feat: add memory profiling support #39
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Submodule instrument-hooks
updated
14 files
| +1 −0 | .github/workflows/ci.yml | |
| +5 −2 | Justfile | |
| +3,280 −2,736 | dist/core.c | |
| +0 −13 | src/c.zig | |
| +6 −0 | src/instruments/analysis.zig | |
| +61 −0 | src/instruments/fifo_instrument.zig | |
| +3 −155 | src/instruments/perf.zig | |
| +25 −14 | src/instruments/root.zig | |
| +5 −1 | src/instruments/valgrind.zig | |
| +199 −0 | src/runner_fifo.zig | |
| +20 −0 | src/shared.zig | |
| +52 −20 | src/tests/deserialize_rust/create_serialized.rs | |
| +29 −0 | src/tests/deserialize_rust/rust_deser.zig | |
| +138 −0 | src/tests/deserialize_rust/serialized.zig |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1 @@ | ||
| ../google_benchmark_cmake/memory_bench.hpp |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,197 @@ | ||
| #pragma once | ||
|
|
||
| #include <benchmark/benchmark.h> | ||
|
|
||
| #include <string> | ||
| #include <vector> | ||
|
|
||
| // Run-length encoding: compress consecutive repeated characters | ||
| // Example: "aaabbbccc" -> "3a3b3c" | ||
| // NOTE: Intentionally inefficient - no pre-allocation to show multiple | ||
| // allocations | ||
| static std::string rle_encode(const std::string& input) { | ||
| if (input.empty()) return ""; | ||
|
|
||
| std::string result; // No reserve - will trigger multiple reallocations | ||
|
|
||
| char current = input[0]; | ||
| size_t count = 1; | ||
|
|
||
| for (size_t i = 1; i < input.size(); ++i) { | ||
| if (input[i] == current) { | ||
| count++; | ||
| } else { | ||
| // Create intermediate strings for each run | ||
| std::string count_str = std::to_string(count); | ||
| std::string run_encoded = count_str + current; | ||
| result += run_encoded; // Concatenation causes reallocations | ||
| current = input[i]; | ||
| count = 1; | ||
| } | ||
| } | ||
|
|
||
| // Final run | ||
| std::string count_str = std::to_string(count); | ||
| std::string final_run = count_str + current; | ||
| result += final_run; | ||
|
|
||
| return result; | ||
| } | ||
|
|
||
| // Run-length decoding: decompress RLE encoded string | ||
| // Example: "3a3b3c" -> "aaabbbccc" | ||
| static std::string rle_decode(const std::string& input) { | ||
| std::string result; | ||
| size_t i = 0; | ||
|
|
||
| while (i < input.size()) { | ||
| // Parse the count | ||
| size_t count = 0; | ||
| while (i < input.size() && std::isdigit(input[i])) { | ||
| count = count * 10 + (input[i] - '0'); | ||
| i++; | ||
| } | ||
|
|
||
| // Get the character | ||
| if (i < input.size()) { | ||
| char ch = input[i]; | ||
| result.append(count, ch); | ||
| i++; | ||
| } | ||
| } | ||
|
|
||
| return result; | ||
| } | ||
|
|
||
| // Generate a string with patterns for RLE | ||
| static std::string generate_rle_input(size_t size, size_t run_length) { | ||
| std::string result; | ||
| result.reserve(size); | ||
|
|
||
| const std::string chars = "abcdefghijklmnopqrstuvwxyz"; | ||
| size_t char_idx = 0; | ||
|
|
||
| while (result.size() < size) { | ||
| size_t count = std::min(run_length, size - result.size()); | ||
| result.append(count, chars[char_idx % chars.size()]); | ||
| char_idx++; | ||
| } | ||
|
|
||
| return result; | ||
| } | ||
|
|
||
| // Benchmark: RLE encoding with small runs (high compression) | ||
| static void BM_RLE_Encode_SmallRuns(benchmark::State& state) { | ||
| const size_t input_size = state.range(0); | ||
| std::string input = generate_rle_input(input_size, 3); | ||
|
|
||
| for (auto _ : state) { | ||
| std::string encoded = rle_encode(input); | ||
| benchmark::DoNotOptimize(encoded); | ||
| benchmark::ClobberMemory(); | ||
| } | ||
|
|
||
| state.SetBytesProcessed(state.iterations() * input_size); | ||
| } | ||
| BENCHMARK(BM_RLE_Encode_SmallRuns) | ||
| ->Arg(100) | ||
| ->Arg(1000) | ||
| ->Arg(10000) | ||
| ->Arg(100000); | ||
|
|
||
| // Benchmark: RLE encoding with large runs (low compression) | ||
| static void BM_RLE_Encode_LargeRuns(benchmark::State& state) { | ||
| const size_t input_size = state.range(0); | ||
| std::string input = generate_rle_input(input_size, 100); | ||
|
|
||
| for (auto _ : state) { | ||
| std::string encoded = rle_encode(input); | ||
| benchmark::DoNotOptimize(encoded); | ||
| benchmark::ClobberMemory(); | ||
| } | ||
|
|
||
| state.SetBytesProcessed(state.iterations() * input_size); | ||
| } | ||
| BENCHMARK(BM_RLE_Encode_LargeRuns) | ||
| ->Arg(100) | ||
| ->Arg(1000) | ||
| ->Arg(10000) | ||
| ->Arg(100000); | ||
|
|
||
| // Benchmark: RLE decoding | ||
| static void BM_RLE_Decode(benchmark::State& state) { | ||
| const size_t input_size = state.range(0); | ||
| std::string input = generate_rle_input(input_size, 10); | ||
| std::string encoded = rle_encode(input); | ||
|
|
||
| for (auto _ : state) { | ||
| std::string decoded = rle_decode(encoded); | ||
| benchmark::DoNotOptimize(decoded); | ||
| benchmark::ClobberMemory(); | ||
| } | ||
|
|
||
| state.SetBytesProcessed(state.iterations() * encoded.size()); | ||
| } | ||
| BENCHMARK(BM_RLE_Decode)->Arg(100)->Arg(1000)->Arg(10000)->Arg(100000); | ||
|
|
||
| // Benchmark: Vector allocations (resizing pattern) | ||
| static void BM_Vector_PushBack(benchmark::State& state) { | ||
| const size_t count = state.range(0); | ||
|
|
||
| for (auto _ : state) { | ||
| std::vector<int> vec; | ||
| for (size_t i = 0; i < count; ++i) { | ||
| vec.push_back(static_cast<int>(i)); | ||
| } | ||
| benchmark::DoNotOptimize(vec); | ||
| benchmark::ClobberMemory(); | ||
| } | ||
| } | ||
| BENCHMARK(BM_Vector_PushBack)->Arg(10)->Arg(100)->Arg(1000)->Arg(10000); | ||
|
|
||
| // Benchmark: Vector allocations with reserve (optimized) | ||
| static void BM_Vector_Reserve(benchmark::State& state) { | ||
| const size_t count = state.range(0); | ||
|
|
||
| for (auto _ : state) { | ||
| std::vector<int> vec; | ||
| vec.reserve(count); | ||
| for (size_t i = 0; i < count; ++i) { | ||
| vec.push_back(static_cast<int>(i)); | ||
| } | ||
| benchmark::DoNotOptimize(vec); | ||
| benchmark::ClobberMemory(); | ||
| } | ||
| } | ||
| BENCHMARK(BM_Vector_Reserve)->Arg(10)->Arg(100)->Arg(1000)->Arg(10000); | ||
|
|
||
| // Benchmark: String concatenation (many allocations) | ||
| static void BM_String_Concatenation(benchmark::State& state) { | ||
| const size_t count = state.range(0); | ||
|
|
||
| for (auto _ : state) { | ||
| std::string result; | ||
| for (size_t i = 0; i < count; ++i) { | ||
| result += "x"; | ||
| } | ||
| benchmark::DoNotOptimize(result); | ||
| benchmark::ClobberMemory(); | ||
| } | ||
| } | ||
| BENCHMARK(BM_String_Concatenation)->Arg(10)->Arg(100)->Arg(1000)->Arg(10000); | ||
|
|
||
| // Benchmark: String concatenation with reserve (optimized) | ||
| static void BM_String_Reserve(benchmark::State& state) { | ||
| const size_t count = state.range(0); | ||
|
|
||
| for (auto _ : state) { | ||
| std::string result; | ||
| result.reserve(count); | ||
| for (size_t i = 0; i < count; ++i) { | ||
| result += "x"; | ||
| } | ||
| benchmark::DoNotOptimize(result); | ||
| benchmark::ClobberMemory(); | ||
| } | ||
| } | ||
| BENCHMARK(BM_String_Reserve)->Arg(10)->Arg(100)->Arg(1000)->Arg(10000); |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
|
|
@@ -186,15 +186,15 @@ State::State(std::string name, IterationCount max_iters, | |||||
| internal::ThreadTimer* timer, internal::ThreadManager* manager, | ||||||
| internal::PerfCountersMeasurement* perf_counters_measurement, | ||||||
| ProfilerManager* profiler_manager | ||||||
| #if defined(CODSPEED_ANALYSIS) || defined(CODSPEED_WALLTIME) | ||||||
| , | ||||||
| codspeed::CodSpeed* codspeed | ||||||
| #endif | ||||||
| ) | ||||||
| : total_iterations_(0), | ||||||
| batch_leftover_(0), | ||||||
| max_iterations(max_iters), | ||||||
| #if defined(CODSPEED_ANALYSIS) || defined(CODSPEED_WALLTIME) | ||||||
| codspeed_(codspeed), | ||||||
| #endif | ||||||
| #ifdef CODSPEED_WALLTIME | ||||||
|
|
@@ -462,7 +462,7 @@ void RunBenchmarks(const std::vector<BenchmarkInstance>& benchmarks, | |||||
| #ifdef CODSPEED_ENABLED | ||||||
| auto& Err = display_reporter->GetErrorStream(); | ||||||
| // Determine the width of the name field using a minimum width of 10. | ||||||
| #ifdef CODSPEED_ANALYSIS | ||||||
| Err << "Codspeed mode: simulation" << "\n"; | ||||||
|
There was a problem hiding this comment. The error message still says 'simulation' but this code path is now used for both simulation and memory modes under CODSPEED_ANALYSIS. The message should differentiate between these modes or be more generic.
Suggested change
Member
Author
There was a problem hiding this comment. Not sure if printing analysis is the best UX, since we said it should be only the internal build mode. I guess we could forward the real measurement mode and then print that, while also enabling CODSPEED_WALLTIME/CODSPEED_ANALYSIS. wdyt? |
||||||
| #elif defined(CODSPEED_WALLTIME) | ||||||
| Err << "Codspeed mode: walltime" << "\n"; | ||||||
|
|
||||||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.