21f9e4a1ed
Avoid infinity arithmetics when computing exp approximations
...
Otherwise this can result a poison value on some platforms see https://bugs.llvm.org/show_bug.cgi?id=51204
Reviewed By: ezhulenev
Differential Revision: https://reviews.llvm.org/D112115
2021-10-21 10:09:18 -07:00
bf32bb7e05
[mlir] Update approximation range for Tanh operation
...
Use wider range for approximating Tanh to match results computed in Eigen with AVX.
Reviewed By: cota
Differential Revision: https://reviews.llvm.org/D112011
2021-10-18 10:57:31 -07:00
a54f4eae0e
[MLIR] Replace std ops with arith dialect ops
...
Precursor: https://reviews.llvm.org/D110200
Removed redundant ops from the standard dialect that were moved to the
`arith` or `math` dialects.
Renamed all instances of operations in the codebase and in tests.
Reviewed By: rriddle, jpienaar
Differential Revision: https://reviews.llvm.org/D110797
2021-10-13 03:07:03 +00:00
42431b8207
[tests] Make testsuite more resilient to "order of constant" changes. NFC.
2021-09-08 10:10:10 -07:00
c1ebefdf77
[mlir] Make polynomial approximation emit std instead of LLVM ops
...
This is a bit cleaner and removes issues with 2d vectors. It also has a
big impact on constant folding, hence the test changes.
Differential Revision: https://reviews.llvm.org/D107896
2021-08-11 16:37:21 +02:00
391456f33c
Fix a bug in algebraic simplification, and enable the tests.
...
Reviewed By: ezhulenev
Differential Revision: https://reviews.llvm.org/D107788
2021-08-10 04:15:56 -07:00
d94426d22a
[mlir] Math: add algebraic simplification patterns to math transforms
...
Reviewed By: bkramer
Differential Revision: https://reviews.llvm.org/D106822
2021-07-27 09:22:33 -07:00
3c952ab25f
[mlir] Check generated IR of math_polynomial_approx.mlir
...
Instead of just checking that we emit something.
Differential Revision: https://reviews.llvm.org/D101940
2021-05-05 16:42:48 -07:00
0edc4bc84a
[mlir] Add polynomial approximation for math::ExpM1
...
This approximation matches the one in Eigen.
```
name old cpu/op new cpu/op delta
BM_mlir_Expm1_f32/10 90.9ns ± 4% 52.2ns ± 4% -42.60% (p=0.000 n=74+87)
BM_mlir_Expm1_f32/100 837ns ± 3% 231ns ± 4% -72.43% (p=0.000 n=79+69)
BM_mlir_Expm1_f32/1k 8.43µs ± 3% 1.58µs ± 5% -81.30% (p=0.000 n=77+83)
BM_mlir_Expm1_f32/10k 83.8µs ± 3% 15.4µs ± 5% -81.65% (p=0.000 n=83+69)
BM_eigen_s_Expm1_f32/10 68.8ns ±17% 72.5ns ±14% +5.40% (p=0.000 n=118+115)
BM_eigen_s_Expm1_f32/100 694ns ±11% 717ns ± 2% +3.34% (p=0.000 n=120+75)
BM_eigen_s_Expm1_f32/1k 7.69µs ± 2% 7.97µs ±11% +3.56% (p=0.000 n=95+117)
BM_eigen_s_Expm1_f32/10k 88.0µs ± 1% 89.3µs ± 6% +1.45% (p=0.000 n=74+106)
BM_eigen_v_Expm1_f32/10 44.3ns ± 6% 45.0ns ± 8% +1.45% (p=0.018 n=81+111)
BM_eigen_v_Expm1_f32/100 351ns ± 1% 360ns ± 9% +2.58% (p=0.000 n=73+99)
BM_eigen_v_Expm1_f32/1k 3.31µs ± 1% 3.42µs ± 9% +3.37% (p=0.000 n=71+100)
BM_eigen_v_Expm1_f32/10k 33.7µs ± 8% 34.1µs ± 9% +1.04% (p=0.007 n=99+98)
```
Reviewed By: ezhulenev
Differential Revision: https://reviews.llvm.org/D101852
2021-05-05 14:31:34 -07:00
1c0374e770
[mlir] Add polynomial approximation for math::Log1p
...
This approximation matches the one in Eigen.
```
name old cpu/op new cpu/op delta
BM_mlir_Log1p_f32/10 83.2ns ± 7% 34.8ns ± 5% -58.19% (p=0.000 n=84+71)
BM_mlir_Log1p_f32/100 664ns ± 4% 129ns ± 4% -80.57% (p=0.000 n=82+82)
BM_mlir_Log1p_f32/1k 6.75µs ± 4% 0.81µs ± 3% -88.07% (p=0.000 n=88+79)
BM_mlir_Log1p_f32/10k 76.5µs ± 3% 7.8µs ± 4% -89.84% (p=0.000 n=80+80)
BM_eigen_s_Log1p_f32/10 70.1ns ±14% 72.6ns ±14% +3.49% (p=0.000 n=116+112)
BM_eigen_s_Log1p_f32/100 706ns ± 9% 717ns ± 3% +1.60% (p=0.018 n=117+80)
BM_eigen_s_Log1p_f32/1k 8.26µs ± 1% 8.26µs ± 1% ~ (p=0.567 n=84+86)
BM_eigen_s_Log1p_f32/10k 92.1µs ± 5% 92.6µs ± 6% +0.60% (p=0.047 n=115+115)
BM_eigen_v_Log1p_f32/10 31.8ns ±24% 34.9ns ±17% +9.72% (p=0.000 n=98+96)
BM_eigen_v_Log1p_f32/100 169ns ±10% 177ns ± 5% +4.66% (p=0.000 n=119+81)
BM_eigen_v_Log1p_f32/1k 1.42µs ± 4% 1.46µs ± 8% +2.70% (p=0.000 n=93+113)
BM_eigen_v_Log1p_f32/10k 14.4µs ± 5% 14.9µs ± 8% +3.61% (p=0.000 n=115+110)
```
Reviewed By: ezhulenev, ftynse
Differential Revision: https://reviews.llvm.org/D101765
2021-05-03 15:11:37 -07:00
c0891706bc
[mlir] Add polynomial approximation for math::Log2
...
```
name old cpu/op new cpu/op delta
BM_mlir_Log2_f32/10 134ns ±15% 45ns ± 4% -66.39% (p=0.000 n=20+17)
BM_mlir_Log2_f32/100 1.03µs ±16% 0.12µs ±10% -88.78% (p=0.000 n=20+18)
BM_mlir_Log2_f32/1k 10.3µs ±16% 0.7µs ± 5% -93.24% (p=0.000 n=20+17)
BM_mlir_Log2_f32/10k 104µs ±15% 7µs ±14% -93.25% (p=0.000 n=20+20)
BM_eigen_s_Log2_f32/10 95.3ns ±17% 90.9ns ± 6% ~ (p=0.228 n=20+18)
BM_eigen_s_Log2_f32/100 907ns ± 3% 911ns ± 6% ~ (p=0.539 n=16+20)
BM_eigen_s_Log2_f32/1k 9.88µs ± 4% 9.85µs ± 3% ~ (p=0.790 n=16+17)
BM_eigen_s_Log2_f32/10k 105µs ±10% 110µs ±16% ~ (p=0.459 n=16+20)
BM_eigen_v_Log2_f32/10 32.5ns ±31% 33.9ns ±14% +4.31% (p=0.028 n=17+20)
BM_eigen_v_Log2_f32/100 176ns ± 8% 180ns ± 7% +2.19% (p=0.045 n=16+17)
BM_eigen_v_Log2_f32/1k 1.44µs ± 4% 1.50µs ± 9% +3.91% (p=0.001 n=16+17)
BM_eigen_v_Log2_f32/10k 14.5µs ±10% 15.0µs ± 8% +3.92% (p=0.002 n=16+19)
```
Reviewed By: ezhulenev
Differential Revision: https://reviews.llvm.org/D98282
2021-03-10 14:49:22 -08:00
ea7f211b2e
[mlir] Add polynomial approximation for math::ExpOp
...
Similar to fast_exp in https://github.com/boulos/syrah
Differential Revision: https://reviews.llvm.org/D97599
2021-03-01 11:02:07 -08:00
ce976d2db3
[mlir] Add polynomial approximation for math::LogOp (using builders API)
...
Replace math::LogOp with an approximations from the the Julien Pommier's SSE math library
Link: http://gruntthepeon.free.fr/ssemath
Reviewed By: asaadaldien
Differential Revision: https://reviews.llvm.org/D97304
2021-02-24 07:50:25 -08:00
f99ccf6516
[mlir] Add math polynomial approximation pass
...
This gives ~30x speedup compared to expanding Tanh into exp operations:
```
name old cpu/op new cpu/op delta
BM_mlir_Tanh_f32/10 253ns ± 3% 55ns ± 7% -78.35% (p=0.000 n=44+41)
BM_mlir_Tanh_f32/100 2.21µs ± 4% 0.14µs ± 8% -93.85% (p=0.000 n=48+49)
BM_mlir_Tanh_f32/1k 22.6µs ± 4% 0.7µs ± 5% -96.68% (p=0.000 n=32+42)
BM_mlir_Tanh_f32/10k 225µs ± 5% 7µs ± 6% -96.88% (p=0.000 n=49+55)
name old time/op new time/op delta
BM_mlir_Tanh_f32/10 259ns ± 1% 56ns ± 2% -78.31% (p=0.000 n=41+39)
BM_mlir_Tanh_f32/100 2.27µs ± 1% 0.14µs ± 5% -93.89% (p=0.000 n=46+49)
BM_mlir_Tanh_f32/1k 22.9µs ± 1% 0.8µs ± 4% -96.67% (p=0.000 n=30+42)
BM_mlir_Tanh_f32/10k 230µs ± 0% 7µs ± 3% -96.88% (p=0.000 n=37+55)
```
This approximations is based on Eigen::generic_fast_tanh function
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D96739
2021-02-19 12:43:36 -08:00
9f581815ae
Add Expm1 op to the math dialect.
...
Differential Revision: https://reviews.llvm.org/D96704
2021-02-16 08:33:37 +01:00
4348d8ab7f
[mlir][math] Split off the math dialect.
...
This does not split transformations, yet. Those will be done as future clean ups.
Differential Revision: https://reviews.llvm.org/D96272
2021-02-12 10:55:12 +01:00
Ahmed Taei