[libc++] Optimize vector push_back to avoid continuous load and store of end pointer

Credits: this change is based on analysis and a proof of concept by
gerbens@google.com.

Before, the compiler loses track of end as 'this' and other references
possibly escape beyond the compiler's scope. This can be see in the
generated assembly:

     16.28 │200c80:   mov     %r15d,(%rax)
     60.87 │200c83:   add     $0x4,%rax
           │200c87:   mov     %rax,-0x38(%rbp)
      0.03 │200c8b: → jmpq    200d4e
      ...
      ...
      1.69 │200d4e:   cmp     %r15d,%r12d
           │200d51: → je      200c40
     16.34 │200d57:   inc     %r15d
      0.05 │200d5a:   mov     -0x38(%rbp),%rax
      3.27 │200d5e:   mov     -0x30(%rbp),%r13
      1.47 │200d62:   cmp     %r13,%rax
           │200d65: → jne     200c80

We fix this by always explicitly storing the loaded local and pointer
back at the end of push back. This generates some slight source 'noise',
but creates nice and compact fast path code, i.e.:

     32.64 │200760:   mov    %r14d,(%r12)
      9.97 │200764:   add    $0x4,%r12
      6.97 │200768:   mov    %r12,-0x38(%rbp)
     32.17 │20076c:   add    $0x1,%r14d
      2.36 │200770:   cmp    %r14d,%ebx
           │200773: → je     200730
      8.98 │200775:   mov    -0x30(%rbp),%r13
      6.75 │200779:   cmp    %r13,%r12
           │20077c: → jne    200760

Now there is a single store for the push_back value (as before), and a
single store for the end without a reload (dependency).

For fully local vectors, (i.e., not referenced elsewhere), the capacity
load and store inside the loop could also be removed, but this requires
more substantial refactoring inside vector.

Differential Revision: https://reviews.llvm.org/D80588

2 files changed, 15 insertions, 0 deletions

diff --git a/libcxx/benchmarks/ContainerBenchmarks.h b/libcxx/benchmarks/ContainerBenchmarks.h
index 071e46c..9a9abfd 100644
--- a/libcxx/benchmarks/ContainerBenchmarks.h
+++ b/libcxx/benchmarks/ContainerBenchmarks.h
@@ -79,6 +79,19 @@ void BM_ConstructFromRange(benchmark::State& st, Container, GenInputs gen) {
   }
 }
 
+template <class Container>
+void BM_Pushback(benchmark::State& state, Container c) {
+  int count = state.range(0);
+  c.reserve(count);
+  while (state.KeepRunningBatch(count)) {
+    c.clear();
+    for (int i = 0; i != count; ++i) {
+      c.push_back(i);
+    }
+    benchmark::DoNotOptimize(c.data());
+  }
+}
+
 template <class Container, class GenInputs>
 void BM_InsertValue(benchmark::State& st, Container c, GenInputs gen) {
   auto in        = gen(st.range(0));
diff --git a/libcxx/benchmarks/vector_operations.bench.cpp b/libcxx/benchmarks/vector_operations.bench.cpp
index be0bee6..38b14c5 100644
--- a/libcxx/benchmarks/vector_operations.bench.cpp
+++ b/libcxx/benchmarks/vector_operations.bench.cpp
@@ -39,4 +39,6 @@ BENCHMARK_CAPTURE(BM_ConstructFromRange, vector_size_t, std::vector<size_t>{}, g
 BENCHMARK_CAPTURE(BM_ConstructFromRange, vector_string, std::vector<std::string>{}, getRandomStringInputs)
     ->Arg(TestNumInputs);
 
+BENCHMARK_CAPTURE(BM_Pushback, vector_int, std::vector<int>{})->Arg(TestNumInputs);
+
 BENCHMARK_MAIN();