using their created TPC kernels. In this custom kernel project, we provide several custom kernel examples, such as custom_div (division), relu6_fwd/relu_fwd (relu6/relu forward path) and relu6_bwd/relu_bwd (relu6/relu backward path). Please visit [TensorFlow Custom OPs Examples](https://github.com/HabanaAI/Model-References/tree/master/TensorFlow/examples/custom_op) and [PyTorch Custom Ops Examples](https://github.com/HabanaAI/Model-References/tree/master/PyTorch/examples/custom_op/custom_relu) for more details and make sure add your custom kernel path to environment variable GC_KERNEL_PATH, like export GC_KERNEL_PATH=/path/to/your_so/libcustom_tpc_perf_lib.so:/usr/lib/habanalabs/libtpc_kernels.so.