Macros | Functions
tensor_benchmarks_cpu.cc File Reference
#include <string>
#include "tensor_benchmarks.h"
Include dependency graph for tensor_benchmarks_cpu.cc:

Go to the source code of this file.

Macros

#define BM_FuncCPU(FUNC, THREADS)
 
#define BM_FuncWithInputDimsCPU(FUNC, D1, D2, D3, THREADS)
 
#define BM_FuncWithKernelDimsCPU(FUNC, DIM1, DIM2, THREADS)
 
#define CREATE_THREAD_POOL(threads)
 
#define EIGEN_USE_THREADS
 

Functions

 BM_FuncCPU (memcpy, 4)
 
 BM_FuncCPU (memcpy, 8)
 
 BM_FuncCPU (memcpy, 12)
 
 BM_FuncCPU (typeCasting, 4)
 
 BM_FuncCPU (typeCasting, 8)
 
 BM_FuncCPU (typeCasting, 12)
 
 BM_FuncCPU (random, 4)
 
 BM_FuncCPU (random, 8)
 
 BM_FuncCPU (random, 12)
 
 BM_FuncCPU (slicing, 4)
 
 BM_FuncCPU (slicing, 8)
 
 BM_FuncCPU (slicing, 12)
 
 BM_FuncCPU (rowChip, 4)
 
 BM_FuncCPU (rowChip, 8)
 
 BM_FuncCPU (rowChip, 12)
 
 BM_FuncCPU (colChip, 4)
 
 BM_FuncCPU (colChip, 8)
 
 BM_FuncCPU (colChip, 12)
 
 BM_FuncCPU (shuffling, 4)
 
 BM_FuncCPU (shuffling, 8)
 
 BM_FuncCPU (shuffling, 12)
 
 BM_FuncCPU (padding, 4)
 
 BM_FuncCPU (padding, 8)
 
 BM_FuncCPU (padding, 12)
 
 BM_FuncCPU (striding, 4)
 
 BM_FuncCPU (striding, 8)
 
 BM_FuncCPU (striding, 12)
 
 BM_FuncCPU (broadcasting, 4)
 
 BM_FuncCPU (broadcasting, 8)
 
 BM_FuncCPU (broadcasting, 12)
 
 BM_FuncCPU (coeffWiseOp, 4)
 
 BM_FuncCPU (coeffWiseOp, 8)
 
 BM_FuncCPU (coeffWiseOp, 12)
 
 BM_FuncCPU (algebraicFunc, 4)
 
 BM_FuncCPU (algebraicFunc, 8)
 
 BM_FuncCPU (algebraicFunc, 12)
 
 BM_FuncCPU (transcendentalFunc, 4)
 
 BM_FuncCPU (transcendentalFunc, 8)
 
 BM_FuncCPU (transcendentalFunc, 12)
 
 BM_FuncCPU (rowReduction, 4)
 
 BM_FuncCPU (rowReduction, 8)
 
 BM_FuncCPU (rowReduction, 12)
 
 BM_FuncCPU (colReduction, 4)
 
 BM_FuncCPU (colReduction, 8)
 
 BM_FuncCPU (colReduction, 12)
 
 BM_FuncWithInputDimsCPU (contraction, N, N, N, 1)
 
 BM_FuncWithInputDimsCPU (contraction, N, N, N, 4)
 
 BM_FuncWithInputDimsCPU (contraction, N, N, N, 8)
 
 BM_FuncWithInputDimsCPU (contraction, N, N, N, 12)
 
 BM_FuncWithInputDimsCPU (contraction, N, N, N, 16)
 
 BM_FuncWithInputDimsCPU (contraction, 64, N, N, 1)
 
 BM_FuncWithInputDimsCPU (contraction, 64, N, N, 4)
 
 BM_FuncWithInputDimsCPU (contraction, 64, N, N, 8)
 
 BM_FuncWithInputDimsCPU (contraction, 64, N, N, 12)
 
 BM_FuncWithInputDimsCPU (contraction, 64, N, N, 16)
 
 BM_FuncWithInputDimsCPU (contraction, N, 64, N, 1)
 
 BM_FuncWithInputDimsCPU (contraction, N, 64, N, 4)
 
 BM_FuncWithInputDimsCPU (contraction, N, 64, N, 8)
 
 BM_FuncWithInputDimsCPU (contraction, N, 64, N, 12)
 
 BM_FuncWithInputDimsCPU (contraction, N, 64, N, 16)
 
 BM_FuncWithInputDimsCPU (contraction, N, N, 64, 1)
 
 BM_FuncWithInputDimsCPU (contraction, N, N, 64, 4)
 
 BM_FuncWithInputDimsCPU (contraction, N, N, 64, 8)
 
 BM_FuncWithInputDimsCPU (contraction, N, N, 64, 12)
 
 BM_FuncWithInputDimsCPU (contraction, N, N, 64, 16)
 
 BM_FuncWithInputDimsCPU (contraction, 1, N, N, 1)
 
 BM_FuncWithInputDimsCPU (contraction, 1, N, N, 4)
 
 BM_FuncWithInputDimsCPU (contraction, 1, N, N, 8)
 
 BM_FuncWithInputDimsCPU (contraction, 1, N, N, 12)
 
 BM_FuncWithInputDimsCPU (contraction, 1, N, N, 16)
 
 BM_FuncWithInputDimsCPU (contraction, N, N, 1, 1)
 
 BM_FuncWithInputDimsCPU (contraction, N, N, 1, 4)
 
 BM_FuncWithInputDimsCPU (contraction, N, N, 1, 8)
 
 BM_FuncWithInputDimsCPU (contraction, N, N, 1, 12)
 
 BM_FuncWithInputDimsCPU (contraction, N, N, 1, 16)
 
 BM_FuncWithKernelDimsCPU (convolution, 7, 1, 4)
 
 BM_FuncWithKernelDimsCPU (convolution, 7, 1, 8)
 
 BM_FuncWithKernelDimsCPU (convolution, 7, 1, 12)
 
 BM_FuncWithKernelDimsCPU (convolution, 1, 7, 4)
 
 BM_FuncWithKernelDimsCPU (convolution, 1, 7, 8)
 
 BM_FuncWithKernelDimsCPU (convolution, 1, 7, 12)
 
 BM_FuncWithKernelDimsCPU (convolution, 7, 4, 4)
 
 BM_FuncWithKernelDimsCPU (convolution, 7, 4, 8)
 
 BM_FuncWithKernelDimsCPU (convolution, 7, 4, 12)
 
 BM_FuncWithKernelDimsCPU (convolution, 4, 7, 4)
 
 BM_FuncWithKernelDimsCPU (convolution, 4, 7, 8)
 
 BM_FuncWithKernelDimsCPU (convolution, 4, 7, 12)
 
 BM_FuncWithKernelDimsCPU (convolution, 7, 64, 4)
 
 BM_FuncWithKernelDimsCPU (convolution, 7, 64, 8)
 
 BM_FuncWithKernelDimsCPU (convolution, 7, 64, 12)
 
 BM_FuncWithKernelDimsCPU (convolution, 64, 7, 4)
 
 BM_FuncWithKernelDimsCPU (convolution, 64, 7, 8)
 
 BM_FuncWithKernelDimsCPU (convolution, 64, 7, 12)
 

Macro Definition Documentation

#define BM_FuncCPU (   FUNC,
  THREADS 
)
Value:
static void BM_##FUNC##_##THREADS##T(int iters, int N) { \
StopBenchmarkTiming(); \
CREATE_THREAD_POOL(THREADS); \
BenchmarkSuite<Eigen::ThreadPoolDevice, float> suite(device, N); \
suite.FUNC(iters); \
} \
BENCHMARK_RANGE(BM_##FUNC##_##THREADS##T, 10, 5000);
N
#define N
Definition: gksort.c:12
CREATE_THREAD_POOL
#define CREATE_THREAD_POOL(threads)
Definition: tensor_benchmarks_cpu.cc:7
BENCHMARK_RANGE
#define BENCHMARK_RANGE(bench, lo, hi)
Definition: tensor_benchmarks.h:10
T
Eigen::Triplet< double > T
Definition: Tutorial_sparse_example.cpp:6
StopBenchmarkTiming
void StopBenchmarkTiming()
Definition: benchmark_main.cc:196
gtsam.examples.Pose2SLAMExample_g2o._
_
Definition: Pose2SLAMExample_g2o.py:80

Definition at line 12 of file tensor_benchmarks_cpu.cc.

#define BM_FuncWithInputDimsCPU (   FUNC,
  D1,
  D2,
  D3,
  THREADS 
)
Value:
static void BM_##FUNC##_##D1##x##D2##x##D3##_##THREADS##T(int iters, int N) { \
StopBenchmarkTiming(); \
if (THREADS == 1) { \
Eigen::DefaultDevice device; \
BenchmarkSuite<Eigen::DefaultDevice, float> suite(device, D1, D2, D3); \
suite.FUNC(iters); \
} else { \
CREATE_THREAD_POOL(THREADS); \
BenchmarkSuite<Eigen::ThreadPoolDevice, float> suite(device, D1, D2, D3); \
suite.FUNC(iters); \
} \
} \
BENCHMARK_RANGE(BM_##FUNC##_##D1##x##D2##x##D3##_##THREADS##T, 10, 5000);
if
if((m *x).isApprox(y))
Definition: FullPivLU_solve.cpp:6
N
#define N
Definition: gksort.c:12
CREATE_THREAD_POOL
#define CREATE_THREAD_POOL(threads)
Definition: tensor_benchmarks_cpu.cc:7
BENCHMARK_RANGE
#define BENCHMARK_RANGE(bench, lo, hi)
Definition: tensor_benchmarks.h:10
T
Eigen::Triplet< double > T
Definition: Tutorial_sparse_example.cpp:6
StopBenchmarkTiming
void StopBenchmarkTiming()
Definition: benchmark_main.cc:196
x
set noclip points set clip one set noclip two set bar set border lt lw set xdata set ydata set zdata set x2data set y2data set boxwidth set dummy x
Definition: gnuplot_common_settings.hh:12
gtsam.examples.Pose2SLAMExample_g2o._
_
Definition: Pose2SLAMExample_g2o.py:80

Definition at line 83 of file tensor_benchmarks_cpu.cc.

#define BM_FuncWithKernelDimsCPU (   FUNC,
  DIM1,
  DIM2,
  THREADS 
)
Value:
static void BM_##FUNC##_##DIM1##x##DIM2##_##THREADS##T(int iters, int N) { \
StopBenchmarkTiming(); \
CREATE_THREAD_POOL(THREADS); \
BenchmarkSuite<Eigen::ThreadPoolDevice, float> suite(device, N); \
suite.FUNC(iters, DIM1, DIM2); \
} \
BENCHMARK_RANGE(BM_##FUNC##_##DIM1##x##DIM2##_##THREADS##T, 128, 5000);
N
#define N
Definition: gksort.c:12
CREATE_THREAD_POOL
#define CREATE_THREAD_POOL(threads)
Definition: tensor_benchmarks_cpu.cc:7
BENCHMARK_RANGE
#define BENCHMARK_RANGE(bench, lo, hi)
Definition: tensor_benchmarks.h:10
T
Eigen::Triplet< double > T
Definition: Tutorial_sparse_example.cpp:6
StopBenchmarkTiming
void StopBenchmarkTiming()
Definition: benchmark_main.cc:196
x
set noclip points set clip one set noclip two set bar set border lt lw set xdata set ydata set zdata set x2data set y2data set boxwidth set dummy x
Definition: gnuplot_common_settings.hh:12
gtsam.examples.Pose2SLAMExample_g2o._
_
Definition: Pose2SLAMExample_g2o.py:80

Definition at line 137 of file tensor_benchmarks_cpu.cc.

#define CREATE_THREAD_POOL (   threads)
Value:
Eigen::ThreadPool pool(threads); \
Eigen::ThreadPoolDevice device(&pool, threads);

Definition at line 7 of file tensor_benchmarks_cpu.cc.

#define EIGEN_USE_THREADS

Definition at line 1 of file tensor_benchmarks_cpu.cc.

Function Documentation

BM_FuncCPU ( memcpy  ,
4   
)
BM_FuncCPU ( memcpy  ,
8   
)
BM_FuncCPU ( memcpy  ,
12   
)
BM_FuncCPU ( typeCasting  ,
4   
)
BM_FuncCPU ( typeCasting  ,
8   
)
BM_FuncCPU ( typeCasting  ,
12   
)
BM_FuncCPU ( random  ,
4   
)
BM_FuncCPU ( random  ,
8   
)
BM_FuncCPU ( random  ,
12   
)
BM_FuncCPU ( slicing  ,
4   
)
BM_FuncCPU ( slicing  ,
8   
)
BM_FuncCPU ( slicing  ,
12   
)
BM_FuncCPU ( rowChip  ,
4   
)
BM_FuncCPU ( rowChip  ,
8   
)
BM_FuncCPU ( rowChip  ,
12   
)
BM_FuncCPU ( colChip  ,
4   
)
BM_FuncCPU ( colChip  ,
8   
)
BM_FuncCPU ( colChip  ,
12   
)
BM_FuncCPU ( shuffling  ,
4   
)
BM_FuncCPU ( shuffling  ,
8   
)
BM_FuncCPU ( shuffling  ,
12   
)
BM_FuncCPU ( padding  ,
4   
)
BM_FuncCPU ( padding  ,
8   
)
BM_FuncCPU ( padding  ,
12   
)
BM_FuncCPU ( striding  ,
4   
)
BM_FuncCPU ( striding  ,
8   
)
BM_FuncCPU ( striding  ,
12   
)
BM_FuncCPU ( broadcasting  ,
4   
)
BM_FuncCPU ( broadcasting  ,
8   
)
BM_FuncCPU ( broadcasting  ,
12   
)
BM_FuncCPU ( coeffWiseOp  ,
4   
)
BM_FuncCPU ( coeffWiseOp  ,
8   
)
BM_FuncCPU ( coeffWiseOp  ,
12   
)
BM_FuncCPU ( algebraicFunc  ,
4   
)
BM_FuncCPU ( algebraicFunc  ,
8   
)
BM_FuncCPU ( algebraicFunc  ,
12   
)
BM_FuncCPU ( transcendentalFunc  ,
4   
)
BM_FuncCPU ( transcendentalFunc  ,
8   
)
BM_FuncCPU ( transcendentalFunc  ,
12   
)
BM_FuncCPU ( rowReduction  ,
4   
)
BM_FuncCPU ( rowReduction  ,
8   
)
BM_FuncCPU ( rowReduction  ,
12   
)
BM_FuncCPU ( colReduction  ,
4   
)
BM_FuncCPU ( colReduction  ,
8   
)
BM_FuncCPU ( colReduction  ,
12   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
N  ,
N  ,
1   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
N  ,
N  ,
4   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
N  ,
N  ,
8   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
N  ,
N  ,
12   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
N  ,
N  ,
16   
)
BM_FuncWithInputDimsCPU ( contraction  ,
64  ,
N  ,
N  ,
1   
)
BM_FuncWithInputDimsCPU ( contraction  ,
64  ,
N  ,
N  ,
4   
)
BM_FuncWithInputDimsCPU ( contraction  ,
64  ,
N  ,
N  ,
8   
)
BM_FuncWithInputDimsCPU ( contraction  ,
64  ,
N  ,
N  ,
12   
)
BM_FuncWithInputDimsCPU ( contraction  ,
64  ,
N  ,
N  ,
16   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
64  ,
N  ,
1   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
64  ,
N  ,
4   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
64  ,
N  ,
8   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
64  ,
N  ,
12   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
64  ,
N  ,
16   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
N  ,
64  ,
1   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
N  ,
64  ,
4   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
N  ,
64  ,
8   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
N  ,
64  ,
12   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
N  ,
64  ,
16   
)
BM_FuncWithInputDimsCPU ( contraction  ,
1  ,
N  ,
N  ,
1   
)
BM_FuncWithInputDimsCPU ( contraction  ,
1  ,
N  ,
N  ,
4   
)
BM_FuncWithInputDimsCPU ( contraction  ,
1  ,
N  ,
N  ,
8   
)
BM_FuncWithInputDimsCPU ( contraction  ,
1  ,
N  ,
N  ,
12   
)
BM_FuncWithInputDimsCPU ( contraction  ,
1  ,
N  ,
N  ,
16   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
N  ,
1  ,
1   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
N  ,
1  ,
4   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
N  ,
1  ,
8   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
N  ,
1  ,
12   
)
BM_FuncWithInputDimsCPU ( contraction  ,
N  ,
N  ,
1  ,
16   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
7  ,
1  ,
4   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
7  ,
1  ,
8   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
7  ,
1  ,
12   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
1  ,
7  ,
4   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
1  ,
7  ,
8   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
1  ,
7  ,
12   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
7  ,
4  ,
4   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
7  ,
4  ,
8   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
7  ,
4  ,
12   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
4  ,
7  ,
4   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
4  ,
7  ,
8   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
4  ,
7  ,
12   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
7  ,
64  ,
4   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
7  ,
64  ,
8   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
7  ,
64  ,
12   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
64  ,
7  ,
4   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
64  ,
7  ,
8   
)
BM_FuncWithKernelDimsCPU ( convolution  ,
64  ,
7  ,
12   
)

gtsam
Author(s):
autogenerated on Sat May 8 2021 02:51:40