You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

138 lines
4.4 KiB

Add dun_render_benchmark Results from a single run (a bit noisy) on my machine: ``` tools/build_and_run_benchmark.py dun_render_benchmark ``` ``` ------------------------------------------------------------------------------------------------------------------------ Benchmark Time CPU Iterations UserCounters... ------------------------------------------------------------------------------------------------------------------------ DunRenderBenchmark/LeftTriangle_Solid_FullyLit 98297 ns 98282 ns 8840 items_per_second=15.1096M/s DunRenderBenchmark/LeftTriangle_Solid_FullyDark 124727 ns 124701 ns 6973 items_per_second=11.9085M/s DunRenderBenchmark/LeftTriangle_Solid_PartiallyLit 514869 ns 514747 ns 1700 items_per_second=2.88491M/s DunRenderBenchmark/LeftTriangle_Transparent_FullyLit 520312 ns 520216 ns 1682 items_per_second=2.85458M/s DunRenderBenchmark/LeftTriangle_Transparent_FullyDark 524440 ns 524331 ns 1664 items_per_second=2.83218M/s DunRenderBenchmark/LeftTriangle_Transparent_PartiallyLit 532300 ns 532162 ns 1647 items_per_second=2.7905M/s DunRenderBenchmark/RightTriangle_Solid_FullyLit 92387 ns 92363 ns 8840 items_per_second=16.7275M/s DunRenderBenchmark/RightTriangle_Solid_FullyDark 85680 ns 85662 ns 9884 items_per_second=18.0361M/s DunRenderBenchmark/RightTriangle_Solid_PartiallyLit 538347 ns 538250 ns 1626 items_per_second=2.87041M/s DunRenderBenchmark/RightTriangle_Transparent_FullyLit 548800 ns 548760 ns 1598 items_per_second=2.81544M/s DunRenderBenchmark/RightTriangle_Transparent_FullyDark 540450 ns 540369 ns 1620 items_per_second=2.85916M/s DunRenderBenchmark/RightTriangle_Transparent_PartiallyLit 555061 ns 555003 ns 1575 items_per_second=2.78377M/s DunRenderBenchmark/TransparentSquare_Solid_FullyLit 700849 ns 700751 ns 1320 items_per_second=3.68176M/s DunRenderBenchmark/TransparentSquare_Solid_FullyDark 664927 ns 664872 ns 1389 items_per_second=3.88045M/s DunRenderBenchmark/TransparentSquare_Solid_PartiallyLit 1131702 ns 1131559 ns 822 items_per_second=2.28004M/s DunRenderBenchmark/TransparentSquare_Transparent_FullyLit 1022384 ns 1022267 ns 916 items_per_second=2.5238M/s DunRenderBenchmark/TransparentSquare_Transparent_FullyDark 1023193 ns 1023057 ns 900 items_per_second=2.52185M/s DunRenderBenchmark/TransparentSquare_Transparent_PartiallyLit 1033573 ns 1033496 ns 895 items_per_second=2.49638M/s DunRenderBenchmark/Square_Solid_FullyLit 53532 ns 53524 ns 10000 items_per_second=30.8272M/s DunRenderBenchmark/Square_Solid_FullyDark 41993 ns 41987 ns 19794 items_per_second=47.1573M/s DunRenderBenchmark/Square_Solid_PartiallyLit 842772 ns 842615 ns 1108 items_per_second=1.56655M/s DunRenderBenchmark/Square_Transparent_FullyLit 834105 ns 834026 ns 1119 items_per_second=1.58269M/s DunRenderBenchmark/Square_Transparent_FullyDark 831912 ns 831823 ns 1122 items_per_second=1.58688M/s DunRenderBenchmark/Square_Transparent_PartiallyLit 924638 ns 924536 ns 1010 items_per_second=1.42774M/s DunRenderBenchmark/LeftTrapezoid_Solid_FullyLit 33728 ns 33725 ns 24962 items_per_second=18.8583M/s DunRenderBenchmark/LeftTrapezoid_Solid_FullyDark 31088 ns 31085 ns 27444 items_per_second=20.4601M/s DunRenderBenchmark/LeftTrapezoid_Solid_PartiallyLit 268792 ns 268768 ns 3254 items_per_second=1.97196M/s DunRenderBenchmark/LeftTrapezoid_Transparent_FullyLit 277990 ns 277965 ns 3140 items_per_second=1.90672M/s DunRenderBenchmark/LeftTrapezoid_Transparent_FullyDark 268952 ns 268912 ns 3250 items_per_second=1.9709M/s DunRenderBenchmark/LeftTrapezoid_Transparent_PartiallyLit 288869 ns 288826 ns 3056 items_per_second=1.83501M/s DunRenderBenchmark/RightTrapezoid_Solid_FullyLit 29581 ns 29576 ns 28347 items_per_second=21.0984M/s DunRenderBenchmark/RightTrapezoid_Solid_FullyDark 25315 ns 25312 ns 32250 items_per_second=24.6523M/s DunRenderBenchmark/RightTrapezoid_Solid_PartiallyLit 259977 ns 259960 ns 3312 items_per_second=2.0003M/s DunRenderBenchmark/RightTrapezoid_Transparent_FullyLit 263079 ns 263056 ns 3322 items_per_second=1.97677M/s DunRenderBenchmark/RightTrapezoid_Transparent_FullyDark 259849 ns 259824 ns 3364 items_per_second=2.00136M/s DunRenderBenchmark/RightTrapezoid_Transparent_PartiallyLit 279623 ns 279594 ns 3127 items_per_second=1.85984M/s ```
2 years ago
#include <cstddef>
#include <span>
#include <ankerl/unordered_dense.h>
#include <benchmark/benchmark.h>
#include "diablo.h"
#include "engine/assets.hpp"
Add dun_render_benchmark Results from a single run (a bit noisy) on my machine: ``` tools/build_and_run_benchmark.py dun_render_benchmark ``` ``` ------------------------------------------------------------------------------------------------------------------------ Benchmark Time CPU Iterations UserCounters... ------------------------------------------------------------------------------------------------------------------------ DunRenderBenchmark/LeftTriangle_Solid_FullyLit 98297 ns 98282 ns 8840 items_per_second=15.1096M/s DunRenderBenchmark/LeftTriangle_Solid_FullyDark 124727 ns 124701 ns 6973 items_per_second=11.9085M/s DunRenderBenchmark/LeftTriangle_Solid_PartiallyLit 514869 ns 514747 ns 1700 items_per_second=2.88491M/s DunRenderBenchmark/LeftTriangle_Transparent_FullyLit 520312 ns 520216 ns 1682 items_per_second=2.85458M/s DunRenderBenchmark/LeftTriangle_Transparent_FullyDark 524440 ns 524331 ns 1664 items_per_second=2.83218M/s DunRenderBenchmark/LeftTriangle_Transparent_PartiallyLit 532300 ns 532162 ns 1647 items_per_second=2.7905M/s DunRenderBenchmark/RightTriangle_Solid_FullyLit 92387 ns 92363 ns 8840 items_per_second=16.7275M/s DunRenderBenchmark/RightTriangle_Solid_FullyDark 85680 ns 85662 ns 9884 items_per_second=18.0361M/s DunRenderBenchmark/RightTriangle_Solid_PartiallyLit 538347 ns 538250 ns 1626 items_per_second=2.87041M/s DunRenderBenchmark/RightTriangle_Transparent_FullyLit 548800 ns 548760 ns 1598 items_per_second=2.81544M/s DunRenderBenchmark/RightTriangle_Transparent_FullyDark 540450 ns 540369 ns 1620 items_per_second=2.85916M/s DunRenderBenchmark/RightTriangle_Transparent_PartiallyLit 555061 ns 555003 ns 1575 items_per_second=2.78377M/s DunRenderBenchmark/TransparentSquare_Solid_FullyLit 700849 ns 700751 ns 1320 items_per_second=3.68176M/s DunRenderBenchmark/TransparentSquare_Solid_FullyDark 664927 ns 664872 ns 1389 items_per_second=3.88045M/s DunRenderBenchmark/TransparentSquare_Solid_PartiallyLit 1131702 ns 1131559 ns 822 items_per_second=2.28004M/s DunRenderBenchmark/TransparentSquare_Transparent_FullyLit 1022384 ns 1022267 ns 916 items_per_second=2.5238M/s DunRenderBenchmark/TransparentSquare_Transparent_FullyDark 1023193 ns 1023057 ns 900 items_per_second=2.52185M/s DunRenderBenchmark/TransparentSquare_Transparent_PartiallyLit 1033573 ns 1033496 ns 895 items_per_second=2.49638M/s DunRenderBenchmark/Square_Solid_FullyLit 53532 ns 53524 ns 10000 items_per_second=30.8272M/s DunRenderBenchmark/Square_Solid_FullyDark 41993 ns 41987 ns 19794 items_per_second=47.1573M/s DunRenderBenchmark/Square_Solid_PartiallyLit 842772 ns 842615 ns 1108 items_per_second=1.56655M/s DunRenderBenchmark/Square_Transparent_FullyLit 834105 ns 834026 ns 1119 items_per_second=1.58269M/s DunRenderBenchmark/Square_Transparent_FullyDark 831912 ns 831823 ns 1122 items_per_second=1.58688M/s DunRenderBenchmark/Square_Transparent_PartiallyLit 924638 ns 924536 ns 1010 items_per_second=1.42774M/s DunRenderBenchmark/LeftTrapezoid_Solid_FullyLit 33728 ns 33725 ns 24962 items_per_second=18.8583M/s DunRenderBenchmark/LeftTrapezoid_Solid_FullyDark 31088 ns 31085 ns 27444 items_per_second=20.4601M/s DunRenderBenchmark/LeftTrapezoid_Solid_PartiallyLit 268792 ns 268768 ns 3254 items_per_second=1.97196M/s DunRenderBenchmark/LeftTrapezoid_Transparent_FullyLit 277990 ns 277965 ns 3140 items_per_second=1.90672M/s DunRenderBenchmark/LeftTrapezoid_Transparent_FullyDark 268952 ns 268912 ns 3250 items_per_second=1.9709M/s DunRenderBenchmark/LeftTrapezoid_Transparent_PartiallyLit 288869 ns 288826 ns 3056 items_per_second=1.83501M/s DunRenderBenchmark/RightTrapezoid_Solid_FullyLit 29581 ns 29576 ns 28347 items_per_second=21.0984M/s DunRenderBenchmark/RightTrapezoid_Solid_FullyDark 25315 ns 25312 ns 32250 items_per_second=24.6523M/s DunRenderBenchmark/RightTrapezoid_Solid_PartiallyLit 259977 ns 259960 ns 3312 items_per_second=2.0003M/s DunRenderBenchmark/RightTrapezoid_Transparent_FullyLit 263079 ns 263056 ns 3322 items_per_second=1.97677M/s DunRenderBenchmark/RightTrapezoid_Transparent_FullyDark 259849 ns 259824 ns 3364 items_per_second=2.00136M/s DunRenderBenchmark/RightTrapezoid_Transparent_PartiallyLit 279623 ns 279594 ns 3127 items_per_second=1.85984M/s ```
2 years ago
#include "engine/clx_sprite.hpp"
#include "engine/displacement.hpp"
#include "engine/load_file.hpp"
#include "engine/render/dun_render.hpp"
#include "engine/surface.hpp"
#include "levels/dun_tile.hpp"
#include "levels/gendung.h"
#include "lighting.h"
#include "options.h"
#include "utils/log.hpp"
#include "utils/sdl_wrap.h"
namespace devilution {
namespace {
SDLSurfaceUniquePtr SdlSurface;
ankerl::unordered_dense::map<TileType, std::vector<LevelCelBlock>> Tiles;
void InitOnce()
{
[[maybe_unused]] static const bool GlobalInitDone = []() {
LoadCoreArchives();
LoadGameArchives();
if (!HaveMainData()) {
Add dun_render_benchmark Results from a single run (a bit noisy) on my machine: ``` tools/build_and_run_benchmark.py dun_render_benchmark ``` ``` ------------------------------------------------------------------------------------------------------------------------ Benchmark Time CPU Iterations UserCounters... ------------------------------------------------------------------------------------------------------------------------ DunRenderBenchmark/LeftTriangle_Solid_FullyLit 98297 ns 98282 ns 8840 items_per_second=15.1096M/s DunRenderBenchmark/LeftTriangle_Solid_FullyDark 124727 ns 124701 ns 6973 items_per_second=11.9085M/s DunRenderBenchmark/LeftTriangle_Solid_PartiallyLit 514869 ns 514747 ns 1700 items_per_second=2.88491M/s DunRenderBenchmark/LeftTriangle_Transparent_FullyLit 520312 ns 520216 ns 1682 items_per_second=2.85458M/s DunRenderBenchmark/LeftTriangle_Transparent_FullyDark 524440 ns 524331 ns 1664 items_per_second=2.83218M/s DunRenderBenchmark/LeftTriangle_Transparent_PartiallyLit 532300 ns 532162 ns 1647 items_per_second=2.7905M/s DunRenderBenchmark/RightTriangle_Solid_FullyLit 92387 ns 92363 ns 8840 items_per_second=16.7275M/s DunRenderBenchmark/RightTriangle_Solid_FullyDark 85680 ns 85662 ns 9884 items_per_second=18.0361M/s DunRenderBenchmark/RightTriangle_Solid_PartiallyLit 538347 ns 538250 ns 1626 items_per_second=2.87041M/s DunRenderBenchmark/RightTriangle_Transparent_FullyLit 548800 ns 548760 ns 1598 items_per_second=2.81544M/s DunRenderBenchmark/RightTriangle_Transparent_FullyDark 540450 ns 540369 ns 1620 items_per_second=2.85916M/s DunRenderBenchmark/RightTriangle_Transparent_PartiallyLit 555061 ns 555003 ns 1575 items_per_second=2.78377M/s DunRenderBenchmark/TransparentSquare_Solid_FullyLit 700849 ns 700751 ns 1320 items_per_second=3.68176M/s DunRenderBenchmark/TransparentSquare_Solid_FullyDark 664927 ns 664872 ns 1389 items_per_second=3.88045M/s DunRenderBenchmark/TransparentSquare_Solid_PartiallyLit 1131702 ns 1131559 ns 822 items_per_second=2.28004M/s DunRenderBenchmark/TransparentSquare_Transparent_FullyLit 1022384 ns 1022267 ns 916 items_per_second=2.5238M/s DunRenderBenchmark/TransparentSquare_Transparent_FullyDark 1023193 ns 1023057 ns 900 items_per_second=2.52185M/s DunRenderBenchmark/TransparentSquare_Transparent_PartiallyLit 1033573 ns 1033496 ns 895 items_per_second=2.49638M/s DunRenderBenchmark/Square_Solid_FullyLit 53532 ns 53524 ns 10000 items_per_second=30.8272M/s DunRenderBenchmark/Square_Solid_FullyDark 41993 ns 41987 ns 19794 items_per_second=47.1573M/s DunRenderBenchmark/Square_Solid_PartiallyLit 842772 ns 842615 ns 1108 items_per_second=1.56655M/s DunRenderBenchmark/Square_Transparent_FullyLit 834105 ns 834026 ns 1119 items_per_second=1.58269M/s DunRenderBenchmark/Square_Transparent_FullyDark 831912 ns 831823 ns 1122 items_per_second=1.58688M/s DunRenderBenchmark/Square_Transparent_PartiallyLit 924638 ns 924536 ns 1010 items_per_second=1.42774M/s DunRenderBenchmark/LeftTrapezoid_Solid_FullyLit 33728 ns 33725 ns 24962 items_per_second=18.8583M/s DunRenderBenchmark/LeftTrapezoid_Solid_FullyDark 31088 ns 31085 ns 27444 items_per_second=20.4601M/s DunRenderBenchmark/LeftTrapezoid_Solid_PartiallyLit 268792 ns 268768 ns 3254 items_per_second=1.97196M/s DunRenderBenchmark/LeftTrapezoid_Transparent_FullyLit 277990 ns 277965 ns 3140 items_per_second=1.90672M/s DunRenderBenchmark/LeftTrapezoid_Transparent_FullyDark 268952 ns 268912 ns 3250 items_per_second=1.9709M/s DunRenderBenchmark/LeftTrapezoid_Transparent_PartiallyLit 288869 ns 288826 ns 3056 items_per_second=1.83501M/s DunRenderBenchmark/RightTrapezoid_Solid_FullyLit 29581 ns 29576 ns 28347 items_per_second=21.0984M/s DunRenderBenchmark/RightTrapezoid_Solid_FullyDark 25315 ns 25312 ns 32250 items_per_second=24.6523M/s DunRenderBenchmark/RightTrapezoid_Solid_PartiallyLit 259977 ns 259960 ns 3312 items_per_second=2.0003M/s DunRenderBenchmark/RightTrapezoid_Transparent_FullyLit 263079 ns 263056 ns 3322 items_per_second=1.97677M/s DunRenderBenchmark/RightTrapezoid_Transparent_FullyDark 259849 ns 259824 ns 3364 items_per_second=2.00136M/s DunRenderBenchmark/RightTrapezoid_Transparent_PartiallyLit 279623 ns 279594 ns 3127 items_per_second=1.85984M/s ```
2 years ago
LogError("This benchmark needs spawn.mpq or diabdat.mpq");
exit(1);
}
leveltype = DTYPE_CATHEDRAL;
pDungeonCels = LoadFileInMem("levels\\l1data\\l1.cel");
SetDungeonMicros();
MakeLightTable();
SdlSurface = SDLWrap::CreateRGBSurfaceWithFormat(
/*flags=*/0, /*width=*/640, /*height=*/480, /*depth=*/8, SDL_PIXELFORMAT_INDEX8);
if (SdlSurface == nullptr) {
LogError("Failed to create SDL Surface: {}", SDL_GetError());
exit(1);
}
for (size_t i = 0; i < 700; ++i) {
for (size_t j = 0; j < 10; ++j) {
if (const LevelCelBlock levelCelBlock = DPieceMicros[i].mt[j]; levelCelBlock.hasValue()) {
if ((j == 0 || j == 1) && levelCelBlock.type() == TileType::TransparentSquare) {
// This could actually be re-encoded foliage, which is a triangle followed by TransparentSquare.
// Simply skip it.
continue;
}
Add dun_render_benchmark Results from a single run (a bit noisy) on my machine: ``` tools/build_and_run_benchmark.py dun_render_benchmark ``` ``` ------------------------------------------------------------------------------------------------------------------------ Benchmark Time CPU Iterations UserCounters... ------------------------------------------------------------------------------------------------------------------------ DunRenderBenchmark/LeftTriangle_Solid_FullyLit 98297 ns 98282 ns 8840 items_per_second=15.1096M/s DunRenderBenchmark/LeftTriangle_Solid_FullyDark 124727 ns 124701 ns 6973 items_per_second=11.9085M/s DunRenderBenchmark/LeftTriangle_Solid_PartiallyLit 514869 ns 514747 ns 1700 items_per_second=2.88491M/s DunRenderBenchmark/LeftTriangle_Transparent_FullyLit 520312 ns 520216 ns 1682 items_per_second=2.85458M/s DunRenderBenchmark/LeftTriangle_Transparent_FullyDark 524440 ns 524331 ns 1664 items_per_second=2.83218M/s DunRenderBenchmark/LeftTriangle_Transparent_PartiallyLit 532300 ns 532162 ns 1647 items_per_second=2.7905M/s DunRenderBenchmark/RightTriangle_Solid_FullyLit 92387 ns 92363 ns 8840 items_per_second=16.7275M/s DunRenderBenchmark/RightTriangle_Solid_FullyDark 85680 ns 85662 ns 9884 items_per_second=18.0361M/s DunRenderBenchmark/RightTriangle_Solid_PartiallyLit 538347 ns 538250 ns 1626 items_per_second=2.87041M/s DunRenderBenchmark/RightTriangle_Transparent_FullyLit 548800 ns 548760 ns 1598 items_per_second=2.81544M/s DunRenderBenchmark/RightTriangle_Transparent_FullyDark 540450 ns 540369 ns 1620 items_per_second=2.85916M/s DunRenderBenchmark/RightTriangle_Transparent_PartiallyLit 555061 ns 555003 ns 1575 items_per_second=2.78377M/s DunRenderBenchmark/TransparentSquare_Solid_FullyLit 700849 ns 700751 ns 1320 items_per_second=3.68176M/s DunRenderBenchmark/TransparentSquare_Solid_FullyDark 664927 ns 664872 ns 1389 items_per_second=3.88045M/s DunRenderBenchmark/TransparentSquare_Solid_PartiallyLit 1131702 ns 1131559 ns 822 items_per_second=2.28004M/s DunRenderBenchmark/TransparentSquare_Transparent_FullyLit 1022384 ns 1022267 ns 916 items_per_second=2.5238M/s DunRenderBenchmark/TransparentSquare_Transparent_FullyDark 1023193 ns 1023057 ns 900 items_per_second=2.52185M/s DunRenderBenchmark/TransparentSquare_Transparent_PartiallyLit 1033573 ns 1033496 ns 895 items_per_second=2.49638M/s DunRenderBenchmark/Square_Solid_FullyLit 53532 ns 53524 ns 10000 items_per_second=30.8272M/s DunRenderBenchmark/Square_Solid_FullyDark 41993 ns 41987 ns 19794 items_per_second=47.1573M/s DunRenderBenchmark/Square_Solid_PartiallyLit 842772 ns 842615 ns 1108 items_per_second=1.56655M/s DunRenderBenchmark/Square_Transparent_FullyLit 834105 ns 834026 ns 1119 items_per_second=1.58269M/s DunRenderBenchmark/Square_Transparent_FullyDark 831912 ns 831823 ns 1122 items_per_second=1.58688M/s DunRenderBenchmark/Square_Transparent_PartiallyLit 924638 ns 924536 ns 1010 items_per_second=1.42774M/s DunRenderBenchmark/LeftTrapezoid_Solid_FullyLit 33728 ns 33725 ns 24962 items_per_second=18.8583M/s DunRenderBenchmark/LeftTrapezoid_Solid_FullyDark 31088 ns 31085 ns 27444 items_per_second=20.4601M/s DunRenderBenchmark/LeftTrapezoid_Solid_PartiallyLit 268792 ns 268768 ns 3254 items_per_second=1.97196M/s DunRenderBenchmark/LeftTrapezoid_Transparent_FullyLit 277990 ns 277965 ns 3140 items_per_second=1.90672M/s DunRenderBenchmark/LeftTrapezoid_Transparent_FullyDark 268952 ns 268912 ns 3250 items_per_second=1.9709M/s DunRenderBenchmark/LeftTrapezoid_Transparent_PartiallyLit 288869 ns 288826 ns 3056 items_per_second=1.83501M/s DunRenderBenchmark/RightTrapezoid_Solid_FullyLit 29581 ns 29576 ns 28347 items_per_second=21.0984M/s DunRenderBenchmark/RightTrapezoid_Solid_FullyDark 25315 ns 25312 ns 32250 items_per_second=24.6523M/s DunRenderBenchmark/RightTrapezoid_Solid_PartiallyLit 259977 ns 259960 ns 3312 items_per_second=2.0003M/s DunRenderBenchmark/RightTrapezoid_Transparent_FullyLit 263079 ns 263056 ns 3322 items_per_second=1.97677M/s DunRenderBenchmark/RightTrapezoid_Transparent_FullyDark 259849 ns 259824 ns 3364 items_per_second=2.00136M/s DunRenderBenchmark/RightTrapezoid_Transparent_PartiallyLit 279623 ns 279594 ns 3127 items_per_second=1.85984M/s ```
2 years ago
Tiles[levelCelBlock.type()].push_back(levelCelBlock);
}
}
}
return true;
}();
}
void RunForTileMaskLight(benchmark::State &state, TileType tileType, MaskType maskType, const uint8_t *lightTable)
{
Surface out = Surface(SdlSurface.get());
Lightmap lightmap(nullptr, {}, 1, nullptr, 0);
Add dun_render_benchmark Results from a single run (a bit noisy) on my machine: ``` tools/build_and_run_benchmark.py dun_render_benchmark ``` ``` ------------------------------------------------------------------------------------------------------------------------ Benchmark Time CPU Iterations UserCounters... ------------------------------------------------------------------------------------------------------------------------ DunRenderBenchmark/LeftTriangle_Solid_FullyLit 98297 ns 98282 ns 8840 items_per_second=15.1096M/s DunRenderBenchmark/LeftTriangle_Solid_FullyDark 124727 ns 124701 ns 6973 items_per_second=11.9085M/s DunRenderBenchmark/LeftTriangle_Solid_PartiallyLit 514869 ns 514747 ns 1700 items_per_second=2.88491M/s DunRenderBenchmark/LeftTriangle_Transparent_FullyLit 520312 ns 520216 ns 1682 items_per_second=2.85458M/s DunRenderBenchmark/LeftTriangle_Transparent_FullyDark 524440 ns 524331 ns 1664 items_per_second=2.83218M/s DunRenderBenchmark/LeftTriangle_Transparent_PartiallyLit 532300 ns 532162 ns 1647 items_per_second=2.7905M/s DunRenderBenchmark/RightTriangle_Solid_FullyLit 92387 ns 92363 ns 8840 items_per_second=16.7275M/s DunRenderBenchmark/RightTriangle_Solid_FullyDark 85680 ns 85662 ns 9884 items_per_second=18.0361M/s DunRenderBenchmark/RightTriangle_Solid_PartiallyLit 538347 ns 538250 ns 1626 items_per_second=2.87041M/s DunRenderBenchmark/RightTriangle_Transparent_FullyLit 548800 ns 548760 ns 1598 items_per_second=2.81544M/s DunRenderBenchmark/RightTriangle_Transparent_FullyDark 540450 ns 540369 ns 1620 items_per_second=2.85916M/s DunRenderBenchmark/RightTriangle_Transparent_PartiallyLit 555061 ns 555003 ns 1575 items_per_second=2.78377M/s DunRenderBenchmark/TransparentSquare_Solid_FullyLit 700849 ns 700751 ns 1320 items_per_second=3.68176M/s DunRenderBenchmark/TransparentSquare_Solid_FullyDark 664927 ns 664872 ns 1389 items_per_second=3.88045M/s DunRenderBenchmark/TransparentSquare_Solid_PartiallyLit 1131702 ns 1131559 ns 822 items_per_second=2.28004M/s DunRenderBenchmark/TransparentSquare_Transparent_FullyLit 1022384 ns 1022267 ns 916 items_per_second=2.5238M/s DunRenderBenchmark/TransparentSquare_Transparent_FullyDark 1023193 ns 1023057 ns 900 items_per_second=2.52185M/s DunRenderBenchmark/TransparentSquare_Transparent_PartiallyLit 1033573 ns 1033496 ns 895 items_per_second=2.49638M/s DunRenderBenchmark/Square_Solid_FullyLit 53532 ns 53524 ns 10000 items_per_second=30.8272M/s DunRenderBenchmark/Square_Solid_FullyDark 41993 ns 41987 ns 19794 items_per_second=47.1573M/s DunRenderBenchmark/Square_Solid_PartiallyLit 842772 ns 842615 ns 1108 items_per_second=1.56655M/s DunRenderBenchmark/Square_Transparent_FullyLit 834105 ns 834026 ns 1119 items_per_second=1.58269M/s DunRenderBenchmark/Square_Transparent_FullyDark 831912 ns 831823 ns 1122 items_per_second=1.58688M/s DunRenderBenchmark/Square_Transparent_PartiallyLit 924638 ns 924536 ns 1010 items_per_second=1.42774M/s DunRenderBenchmark/LeftTrapezoid_Solid_FullyLit 33728 ns 33725 ns 24962 items_per_second=18.8583M/s DunRenderBenchmark/LeftTrapezoid_Solid_FullyDark 31088 ns 31085 ns 27444 items_per_second=20.4601M/s DunRenderBenchmark/LeftTrapezoid_Solid_PartiallyLit 268792 ns 268768 ns 3254 items_per_second=1.97196M/s DunRenderBenchmark/LeftTrapezoid_Transparent_FullyLit 277990 ns 277965 ns 3140 items_per_second=1.90672M/s DunRenderBenchmark/LeftTrapezoid_Transparent_FullyDark 268952 ns 268912 ns 3250 items_per_second=1.9709M/s DunRenderBenchmark/LeftTrapezoid_Transparent_PartiallyLit 288869 ns 288826 ns 3056 items_per_second=1.83501M/s DunRenderBenchmark/RightTrapezoid_Solid_FullyLit 29581 ns 29576 ns 28347 items_per_second=21.0984M/s DunRenderBenchmark/RightTrapezoid_Solid_FullyDark 25315 ns 25312 ns 32250 items_per_second=24.6523M/s DunRenderBenchmark/RightTrapezoid_Solid_PartiallyLit 259977 ns 259960 ns 3312 items_per_second=2.0003M/s DunRenderBenchmark/RightTrapezoid_Transparent_FullyLit 263079 ns 263056 ns 3322 items_per_second=1.97677M/s DunRenderBenchmark/RightTrapezoid_Transparent_FullyDark 259849 ns 259824 ns 3364 items_per_second=2.00136M/s DunRenderBenchmark/RightTrapezoid_Transparent_PartiallyLit 279623 ns 279594 ns 3127 items_per_second=1.85984M/s ```
2 years ago
size_t numItemsProcessed = 0;
const std::span<const LevelCelBlock> tiles = Tiles[tileType];
for (auto _ : state) {
for (const LevelCelBlock &levelCelBlock : tiles) {
RenderTile(out, lightmap, Point { 320, 240 }, levelCelBlock, maskType, lightTable);
Add dun_render_benchmark Results from a single run (a bit noisy) on my machine: ``` tools/build_and_run_benchmark.py dun_render_benchmark ``` ``` ------------------------------------------------------------------------------------------------------------------------ Benchmark Time CPU Iterations UserCounters... ------------------------------------------------------------------------------------------------------------------------ DunRenderBenchmark/LeftTriangle_Solid_FullyLit 98297 ns 98282 ns 8840 items_per_second=15.1096M/s DunRenderBenchmark/LeftTriangle_Solid_FullyDark 124727 ns 124701 ns 6973 items_per_second=11.9085M/s DunRenderBenchmark/LeftTriangle_Solid_PartiallyLit 514869 ns 514747 ns 1700 items_per_second=2.88491M/s DunRenderBenchmark/LeftTriangle_Transparent_FullyLit 520312 ns 520216 ns 1682 items_per_second=2.85458M/s DunRenderBenchmark/LeftTriangle_Transparent_FullyDark 524440 ns 524331 ns 1664 items_per_second=2.83218M/s DunRenderBenchmark/LeftTriangle_Transparent_PartiallyLit 532300 ns 532162 ns 1647 items_per_second=2.7905M/s DunRenderBenchmark/RightTriangle_Solid_FullyLit 92387 ns 92363 ns 8840 items_per_second=16.7275M/s DunRenderBenchmark/RightTriangle_Solid_FullyDark 85680 ns 85662 ns 9884 items_per_second=18.0361M/s DunRenderBenchmark/RightTriangle_Solid_PartiallyLit 538347 ns 538250 ns 1626 items_per_second=2.87041M/s DunRenderBenchmark/RightTriangle_Transparent_FullyLit 548800 ns 548760 ns 1598 items_per_second=2.81544M/s DunRenderBenchmark/RightTriangle_Transparent_FullyDark 540450 ns 540369 ns 1620 items_per_second=2.85916M/s DunRenderBenchmark/RightTriangle_Transparent_PartiallyLit 555061 ns 555003 ns 1575 items_per_second=2.78377M/s DunRenderBenchmark/TransparentSquare_Solid_FullyLit 700849 ns 700751 ns 1320 items_per_second=3.68176M/s DunRenderBenchmark/TransparentSquare_Solid_FullyDark 664927 ns 664872 ns 1389 items_per_second=3.88045M/s DunRenderBenchmark/TransparentSquare_Solid_PartiallyLit 1131702 ns 1131559 ns 822 items_per_second=2.28004M/s DunRenderBenchmark/TransparentSquare_Transparent_FullyLit 1022384 ns 1022267 ns 916 items_per_second=2.5238M/s DunRenderBenchmark/TransparentSquare_Transparent_FullyDark 1023193 ns 1023057 ns 900 items_per_second=2.52185M/s DunRenderBenchmark/TransparentSquare_Transparent_PartiallyLit 1033573 ns 1033496 ns 895 items_per_second=2.49638M/s DunRenderBenchmark/Square_Solid_FullyLit 53532 ns 53524 ns 10000 items_per_second=30.8272M/s DunRenderBenchmark/Square_Solid_FullyDark 41993 ns 41987 ns 19794 items_per_second=47.1573M/s DunRenderBenchmark/Square_Solid_PartiallyLit 842772 ns 842615 ns 1108 items_per_second=1.56655M/s DunRenderBenchmark/Square_Transparent_FullyLit 834105 ns 834026 ns 1119 items_per_second=1.58269M/s DunRenderBenchmark/Square_Transparent_FullyDark 831912 ns 831823 ns 1122 items_per_second=1.58688M/s DunRenderBenchmark/Square_Transparent_PartiallyLit 924638 ns 924536 ns 1010 items_per_second=1.42774M/s DunRenderBenchmark/LeftTrapezoid_Solid_FullyLit 33728 ns 33725 ns 24962 items_per_second=18.8583M/s DunRenderBenchmark/LeftTrapezoid_Solid_FullyDark 31088 ns 31085 ns 27444 items_per_second=20.4601M/s DunRenderBenchmark/LeftTrapezoid_Solid_PartiallyLit 268792 ns 268768 ns 3254 items_per_second=1.97196M/s DunRenderBenchmark/LeftTrapezoid_Transparent_FullyLit 277990 ns 277965 ns 3140 items_per_second=1.90672M/s DunRenderBenchmark/LeftTrapezoid_Transparent_FullyDark 268952 ns 268912 ns 3250 items_per_second=1.9709M/s DunRenderBenchmark/LeftTrapezoid_Transparent_PartiallyLit 288869 ns 288826 ns 3056 items_per_second=1.83501M/s DunRenderBenchmark/RightTrapezoid_Solid_FullyLit 29581 ns 29576 ns 28347 items_per_second=21.0984M/s DunRenderBenchmark/RightTrapezoid_Solid_FullyDark 25315 ns 25312 ns 32250 items_per_second=24.6523M/s DunRenderBenchmark/RightTrapezoid_Solid_PartiallyLit 259977 ns 259960 ns 3312 items_per_second=2.0003M/s DunRenderBenchmark/RightTrapezoid_Transparent_FullyLit 263079 ns 263056 ns 3322 items_per_second=1.97677M/s DunRenderBenchmark/RightTrapezoid_Transparent_FullyDark 259849 ns 259824 ns 3364 items_per_second=2.00136M/s DunRenderBenchmark/RightTrapezoid_Transparent_PartiallyLit 279623 ns 279594 ns 3127 items_per_second=1.85984M/s ```
2 years ago
uint8_t color = out[Point { 310, 200 }];
benchmark::DoNotOptimize(color);
}
numItemsProcessed += tiles.size();
}
state.SetItemsProcessed(numItemsProcessed);
}
using GetLightTableFn = const uint8_t *();
const uint8_t *FullyLit() { return FullyLitLightTable; }
const uint8_t *FullyDark() { return FullyDarkLightTable; }
const uint8_t *PartiallyLit() { return LightTables[5].data(); }
template <TileType TileT, MaskType MaskT, GetLightTableFn GetLightTableFnT>
void Render(benchmark::State &state)
{
InitOnce();
RunForTileMaskLight(state, TileT, MaskT, GetLightTableFnT());
}
// Define aliases in order to have shorter benchmark names.
constexpr auto LeftTriangle = TileType::LeftTriangle;
constexpr auto RightTriangle = TileType::RightTriangle;
constexpr auto TransparentSquare = TileType::TransparentSquare;
constexpr auto Square = TileType::Square;
constexpr auto LeftTrapezoid = TileType::LeftTrapezoid;
constexpr auto RightTrapezoid = TileType::RightTrapezoid;
constexpr auto Transparent = MaskType::Transparent;
constexpr auto Solid = MaskType::Solid;
#define DEFINE_FOR_TILE_AND_MASK_TYPE(TILE_TYPE, MASK_TYPE) \
BENCHMARK_TEMPLATE(Render, TILE_TYPE, MASK_TYPE, FullyLit); \
BENCHMARK_TEMPLATE(Render, TILE_TYPE, MASK_TYPE, FullyDark); \
BENCHMARK_TEMPLATE(Render, TILE_TYPE, MASK_TYPE, PartiallyLit);
#define DEFINE_FOR_TILE_TYPE(TILE_TYPE) \
DEFINE_FOR_TILE_AND_MASK_TYPE(TILE_TYPE, Solid) \
DEFINE_FOR_TILE_AND_MASK_TYPE(TILE_TYPE, Transparent)
DEFINE_FOR_TILE_TYPE(LeftTriangle)
DEFINE_FOR_TILE_TYPE(RightTriangle)
DEFINE_FOR_TILE_TYPE(TransparentSquare)
DEFINE_FOR_TILE_TYPE(Square)
DEFINE_FOR_TILE_TYPE(LeftTrapezoid)
DEFINE_FOR_TILE_TYPE(RightTrapezoid)
void BM_RenderBlackTile(benchmark::State &state)
{
InitOnce();
Surface out = Surface(SdlSurface.get());
size_t numItemsProcessed = 0;
for (auto _ : state) {
world_draw_black_tile(out, 320, 240);
uint8_t color = out[Point { 310, 200 }];
benchmark::DoNotOptimize(color);
++numItemsProcessed;
}
state.SetItemsProcessed(numItemsProcessed);
}
BENCHMARK(BM_RenderBlackTile);
Add dun_render_benchmark Results from a single run (a bit noisy) on my machine: ``` tools/build_and_run_benchmark.py dun_render_benchmark ``` ``` ------------------------------------------------------------------------------------------------------------------------ Benchmark Time CPU Iterations UserCounters... ------------------------------------------------------------------------------------------------------------------------ DunRenderBenchmark/LeftTriangle_Solid_FullyLit 98297 ns 98282 ns 8840 items_per_second=15.1096M/s DunRenderBenchmark/LeftTriangle_Solid_FullyDark 124727 ns 124701 ns 6973 items_per_second=11.9085M/s DunRenderBenchmark/LeftTriangle_Solid_PartiallyLit 514869 ns 514747 ns 1700 items_per_second=2.88491M/s DunRenderBenchmark/LeftTriangle_Transparent_FullyLit 520312 ns 520216 ns 1682 items_per_second=2.85458M/s DunRenderBenchmark/LeftTriangle_Transparent_FullyDark 524440 ns 524331 ns 1664 items_per_second=2.83218M/s DunRenderBenchmark/LeftTriangle_Transparent_PartiallyLit 532300 ns 532162 ns 1647 items_per_second=2.7905M/s DunRenderBenchmark/RightTriangle_Solid_FullyLit 92387 ns 92363 ns 8840 items_per_second=16.7275M/s DunRenderBenchmark/RightTriangle_Solid_FullyDark 85680 ns 85662 ns 9884 items_per_second=18.0361M/s DunRenderBenchmark/RightTriangle_Solid_PartiallyLit 538347 ns 538250 ns 1626 items_per_second=2.87041M/s DunRenderBenchmark/RightTriangle_Transparent_FullyLit 548800 ns 548760 ns 1598 items_per_second=2.81544M/s DunRenderBenchmark/RightTriangle_Transparent_FullyDark 540450 ns 540369 ns 1620 items_per_second=2.85916M/s DunRenderBenchmark/RightTriangle_Transparent_PartiallyLit 555061 ns 555003 ns 1575 items_per_second=2.78377M/s DunRenderBenchmark/TransparentSquare_Solid_FullyLit 700849 ns 700751 ns 1320 items_per_second=3.68176M/s DunRenderBenchmark/TransparentSquare_Solid_FullyDark 664927 ns 664872 ns 1389 items_per_second=3.88045M/s DunRenderBenchmark/TransparentSquare_Solid_PartiallyLit 1131702 ns 1131559 ns 822 items_per_second=2.28004M/s DunRenderBenchmark/TransparentSquare_Transparent_FullyLit 1022384 ns 1022267 ns 916 items_per_second=2.5238M/s DunRenderBenchmark/TransparentSquare_Transparent_FullyDark 1023193 ns 1023057 ns 900 items_per_second=2.52185M/s DunRenderBenchmark/TransparentSquare_Transparent_PartiallyLit 1033573 ns 1033496 ns 895 items_per_second=2.49638M/s DunRenderBenchmark/Square_Solid_FullyLit 53532 ns 53524 ns 10000 items_per_second=30.8272M/s DunRenderBenchmark/Square_Solid_FullyDark 41993 ns 41987 ns 19794 items_per_second=47.1573M/s DunRenderBenchmark/Square_Solid_PartiallyLit 842772 ns 842615 ns 1108 items_per_second=1.56655M/s DunRenderBenchmark/Square_Transparent_FullyLit 834105 ns 834026 ns 1119 items_per_second=1.58269M/s DunRenderBenchmark/Square_Transparent_FullyDark 831912 ns 831823 ns 1122 items_per_second=1.58688M/s DunRenderBenchmark/Square_Transparent_PartiallyLit 924638 ns 924536 ns 1010 items_per_second=1.42774M/s DunRenderBenchmark/LeftTrapezoid_Solid_FullyLit 33728 ns 33725 ns 24962 items_per_second=18.8583M/s DunRenderBenchmark/LeftTrapezoid_Solid_FullyDark 31088 ns 31085 ns 27444 items_per_second=20.4601M/s DunRenderBenchmark/LeftTrapezoid_Solid_PartiallyLit 268792 ns 268768 ns 3254 items_per_second=1.97196M/s DunRenderBenchmark/LeftTrapezoid_Transparent_FullyLit 277990 ns 277965 ns 3140 items_per_second=1.90672M/s DunRenderBenchmark/LeftTrapezoid_Transparent_FullyDark 268952 ns 268912 ns 3250 items_per_second=1.9709M/s DunRenderBenchmark/LeftTrapezoid_Transparent_PartiallyLit 288869 ns 288826 ns 3056 items_per_second=1.83501M/s DunRenderBenchmark/RightTrapezoid_Solid_FullyLit 29581 ns 29576 ns 28347 items_per_second=21.0984M/s DunRenderBenchmark/RightTrapezoid_Solid_FullyDark 25315 ns 25312 ns 32250 items_per_second=24.6523M/s DunRenderBenchmark/RightTrapezoid_Solid_PartiallyLit 259977 ns 259960 ns 3312 items_per_second=2.0003M/s DunRenderBenchmark/RightTrapezoid_Transparent_FullyLit 263079 ns 263056 ns 3322 items_per_second=1.97677M/s DunRenderBenchmark/RightTrapezoid_Transparent_FullyDark 259849 ns 259824 ns 3364 items_per_second=2.00136M/s DunRenderBenchmark/RightTrapezoid_Transparent_PartiallyLit 279623 ns 279594 ns 3127 items_per_second=1.85984M/s ```
2 years ago
} // namespace
} // namespace devilution