vylsaz
d570f8d303
Implement •file.MapBytes for Windows
2024-01-27 07:12:09 +00:00
vylsaz
f1cc597317
Util to report Windows error
2024-01-27 06:59:56 +00:00
dzaima
ffffdb5895
relax take/drop overflow checking
2024-01-19 18:03:54 +02:00
dzaima
0f691138c9
basic fix for •ReBQN{primitives⇐⟨','‿+⟩}
2024-01-19 18:02:24 +02:00
dzaima
83afa4ba99
rename functions in cmp.singeli
2024-01-11 23:36:03 +02:00
Marshall Lochbaum
f62981e370
Make Singeli if conditions have type u1
2024-01-10 17:10:53 -05:00
Marshall Lochbaum
7511420077
Fix first element of 1-byte Deduplicate result in some cases with 256 uniques
2024-01-07 21:27:12 -05:00
Marshall Lochbaum
2af2fb8e0c
Use ⍷⊸⊐ for Classify (⊐) on long 1-byte arguments if SIMD bit-table is available
2024-01-07 19:54:13 -05:00
dzaima
20185b57c5
fix nested •FFI calls, more FFI testing
2024-01-02 19:33:28 +02:00
dzaima
ca7e62d09f
fix •FFI with various arguments while mutable ones are present more
2024-01-02 18:30:33 +02:00
dzaima
381c03a456
fix •FFI with both a mutated & struct/array argument
2024-01-02 17:08:10 +02:00
Marshall Lochbaum
dbb6fbade1
Fast interleaving (≍˘) for pointer arrays
2023-12-31 16:28:59 -05:00
Marshall Lochbaum
5f3a4769be
Rename constrep.singeli to replicate.singeli; not just constant now
2023-12-31 15:30:20 -05:00
Marshall Lochbaum
e50ae40f8b
Port replicate-by-scan code from C to Singeli
2023-12-31 15:26:58 -05:00
Marshall Lochbaum
771496a25c
Pass slow-pdep build option to Singeli to suppress BMI2 bool/bool
2023-12-31 10:05:51 -05:00
Marshall Lochbaum
9604844d0b
Don't need ..._ before & in Singeli any more
2023-12-30 21:45:24 -05:00
Marshall Lochbaum
3584ebd7a6
Non-BMI2 bit interleaving implementation
2023-12-30 21:45:24 -05:00
Marshall Lochbaum
eb34213f0f
Fast ≍˘ for matching-type type-sized cells
2023-12-30 21:45:24 -05:00
Marshall Lochbaum
58f4f15f8f
Move more functionality to avx512.singeli
2023-12-30 10:43:40 -05:00
Marshall Lochbaum
92db3f15d0
Implement ≠` with AVX-512 clmul and GFNI
2023-12-30 10:43:06 -05:00
dzaima
9dc44ed1a9
make singeli/arch.bqn the source of SINGELI_AVX2
...
+ removes noting of lack of AVX2, which isn't shown from the makefile anyway
2023-12-30 02:09:56 +02:00
dzaima
18d2fa5f1c
rename Singeli select function
...
in anticipation to Singeli update which adds select as a builtin
2023-12-29 23:35:22 +02:00
dzaima
f11bebf8f4
fix usz=64 build
2023-12-28 19:17:57 +02:00
Marshall Lochbaum
dcb031d142
Make sure value in store{} has an appropriate type
2023-12-27 16:44:53 -05:00
dzaima
ce31945124
fix "ab"⍷⟨⟩
2023-12-27 19:16:34 +02:00
dzaima
add8ba353e
require MAP_FIXED_NOREPLACE on linux for JIT
2023-12-26 02:53:47 +02:00
dzaima
7c50d210ff
fix FreeBSD name conflict
2023-12-26 00:47:11 +02:00
dzaima
2e61f52d22
use MAP_EXCL on FreeBSD
...
OpenBSD should be fine as is, as it by default respects the hint if possible (I believe, at least, looking at its man page)
2023-12-26 00:47:11 +02:00
dzaima
f0c1962596
more typed ⌾(list⊸⊏)
2023-12-19 17:41:17 +02:00
dzaima
17c575edba
trivial fast path for >depth1arr
2023-12-16 01:45:29 +02:00
dzaima
470e77b6b3
more typed 𝔽⌾(m⊸/)
2023-12-15 23:53:26 +02:00
dzaima
72893fc2f5
cell-wise PervasiveDy` highRank
2023-12-15 21:43:07 +02:00
dzaima
66b5c1fc0a
fix a⊒b on mixed-width characters
2023-12-15 20:02:14 +02:00
dzaima
840c40748f
fix f64 scans on SSE2
2023-12-15 19:18:23 +02:00
dzaima
c785b3a7b8
squeeze created arrays in F⍟arr
2023-12-15 18:05:20 +02:00
dzaima
94b1d90995
SSE2 & NEON /⁼
2023-12-14 18:08:56 +02:00
dzaima
f71d2ff376
remove unused name variables
2023-12-14 17:45:04 +02:00
dzaima
7268c11df4
more fixes of path display
2023-12-13 22:03:00 +02:00
dzaima
a3a9403b59
fix paths shown in error stacktraces
2023-12-13 21:59:23 +02:00
dzaima
7bf379a44e
check that -o output is a list
2023-12-13 17:49:54 +02:00
dzaima
8cce6b7add
set re_map more properly
2023-12-12 13:32:46 +02:00
dzaima
653583eb1d
make •Import follow ReBQN
2023-12-11 14:02:38 +02:00
dzaima
ec4db6dbad
tiny Singeli include changes
2023-12-10 15:55:57 +02:00
dzaima
3454fbe3ee
defer negated ≤AVX2 comparison negation to GPR result
2023-12-05 17:37:37 +02:00
dzaima
b9b90fbe8f
improve error messages of o2i/o2i64/o2u64 & usum
2023-12-05 17:19:36 +02:00
dzaima
9984d720c9
move bit_sum to fold.c
2023-12-05 16:41:38 +02:00
dzaima
a439c64e85
fix error message of usum of i32arr encountering a negative element
2023-12-05 16:03:53 +02:00
dzaima
5c7ab3f9a8
change heuristic for when ⊔ separates filtering out ¯1
...
measurements of the previous one were affected by 08c4627686
2023-12-04 22:50:19 +02:00
dzaima
8870acd2c1
don't try to do 32 >> -1
2023-12-04 17:45:00 +02:00
dzaima
065f15d0e3
fix function type
2023-12-04 17:39:13 +02:00
dzaima
e2db41547d
change threshold for a 𝕨⊐𝕩 case
2023-12-04 17:37:35 +02:00
dzaima
d7c153286e
gc tests, more reuse removal
2023-12-04 12:07:03 +02:00
dzaima
baa23cb527
add a trailing newline to double-fatal message
...
apparently 'puts' has a trailing newline but 'fputs' doesn't
2023-12-04 11:35:34 +02:00
dzaima
ecb2d5f63a
fix GC referencing bug in reusing 𝕨𝔽`𝕩 by not bothering to reuse
2023-12-04 01:27:38 +02:00
dzaima
fcc939dbed
debug flag for running a GC every n'th allocation
2023-12-03 23:34:49 +02:00
dzaima
6573232694
macro option for an intentionally-bad hash function for testing purposes
2023-11-29 18:58:34 +02:00
dzaima
609980f950
comment about HashMap entry format
2023-11-29 18:05:08 +02:00
Marshall Lochbaum
72a9a95819
Make sure •HashMap table leaves last entry empty, as a sentinel
2023-11-28 20:08:27 -05:00
Marshall Lochbaum
51027cabe1
Fix GC-after-free with multiple hash resizes
2023-11-28 16:53:45 -05:00
Marshall Lochbaum
53beab531b
•HashMap key and value list compaction and methods to return those lists
2023-11-28 11:09:32 -05:00
Marshall Lochbaum
95f5e65b6c
•HashMap delete with backwards shift; no key/value compaction yet
2023-11-28 10:52:56 -05:00
Marshall Lochbaum
ce9f460e2c
•HashMap count and set functions
2023-11-28 10:33:41 -05:00
Marshall Lochbaum
016e428db6
Always store •HashMap keys and values as HArrs
2023-11-27 19:20:38 -05:00
Marshall Lochbaum
96c7f2eb1a
Move •HashMap implementation details to search.c
2023-11-27 19:20:38 -05:00
Marshall Lochbaum
77bfc7dd1a
Non-resizing static Robin Hood hashmap
2023-11-27 19:20:38 -05:00
Marshall Lochbaum
8edc965686
•HashMap stub with linear lookup
2023-11-27 19:20:38 -05:00
dzaima
adc4506ac8
fast path for ind integer checking
2023-11-26 22:16:53 +02:00
dzaima
4b67de5f83
don't need these comments
...
they're present in h.h, and trivial to determine from source anyway
2023-11-26 22:16:53 +02:00
dzaima
e9b7d027ca
cleanup & fix various build types
2023-11-26 16:56:26 +02:00
dzaima
01a60dceff
separate path & name, store path+name+args in state
2023-11-26 16:32:37 +02:00
dzaima
fe280613af
fix toHArr usage in another place
2023-11-26 15:53:44 +02:00
dzaima
789064140b
use isStr more, include builtin name in bad path messages
2023-11-26 15:37:41 +02:00
dzaima
31e4b29115
proper toHArr usage
2023-11-26 14:56:08 +02:00
dzaima
fce64987b1
helper for immediately-consumed block
2023-11-26 14:54:37 +02:00
dzaima
633bbc8112
don't need def_rt & def_glyphs either actually
...
+ clean up some gc_add-ing
2023-11-26 14:45:54 +02:00
dzaima
b28c1a8f01
get rid of global def_comp & def_compOpts, refcount fixes
2023-11-26 13:56:26 +02:00
dzaima
7dd398433b
fix native compiler
2023-11-26 13:46:07 +02:00
dzaima
71ade3e9c6
add missed decrements, expand test
2023-11-26 01:27:36 +02:00
dzaima
3f62a51305
system value inheriting
2023-11-26 01:21:11 +02:00
dzaima
a93ea4dbaf
base •ReBQN and •BQN onto outer re
2023-11-25 23:39:58 +02:00
dzaima
5e455372f0
more renaming & shuffling of things
2023-11-25 23:21:32 +02:00
dzaima
e25281518c
move more things into re
2023-11-25 23:21:32 +02:00
dzaima
7c28c64178
change •BQN and •ReBQN to dynamically-computed functions
2023-11-25 23:21:32 +02:00
dzaima
7214017bb2
move •BQN and •ReBQN to computed sysvals
2023-11-25 23:21:32 +02:00
dzaima
7e0204083e
name re parts
2023-11-25 23:21:32 +02:00
dzaima
7fb8ecfa86
rename things
2023-11-25 23:21:32 +02:00
dzaima
cd6da03fd9
always supply a valid re object
2023-11-25 23:21:32 +02:00
dzaima
7357820f19
start of compiler state refactoring
2023-11-25 23:21:32 +02:00
dzaima
dcf26f88d7
fix segfault during GC from compileAll's cpyHArr(objs)
2023-11-25 21:37:48 +02:00
dzaima
5458739cf2
don't have a ⌾ character in m_c8vec_0
...
name shouldn't ever be visible either, so shortening it while at it
2023-11-24 22:21:23 +02:00
dzaima
db0bb1378c
rearrange Body fields to pack better
2023-11-24 16:00:11 +02:00
dzaima
1d8479b589
apparently nothing uses the bc field in Comp anymore
2023-11-24 15:30:47 +02:00
dzaima
eb62b48e4e
don't inline wyhash make_secret
...
+ remove wyhashmap, we don't need it, it breaks on collisions
2023-11-24 15:24:28 +02:00
dzaima
f02c92ee6a
fix 3 ∨ "abc"
2023-11-23 18:13:51 +02:00
dzaima
8814a7e66e
use 2x unroll for i16→u1 copying to utilize two-vector homMask
2023-11-21 02:45:33 +02:00
dzaima
773429a959
recursive base-case of homMask
2023-11-21 02:40:50 +02:00
dzaima
08fa7d3d30
specialize x86-64 homMask of 2x[n]i16, use for comparison
2023-11-21 02:29:03 +02:00
dzaima
3ebfb24b0f
unroll copying to bitarr
...
+ clean up comparison code as bulk homMask is supported everywhere
2023-11-21 00:18:18 +02:00
dzaima
fe985722c2
move multi-vector homMask to allow NEON to override it
2023-11-21 00:18:18 +02:00
dzaima
d1f66dc75b
check created bitarr size for overflow
2023-11-18 19:56:39 +02:00
dzaima
56cbe4aa03
mulHi → mulh for high half of element result
...
to not be confused with mulwHi or zipHi where it means providing the high batch of elements
2023-11-18 00:43:20 +02:00
dzaima
c8cdaf0216
Clear assumption about assignment result in const-folder
2023-11-17 17:44:32 +02:00
dzaima
2b56a300bc
probably make ⊔ able to handle output subarray lengths over 2^32
...
still no support for (≠𝕨)≥2⋆32 though
2023-11-17 00:40:26 +02:00
dzaima
46e8ed1a3f
fix SSE4.2 usz=64 build
2023-11-13 23:28:30 +02:00
dzaima
59208af520
remove old group path
...
effectively only got used for f64arr 𝕨; could transform to doing just that, but its inefficient type of the group arrays make it bad for that too
2023-11-13 23:16:02 +02:00
dzaima
f037754880
more specific empty array types
2023-11-13 23:16:02 +02:00
dzaima
8c7a3be036
remove unused includes
2023-11-13 21:48:01 +02:00
dzaima
b4e53abbe4
some comments
2023-11-13 16:38:02 +02:00
Marshall Lochbaum
c94d51dcaf
Fixes for 64-bit usz
2023-11-13 08:24:51 -05:00
dzaima
4fb6ce602f
add a require{} for CRC32
2023-11-13 12:56:48 +02:00
dzaima
5910c93fcb
silence some warnings & errors in various build types
2023-11-13 12:54:49 +02:00
Marshall Lochbaum
09572de49a
Credible resizing policy for dyadic search hashes
2023-11-12 22:07:29 -05:00
Marshall Lochbaum
ee7a11a279
Unify self-search hash thresholds across primitives; doesn't seem to hurt performance
2023-11-12 14:35:25 -05:00
Marshall Lochbaum
5957487b70
Faster iteration over non-empty entries for hash table resizing
2023-11-11 20:24:20 -05:00
Marshall Lochbaum
b404c7c1d1
Eliminate a loop when resizing ordered hash
2023-11-11 20:24:20 -05:00
Marshall Lochbaum
3a50cda5d3
Specialize Index-of tables on result type
2023-11-10 17:12:37 -05:00
Marshall Lochbaum
b782693d15
Insert maxh to a special end bucket for ⊒ and reverse ⊐ (fixes ⊒ maxh bugs)
2023-11-10 12:04:55 -05:00
Marshall Lochbaum
e1b0c53c92
Fix various sentinel bugs
2023-11-09 20:24:46 -05:00
Marshall Lochbaum
7b79dfc94e
Update search implementation comments
2023-11-09 15:20:50 -05:00
Marshall Lochbaum
2c625127d5
Reverse hashed Index-of
2023-11-09 10:39:07 -05:00
Marshall Lochbaum
f1485ca98c
Turn hash function definition structure inside-out
2023-11-09 09:19:47 -05:00
Marshall Lochbaum
aded9d4782
Shortcutting for reverse Member-of hash
2023-11-08 17:34:33 -05:00
Marshall Lochbaum
8e9c04523a
Fix overflow bug in hashed Member-of max_off calculation
2023-11-08 10:28:14 -05:00
Marshall Lochbaum
c75fdbc277
Reverse Member-of hash lookup
2023-11-07 22:07:17 -05:00
Marshall Lochbaum
8a2190b092
64-bit hashes with float normalization
2023-11-07 14:54:16 -05:00
Marshall Lochbaum
a4290b1f5c
Shortcut for hash-table dyadic ⊒
2023-11-07 09:59:53 -05:00
Marshall Lochbaum
4bf4149d40
Use hash deletion for forward ⊒ as well as reverse
2023-11-07 09:41:50 -05:00
Marshall Lochbaum
289658a59c
Delete hash entry as soon as it's cleared, not on next access
2023-11-07 07:53:45 -05:00
Marshall Lochbaum
30331eb800
Fix write off end for reverse ⊒
2023-11-07 07:15:17 -05:00
Marshall Lochbaum
c042fe6ca3
Vector binary search for integer Index-of
2023-11-06 15:43:26 -05:00
Marshall Lochbaum
52bca6a55c
Multiple IndexOfOne to search for a few values in a large array
2023-11-06 12:16:59 -05:00
Marshall Lochbaum
d154ece51a
Vector binary search for 16-bit Member-of in addition to 32 (8 is too slow)
2023-11-06 09:37:58 -05:00
Marshall Lochbaum
11245d385e
Vector binary search Member-of
2023-11-05 22:10:39 -05:00
Marshall Lochbaum
75aed91f32
And max offset of 8 by testing two vectors
2023-11-05 15:46:26 -05:00
Marshall Lochbaum
ec31543604
Vector Member-of search up to an offset of 4
2023-11-05 15:45:07 -05:00
Marshall Lochbaum
af81da50e4
Don't need to initialize indices for hashed Index-of
2023-11-04 17:52:22 -04:00
Marshall Lochbaum
1286ee32ec
Reverse lookup for hashed Progressive Index-of
2023-11-03 21:58:17 -04:00
Marshall Lochbaum
84f3205547
Use a larger initial hash table if non-hashed argument is large
2023-11-03 21:50:38 -04:00
Marshall Lochbaum
a9f33c1454
Refactoring
2023-11-03 16:38:08 -04:00
Marshall Lochbaum
8aa6c07199
And hashed 32-bit Progressive Index-of
2023-11-02 20:29:54 -04:00
Marshall Lochbaum
64f2a10fbb
Return hash_resize{} from hash_alloc{}
2023-11-02 13:21:11 -04:00
Marshall Lochbaum
d54621b5dd
Extend hash table to 32-bit Index-of
2023-11-02 12:00:32 -04:00
Marshall Lochbaum
ed03720441
Robin Hood hash table for 32-bit membership
2023-11-01 15:46:45 -04:00
Marshall Lochbaum
cb8be206be
Move hash allocation to a generator
2023-10-31 22:09:11 -04:00
Marshall Lochbaum
ee856a4880
Move hash resizing to a generator, and other refactoring
2023-10-31 22:09:11 -04:00
Marshall Lochbaum
0391cf4ca3
Fast number-character (no matches) searches
2023-10-31 22:09:11 -04:00
Marshall Lochbaum
0fb845d336
Move self-search hash table code to Singeli
2023-10-31 22:09:11 -04:00
dzaima
ad574d2269
refactor & document #define-s, always-available ')gc log' and ')mem log'
2023-10-31 03:16:48 +02:00
dzaima
08c4627686
fix dense case of •rand.Subset not updating seed
2023-10-30 17:03:38 +02:00
dzaima
a4befbd8bf
FFI: check for 𝕨 being present when required
2023-10-29 01:01:48 +03:00
dzaima
7ffd744375
reorganize file writing
...
fixes some unclosed file descriptors & files being made on an invalid argument
2023-10-28 19:27:00 +03:00
dzaima
b6594008cd
fix non-Singeli builds
2023-10-26 17:32:12 +03:00
dzaima
3775cd0025
typo
2023-10-22 15:18:39 +03:00
dzaima
577442449d
inverses for •math.Atan2, •math error tests
2023-10-22 14:33:51 +03:00
dzaima
1ec48bb761
cleanup
...
makefile doesn't care about emcc anymore
2023-10-21 14:46:41 +03:00
dzaima
4322303031
Fix 2‿2↕3‿3‿3⥊↕27
2023-10-12 12:43:08 +03:00
dzaima
9c68e67544
fix compilation error when targeting AVX1-only
2023-10-07 13:22:27 +03:00
dzaima
e7b87f669f
fix arr÷negativeZero, set proper float expected values
2023-09-21 19:03:30 +03:00
dzaima
f6a9c30889
•internal.HeapStats
2023-09-18 23:38:06 +03:00
dzaima
df0ccdf2d7
add error message on missing posix_spawn support in make for-build
2023-09-17 13:39:22 +03:00
dzaima
299168fb16
fast numarr÷scalarPowOf2
2023-09-12 23:57:50 +03:00
dzaima
5efd90cc91
rename elWidthLogBits to something less long & add byte variant
2023-09-12 19:58:56 +03:00
Marshall Lochbaum
6330d61a88
Some rearrangement and minor simplifications
2023-09-12 10:24:00 -04:00
Marshall Lochbaum
72da47d48a
Use standard for loops
2023-09-12 09:12:57 -04:00
Marshall Lochbaum
40ed55bc43
Use built-in NEON include for basic vector instructions
2023-09-11 21:17:38 -04:00
Marshall Lochbaum
7b9f7ba331
Move x86 vector and NEON includes into base.singeli
2023-09-11 20:25:25 -04:00
Marshall Lochbaum
082f800b3e
Combine x86 vector extensions and use iintrinsic/basic when possible
2023-09-11 20:11:16 -04:00
Marshall Lochbaum
c85ca66dae
Unify Scan and Bins min-scan code
2023-08-26 09:27:59 -04:00
Marshall Lochbaum
0a30fb309d
SSE2 min- and max-scans
2023-08-26 07:26:33 -04:00
Marshall Lochbaum
a040a14744
Unify power-of-two shift pattern for scans
2023-08-26 07:26:33 -04:00
Marshall Lochbaum
d16ba6c3b1
Move xor-scan to scan.singeli; remove neq.singeli
2023-08-26 07:26:33 -04:00
Marshall Lochbaum
e261e80168
SSE min/max and pluswrap scans
2023-08-26 07:26:33 -04:00
Marshall Lochbaum
f9a4a5b68c
Remove duplicated SSE4.1 min/max bindings
2023-08-26 07:26:33 -04:00
Marshall Lochbaum
00c454d37a
Add generic-architecture versions of Singeli scans
2023-08-26 07:26:33 -04:00
dzaima
ec14d45c50
round up pointers in self-search allocs
2023-08-25 04:03:25 +03:00
dzaima
81a291f860
round up some pointers
2023-08-25 03:47:05 +03:00
dzaima
f0d6a65240
move unaligned load/store helpers to stuff.h
...
also replace a NULL with "" to make iBuf+0 not be UB
2023-08-25 03:24:42 +03:00
dzaima
8975f6af00
fast 1|x
2023-08-24 21:32:35 +03:00
dzaima
3e6e158696
native 𝕨⍷𝕩 when 1≥=𝕨 and 2≥=𝕩
2023-08-24 19:46:57 +03:00
dzaima
c5b98ea7a1
apparently LLVM actually uses pointer type to determine alignment
2023-08-20 22:57:30 +03:00
dzaima
6eaa9238bc
separate BSDs
2023-08-20 19:33:11 +03:00
dzaima
34d4fd6433
more explicit loadu/storeu
2023-08-20 00:18:09 +03:00
dzaima
1bb686a9ff
fix UB in grade.h
2023-08-19 21:48:11 +03:00
dzaima
2732becf50
global STR0/STR1 definitions
2023-08-19 20:12:53 +03:00
dzaima
721dccf636
fix FFI integer overflow check on ARM
...
clang optimizes a raw f!=(u8)f to like f!=(u32)f on ARM which changes behavior (we're technically using UB here, but there's no reasonable alternative); use q_ functions that know how to work around this
2023-08-19 20:12:53 +03:00
dzaima
25c2629842
•platform
...
incl. adding support for REPL completion of •a.b.c (i.e. >1 '.')
2023-08-19 18:25:52 +03:00
dzaima
4d19654e3b
fix store types
2023-08-16 19:01:04 +03:00
dzaima
acca5c0c7c
fix completely wrong dyTable lookup
2023-08-15 14:45:27 +03:00
dzaima
df56f6b2fc
fix 𝕨•FLines𝕩 with invalid elements in 𝕩
2023-08-13 03:51:06 +03:00
Marshall Lochbaum
2dd3a0fdfa
Boolean compress implementation comments
2023-08-07 15:33:37 -04:00
Marshall Lochbaum
4e9745688b
Use generic boolean Compress as the sparse case with Singeli
2023-08-07 13:47:58 -04:00
Marshall Lochbaum
a7908a10b0
Faster, sparse, non-Singeli boolean Compress
2023-08-07 12:26:40 -04:00
Marshall Lochbaum
bbad98bce1
In AVX2 boolean Compress, jump from 8 to 32 with 32-bit shifts
2023-08-07 11:41:53 -04:00
Marshall Lochbaum
120df26814
mullo works for both signed and unsigned
2023-08-07 11:23:38 -04:00
Marshall Lochbaum
d039562efe
Fix disabled BMI2 boolean Compress; cleaner SIMD width system
2023-08-06 08:09:08 -04:00
Marshall Lochbaum
9046dd6b53
Handle boolean Compress SIMD tail with conditional write, not scalar loop
2023-08-06 08:03:14 -04:00
Marshall Lochbaum
07ace41d6c
Vectorized version of the clmul boolean Compress
2023-08-06 07:36:05 -04:00
Marshall Lochbaum
371aa6f2ef
AVX2 boolean Compress using variable shifts
2023-08-05 21:50:22 -04:00
Marshall Lochbaum
66c0fe041c
Get pext and popcount together, since generic pext emulation includes popc
2023-08-05 20:38:54 -04:00
Marshall Lochbaum
056b18edd2
Move pext-based compress loop from C to Singeli
2023-08-05 20:38:54 -04:00