mirror of
https://github.com/llvm-mirror/libcxx.git
synced 2025-10-24 20:29:39 +08:00
6cebf7c36f
This patch rewrites a few loops in deque and split_buffer to better
optimize the codegen. For constructors like
`deque<unsigned char> d(500000, 0);` this patch results in a 2x speedup.
The patch improves the codegen in roughly three ways:
1. Changes do { ... } while (...) loops into more typical for loops.
The optimizer can reason about normal looking loops better.
2. Split the iteration over a range into (A) iteration over the blocks,
then (B) iteration within the block. This nested structure helps LLVM
lower the inner loop to `memset`.
3. Do fewer things each iteration. Some of these loops were incrementing
or changing 4-5 variables every loop (in addition to the
construction). Previously most loops would increment the end pointer,
the size, and decrement the count of remaining items to construct.
Now we only increment a single pointer for most iterations.
git-svn-id: https://llvm.org/svn/llvm-project/libcxx/trunk@368547 91177308-0d34-0410-b5e6-96231b3b80d8
141 lines
4.1 KiB
C++
141 lines
4.1 KiB
C++
// -*- C++ -*-
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef BENCHMARK_CONTAINER_BENCHMARKS_HPP
|
|
#define BENCHMARK_CONTAINER_BENCHMARKS_HPP
|
|
|
|
#include <cassert>
|
|
|
|
#include "Utilities.hpp"
|
|
#include "benchmark/benchmark.h"
|
|
|
|
namespace ContainerBenchmarks {
|
|
|
|
template <class Container>
|
|
void BM_ConstructSize(benchmark::State& st, Container) {
|
|
auto size = st.range(0);
|
|
for (auto _ : st) {
|
|
Container c(size);
|
|
DoNotOptimizeData(c);
|
|
}
|
|
}
|
|
|
|
template <class Container>
|
|
void BM_ConstructSizeValue(benchmark::State& st, Container, typename Container::value_type const& val) {
|
|
const auto size = st.range(0);
|
|
for (auto _ : st) {
|
|
Container c(size, val);
|
|
DoNotOptimizeData(c);
|
|
}
|
|
}
|
|
|
|
template <class Container, class GenInputs>
|
|
void BM_ConstructIterIter(benchmark::State& st, Container, GenInputs gen) {
|
|
auto in = gen(st.range(0));
|
|
const auto begin = in.begin();
|
|
const auto end = in.end();
|
|
benchmark::DoNotOptimize(&in);
|
|
while (st.KeepRunning()) {
|
|
Container c(begin, end);
|
|
DoNotOptimizeData(c);
|
|
}
|
|
}
|
|
|
|
template <class Container, class GenInputs>
|
|
void BM_InsertValue(benchmark::State& st, Container c, GenInputs gen) {
|
|
auto in = gen(st.range(0));
|
|
const auto end = in.end();
|
|
while (st.KeepRunning()) {
|
|
c.clear();
|
|
for (auto it = in.begin(); it != end; ++it) {
|
|
benchmark::DoNotOptimize(&(*c.insert(*it).first));
|
|
}
|
|
benchmark::ClobberMemory();
|
|
}
|
|
}
|
|
|
|
template <class Container, class GenInputs>
|
|
void BM_InsertValueRehash(benchmark::State& st, Container c, GenInputs gen) {
|
|
auto in = gen(st.range(0));
|
|
const auto end = in.end();
|
|
while (st.KeepRunning()) {
|
|
c.clear();
|
|
c.rehash(16);
|
|
for (auto it = in.begin(); it != end; ++it) {
|
|
benchmark::DoNotOptimize(&(*c.insert(*it).first));
|
|
}
|
|
benchmark::ClobberMemory();
|
|
}
|
|
}
|
|
|
|
|
|
template <class Container, class GenInputs>
|
|
void BM_InsertDuplicate(benchmark::State& st, Container c, GenInputs gen) {
|
|
auto in = gen(st.range(0));
|
|
const auto end = in.end();
|
|
c.insert(in.begin(), in.end());
|
|
benchmark::DoNotOptimize(&c);
|
|
benchmark::DoNotOptimize(&in);
|
|
while (st.KeepRunning()) {
|
|
for (auto it = in.begin(); it != end; ++it) {
|
|
benchmark::DoNotOptimize(&(*c.insert(*it).first));
|
|
}
|
|
benchmark::ClobberMemory();
|
|
}
|
|
}
|
|
|
|
|
|
template <class Container, class GenInputs>
|
|
void BM_EmplaceDuplicate(benchmark::State& st, Container c, GenInputs gen) {
|
|
auto in = gen(st.range(0));
|
|
const auto end = in.end();
|
|
c.insert(in.begin(), in.end());
|
|
benchmark::DoNotOptimize(&c);
|
|
benchmark::DoNotOptimize(&in);
|
|
while (st.KeepRunning()) {
|
|
for (auto it = in.begin(); it != end; ++it) {
|
|
benchmark::DoNotOptimize(&(*c.emplace(*it).first));
|
|
}
|
|
benchmark::ClobberMemory();
|
|
}
|
|
}
|
|
|
|
template <class Container, class GenInputs>
|
|
static void BM_Find(benchmark::State& st, Container c, GenInputs gen) {
|
|
auto in = gen(st.range(0));
|
|
c.insert(in.begin(), in.end());
|
|
benchmark::DoNotOptimize(&(*c.begin()));
|
|
const auto end = in.data() + in.size();
|
|
while (st.KeepRunning()) {
|
|
for (auto it = in.data(); it != end; ++it) {
|
|
benchmark::DoNotOptimize(&(*c.find(*it)));
|
|
}
|
|
benchmark::ClobberMemory();
|
|
}
|
|
}
|
|
|
|
template <class Container, class GenInputs>
|
|
static void BM_FindRehash(benchmark::State& st, Container c, GenInputs gen) {
|
|
c.rehash(8);
|
|
auto in = gen(st.range(0));
|
|
c.insert(in.begin(), in.end());
|
|
benchmark::DoNotOptimize(&(*c.begin()));
|
|
const auto end = in.data() + in.size();
|
|
while (st.KeepRunning()) {
|
|
for (auto it = in.data(); it != end; ++it) {
|
|
benchmark::DoNotOptimize(&(*c.find(*it)));
|
|
}
|
|
benchmark::ClobberMemory();
|
|
}
|
|
}
|
|
|
|
} // end namespace ContainerBenchmarks
|
|
|
|
#endif // BENCHMARK_CONTAINER_BENCHMARKS_HPP
|