diff options
| author |  Rasmus Munk Larsen <rmlarsen@google.com> | 2018-09-26 16:47:13 -0700 |
|---|---|---|
| committer | Rasmus Munk Larsen <rmlarsen@google.com> | 2018-09-26 16:47:13 -0700 |
| commit | 3815aeed7a0304ea7703adf96124bd7f2d0530c1 (patch) | |
| tree | 6c75c53471ff3c600952f775e8988dfd693afa47 /unsupported/Eigen/CXX11/src/Tensor/TensorCostModel.h | |
| parent | 0a3356f4ece30cd486b616eb1da9128aa4f245be (diff) | |
Parallelize tensor contraction over the inner dimension in cases where where one or both of the outer dimensions (m and n) are small but k is large. This speeds up individual matmul microbenchmarks by up to 85%.
Naming below is BM_Matmul_M_K_N_THREADS, measured on a 2-socket Intel Broadwell-based server.
Benchmark Base (ns) New (ns) Improvement
------------------------------------------------------------------
BM_Matmul_1_80_13522_1 387457 396013 -2.2%
BM_Matmul_1_80_13522_2 406487 230789 +43.2%
BM_Matmul_1_80_13522_4 395821 123211 +68.9%
BM_Matmul_1_80_13522_6 391625 97002 +75.2%
BM_Matmul_1_80_13522_8 408986 113828 +72.2%
BM_Matmul_1_80_13522_16 399988 67600 +83.1%
BM_Matmul_1_80_13522_22 411546 60044 +85.4%
BM_Matmul_1_80_13522_32 393528 57312 +85.4%
BM_Matmul_1_80_13522_44 390047 63525 +83.7%
BM_Matmul_1_80_13522_88 387876 63592 +83.6%
BM_Matmul_1_1500_500_1 245359 248119 -1.1%
BM_Matmul_1_1500_500_2 401833 143271 +64.3%
BM_Matmul_1_1500_500_4 210519 100231 +52.4%
BM_Matmul_1_1500_500_6 251582 86575 +65.6%
BM_Matmul_1_1500_500_8 211499 80444 +62.0%
BM_Matmul_3_250_512_1 70297 68551 +2.5%
BM_Matmul_3_250_512_2 70141 52450 +25.2%
BM_Matmul_3_250_512_4 67872 58204 +14.2%
BM_Matmul_3_250_512_6 71378 63340 +11.3%
BM_Matmul_3_250_512_8 69595 41652 +40.2%
BM_Matmul_3_250_512_16 72055 42549 +40.9%
BM_Matmul_3_250_512_22 70158 54023 +23.0%
BM_Matmul_3_250_512_32 71541 56042 +21.7%
BM_Matmul_3_250_512_44 71843 57019 +20.6%
BM_Matmul_3_250_512_88 69951 54045 +22.7%
BM_Matmul_3_1500_512_1 369328 374284 -1.4%
BM_Matmul_3_1500_512_2 428656 223603 +47.8%
BM_Matmul_3_1500_512_4 205599 139508 +32.1%
BM_Matmul_3_1500_512_6 214278 139071 +35.1%
BM_Matmul_3_1500_512_8 184149 142338 +22.7%
BM_Matmul_3_1500_512_16 156462 156983 -0.3%
BM_Matmul_3_1500_512_22 163905 158259 +3.4%
BM_Matmul_3_1500_512_32 155314 157662 -1.5%
BM_Matmul_3_1500_512_44 235434 158657 +32.6%
BM_Matmul_3_1500_512_88 156779 160275 -2.2%
BM_Matmul_1500_4_512_1 363358 349528 +3.8%
BM_Matmul_1500_4_512_2 303134 263319 +13.1%
BM_Matmul_1500_4_512_4 176208 130086 +26.2%
BM_Matmul_1500_4_512_6 148026 115449 +22.0%
BM_Matmul_1500_4_512_8 131656 98421 +25.2%
BM_Matmul_1500_4_512_16 134011 82861 +38.2%
BM_Matmul_1500_4_512_22 134950 85685 +36.5%
BM_Matmul_1500_4_512_32 133165 90081 +32.4%
BM_Matmul_1500_4_512_44 133203 90644 +32.0%
BM_Matmul_1500_4_512_88 134106 100566 +25.0%
BM_Matmul_4_1500_512_1 439243 435058 +1.0%
BM_Matmul_4_1500_512_2 451830 257032 +43.1%
BM_Matmul_4_1500_512_4 276434 164513 +40.5%
BM_Matmul_4_1500_512_6 182542 144827 +20.7%
BM_Matmul_4_1500_512_8 179411 166256 +7.3%
BM_Matmul_4_1500_512_16 158101 155560 +1.6%
BM_Matmul_4_1500_512_22 152435 155448 -1.9%
BM_Matmul_4_1500_512_32 155150 149538 +3.6%
BM_Matmul_4_1500_512_44 193842 149777 +22.7%
BM_Matmul_4_1500_512_88 149544 154468 -3.3%
Diffstat (limited to 'unsupported/Eigen/CXX11/src/Tensor/TensorCostModel.h')
| -rw-r--r-- | unsupported/Eigen/CXX11/src/Tensor/TensorCostModel.h | 1 |
1 files changed, 0 insertions, 1 deletions
diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorCostModel.h b/unsupported/Eigen/CXX11/src/Tensor/TensorCostModel.h index bb63baee2..7f79ac30d 100644 --- a/unsupported/Eigen/CXX11/src/Tensor/TensorCostModel.h +++ b/unsupported/Eigen/CXX11/src/Tensor/TensorCostModel.h @@ -188,7 +188,6 @@ class TensorCostModel { return totalCost(output_size, cost_per_coeff) / kTaskSize; } - private: static EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE double totalCost( double output_size, const TensorOpCost& cost_per_coeff) { // Cost of memory fetches from L2 cache. 64 is typical cache line size. |