4c5c0305e4
Bump ndarray approx
2022-07-19 20:33:50 +02:00
5acd46af6d
Upgrade dependencies
2022-07-05 21:59:27 +02:00
2a1bb3f815
Use serde1 feature
2022-07-05 20:19:49 +02:00
bb1909c2a8
Use StdFloat to fix compile error
2022-07-05 19:51:48 +02:00
f40de866ce
Clippy lints
2022-05-17 08:24:33 +02:00
70cab01334
Use weak dependencies
2022-05-17 08:03:05 +02:00
cfeb30fac0
Small clippy lint fixes
2022-02-25 20:43:57 +01:00
9679ae5ba2
Remove superfluous import
2021-11-21 11:21:05 +01:00
d16b274fe0
Update hdf5/ndarray
2021-10-23 19:35:37 +00:00
0ec3e16566
Align portable-simd with master
2021-09-30 05:15:31 +00:00
d0901f5755
SAT boundaries for multi-thread fixing
2021-08-21 09:29:45 +00:00
d2c811d3af
Rework wait primitive to condvar
2021-08-20 15:57:12 +00:00
2d473b8255
Clippy lints
2021-08-16 20:33:57 +00:00
3edd18c4fd
Use core_simd over packed_simd
2021-07-27 18:32:22 +00:00
8873f458b4
useless conversion
2021-06-29 18:07:26 +02:00
9e2ce3ae24
Add Metrics iterator
2021-03-26 16:27:45 +01:00
a33e1d37ba
Document what compiler is doing for diffxi
2021-03-25 22:39:00 +01:00
76f5291131
Elide bounds check in diffxi
...
array_windows.skip did not elide bounds checks as it should. If
the slice is instead offset by the skipped amount, we have the
same behavour, but aids the compiler enough.
The two changed lines allows SIMD optimisations, giving an
impressive reduction in instructions by two thirds in the
benchmark.
2021-03-25 17:23:01 +01:00
4ae5c02bb1
Replace FastFloat with mul_add
2021-03-23 19:21:38 +01:00
7aadda3de9
Move integrate to separate crate
2021-03-22 17:49:35 +01:00
be1330ec02
Add constrmatrix as separate crate
2021-03-22 16:24:32 +01:00
502679c9a1
Move Float to separate crate
2021-03-22 16:17:27 +01:00
be984fbdac
Bump sprs to 0.10
2021-03-18 23:27:03 +01:00
550b43b4cd
Bump ndarray
2021-03-16 19:03:35 +01:00
f098981d3e
Update email
2021-03-16 19:00:24 +01:00
8383517ba3
ensure slice can be cast to Matrix
2021-03-15 20:18:19 +01:00
17ab18e953
zero-pad diffxi kernel
2021-03-15 20:07:41 +01:00
e43e71a4d8
Make flip_XX impl on Matrix
2021-03-15 19:31:41 +01:00
6fc045ae17
Replace transmute with cast
2021-02-12 19:02:13 +01:00
a02c7daafc
remove iterator inhibiting optimisation
2021-02-10 21:17:05 +01:00
02175d1734
use some unsafe...
2021-02-10 19:29:26 +01:00
8a6dc60edf
remove some unsafe from simd
2021-02-10 19:02:48 +01:00
87c055f81e
Add back simd column algo
2021-02-09 21:44:35 +01:00
cf4d8f1e9b
add Zero for constmatrix
2021-02-03 08:41:11 +01:00
7ec426b5a8
add more fast intrinsics
2021-02-03 08:31:33 +01:00
64a4e92dd2
specialise on contigous ny
2021-02-02 00:33:37 +01:00
c709cf465e
remove ndarray transmute
2021-02-02 00:12:03 +01:00
74d99a4a18
try ndarray transmute
2021-02-02 00:12:03 +01:00
b15ea57e6d
inline for perf
2021-02-02 00:12:03 +01:00
299b4f8083
ensure FastFloat flag works
2021-02-02 00:12:03 +01:00
6f7268bf33
use matrices everywhere
2021-02-02 00:12:02 +01:00
31ac46e386
move data structs into separate files
2021-02-02 00:12:02 +01:00
f7f8a7ffff
make flip const functions
2021-02-02 00:12:02 +01:00
1f3aa2c116
make core-intrinsics cfg'ed
2021-02-02 00:12:02 +01:00
c73c6e7407
diff_op_col_naive_matrix
2021-02-02 00:12:02 +01:00
c660354c3f
Matrix for Upwind4
2021-02-02 00:12:02 +01:00
45e4d51513
remove a closure
2021-02-02 00:12:02 +01:00
b0e1ec62f8
change order in matmul_into
2021-02-02 00:12:02 +01:00
481f2d607e
remove a lot of unsafe, lost perf
2021-02-02 00:12:02 +01:00
00f3ba6a01
use split_at_mut
2021-02-02 00:12:02 +01:00
