a_ | BenchmarkSuite< Device, T > | private |
algebraicFunc(int num_iters) | BenchmarkSuite< Device, T > | inline |
b_ | BenchmarkSuite< Device, T > | private |
BenchmarkSuite(const Device &device, size_t m, size_t k, size_t n) | BenchmarkSuite< Device, T > | inline |
BenchmarkSuite(const Device &device, size_t m) | BenchmarkSuite< Device, T > | inline |
BenchmarkSuite(const Device &device, size_t m, size_t k) | BenchmarkSuite< Device, T > | inline |
broadcasting(int num_iters) | BenchmarkSuite< Device, T > | inline |
c_ | BenchmarkSuite< Device, T > | private |
coeffWiseOp(int num_iters) | BenchmarkSuite< Device, T > | inline |
colChip(int num_iters) | BenchmarkSuite< Device, T > | inline |
colReduction(int num_iters) | BenchmarkSuite< Device, T > | inline |
contraction(int num_iters) | BenchmarkSuite< Device, T > | inline |
contraction(int num_iters, bool trans_a, bool trans_b) | BenchmarkSuite< Device, T > | inlineprivate |
contractionRowMajor(int num_iters) | BenchmarkSuite< Device, T > | inline |
contractionRowMajorABT(int num_iters) | BenchmarkSuite< Device, T > | inline |
contractionRowMajorAT(int num_iters) | BenchmarkSuite< Device, T > | inline |
contractionRowMajorBT(int num_iters) | BenchmarkSuite< Device, T > | inline |
convolution(int num_iters, int kernel_x, int kernel_y) | BenchmarkSuite< Device, T > | inline |
device_ | BenchmarkSuite< Device, T > | private |
finalizeBenchmark(int64_t num_items) | BenchmarkSuite< Device, T > | inlineprivate |
fullReduction(int num_iters) | BenchmarkSuite< Device, T > | inline |
initialize() | BenchmarkSuite< Device, T > | inlineprivate |
k_ | BenchmarkSuite< Device, T > | private |
m_ | BenchmarkSuite< Device, T > | private |
memcpy(int num_iters) | BenchmarkSuite< Device, T > | inline |
n_ | BenchmarkSuite< Device, T > | private |
padding(int num_iters) | BenchmarkSuite< Device, T > | inline |
random(int num_iters) | BenchmarkSuite< Device, T > | inline |
rowChip(int num_iters) | BenchmarkSuite< Device, T > | inline |
rowReduction(int num_iters) | BenchmarkSuite< Device, T > | inline |
shuffling(int num_iters) | BenchmarkSuite< Device, T > | inline |
slicing(int num_iters) | BenchmarkSuite< Device, T > | inline |
striding(int num_iters) | BenchmarkSuite< Device, T > | inline |
transcendentalFunc(int num_iters) | BenchmarkSuite< Device, T > | inline |
typeCasting(int num_iters) | BenchmarkSuite< Device, T > | inline |
~BenchmarkSuite() | BenchmarkSuite< Device, T > | inline |