diff --git a/README.adoc b/README.adoc
index 2822420..ea236b2 100644
--- a/README.adoc
+++ b/README.adoc
@@ -10227,7 +10227,7 @@ To benchmark on the host, we do:
 
 ....
 ./build-userland-in-tree --force-rebuild --optimization-level 3 ./userland/cpp/bst_vs_heap_vs_hashmap.cpp
-./userland/cpp/bst_vs_heap_vs_hashmap.out | tee bst_vs_heap_vs_hashmap.dat
+./userland/cpp/bst_vs_heap_vs_hashmap.out 10000000 10000 | tee bst_vs_heap_vs_hashmap.dat
 gnuplot \
   -e 'input_noext="bst_vs_heap_vs_hashmap"' \
   -e 'heap_zoom_max=50' \
@@ -10274,6 +10274,8 @@ gnuplot \
 xdg-open bst_vs_heap_vs_hashmap_gem5.tmp.png
 ....
 
+TODO: the gem5 simulation blows up on a tcmalloc allocation somewhere near 25k elements as of 3fdd83c2c58327d9714fa2347c724b78d7c05e2b + 1, likely linked to the extreme inefficiency of the stats collection?
+
 The cache sizes were chosen to match the host <<p51>> to improve the comparison. Ideally we sould also use the same standard library.
 
 Note that this will take a long time, and will produce a humongous ~40Gb stats file due to: <<gem5-only-dump-selected-stats>>
@@ -14060,6 +14062,11 @@ That document then describes the SVE instructions and registers.
 
 * LDADD: link:userland/cpp/atomic.cpp[]
 
+Bibliography:
+
+* https://stackoverflow.com/questions/21535058/arm64-ldxr-stxr-vs-ldaxr-stlxr
+* https://preshing.com/20120710/memory-barriers-are-like-source-control-operations/
+
 === ARM assembly bibliography
 
 ==== ARM non-official bibliography
diff --git a/path_properties.py b/path_properties.py
index 56afd45..5aab2e7 100644
--- a/path_properties.py
+++ b/path_properties.py
@@ -478,9 +478,7 @@ path_properties_tuples = (
                 ),
                 'cpp': (
                     {},
-                    {
-                        'bst_vs_heap_vs_hashmap.cpp': {'more_than_1s': True},
-                    },
+                    {},
                 ),
                 'gcc': (
                     gnu_extension_properties,
diff --git a/userland/cpp/bst_vs_heap_vs_hashmap.cpp b/userland/cpp/bst_vs_heap_vs_hashmap.cpp
index 4fe3e3d..0e544ad 100644
--- a/userland/cpp/bst_vs_heap_vs_hashmap.cpp
+++ b/userland/cpp/bst_vs_heap_vs_hashmap.cpp
@@ -1,48 +1,5 @@
 // https://github.com/cirosantilli/linux-kernel-module-cheat#bst-vs-heap-vs-hashmap
 
-//#include <algorithm>
-//#include <iostream>
-//#include <queue>
-//#include <random>
-//#include <set>
-//
-//#include <lkmc/m5ops.h>
-//
-//int main(int argc, char **argv) {
-//    typedef uint64_t I;
-//    std::vector<I> randoms;
-//    size_t i, n;
-//    std::priority_queue<I> heap;
-//    std::set<I> bst;
-//    unsigned int seed = std::random_device()();
-//
-//    // CLI arguments.
-//    if (argc > 1) {
-//        n = std::stoi(argv[1]);
-//    } else {
-//        n = 1;
-//    }
-//
-//    // Action.
-//    for (i = 0; i < n; ++i) {
-//        randoms.push_back(i);
-//    }
-//    std::shuffle(randoms.begin(), randoms.end(), std::mt19937(seed));
-//    for (i = 0; i < n; ++i) {
-//        auto random = randoms[i];
-//
-//        // Heap.
-//        LKMC_M5OPS_RESETSTATS;
-//        heap.emplace(random);
-//        LKMC_M5OPS_DUMPSTATS;
-//
-//        // BST.
-//        LKMC_M5OPS_RESETSTATS;
-//        bst.insert(random);
-//        LKMC_M5OPS_DUMPSTATS;
-//    }
-//}
-
 #include <algorithm>
 #include <cassert>
 #include <chrono>
@@ -67,7 +24,7 @@ int main(int argc, char **argv) {
     if (argc > 1) {
         n = std::stoi(argv[1]);
     } else {
-        n = 10000000;
+        n = 10;
     }
 #ifdef LKMC_M5OPS_ENABLE
     // Let's comment useless stuff out to speed up gem5 simulations.
@@ -77,7 +34,7 @@ int main(int argc, char **argv) {
     if (argc > 2) {
         granule = std::stoi(argv[2]);
     } else {
-        granule = 10000;
+        granule = 1;
     }
 #endif