Commit Graph

3081 Commits

Author SHA1 Message Date
Marshall Lochbaum
bf69705c82 Factor (8×k)/bool as bit-replicate, then byte-replicate 2024-08-14 10:30:26 -04:00
Marshall Lochbaum
fc1265b3f2 Enable (non-boolean) constrep on SSSE3 2024-08-14 10:30:26 -04:00
Marshall Lochbaum
048529740b SSE2 k/bool where k divides 8 implementations 2024-08-14 10:30:26 -04:00
Marshall Lochbaum
ee27717c97 SSE2 odd/bool implementation using [4]u32 shuffles 2024-08-14 10:30:26 -04:00
Marshall Lochbaum
36e9ca5814 Extend odd/bool SSSE3 code to support AVX2 2024-08-14 10:30:26 -04:00
Marshall Lochbaum
2be022921e Combine generic and SSSE3 general-case odd/bool, so SSSE3 uses mask unpacking 2024-08-14 10:30:26 -04:00
Marshall Lochbaum
3e5dbdbf8d Dedicated generic k/bool for divisors of 8; factor; remove pdep emulation 2024-08-14 10:30:26 -04:00
Marshall Lochbaum
13ec029d9f Get odd k/bool carry by shifting in the unified register, not after masking 2024-08-14 10:30:26 -04:00
Marshall Lochbaum
1621c7d07c Generic-arch k/bool algorithm for odd k with mask unpacking 2024-08-14 10:30:26 -04:00
Marshall Lochbaum
7d7d36b354 Extend SSSE3 k/bool to k<32 using pairwise swaps 2024-08-14 10:30:26 -04:00
Marshall Lochbaum
696a23af9e Mask off last k/bool vector properly 2024-08-14 10:30:26 -04:00
Marshall Lochbaum
1a4cada0cb AVX2 support in rep_const_bool_ssse3_div8 2024-08-14 10:30:26 -04:00
Marshall Lochbaum
b4d84041bc Extend odd k/bool SSSE3 algorithm to k<16, factor even k≤32 2024-08-14 10:30:26 -04:00
Marshall Lochbaum
a439a0a430 SSSE3 k/bool for 2≤k≤8, k≠6 2024-08-14 10:30:26 -04:00
Marshall Lochbaum
a4b6d8d827 SSSE3 3/bool, faster than BMI2 2024-08-14 10:30:26 -04:00
Marshall Lochbaum
7f6c401eb3 Generic-architecture k/bool for small 8<k 2024-08-14 10:30:26 -04:00
Marshall Lochbaum
0602927b17 Move pdep-based k/bool code to Singeli 2024-08-14 10:30:26 -04:00
dzaima
de5bebb239 fix bitnarrow on aarch64 2024-08-14 16:41:58 +03:00
dzaima
e4005e9d7c add SINGELI_SSSE3 2024-08-14 15:51:06 +03:00
dzaima
f83f63b22d add has=ssse3, has=sse4.1, and has=sse4.2 2024-08-14 15:47:17 +03:00
dzaima
565a0a8458 inline zeroPadToCellBits0 2024-08-14 15:21:42 +03:00
dzaima
fc800ee191 remove debug include 2024-08-14 15:06:43 +03:00
dzaima
ef1ea4ad0f make gcc not complain about break
funky
2024-08-14 05:25:13 +03:00
dzaima
2ca2c52c16 use direct bitwiden & bitnarrow in select-rows 2024-08-14 05:18:13 +03:00
dzaima
d95a792230 add bitwiden & bitnarrow to header 2024-08-14 05:18:13 +03:00
dzaima
d0f30bd717 extract direct pointer version of bitnarrow 2024-08-14 05:18:13 +03:00
dzaima
d676663f45 better unaligned load option for bitwiden 2024-08-14 05:18:13 +03:00
dzaima
6e8c6d2e10 extract direct pointer version of bitwiden 2024-08-14 05:18:13 +03:00
dzaima
9672f07c1b add select-bit-cells test 2024-08-14 05:18:13 +03:00
dzaima
7eb2b97e29 use COPY_TO_FROM in cpyU16Bits & cpyU8Bits 2024-08-14 05:18:13 +03:00
dzaima
c445f24aae COPY_TO_FROM 2024-08-14 05:18:13 +03:00
dzaima
9b515c3fad reverse pointer arguments of copy.singeli exports 2024-08-14 05:18:13 +03:00
dzaima
6d7648c947 more things that could be select-rows'd 2024-08-14 05:18:13 +03:00
dzaima
f6c52ef3b3 disable Singeli bitwiden on SSE2 2024-08-14 05:18:13 +03:00
dzaima
f356ba0f36 more definitions in base.singeli 2024-08-14 05:18:13 +03:00
dzaima
3fc92eceaa include util/tup in base.singeli 2024-08-14 05:18:13 +03:00
dzaima
a9460da19c more missing NEON comments 2024-08-14 05:18:13 +03:00
dzaima
eccbac37ab aarch64 8→n bitnarrow 2024-08-14 05:18:13 +03:00
dzaima
c72ed51149 Singeli n→8 bitwiden 2024-08-14 05:18:13 +03:00
dzaima
f36cefc9ac more Singeli utils 2024-08-14 05:18:13 +03:00
dzaima
5748833060 fast inds⊸⊏˘bits for ≤8-bit input & output cells 2024-08-14 05:18:13 +03:00
dzaima
920a89f019 native ⋈⁼ & ⌾⋈
plus some more undo & under tests
2024-08-14 05:18:13 +03:00
dzaima
ae0d392d43 tyarrv_free 2024-08-14 05:02:24 +03:00
dzaima
46b63125bc ARBITRARY & GUARANTEED 2024-08-14 05:02:24 +03:00
dzaima
2c36a3e399 fix ⟨1‿2⟩⊸⊏˘ mat 2024-08-09 00:36:23 +03:00
dzaima
3716162e69 use q_fbit more 2024-08-09 00:32:27 +03:00
dzaima
e0facc54f8 minor src/README.md cleanup 2024-08-09 00:32:27 +03:00
dzaima
8e49fc04bb --replxx-read-only 2024-08-09 00:32:27 +03:00
dzaima
ced082cc82 use custom valgrind pdep/pext everywhere 2024-08-09 00:32:27 +03:00
dzaima
d1469df96b fix out-of-bounds load on empty replxx line
`chars[0] == ')'` was branching on empty data; not UB due to custom heap
usage and the code that does run is harmless, but still hit under
valgrind
2024-08-09 00:32:27 +03:00