Commit Graph

389 Commits

Author SHA1 Message Date
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
34d4fd6433 more explicit loadu/storeu 2023-08-20 00:18:09 +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
Marshall Lochbaum
4e9745688b Use generic boolean Compress as the sparse case with Singeli 2023-08-07 13:47:58 -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
Marshall Lochbaum
e09d385df5 Simplify pairwise pext implementation; drop 12-bit as no longer competitive 2023-08-05 20:38:54 -04:00
dzaima
0b6c5189d8 move arithdDispatch declarations to a header
+ rename some things to make more sense
2023-07-31 20:26:05 +03:00
dzaima
0d7de8b190 define ux in Singeli, replacing Size; return ux from popc/clz/ctz 2023-07-26 17:42:23 +03:00
dzaima
f7a0eb94a3 don't use AVX2 buffer copying for a 16-byte buffer 2023-07-22 21:34:20 +03:00
dzaima
1451395ef5 don't do fancy char stuff for unchecked arith 2023-07-22 21:13:49 +03:00
dzaima
959614c785 use partial application 2023-07-22 18:19:31 +03:00
dzaima
033f3de6b9 remove unnecessary lambda wrappers
also use fmtnat
2023-07-22 18:15:07 +03:00
dzaima
446b2d09ed Singeli renames & docs 2023-07-22 17:37:20 +03:00
dzaima
6e96600878 move unaligned load & store to base.singeli 2023-07-20 00:21:09 +03:00
dzaima
0486adccb5 fix signedness of abs{x} 2023-07-20 00:19:54 +03:00
dzaima
2243fa76c1 better base case list 2023-07-19 21:56:35 +03:00
dzaima
eb46ec8d9c rename __mulhi & __mul32 2023-07-19 21:54:12 +03:00
dzaima
700d69e7dd unpack → zip & mzip; enable slash.singeli SIMD parts for NEON 2023-07-19 21:39:22 +03:00
dzaima
ba2e859dce use existing unpackLo in neq.singeli 2023-07-19 20:56:08 +03:00
dzaima
19b35e1074 fix size comment 2023-07-19 20:11:14 +03:00
dzaima
9945711b5e AVX2 i32 & i64 slash{} via widening load 2023-07-19 20:00:46 +03:00
dzaima
ff9bb258c2 more comments in slash.singeli 2023-07-19 18:50:01 +03:00
dzaima
48111d4873 extract iota{} for AVX-512 2023-07-19 17:24:20 +03:00
dzaima
a0797318ca use has_simd & arch_defvw 2023-07-19 17:03:41 +03:00
dzaima
03c21112c2 make NEON builds work 2023-07-19 16:58:35 +03:00
Marshall Lochbaum
77188b8e73 Add clmul.singeli 2023-07-19 09:38:37 -04:00
Marshall Lochbaum
c4364aefa6 SSSE3 4-byte compress with half-width table 2023-07-19 08:15:53 -04:00
Marshall Lochbaum
ba837ba01b Remove table-less where/compress methods, as they're not competitive 2023-07-19 07:22:55 -04:00
Marshall Lochbaum
64d65ae837 Never use generic dense compress methods if use_table: where is faster 2023-07-18 21:35:12 -04:00
Marshall Lochbaum
b0e0f210c6 2- and 4-byte Where with unpack and table 2023-07-18 21:10:39 -04:00
Marshall Lochbaum
93e1262864 Avoid using popcount primitive in Singeli if POPCNT isn't present 2023-07-18 16:52:08 -04:00
Marshall Lochbaum
6df283c379 Always increment by full popcount instead of two halves when splitting byte 2023-07-17 17:52:59 -04:00
Marshall Lochbaum
2f6a8e55a1 Always use vectors for for_special_buffered buffer copy 2023-07-17 16:52:10 -04:00
Marshall Lochbaum
8add95b7ab Remove BMI2 where/compress methods 2023-07-17 16:20:30 -04:00
Marshall Lochbaum
f005169518 1- and 2-byte compress with table and SSSE3 2023-07-17 16:19:05 -04:00
Marshall Lochbaum
68978f7e10 Table-based 1- and 2-byte Where 2023-07-17 16:05:06 -04:00
Marshall Lochbaum
fc187afdf2 Extend 1-byte SSE2 Where to 2-byte and 4-byte with unpacked writes 2023-07-17 11:28:04 -04:00