update sample cp

This commit is contained in:
Kevin Zhang
2025-09-16 01:10:58 +08:00
parent aaebb13ff7
commit 1c7a560d20
9 changed files with 0 additions and 0 deletions

View File

@@ -0,0 +1,114 @@
#pragma once
#include <iostream>
#include <iomanip>
#include <string>
// ============================================================================
// 性能计算和显示工具
// ============================================================================
class PerformanceCalculator {
public:
// ReduceSum性能计算
struct ReduceSumMetrics {
double throughput_gps; // G elements/s
};
static ReduceSumMetrics calculateReduceSum(int size, float time_ms) {
ReduceSumMetrics metrics;
metrics.throughput_gps = (size / 1e9) / (time_ms / 1000.0);
return metrics;
}
// SortPair性能计算
struct SortPairMetrics {
double throughput_gps; // G elements/s
};
static SortPairMetrics calculateSortPair(int size, float time_ms) {
SortPairMetrics metrics;
metrics.throughput_gps = (size / 1e9) / (time_ms / 1000.0);
return metrics;
}
// TopkPair性能计算
struct TopkPairMetrics {
double throughput_gps; // G elements/s
};
static TopkPairMetrics calculateTopkPair(int size, int k, float time_ms) {
TopkPairMetrics metrics;
metrics.throughput_gps = (size / 1e9) / (time_ms / 1000.0);
return metrics;
}
};
// ============================================================================
// 性能显示工具
// ============================================================================
class PerformanceDisplay {
public:
// 显示ReduceSum性能表头
static void printReduceSumHeader() {
std::cout << "\nReduceSum 性能测试..." << std::endl;
std::cout << "数据类型: float -> float" << std::endl;
std::cout << "计算公式:" << std::endl;
std::cout << " 吞吐量 = 元素数 / 时间(s) / 1e9 (G/s)" << std::endl;
std::cout << std::setw(12) << "数据规模" << std::setw(15) << "时间(ms)"
<< std::setw(20) << "吞吐量(G/s)" << std::endl;
std::cout << std::string(47, '-') << std::endl;
}
// 显示SortPair性能表头
static void printSortPairHeader() {
std::cout << "\nSortPair 性能测试..." << std::endl;
std::cout << "数据类型: <float, uint32_t>" << std::endl;
std::cout << "计算公式:" << std::endl;
std::cout << " 吞吐量 = 元素数 / 时间(s) / 1e9 (G/s)" << std::endl;
std::cout << std::setw(12) << "数据规模" << std::setw(15) << "升序(ms)" << std::setw(15) << "降序(ms)"
<< std::setw(16) << "升序(G/s)" << std::setw(16) << "降序(G/s)" << std::endl;
std::cout << std::string(78, '-') << std::endl;
}
// 显示TopkPair性能表头
static void printTopkPairHeader() {
std::cout << "\nTopkPair 性能测试..." << std::endl;
std::cout << "数据类型: <float, uint32_t>" << std::endl;
std::cout << "计算公式:" << std::endl;
std::cout << " 吞吐量 = 元素数 / 时间(s) / 1e9 (G/s)" << std::endl;
}
static void printTopkPairDataHeader() {
std::cout << std::setw(8) << "k值" << std::setw(15) << "升序(ms)" << std::setw(15) << "降序(ms)"
<< std::setw(16) << "升序(G/s)" << std::setw(16) << "降序(G/s)" << std::endl;
std::cout << std::string(74, '-') << std::endl;
}
// 显示性能数据行
static void printReduceSumData(int size, float time_ms, const PerformanceCalculator::ReduceSumMetrics& metrics) {
std::cout << std::setw(12) << size << std::setw(15) << std::fixed << std::setprecision(3)
<< time_ms << std::setw(20) << std::setprecision(3) << metrics.throughput_gps << std::endl;
}
static void printSortPairData(int size, float asc_time, float desc_time,
const PerformanceCalculator::SortPairMetrics& asc_metrics,
const PerformanceCalculator::SortPairMetrics& desc_metrics) {
std::cout << std::setw(12) << size << std::setw(15) << std::fixed << std::setprecision(3)
<< asc_time << std::setw(15) << desc_time << std::setw(16) << std::setprecision(3)
<< asc_metrics.throughput_gps << std::setw(16) << desc_metrics.throughput_gps << std::endl;
}
static void printTopkPairData(int k, float asc_time, float desc_time,
const PerformanceCalculator::TopkPairMetrics& asc_metrics,
const PerformanceCalculator::TopkPairMetrics& desc_metrics) {
std::cout << std::setw(8) << k << std::setw(15) << std::fixed << std::setprecision(3)
<< asc_time << std::setw(15) << desc_time << std::setw(16) << std::setprecision(3)
<< asc_metrics.throughput_gps << std::setw(16) << desc_metrics.throughput_gps << std::endl;
}
// 显示性能文件保存消息
static void printSavedMessage(const std::string& filename) {
std::cout << "\n性能结果已保存到: " << filename << std::endl;
}
};

234
S1/3/utils/test_utils.h Normal file
View File

@@ -0,0 +1,234 @@
#pragma once
#include <vector>
#include <random>
#include <algorithm>
#include <mc_runtime.h>
#include <maca_fp16.h>
#include <iostream>
#include <chrono>
#include <cmath>
// 引入模块化头文件
#include "yaml_reporter.h"
#include "performance_utils.h"
// ============================================================================
// 测试配置常量
// ============================================================================
#ifndef RUN_FULL_TEST
const int TEST_SIZES[] = {1000000, 134217728}; // 1M, 128M, 512M, 1G
#else
const int TEST_SIZES[] = {1000000, 134217728, 536870912, 1073741824}; // 1M, 128M, 512M, 1G
#endif
const int NUM_TEST_SIZES = sizeof(TEST_SIZES) / sizeof(TEST_SIZES[0]);
// 性能测试重复次数
constexpr int WARMUP_ITERATIONS = 5;
constexpr int BENCHMARK_ITERATIONS = 10;
// ============================================================================
// 错误检查宏
// ============================================================================
#define MACA_CHECK(call) \
do { \
mcError_t error = call; \
if (error != mcSuccess) { \
std::cerr << "MACA error at " << __FILE__ << ":" << __LINE__ \
<< " - " << mcGetErrorString(error) << std::endl; \
exit(1); \
} \
} while(0)
// ============================================================================
// 测试数据生成器
// ============================================================================
class TestDataGenerator {
private:
std::mt19937 rng;
public:
TestDataGenerator(uint32_t seed = 42) : rng(seed) {}
// 生成随机float数组
std::vector<float> generateRandomFloats(int size, float min_val = -1000.0f, float max_val = 1000.0f) {
std::vector<float> data(size);
std::uniform_real_distribution<float> dist(min_val, max_val);
for (int i = 0; i < size; i++) {
data[i] = dist(rng);
}
return data;
}
// 生成随机half数组
std::vector<half> generateRandomHalfs(int size, float min_val = -100.0f, float max_val = 100.0f) {
std::vector<half> data(size);
std::uniform_real_distribution<float> dist(min_val, max_val);
for (int i = 0; i < size; i++) {
data[i] = __float2half(dist(rng));
}
return data;
}
// 生成随机uint32_t数组
std::vector<uint32_t> generateRandomUint32(int size) {
std::vector<uint32_t> data(size);
for (int i = 0; i < size; i++) {
data[i] = static_cast<uint32_t>(i); // 使用索引作为值,便于验证稳定排序
}
return data;
}
// 生成随机int64_t数组
std::vector<int64_t> generateRandomInt64(int size) {
std::vector<int64_t> data(size);
for (int i = 0; i < size; i++) {
data[i] = static_cast<int64_t>(i);
}
return data;
}
// 生成包含NaN和Inf的测试数据 (half版本)
std::vector<half> generateSpecialHalfs(int size) {
std::vector<half> data = generateRandomHalfs(size, -10.0f, 10.0f);
if (size > 100) {
data[10] = __float2half(NAN);
data[20] = __float2half(INFINITY);
data[30] = __float2half(-INFINITY);
}
return data;
}
// 生成包含NaN和Inf的测试数据 (float版本)
std::vector<float> generateSpecialFloats(int size) {
std::vector<float> data = generateRandomFloats(size, -10.0f, 10.0f);
if (size > 100) {
data[10] = NAN;
data[20] = INFINITY;
data[30] = -INFINITY;
}
return data;
}
};
// ============================================================================
// 性能测试工具
// ============================================================================
class PerformanceMeter {
private:
mcEvent_t start, stop;
public:
PerformanceMeter() {
MACA_CHECK(mcEventCreate(&start));
MACA_CHECK(mcEventCreate(&stop));
}
~PerformanceMeter() {
mcEventDestroy(start);
mcEventDestroy(stop);
}
void startTiming() {
MACA_CHECK(mcEventRecord(start));
}
float stopTiming() {
MACA_CHECK(mcEventRecord(stop));
MACA_CHECK(mcEventSynchronize(stop));
float milliseconds = 0;
MACA_CHECK(mcEventElapsedTime(&milliseconds, start, stop));
return milliseconds;
}
};
// ============================================================================
// 正确性验证工具
// ============================================================================
template<typename T>
bool compareArrays(const std::vector<T>& a, const std::vector<T>& b, double tolerance = 1e-6) {
if (a.size() != b.size()) return false;
for (size_t i = 0; i < a.size(); i++) {
if constexpr (std::is_same_v<T, half>) {
float fa = __half2float(a[i]);
float fb = __half2float(b[i]);
if (std::isnan(fa) && std::isnan(fb)) continue;
if (std::isinf(fa) && std::isinf(fb) && (fa > 0) == (fb > 0)) continue;
if (std::abs(fa - fb) > tolerance) return false;
} else if constexpr (std::is_floating_point_v<T>) {
if (std::isnan(a[i]) && std::isnan(b[i])) continue;
if (std::isinf(a[i]) && std::isinf(b[i]) && (a[i] > 0) == (b[i] > 0)) continue;
if (std::abs(a[i] - b[i]) > tolerance) return false;
} else {
if (a[i] != b[i]) return false;
}
}
return true;
}
// CPU参考实现 - 稳定排序
template<typename KeyType, typename ValueType>
void cpuSortPair(std::vector<KeyType>& keys, std::vector<ValueType>& values, bool descending) {
std::vector<std::pair<KeyType, ValueType>> pairs;
for (size_t i = 0; i < keys.size(); i++) {
pairs.emplace_back(keys[i], values[i]);
}
if (descending) {
std::stable_sort(pairs.begin(), pairs.end(),
[](const auto& a, const auto& b) { return a.first > b.first; });
} else {
std::stable_sort(pairs.begin(), pairs.end());
}
for (size_t i = 0; i < pairs.size(); i++) {
keys[i] = pairs[i].first;
values[i] = pairs[i].second;
}
}
// CPU参考实现 - TopK
template<typename KeyType, typename ValueType>
void cpuTopkPair(const std::vector<KeyType>& keys_in, const std::vector<ValueType>& values_in,
std::vector<KeyType>& keys_out, std::vector<ValueType>& values_out,
int k, bool descending) {
std::vector<std::pair<KeyType, ValueType>> pairs;
for (size_t i = 0; i < keys_in.size(); i++) {
pairs.emplace_back(keys_in[i], values_in[i]);
}
if (descending) {
std::stable_sort(pairs.begin(), pairs.end(),
[](const auto& a, const auto& b) { return a.first > b.first; });
} else {
std::stable_sort(pairs.begin(), pairs.end());
}
keys_out.resize(k);
values_out.resize(k);
for (int i = 0; i < k; i++) {
keys_out[i] = pairs[i].first;
values_out[i] = pairs[i].second;
}
}
// CPU参考实现 - ReduceSum (使用double精度)
template<typename InputT>
double cpuReduceSum(const std::vector<InputT>& data, double init_value) {
double sum = init_value;
for (const auto& val : data) {
if constexpr (std::is_same_v<InputT, half>) {
float f_val = __half2float(val);
if (!std::isnan(f_val)) {
sum += static_cast<double>(f_val);
}
} else {
if (!std::isnan(val)) {
sum += static_cast<double>(val);
}
}
}
return sum;
}

154
S1/3/utils/yaml_reporter.h Normal file
View File

@@ -0,0 +1,154 @@
#pragma once
#include <fstream>
#include <vector>
#include <map>
#include <string>
#include <chrono>
#include <iomanip>
#include <sstream>
// ============================================================================
// YAML性能报告生成器
// ============================================================================
class YAMLPerformanceReporter {
public:
struct PerformanceData {
std::string algorithm;
std::string input_type;
std::string output_type;
std::string key_type;
std::string value_type;
std::vector<std::map<std::string, std::string>> metrics;
};
// 创建性能数据条目
static std::map<std::string, std::string> createEntry() {
return std::map<std::string, std::string>();
}
// 生成ReduceSum性能YAML
static void generateReduceSumYAML(const std::vector<std::map<std::string, std::string>>& perf_data,
const std::string& filename = "reduce_sum_performance.yaml") {
std::ofstream yaml_file(filename);
// 写入头部信息
writeHeader(yaml_file, "ReduceSum算法性能测试结果");
// 算法信息
yaml_file << "algorithm: \"ReduceSum\"\n";
yaml_file << "data_types:\n";
yaml_file << " input: \"float\"\n";
yaml_file << " output: \"float\"\n";
// 计算公式
yaml_file << "formulas:\n";
yaml_file << " throughput: \"elements / time(s) / 1e9 (G/s)\"\n";
// 性能数据
yaml_file << "performance_data:\n";
for (const auto& data : perf_data) {
yaml_file << " - data_size: " << data.at("data_size") << "\n";
yaml_file << " time_ms: " << formatFloat(data.at("time_ms")) << "\n";
yaml_file << " throughput_gps: " << formatFloat(data.at("throughput_gps")) << "\n";
yaml_file << " data_type: \"" << data.at("data_type") << "\"\n";
}
yaml_file.close();
}
// 生成SortPair性能YAML
static void generateSortPairYAML(const std::vector<std::map<std::string, std::string>>& perf_data,
const std::string& filename = "sort_pair_performance.yaml") {
std::ofstream yaml_file(filename);
// 写入头部信息
writeHeader(yaml_file, "SortPair算法性能测试结果");
// 算法信息
yaml_file << "algorithm: \"SortPair\"\n";
yaml_file << "data_types:\n";
yaml_file << " key_type: \"float\"\n";
yaml_file << " value_type: \"uint32_t\"\n";
// 计算公式
yaml_file << "formulas:\n";
yaml_file << " throughput: \"elements / time(s) / 1e9 (G/s)\"\n";
// 性能数据
yaml_file << "performance_data:\n";
for (const auto& data : perf_data) {
yaml_file << " - data_size: " << data.at("data_size") << "\n";
yaml_file << " ascending:\n";
yaml_file << " time_ms: " << formatFloat(data.at("asc_time_ms")) << "\n";
yaml_file << " throughput_gps: " << formatFloat(data.at("asc_throughput_gps")) << "\n";
yaml_file << " descending:\n";
yaml_file << " time_ms: " << formatFloat(data.at("desc_time_ms")) << "\n";
yaml_file << " throughput_gps: " << formatFloat(data.at("desc_throughput_gps")) << "\n";
yaml_file << " key_type: \"" << data.at("key_type") << "\"\n";
yaml_file << " value_type: \"" << data.at("value_type") << "\"\n";
}
yaml_file.close();
}
// 生成TopkPair性能YAML
static void generateTopkPairYAML(const std::vector<std::map<std::string, std::string>>& perf_data,
const std::string& filename = "topk_pair_performance.yaml") {
std::ofstream yaml_file(filename);
// 写入头部信息
writeHeader(yaml_file, "TopkPair算法性能测试结果");
// 算法信息
yaml_file << "algorithm: \"TopkPair\"\n";
yaml_file << "data_types:\n";
yaml_file << " key_type: \"float\"\n";
yaml_file << " value_type: \"uint32_t\"\n";
// 计算公式
yaml_file << "formulas:\n";
yaml_file << " throughput: \"elements / time(s) / 1e9 (G/s)\"\n";
// 性能数据
yaml_file << "performance_data:\n";
for (const auto& data : perf_data) {
yaml_file << " - data_size: " << data.at("data_size") << "\n";
yaml_file << " k_value: " << data.at("k_value") << "\n";
yaml_file << " ascending:\n";
yaml_file << " time_ms: " << formatFloat(data.at("asc_time_ms")) << "\n";
yaml_file << " throughput_gps: " << formatFloat(data.at("asc_throughput_gps")) << "\n";
yaml_file << " descending:\n";
yaml_file << " time_ms: " << formatFloat(data.at("desc_time_ms")) << "\n";
yaml_file << " throughput_gps: " << formatFloat(data.at("desc_throughput_gps")) << "\n";
yaml_file << " key_type: \"" << data.at("key_type") << "\"\n";
yaml_file << " value_type: \"" << data.at("value_type") << "\"\n";
}
yaml_file.close();
}
private:
// 写入YAML文件头部
static void writeHeader(std::ofstream& file, const std::string& title) {
file << "# " << title << "\n";
file << "# 生成时间: ";
auto now = std::chrono::system_clock::now();
auto time_t = std::chrono::system_clock::to_time_t(now);
file << std::put_time(std::localtime(&time_t), "%Y-%m-%d %H:%M:%S");
file << "\n\n";
}
// 格式化浮点数
static std::string formatFloat(const std::string& value) {
try {
double d = std::stod(value);
std::ostringstream oss;
oss << std::fixed << std::setprecision(6) << d;
return oss.str();
} catch (...) {
return value;
}
}
};