commits

C++ wrappers for SIMD intrinsics and parallelized, optimized mathematical functions (SSE, AVX, AVX512, NEON, SVE))

SHA	Message	Author	Date
3b3151ff	Add more examples of adoption (#1403)	Sylvain Corlay <s**y@gm> Committed by: GitHub <ny@g**m>	5 days ago
6c89e941	Delete pre 201703L code (#1395)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	6 days ago
eb34bc1f	Migrate recursive template instantiations (#1398)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	15 days ago
2b09e977	Use C++17 type traits (#1397)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	18 days ago
e3cdb6ae	refactor: split is_dup_lo/is_dup_hi into named predicates	Marco Barbone <m**e@fg> Committed by: Marco Barbone <Da@u**m>	22 days ago
5a7dc07e	refactor: replace swizzle template recursion with C++17 constexpr predicates	Marco Barbone <m**e@fg> Committed by: Marco Barbone <Da@u**m>	22 days ago
8ab55669	Use the SSE saturating subtract for 8 and 16 bit types on AVX	Vladimir Saraikin <s**v@pu> Committed by: serge-sans-paille <se@f**r>	25 days ago
67e96b04	fix: make scalar fms fused (std::fma(a, b, -c))	Marco Barbone <m**e@fg> Committed by: serge-sans-paille <se@f**r>	26 days ago
13b9bbe2	Add runtime batch_bool mask overloads for complex batch load/store (#1391)	Marco Barbone <D**a@um> Committed by: GitHub <ny@g**m>	28 days ago
5491a134	no macros or symbols from endian.h are being used in this file (#1386)	Prajwal B Mehendarkar <p**r@im> Committed by: GitHub <ny@g**m>	30 days ago
c30eafeb	Fix clang-tidy warnings (#1390)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	about 1 month ago
7cf60c8e	Backport cleanup (#1385)	Johan Mabille <j**e@gm> Committed by: GitHub <ny@g**m>	about 1 month ago
9d489221	Fix clang tidy check (#1388)	serge-sans-paille <s**n@tu> Committed by: GitHub <ny@g**m>	about 1 month ago
c71a9b23	fix: bind swizzle shuffle mask to constexpr for gcc-15	Marco Barbone <m**e@fg> Committed by: serge-sans-paille <se@f**r>	about 1 month ago
82a37aa7	Remove XSIMD_IF_CONSTEXPR macros, use if constexpr instead (#1382)	Johan Mabille <j**e@gm> Committed by: GitHub <ny@g**m>	about 1 month ago
d0c4a8f4	Fixed documentation badge	Johan Mabille <j**e@g**m>	about 1 month ago
ea590d54	Moved to C++17	Johan Mabille <j**e@gm> Committed by: Marco Barbone <Da@u**m>	about 1 month ago
e88a7283	Release 14.3.0	Johan Mabille <j**e@g**m>	about 1 month ago
9dedfec0	Prefer avx512vl_256 over avxvnni for 256-bit sized batches (#1381)	Marco Barbone <D**a@um> Committed by: GitHub <ny@g**m>	about 1 month ago
90365b6b	Fix saturating subtraction when the subtrahend is the type minimum	Vladimir Saraikin <s**v@pu> Committed by: serge-sans-paille <se@f**r>	about 1 month ago
a4b91131	perf(avx2/avx512): plain-move lowering for int & EVEX constant-mask load/stor...	Marco Barbone <D**a@um> Committed by: GitHub <ny@g**m>	about 1 month ago
171349b0	perf(avx/avx2): plain-move lowering for constant-mask load/store	Marco Barbone <m**e@fg> Committed by: Marco Barbone <Da@u**m>	about 2 months ago
4bb4fe44	fix: correct constant-mask load/store kernels and add shape predicates	Marco Barbone <m**e@fg> Committed by: Marco Barbone <Da@u**m>	about 2 months ago
6488be77	fix(trigo): under-aligned buffers in large-arg range reduction	Marco Barbone <m**e@fg> Committed by: serge-sans-paille <se@f**r>	about 2 months ago
7778faa0	fix(neon): under-aligned store in generic swizzle kernel (#1374)	vsaraikin <s**s@gm> Committed by: GitHub <ny@g**m>	about 2 months ago
978d222a	Add AVX512VL gather scatter kernels	Marco Barbone <m**e@fg> Committed by: Marco Barbone <Da@u**m>	about 2 months ago
92ca9625	Add an explicit SSE2 path for batch_bool_constant masks where the three	Marco Barbone <m**e@fg> Committed by: serge-sans-paille <se@f**r>	about 2 months ago
f320683b	Without a 32/64-bit avx512f transpose specialization, batch<float>/<double>	Marco Barbone <m**e@fg> Committed by: serge-sans-paille <se@f**r>	about 2 months ago
8b12d389	perf(avx512f): single vpermt2 for zip_lo/zip_hi	Marco Barbone <m**e@fg> Committed by: Marco Barbone <Da@u**m>	about 2 months ago
e79f9d36	Fix avx512vl_{128,256} correctness bugs + CI default-arch typo (#1357)	Marco Barbone <D**a@um> Committed by: GitHub <ny@g**m>	2 months ago
0929f1a1	fix: route avxvnni FMA ops through fma3<avx2> kernels (#1368)	Marco Barbone <D**a@um> Committed by: GitHub <ny@g**m>	2 months ago
122d083b	fix: route avx512vl_128 FMA ops through fma3<avx2_128>	Marco Barbone <m**e@fg> Committed by: serge-sans-paille <se@f**r>	2 months ago
5d2490f5	feat: fused mul_hilo for 64-bit batches (shared 32x32->64 partials)	Marco Barbone <m**e@fg> Committed by: serge-sans-paille <se@f**r>	3 months ago
801631ce	feat: masked load/store capability traits + AVX integer masked memory	Marco Barbone <m**e@fg> Committed by: Marco Barbone <Da@u**m>	3 months ago
01f17ece	feat: Add batch::raw (#1363)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	3 months ago
0aa20905	doc: Add link to deployed jupyterlite (#1365)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	3 months ago
4fc99e0c	Add simple notebook (#1364)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	3 months ago
e21128e9	doc: Consolidate build options in one place (#1360)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	3 months ago
4ca27af5	doc: Update RTD deps (#1362)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	3 months ago
1bbcdae4	doc: Fix typos (#1361)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	3 months ago
8fd370e7	Fix doc logo (#1359)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	3 months ago
19d9d27d	perf(avx512vl): native EVEX for int64 sra, signed rotr, compress/expand	Marco Barbone <m**e@fg> Committed by: serge-sans-paille <se@f**r>	3 months ago
24053b57	refactor(masked-memory): dispatch via overload conversion ranking	Marco Barbone <m**e@fg> Committed by: Marco Barbone <Da@u**m>	3 months ago
8c0122bb	chore: small drive-by fixes (avx_128 swizzle, doc typo)	Marco Barbone <m**e@fg> Committed by: Marco Barbone <Da@u**m>	3 months ago
7b357e3e	feat(avx512vl): native EVEX masked load/store on avx512vl_128/256	Marco Barbone <m**e@fg> Committed by: Marco Barbone <Da@u**m>	3 months ago
1eb5aa02	ci: support XSIMD_DEFAULT_ARCH override and verify default_arch	Marco Barbone <m**e@fg> Committed by: Marco Barbone <Da@u**m>	3 months ago
510b4f18	Add efficient_bmi2 (#1354)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	3 months ago
4198b3d7	Fix avx512vp cpuid	AntoinePrv <A**v@um> Committed by: serge-sans-paille <se@f**r>	3 months ago
b707616e	Resolve xtl in user cmake (#1351)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	3 months ago
7d30b9cc	Tentative support for avx512vl extensions to 128 bit registers	serge-sans-paille <s**e@f**r>	3 months ago
60ca510c	Extra masked load/store testing	serge-sans-paille <s**e@f**r>	3 months ago
0e78b8b1	Extra batch_bool invariant testing	serge-sans-paille <s**e@f**r>	3 months ago
f925249c	[ci] Fix lower batch test setup	serge-sans-paille <s**e@f**r>	3 months ago
50d205d4	[x86_64] Minimal support for avx512vl	serge-sans-paille <s**e@f**r>	4 months ago
365b3535	Uniform header inclusion and clang-format tooling (#1343)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	4 months ago
a9039449	[neon] Fix incorrect guard for system headers on Windows	serge-sans-paille <s**e@f**r>	4 months ago
eae2990d	Tentative support for avx512vl extensions to 256 bit registers	serge-sans-paille <s**e@f**r>	4 months ago
cc9ca383	Fix C++ version detection for MSVC (#1342)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	4 months ago
913188e8	Add more x86 cpu feature (#1341)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	4 months ago
f5161a42	refactor: trim masked load/store comments and consolidate AVX2-128 helpers	Marco Barbone <m**e@fg> Committed by: Marco Barbone <Da@u**m>	4 months ago
8af83719	feat: dynamic batch_bool masks + avx_128 / avx2_128 mask overloads	Marco Barbone <m**e@fg> Committed by: Marco Barbone <Da@u**m>	4 months ago
b4348343	Add clang workflow for PPC (#1340)	Andreas Krebbel <k**l@lm> Committed by: GitHub <ny@g**m>	4 months ago
8b816872	ci: split RVV cross-compile into apt-qemu (vlen>=256) + arch-qemu11 (vlen=128)	Marco Barbone <m**e@fg> Committed by: serge-sans-paille <se@f**r>	4 months ago
8df8da7d	Fix VSX clang build	Andreas Krebbel <k**l@lm> Committed by: serge-sans-paille <se@f**r>	4 months ago
93a450e6	fix: avoid atan branch cut in complex trigonometric test	Marco Barbone <m**e@fg> Committed by: serge-sans-paille <se@f**r>	4 months ago
3a61c904	Tentative support for avx2 extensions to 128 bit registers	serge-sans-paille <s**e@f**r>	4 months ago
80c23624	Update changelog and bump for 14.2.0 (#1335)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	4 months ago
5141ff0c	Rename project_num_t to map_to_sized_type_t (#1330)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	4 months ago
5431ec2c	Neon nitpicks (#1331)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	4 months ago
9748316e	Tentative support for avx extensions to 128 bit registers	serge-sans-paille <s**e@f**r>	4 months ago
1c6c7f0a	Fix windows on Neon (#1317)	Antoine Prouvost <A**v@um> Committed by: Johan Mabille <je@g**m>	4 months ago
e80ac4f6	Fix emulated arch interaction with avx512	serge-sans-paille <s**e@f**r>	4 months ago
1f64be37	Provide cmake-level configuration switch for emulated build	serge-sans-paille <s**e@f**r>	4 months ago
4f6601ba	merge Merge pull request #1325 from Andreas-Krebbel/s390x-fixes	Johan Mabille <j**e@gm> Committed by: GitHub <ny@g**m>	4 months ago
ac9a4981	IBM Z (s390x) fixes	Andreas Krebbel <k**l@l**m>	4 months ago
9ce53479	fix build for old compilers (#1323) Signed-off-by: Liu Zixian <z**u@d**m>	Liu Zixian <z**u@dm> Committed by: serge-sans-paille <se@f**r>	4 months ago
233b2def	Force alignment of an aligned test	serge-sans-paille <s**e@f**r>	4 months ago
d8c8b950	Fix rvv_enable_all (#1322)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	4 months ago
9cf14f9c	Fix VSX rounding	Andreas Krebbel <k**l@lm> Committed by: serge-sans-paille <se@f**r>	4 months ago
5680ea9d	Fix test_rounding	Andreas Krebbel <k**l@lm> Committed by: serge-sans-paille <se@f**r>	4 months ago
ed7594f4	merge Merge pull request #1316 from AntoinePrv/odr-violation	Johan Mabille <j**e@gm> Committed by: GitHub <ny@g**m>	4 months ago
d44949bb	merge Merge pull request #1315 from AntoinePrv/factor	Johan Mabille <j**e@gm> Committed by: GitHub <ny@g**m>	4 months ago
ee89900b	Fix load complex	AntoinePrv <A**v@u**m>	4 months ago
efc1bfba	Move to detail_rvv namespace	AntoinePrv <A**v@u**m>	4 months ago
e81b2690	Fix rvv enable_if	AntoinePrv <A**v@u**m>	4 months ago
392decfc	Add enable_signed_numeral	AntoinePrv <A**v@u**m>	4 months ago
708a8691	Factor rvv enable_if	AntoinePrv <A**v@u**m>	4 months ago
32ed0465	Add Sve inline namespace	AntoinePrv <A**v@u**m>	4 months ago
26a5b2c0	Rename sve detail namespace detail_sve	AntoinePrv <A**v@u**m>	4 months ago
b98585a8	Add XSIMD_INLINE	AntoinePrv <A**v@u**m>	4 months ago
ed818748	Remove rvv_fix_char_t	AntoinePrv <A**v@u**m>	4 months ago
142c976a	Factor enable_if utilities	AntoinePrv <A**v@u**m>	4 months ago
91ee1ceb	Add project_num_t	AntoinePrv <A**v@u**m>	4 months ago
368f3581	Factor integer traits (#1314)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	4 months ago
f13baebd	merge Merge pull request #1313 from AntoinePrv/factoring	Johan Mabille <j**e@gm> Committed by: GitHub <ny@g**m>	4 months ago
924ef865	Move macros to macro header	AntoinePrv <A**v@u**m>	4 months ago
29f23cb0	Use XSIMD_CONCAT	AntoinePrv <A**v@u**m>	4 months ago
7d0a3779	Fix SVE dynamic dispatch ODR violation (#1311)	Antoine Prouvost <A**v@um> Committed by: GitHub <ny@g**m>	4 months ago
05b9d84b	merge Merge pull request #1312 from AntoinePrv/cpu-features	Johan Mabille <j**e@gm> Committed by: GitHub <ny@g**m>	4 months ago
dec12b88	feat: add xsimd::get<I>() for compile-time element extraction	Marco Barbone <m**e@fg> Committed by: serge-sans-paille <se@f**r>	4 months ago

← Back to repository

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Commits

GitHub / xtensor-stack/xsimd / commits