dzaima
|
81abc80863
|
fast highrank⊸⊏˘ table
|
2024-12-02 21:57:44 +02:00 |
|
dzaima
|
d988a620fd
|
native F⌾(a⊸⥊)
|
2024-11-26 18:08:15 +02:00 |
|
dzaima
|
92641f26ba
|
squeeze fns haven't been AVX2-specific for a while
|
2024-11-22 12:48:59 +02:00 |
|
dzaima
|
7df2f9ba4f
|
a couple renames & simplifications
|
2024-11-22 00:44:03 +02:00 |
|
dzaima
|
f0223b8baf
|
properly add 1<<31
|
2024-11-21 23:04:02 +02:00 |
|
Marshall Lochbaum
|
342cadfc00
|
Check for or handle argument length >2⋆31 in /⁼
|
2024-11-17 15:29:36 -05:00 |
|
Marshall Lochbaum
|
194e8c3f22
|
Update /⁼ implementation comments
|
2024-11-17 15:29:36 -05:00 |
|
Marshall Lochbaum
|
0bbb335893
|
Do general i8 and i16 /⁼ counts to i16 buffer, plus overflow list
|
2024-11-17 15:29:36 -05:00 |
|
Marshall Lochbaum
|
fb5ee179cb
|
Squeeze for slash_im generic case instead of converting individual elements to numbers
|
2024-11-17 15:29:36 -05:00 |
|
Marshall Lochbaum
|
96b198f643
|
Condition all the i8 to i32 /⁼ optimization on SINGELI_SIMD, for simplicity
|
2024-11-17 15:29:36 -05:00 |
|
Marshall Lochbaum
|
e6940e73d0
|
Fast /⁼ of sorted arguments using semi-sparse representation
|
2024-11-17 15:29:36 -05:00 |
|
Marshall Lochbaum
|
3b103aadd0
|
Run-based i32 /⁼ (leaving out sum-based)
|
2024-11-17 15:29:36 -05:00 |
|
Marshall Lochbaum
|
4aea668a6c
|
Allow i16 /⁼ to jump to Singeli code after range checking
|
2024-11-17 15:29:36 -05:00 |
|
Marshall Lochbaum
|
926e59483d
|
More precise sparse check for i8 /⁼ result: previously stopped at 65
|
2024-11-17 15:29:36 -05:00 |
|
Marshall Lochbaum
|
e24d0bac63
|
Extend SIMD counting to i16 in addition to i8
|
2024-11-17 15:29:36 -05:00 |
|
dzaima
|
cbac419b4a
|
fix ⍷2‿0⥊x
|
2024-11-06 22:34:55 +02:00 |
|
dzaima
|
d47cedb165
|
some cleanup
|
2024-11-06 22:32:05 +02:00 |
|
Marshall Lochbaum
|
15df6afc7d
|
Implementation comments for transpose with short height/width
|
2024-11-05 22:04:23 -05:00 |
|
Marshall Lochbaum
|
d7b508ff3b
|
Move select_cells_single (atom⊸⊏˘) to select.c and use for any singleton index
|
2024-11-05 21:48:54 -05:00 |
|
Marshall Lochbaum
|
5bdee886cc
|
Extend kernel transpose from AVX2 only to SSE2, NEON
|
2024-11-05 21:48:54 -05:00 |
|
Marshall Lochbaum
|
4669418f1c
|
Extend modular permutation ⊣˝˘ to multi-byte element types
|
2024-11-05 21:48:54 -05:00 |
|
Marshall Lochbaum
|
9997c52e4c
|
Initial 1-byte ⊣˝˘ with blends and modular permutation
|
2024-11-05 21:48:54 -05:00 |
|
dzaima
|
0c6e32a24c
|
fix si_select_cells_bit_lt64 signature
|
2024-10-23 21:53:48 +03:00 |
|
dzaima
|
52f318e755
|
EACH_FILLS tests
|
2024-10-14 05:09:03 +03:00 |
|
dzaima
|
1e00aa71c9
|
atomEqualF & atomEEqual cleanup
|
2024-10-10 04:12:07 +03:00 |
|
dzaima
|
503bddced5
|
bring back atomEqualF fast path
|
2024-10-10 04:00:43 +03:00 |
|
dzaima
|
6bd47b067e
|
split apart def_decompose
|
2024-10-10 02:38:17 +03:00 |
|
dzaima
|
3d4a31ae6f
|
access function/modifier runtime ID through macro
|
2024-10-10 02:38:17 +03:00 |
|
dzaima
|
d4b36b3017
|
access function/modifier native ID through macro
|
2024-10-10 02:38:17 +03:00 |
|
dzaima
|
03fc22662b
|
add •internal.Properties for better build parameter detecting
|
2024-10-10 01:33:17 +03:00 |
|
dzaima
|
3ed6241609
|
don't attempt to use BMI2 on x86-32
|
2024-10-09 03:31:20 +03:00 |
|
dzaima
|
183f64c1f9
|
make ⟨⟩≡∾⟨⟩ under PROPER_FILLS
|
2024-10-09 02:42:17 +03:00 |
|
dzaima
|
03f2f29f3b
|
use tagu64 in more cases where it should be
and make misused tag() an error
|
2024-10-09 02:42:17 +03:00 |
|
dzaima
|
0eb7f2e5f4
|
make ⊢¨ attempt to squeeze generic arrays in PROPER_FILLS
also make it not segfault on an input without a fill
|
2024-10-09 02:42:17 +03:00 |
|
dzaima
|
f33e1e0dcc
|
allZeroes & allOnes variants which set result flags
|
2024-10-09 02:42:17 +03:00 |
|
dzaima
|
b2bfa06a4c
|
allBit cleanup in cells.c
|
2024-10-09 02:42:17 +03:00 |
|
dzaima
|
1eee4d7450
|
mark input of ∊𝕩 as fl_asc|fl_dsc if it's all same
|
2024-10-09 01:48:23 +03:00 |
|
dzaima
|
7326348c79
|
fast ⍷𝕩 & ∊𝕩 on fl_asc+fl_dsc 𝕩
|
2024-10-09 01:48:23 +03:00 |
|
dzaima
|
12cc7af83d
|
fast path for squeeze target determining on sorted input
|
2024-10-09 01:48:23 +03:00 |
|
dzaima
|
72cdb0d5fb
|
mark reshape_one as ascending & descending
|
2024-10-09 01:48:23 +03:00 |
|
dzaima
|
4b38a8cf6b
|
no need to unroll ≢x size checking
|
2024-10-09 01:48:23 +03:00 |
|
dzaima
|
0d238f2b88
|
mark ↕n with fl_squoze
|
2024-10-09 01:48:23 +03:00 |
|
dzaima
|
fc617b6e32
|
don't try sorting sorted arrays
|
2024-10-09 01:16:23 +03:00 |
|
dzaima
|
989970f7fd
|
fix ∾2‿2⥊<0‿0⥊⟨⟩
|
2024-09-22 01:42:26 +03:00 |
|
dzaima
|
4eb632a48d
|
TO_GET helper
|
2024-09-21 21:26:02 +03:00 |
|
dzaima
|
6f7e82e52b
|
include JIT heap in used heap measurements
|
2024-09-21 21:26:02 +03:00 |
|
dzaima
|
5192a1d466
|
fix x⊸≍˘list & ≍⟜x˘list on non-atom x
|
2024-09-16 00:41:17 +03:00 |
|
dzaima
|
51ab5db2c8
|
move interleave_cells to cells.c
|
2024-09-14 16:18:54 +03:00 |
|
dzaima
|
884d61476f
|
fix flags of take_head
|
2024-09-14 16:15:11 +03:00 |
|
dzaima
|
f3c63d3887
|
use reshape_one for c¨
|
2024-09-13 22:11:40 +03:00 |
|