diff --git a/README.adoc b/README.adoc
index e0c594b..1db8582 100644
--- a/README.adoc
+++ b/README.adoc
@@ -23,7 +23,7 @@ cd linux-kernel-module-cheat
 ./configure && ./build && ./run
 ....
 
-The first build will take a while (https://stackoverflow.com/questions/10833672/buildroot-environment-with-host-toolchain[GCC], Linux kernel), e.g.:
+The first build will take a while (link:https://stackoverflow.com/questions/10833672/buildroot-environment-with-host-toolchain[GCC], Linux kernel), e.g.:
 
 * 2 hours on a mid end 2012 laptop
 * 30 minutes on a high end 2017 desktop
@@ -1608,6 +1608,8 @@ It works like this:
 * the first commond boots linux with the default simplified `AtomicSimpleCPU`, and generates a <<gem5-checkpoint,checkpoint>> after the kernel boots and before running the benchmark
 * the second command restores the checkpoint with the more detailed `HPI` CPU model, and runs the benchmark. We don't boot with it because that is much slower.
 
+ARM employees have just been modifying benchmarking code with instrumentation directly: https://github.com/arm-university/arm-gem5-rsk/blob/aa3b51b175a0f3b6e75c9c856092ae0c8f2a7cdc/parsec_patches/xcompile-patch.diff#L230
+
 A few imperfections of our benchmarking method are:
 
 * when we do `m5 resetstats` and `m5 exit`, there is some time passed before the `exec` system call returns and the actual benchmark starts and ends