Tweak some tests to avoid the slowest path.

By caching the result of the first call to ThreadAlloc::get(), we were
always hitting a code path that should be hit once per thread in normal
operation.

src/test/perf/external_pointer/externalpointer.cc

@@ -69,6 +69,9 @@ namespace test
 int main(int, char**)
 {
   xoroshiro::p128r64 r;
+  // Force a per-thread allocator to actually exist.
+  void* p = ThreadAlloc::get()->alloc(16);
+  ThreadAlloc::get()->dealloc(p);
 #if NDEBUG
   size_t nn = 30;
 #else

src/test/perf/singlethread/singlethread.cc

@@ -7,7 +7,7 @@ using namespace snmalloc;
 template<ZeroMem zero_mem>
 void test_alloc_dealloc(size_t count, size_t size, bool write)
 {
-  auto* alloc = ThreadAlloc::get();
+  auto*& alloc = ThreadAlloc::get();
 
   DO_TIME(
     "Count: " << std::setw(6) << count << ", Size: " << std::setw(6) << size