mirror of
https://github.com/ceres-solver/ceres-solver.git
synced 2026-08-29 08:34:37 +08:00
Refactor small_blas_gemm_benchmark
This allows benchmarking both dynamic and static problem sizes. On my X86 2Ghz machine: CPU Caches: L1 Data 32 KiB (x48) L1 Instruction 32 KiB (x48) L2 Unified 1024 KiB (x48) L3 Unified 39424 KiB (x2) ---------------------------------------------------------------------------------------------- Benchmark Time CPU Iterations ---------------------------------------------------------------------------------------------- BM_MatrixMatrixMultiplyEigen_Static_2x3x4 10.9 ns 10.9 ns 63960496 BM_MatrixMatrixMultiplyEigen_Static_3x3x3 11.9 ns 11.9 ns 58093785 BM_MatrixMatrixMultiplyEigen_Static_4x4x4 24.9 ns 24.9 ns 28540133 BM_MatrixMatrixMultiplyEigen_Static_8x8x8 258 ns 258 ns 2755921 BM_MatrixMatrixMultiplyEigen_Static_9x9x3 255 ns 255 ns 2778628 BM_MatrixMatrixMultiplyEigen_Static_9x3x3 37.7 ns 37.7 ns 18556359 BM_MatrixMatrixMultiplyEigen_Static_3x9x9 220 ns 220 ns 3195163 BM_MatrixMatrixMultiplyEigen_Dynamic_2x3x4 37.8 ns 37.7 ns 18491162 BM_MatrixMatrixMultiplyEigen_Dynamic_3x3x3 48.8 ns 48.8 ns 13724884 BM_MatrixMatrixMultiplyEigen_Dynamic_4x4x4 74.5 ns 74.5 ns 9313146 BM_MatrixMatrixMultiplyEigen_Dynamic_8x8x8 271 ns 271 ns 2595807 BM_MatrixMatrixMultiplyEigen_Dynamic_9x9x3 259 ns 259 ns 2688515 BM_MatrixMatrixMultiplyEigen_Dynamic_9x3x3 123 ns 123 ns 5792115 BM_MatrixMatrixMultiplyEigen_Dynamic_3x9x9 236 ns 236 ns 2963896 BM_MatrixMatrixMultiplyNaive_Static_2x3x4 12.2 ns 12.2 ns 56472772 BM_MatrixMatrixMultiplyNaive_Static_3x3x3 15.5 ns 15.5 ns 44346456 BM_MatrixMatrixMultiplyNaive_Static_4x4x4 41.5 ns 41.5 ns 17196984 BM_MatrixMatrixMultiplyNaive_Static_8x8x8 199 ns 199 ns 3561730 BM_MatrixMatrixMultiplyNaive_Static_9x9x3 148 ns 148 ns 4764814 BM_MatrixMatrixMultiplyNaive_Static_9x3x3 38.4 ns 38.4 ns 17259019 BM_MatrixMatrixMultiplyNaive_Static_3x9x9 115 ns 115 ns 6104752 BM_MatrixMatrixMultiplyNaive_Dynamic_2x3x4 9.66 ns 9.66 ns 74722971 BM_MatrixMatrixMultiplyNaive_Dynamic_3x3x3 13.0 ns 13.0 ns 53435308 BM_MatrixMatrixMultiplyNaive_Dynamic_4x4x4 47.8 ns 47.8 ns 14358184 BM_MatrixMatrixMultiplyNaive_Dynamic_8x8x8 200 ns 200 ns 3572809 BM_MatrixMatrixMultiplyNaive_Dynamic_9x9x3 104 ns 104 ns 6793797 BM_MatrixMatrixMultiplyNaive_Dynamic_9x3x3 34.0 ns 34.0 ns 20790695 BM_MatrixMatrixMultiplyNaive_Dynamic_3x9x9 130 ns 130 ns 5170402 BM_MatrixTransposeMatrixMultiplyEigen_Static_2x3x4 10.3 ns 10.3 ns 69105234 BM_MatrixTransposeMatrixMultiplyEigen_Static_3x3x3 28.9 ns 28.9 ns 24478934 BM_MatrixTransposeMatrixMultiplyEigen_Static_4x4x4 23.7 ns 23.7 ns 29351926 BM_MatrixTransposeMatrixMultiplyEigen_Static_8x8x8 233 ns 233 ns 2929398 BM_MatrixTransposeMatrixMultiplyEigen_Static_9x9x3 211 ns 211 ns 3287409 BM_MatrixTransposeMatrixMultiplyEigen_Static_9x3x3 26.5 ns 26.5 ns 26515136 BM_MatrixTransposeMatrixMultiplyEigen_Static_3x9x9 196 ns 196 ns 3594314 BM_MatrixTransposeMatrixMultiplyEigen_Dynamic_2x3x4 9.05 ns 9.05 ns 77621001 BM_MatrixTransposeMatrixMultiplyEigen_Dynamic_3x3x3 11.1 ns 11.1 ns 62227812 BM_MatrixTransposeMatrixMultiplyEigen_Dynamic_4x4x4 25.5 ns 25.5 ns 27356089 BM_MatrixTransposeMatrixMultiplyEigen_Dynamic_8x8x8 248 ns 248 ns 2834983 BM_MatrixTransposeMatrixMultiplyEigen_Dynamic_9x9x3 229 ns 229 ns 3082369 BM_MatrixTransposeMatrixMultiplyEigen_Dynamic_9x3x3 28.4 ns 28.4 ns 24318629 BM_MatrixTransposeMatrixMultiplyEigen_Dynamic_3x9x9 229 ns 229 ns 3091288 BM_MatrixTransposeMatrixMultiplyNaive_Static_2x3x4 11.0 ns 11.0 ns 63773538 BM_MatrixTransposeMatrixMultiplyNaive_Static_3x3x3 19.1 ns 19.1 ns 37003139 BM_MatrixTransposeMatrixMultiplyNaive_Static_4x4x4 49.1 ns 49.1 ns 14142301 BM_MatrixTransposeMatrixMultiplyNaive_Static_8x8x8 244 ns 244 ns 2874755 BM_MatrixTransposeMatrixMultiplyNaive_Static_9x9x3 140 ns 140 ns 4992156 BM_MatrixTransposeMatrixMultiplyNaive_Static_9x3x3 46.2 ns 46.2 ns 15068317 BM_MatrixTransposeMatrixMultiplyNaive_Static_3x9x9 112 ns 112 ns 6213574 BM_MatrixTransposeMatrixMultiplyNaive_Dynamic_2x3x4 9.74 ns 9.74 ns 72155001 BM_MatrixTransposeMatrixMultiplyNaive_Dynamic_3x3x3 11.5 ns 11.5 ns 60070577 BM_MatrixTransposeMatrixMultiplyNaive_Dynamic_4x4x4 52.5 ns 52.5 ns 13473642 BM_MatrixTransposeMatrixMultiplyNaive_Dynamic_8x8x8 224 ns 224 ns 3124264 BM_MatrixTransposeMatrixMultiplyNaive_Dynamic_9x9x3 98.0 ns 98.0 ns 7199292 BM_MatrixTransposeMatrixMultiplyNaive_Dynamic_9x3x3 34.7 ns 34.6 ns 20203685 BM_MatrixTransposeMatrixMultiplyNaive_Dynamic_3x9x9 105 ns 105 ns 6653151 Change-Id: Iee403b4d27801d1614ecc1f78a1f8c0011514bd7
This commit is contained in:
Ahmed Taei
@@ -47,10 +47,10 @@ namespace internal {
|
||||
// benchmark.
|
||||
class MatrixMatrixMultiplyData {
|
||||
public:
|
||||
MatrixMatrixMultiplyData(
|
||||
int a_rows, int a_cols, int b_rows, int b_cols, int c_rows, int c_cols)
|
||||
MatrixMatrixMultiplyData(int a_rows, int a_cols, int b_rows, int b_cols,
|
||||
int c_rows, int c_cols)
|
||||
: num_elements_(1000),
|
||||
a_size_(a_rows * a_cols),
|
||||
a_size_(num_elements_ * a_rows * a_cols),
|
||||
b_size_(b_rows * b_cols),
|
||||
c_size_(c_rows * c_cols),
|
||||
a_(num_elements_ * a_size_, 1.00001),
|
||||
@@ -72,97 +72,130 @@ class MatrixMatrixMultiplyData {
|
||||
std::vector<double> c_;
|
||||
};
|
||||
|
||||
static void MatrixMatrixMultiplySizeArguments(
|
||||
benchmark::internal::Benchmark* benchmark) {
|
||||
const std::vector<int> b_rows = {1, 2, 3, 4, 6, 8};
|
||||
const std::vector<int> b_cols = {1, 2, 3, 4, 8, 12, 15};
|
||||
const std::vector<int> c_cols = b_cols;
|
||||
for (int i : b_rows) {
|
||||
for (int j : b_cols) {
|
||||
for (int k : c_cols) {
|
||||
benchmark->Args({i, j, k});
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
#define GEMM_KIND_EQ 0
|
||||
#define GEMM_KIND_ADD 1
|
||||
#define GEMM_KIND_SUB -1
|
||||
|
||||
void BM_MatrixMatrixMultiplyDynamic(benchmark::State& state) {
|
||||
const int i = state.range(0);
|
||||
const int j = state.range(1);
|
||||
const int k = state.range(2);
|
||||
#define BENCHMARK_MM_FN(FN, M, N, K, NAME, MT, NT, KT) \
|
||||
void static BM_##FN##_##NAME##_##M##x##N##x##K(benchmark::State& state) { \
|
||||
const int b_rows = M; \
|
||||
const int b_cols = N; \
|
||||
const int c_rows = b_cols; \
|
||||
const int c_cols = K; \
|
||||
const int a_rows = b_rows; \
|
||||
const int a_cols = c_cols; \
|
||||
MatrixMatrixMultiplyData data(a_rows, a_cols, b_rows, b_cols, c_rows, \
|
||||
c_cols); \
|
||||
const int num_elements = data.num_elements(); \
|
||||
int iter = 0; \
|
||||
for (auto _ : state) { \
|
||||
FN<MT, KT, KT, NT, GEMM_KIND_ADD>( \
|
||||
data.GetB(iter), b_rows, b_cols, data.GetC(iter), c_rows, c_cols, \
|
||||
data.GetA(iter), 512, 512, a_rows, a_cols); \
|
||||
iter = (iter + 1) % num_elements; \
|
||||
} \
|
||||
} \
|
||||
BENCHMARK(BM_##FN##_##NAME##_##M##x##N##x##K);
|
||||
|
||||
const int b_rows = i;
|
||||
const int b_cols = j;
|
||||
const int c_rows = b_cols;
|
||||
const int c_cols = k;
|
||||
const int a_rows = b_rows;
|
||||
const int a_cols = c_cols;
|
||||
#define BENCHMARK_STATIC_MM_FN(FN, M, N, K) \
|
||||
BENCHMARK_MM_FN(FN, M, N, K, Static, M, N, K)
|
||||
#define BENCHMARK_DYNAMIC_MM_FN(FN, M, N, K) \
|
||||
BENCHMARK_MM_FN(FN, M, N, K, Dynamic, Eigen::Dynamic, Eigen::Dynamic, \
|
||||
Eigen::Dynamic)
|
||||
|
||||
MatrixMatrixMultiplyData data(a_rows, a_cols, b_rows, b_cols, c_rows, c_cols);
|
||||
const int num_elements = data.num_elements();
|
||||
#define BENCHMARK_MTM_FN(FN, M, N, K, NAME, MT, NT, KT) \
|
||||
void static BM_##FN##_##NAME##_##M##x##N##x##K(benchmark::State& state) { \
|
||||
const int b_rows = M; \
|
||||
const int b_cols = N; \
|
||||
const int c_rows = b_rows; \
|
||||
const int c_cols = K; \
|
||||
const int a_rows = b_cols; \
|
||||
const int a_cols = c_cols; \
|
||||
MatrixMatrixMultiplyData data(a_rows, a_cols, b_rows, b_cols, c_rows, \
|
||||
c_cols); \
|
||||
const int num_elements = data.num_elements(); \
|
||||
int iter = 0; \
|
||||
for (auto _ : state) { \
|
||||
FN<KT, MT, KT, NT, GEMM_KIND_ADD>( \
|
||||
data.GetB(iter), b_rows, b_cols, data.GetC(iter), c_rows, c_cols, \
|
||||
data.GetA(iter), 0, 0, a_rows, a_cols); \
|
||||
iter = (iter + 1) % num_elements; \
|
||||
} \
|
||||
} \
|
||||
BENCHMARK(BM_##FN##_##NAME##_##M##x##N##x##K);
|
||||
|
||||
int iter = 0;
|
||||
for (auto _ : state) {
|
||||
// a += b * c
|
||||
// clang-format off
|
||||
MatrixMatrixMultiply
|
||||
<Eigen::Dynamic, Eigen::Dynamic,Eigen::Dynamic,Eigen::Dynamic, 1>
|
||||
(data.GetB(iter), b_rows, b_cols,
|
||||
data.GetC(iter), c_rows, c_cols,
|
||||
data.GetA(iter), 0, 0, a_rows, a_cols);
|
||||
// clang-format on
|
||||
iter = (iter + 1) % num_elements;
|
||||
}
|
||||
}
|
||||
#define BENCHMARK_STATIC_MMT_FN(FN, M, N, K) \
|
||||
BENCHMARK_MTM_FN(FN, M, N, K, Static, M, N, K)
|
||||
#define BENCHMARK_DYNAMIC_MMT_FN(FN, M, N, K) \
|
||||
BENCHMARK_MTM_FN(FN, M, N, K, Dynamic, Eigen::Dynamic, Eigen::Dynamic, \
|
||||
Eigen::Dynamic)
|
||||
|
||||
BENCHMARK(BM_MatrixMatrixMultiplyDynamic)
|
||||
->Apply(MatrixMatrixMultiplySizeArguments);
|
||||
BENCHMARK_STATIC_MM_FN(MatrixMatrixMultiplyEigen, 2, 3, 4)
|
||||
BENCHMARK_STATIC_MM_FN(MatrixMatrixMultiplyEigen, 3, 3, 3)
|
||||
BENCHMARK_STATIC_MM_FN(MatrixMatrixMultiplyEigen, 4, 4, 4)
|
||||
BENCHMARK_STATIC_MM_FN(MatrixMatrixMultiplyEigen, 8, 8, 8)
|
||||
BENCHMARK_STATIC_MM_FN(MatrixMatrixMultiplyEigen, 9, 9, 3)
|
||||
BENCHMARK_STATIC_MM_FN(MatrixMatrixMultiplyEigen, 9, 3, 3)
|
||||
BENCHMARK_STATIC_MM_FN(MatrixMatrixMultiplyEigen, 3, 9, 9)
|
||||
BENCHMARK_DYNAMIC_MM_FN(MatrixMatrixMultiplyEigen, 2, 3, 4)
|
||||
BENCHMARK_DYNAMIC_MM_FN(MatrixMatrixMultiplyEigen, 3, 3, 3)
|
||||
BENCHMARK_DYNAMIC_MM_FN(MatrixMatrixMultiplyEigen, 4, 4, 4)
|
||||
BENCHMARK_DYNAMIC_MM_FN(MatrixMatrixMultiplyEigen, 8, 8, 8)
|
||||
BENCHMARK_DYNAMIC_MM_FN(MatrixMatrixMultiplyEigen, 9, 9, 3)
|
||||
BENCHMARK_DYNAMIC_MM_FN(MatrixMatrixMultiplyEigen, 9, 3, 3)
|
||||
BENCHMARK_DYNAMIC_MM_FN(MatrixMatrixMultiplyEigen, 3, 9, 9)
|
||||
BENCHMARK_STATIC_MM_FN(MatrixMatrixMultiplyNaive, 2, 3, 4)
|
||||
BENCHMARK_STATIC_MM_FN(MatrixMatrixMultiplyNaive, 3, 3, 3)
|
||||
BENCHMARK_STATIC_MM_FN(MatrixMatrixMultiplyNaive, 4, 4, 4)
|
||||
BENCHMARK_STATIC_MM_FN(MatrixMatrixMultiplyNaive, 8, 8, 8)
|
||||
BENCHMARK_STATIC_MM_FN(MatrixMatrixMultiplyNaive, 9, 9, 3)
|
||||
BENCHMARK_STATIC_MM_FN(MatrixMatrixMultiplyNaive, 9, 3, 3)
|
||||
BENCHMARK_STATIC_MM_FN(MatrixMatrixMultiplyNaive, 3, 9, 9)
|
||||
BENCHMARK_DYNAMIC_MM_FN(MatrixMatrixMultiplyNaive, 2, 3, 4)
|
||||
BENCHMARK_DYNAMIC_MM_FN(MatrixMatrixMultiplyNaive, 3, 3, 3)
|
||||
BENCHMARK_DYNAMIC_MM_FN(MatrixMatrixMultiplyNaive, 4, 4, 4)
|
||||
BENCHMARK_DYNAMIC_MM_FN(MatrixMatrixMultiplyNaive, 8, 8, 8)
|
||||
BENCHMARK_DYNAMIC_MM_FN(MatrixMatrixMultiplyNaive, 9, 9, 3)
|
||||
BENCHMARK_DYNAMIC_MM_FN(MatrixMatrixMultiplyNaive, 9, 3, 3)
|
||||
BENCHMARK_DYNAMIC_MM_FN(MatrixMatrixMultiplyNaive, 3, 9, 9)
|
||||
BENCHMARK_STATIC_MMT_FN(MatrixTransposeMatrixMultiplyEigen, 2, 3, 4)
|
||||
BENCHMARK_STATIC_MMT_FN(MatrixTransposeMatrixMultiplyEigen, 3, 3, 3)
|
||||
BENCHMARK_STATIC_MMT_FN(MatrixTransposeMatrixMultiplyEigen, 4, 4, 4)
|
||||
BENCHMARK_STATIC_MMT_FN(MatrixTransposeMatrixMultiplyEigen, 8, 8, 8)
|
||||
BENCHMARK_STATIC_MMT_FN(MatrixTransposeMatrixMultiplyEigen, 9, 9, 3)
|
||||
BENCHMARK_STATIC_MMT_FN(MatrixTransposeMatrixMultiplyEigen, 9, 3, 3)
|
||||
BENCHMARK_STATIC_MMT_FN(MatrixTransposeMatrixMultiplyEigen, 3, 9, 9)
|
||||
BENCHMARK_DYNAMIC_MMT_FN(MatrixTransposeMatrixMultiplyEigen, 2, 3, 4)
|
||||
BENCHMARK_DYNAMIC_MMT_FN(MatrixTransposeMatrixMultiplyEigen, 3, 3, 3)
|
||||
BENCHMARK_DYNAMIC_MMT_FN(MatrixTransposeMatrixMultiplyEigen, 4, 4, 4)
|
||||
BENCHMARK_DYNAMIC_MMT_FN(MatrixTransposeMatrixMultiplyEigen, 8, 8, 8)
|
||||
BENCHMARK_DYNAMIC_MMT_FN(MatrixTransposeMatrixMultiplyEigen, 9, 9, 3)
|
||||
BENCHMARK_DYNAMIC_MMT_FN(MatrixTransposeMatrixMultiplyEigen, 9, 3, 3)
|
||||
BENCHMARK_DYNAMIC_MMT_FN(MatrixTransposeMatrixMultiplyEigen, 3, 9, 9)
|
||||
BENCHMARK_STATIC_MMT_FN(MatrixTransposeMatrixMultiplyNaive, 2, 3, 4)
|
||||
BENCHMARK_STATIC_MMT_FN(MatrixTransposeMatrixMultiplyNaive, 3, 3, 3)
|
||||
BENCHMARK_STATIC_MMT_FN(MatrixTransposeMatrixMultiplyNaive, 4, 4, 4)
|
||||
BENCHMARK_STATIC_MMT_FN(MatrixTransposeMatrixMultiplyNaive, 8, 8, 8)
|
||||
BENCHMARK_STATIC_MMT_FN(MatrixTransposeMatrixMultiplyNaive, 9, 9, 3)
|
||||
BENCHMARK_STATIC_MMT_FN(MatrixTransposeMatrixMultiplyNaive, 9, 3, 3)
|
||||
BENCHMARK_STATIC_MMT_FN(MatrixTransposeMatrixMultiplyNaive, 3, 9, 9)
|
||||
BENCHMARK_DYNAMIC_MMT_FN(MatrixTransposeMatrixMultiplyNaive, 2, 3, 4)
|
||||
BENCHMARK_DYNAMIC_MMT_FN(MatrixTransposeMatrixMultiplyNaive, 3, 3, 3)
|
||||
BENCHMARK_DYNAMIC_MMT_FN(MatrixTransposeMatrixMultiplyNaive, 4, 4, 4)
|
||||
BENCHMARK_DYNAMIC_MMT_FN(MatrixTransposeMatrixMultiplyNaive, 8, 8, 8)
|
||||
BENCHMARK_DYNAMIC_MMT_FN(MatrixTransposeMatrixMultiplyNaive, 9, 9, 3)
|
||||
BENCHMARK_DYNAMIC_MMT_FN(MatrixTransposeMatrixMultiplyNaive, 9, 3, 3)
|
||||
BENCHMARK_DYNAMIC_MMT_FN(MatrixTransposeMatrixMultiplyNaive, 3, 9, 9)
|
||||
|
||||
static void MatrixTransposeMatrixMultiplySizeArguments(
|
||||
benchmark::internal::Benchmark* benchmark) {
|
||||
std::vector<int> b_rows = {1, 2, 3, 4, 6, 8};
|
||||
std::vector<int> b_cols = {1, 2, 3, 4, 8, 12, 15};
|
||||
std::vector<int> c_cols = b_rows;
|
||||
for (int i : b_rows) {
|
||||
for (int j : b_cols) {
|
||||
for (int k : c_cols) {
|
||||
benchmark->Args({i, j, k});
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
void BM_MatrixTransposeMatrixMultiplyDynamic(benchmark::State& state) {
|
||||
const int i = state.range(0);
|
||||
const int j = state.range(1);
|
||||
const int k = state.range(2);
|
||||
|
||||
const int b_rows = i;
|
||||
const int b_cols = j;
|
||||
const int c_rows = b_rows;
|
||||
const int c_cols = k;
|
||||
const int a_rows = b_cols;
|
||||
const int a_cols = c_cols;
|
||||
|
||||
MatrixMatrixMultiplyData data(a_rows, a_cols, b_rows, b_cols, c_rows, c_cols);
|
||||
const int num_elements = data.num_elements();
|
||||
|
||||
int iter = 0;
|
||||
for (auto _ : state) {
|
||||
// a += b' * c
|
||||
// clang-format off
|
||||
MatrixTransposeMatrixMultiply
|
||||
<Eigen::Dynamic,Eigen::Dynamic,Eigen::Dynamic,Eigen::Dynamic, 1>
|
||||
(data.GetB(iter), b_rows, b_cols,
|
||||
data.GetC(iter), c_rows, c_cols,
|
||||
data.GetA(iter), 0, 0, a_rows, a_cols);
|
||||
// clang-format on
|
||||
iter = (iter + 1) % num_elements;
|
||||
}
|
||||
}
|
||||
|
||||
BENCHMARK(BM_MatrixTransposeMatrixMultiplyDynamic)
|
||||
->Apply(MatrixTransposeMatrixMultiplySizeArguments);
|
||||
#undef GEMM_KIND_EQ
|
||||
#undef GEMM_KIND_ADD
|
||||
#undef GEMM_KIND_SUB
|
||||
#undef BENCHMARK_MM_FN
|
||||
#undef BENCHMARK_STATIC_MM_FN
|
||||
#undef BENCHMARK_DYNAMIC_MM_FN
|
||||
#undef BENCHMARK_MTM_FN
|
||||
#undef BENCHMARK_DYNAMIC_MMT_FN
|
||||
#undef BENCHMARK_STATIC_MMT_FN
|
||||
|
||||
} // namespace internal
|
||||
} // namespace ceres
|
||||
|
||||
Reference in New Issue
Block a user