sse2neon

What's Changed

• refactor: Add missing ARM64 implementation by @howjmay in https://github.com/DLTcollab/sse2neon/pull/576
• test: Build/run with crypto and/or crc by @howjmay in https://github.com/DLTcollab/sse2neon/pull/574
• doc: Describe the right coverage of SSE2NEON_PRECISE_MINMAX by @howjmay in https://github.com/DLTcollab/sse2neon/pull/578
• refactor: Reimplement _mm_movelh_ps for Arm64 by @howjmay in https://github.com/DLTcollab/sse2neon/pull/579
• tests: Cover all immediate numbers by @howjmay in https://github.com/DLTcollab/sse2neon/pull/584
• test: Use macro for validate results by @howjmay in https://github.com/DLTcollab/sse2neon/pull/585
• Improve precision of mm{rsqrt,sqrt,rcp,div}_{ps,ss} conversions by @Cuda-Chen in https://github.com/DLTcollab/sse2neon/pull/580
• Fix MSVC compile issues by @toxieainc in https://github.com/DLTcollab/sse2neon/pull/588
• Tweak MSVC ifdef guard for _BitScanForward64 by @aqrit in https://github.com/DLTcollab/sse2neon/pull/592
• Add notice that NEON handles certain IEEE single-precision values by @Cuda-Chen in https://github.com/DLTcollab/sse2neon/pull/593
• Add infinity test in test_mm_{max,min}_{pd,sd} by @Cuda-Chen in https://github.com/DLTcollab/sse2neon/pull/594
• Remove Kahan algorithm in _mm_dp_ps by @Cuda-Chen in https://github.com/DLTcollab/sse2neon/pull/597
• MSVC support by @anthony-linaro in https://github.com/DLTcollab/sse2neon/pull/596
• test: Cover all the valid imm range in tests by @howjmay in https://github.com/DLTcollab/sse2neon/pull/586
• Add test running for MSVC to CI by @anthony-linaro in https://github.com/DLTcollab/sse2neon/pull/598
• Align result to SSE when input is 0.0f/-0.0f in mm_rsqrt{ps, ss} by @Cuda-Chen in https://github.com/DLTcollab/sse2neon/pull/599
• fix: Fix exceeding width of type warning by @howjmay in https://github.com/DLTcollab/sse2neon/pull/601
• docs: Fix the typos by @howjmay in https://github.com/DLTcollab/sse2neon/pull/603
• docs: Fix the typos by @spacemiqote in https://github.com/DLTcollab/sse2neon/pull/605
• Fix build for gcc-13 and 32 bit arm systems. by @balister in https://github.com/DLTcollab/sse2neon/pull/609
• Fix unused parameters warning by @anakinxc in https://github.com/DLTcollab/sse2neon/pull/610
• Fixed gcc strict prototype and other build errors by @mnjdhl in https://github.com/DLTcollab/sse2neon/pull/611
• Fix _mm_cmplt_sd and _mm_cmpnlt_sd test cases by @Cuda-Chen in https://github.com/DLTcollab/sse2neon/pull/612
• disambiguate vector type to avoid errors depending on lax conversion … by @JoachimSchurig in https://github.com/DLTcollab/sse2neon/pull/614
• docs: fix typo failback by @howjmay in https://github.com/DLTcollab/sse2neon/pull/616
• Introduce fast and deterministic RNG by @Cuda-Chen in https://github.com/DLTcollab/sse2neon/pull/615
• fix: Fix typo nand by @howjmay in https://github.com/DLTcollab/sse2neon/pull/617
• fix: Fix MSVC warnings by @howjmay in https://github.com/DLTcollab/sse2neon/pull/604
• Add A32 support in CI by @Cuda-Chen in https://github.com/DLTcollab/sse2neon/pull/620
• Fix _mm_test_mix_ones_zeros and _mm_testnzc_si128 by @aqrit in https://github.com/DLTcollab/sse2neon/pull/621

New Contributors

• @anthony-linaro made their first contribution in https://github.com/DLTcollab/sse2neon/pull/596
• @spacemiqote made their first contribution in https://github.com/DLTcollab/sse2neon/pull/605
• @anakinxc made their first contribution in https://github.com/DLTcollab/sse2neon/pull/610
• @mnjdhl made their first contribution in https://github.com/DLTcollab/sse2neon/pull/611
• @JoachimSchurig made their first contribution in https://github.com/DLTcollab/sse2neon/pull/614

Full Changelog: https://github.com/DLTcollab/sse2neon/compare/v1.6.0...v1.7.0

What's Changed

• 100% intrinsics coverage for SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2 and AES extension.
• Implement _rdtsc by @Cuda-Chen in https://github.com/DLTcollab/sse2neon/pull/532
• Improve _mm_srai_epi32 to handle complex arguments by @Developer-Ecosystem-Engineering in https://github.com/DLTcollab/sse2neon/pull/533
• Implement _mm_cmpestri and _mm_cmpestrm by @Cuda-Chen in https://github.com/DLTcollab/sse2neon/pull/534
• Implement five _mm_cmpestr by @Cuda-Chen in https://github.com/DLTcollab/sse2neon/pull/552
• Implement _mm_cmpistri and _mm_cmpistrm by @Cuda-Chen in https://github.com/DLTcollab/sse2neon/pull/553
• Implement five _mm_cmpistr by @Cuda-Chen in https://github.com/DLTcollab/sse2neon/pull/555
• tests: Fix warnings raised by clang++ by @Cuda-Chen in https://github.com/DLTcollab/sse2neon/pull/540
• Exclude _mm_malloc/free definitions on Windows by @invertego in https://github.com/DLTcollab/sse2neon/pull/541
• Remove designated initialization of an array by @invertego in https://github.com/DLTcollab/sse2neon/pull/542
• Reintroduce ext-based implementations for shift intrinsics by @AymenQ in https://github.com/DLTcollab/sse2neon/pull/543
• Improve performance of float-to-integer intrinsics by @AymenQ in https://github.com/DLTcollab/sse2neon/pull/546
• Support __builtin_shuffle as an alternative to __builtin_shufflevector by @AymenQ in https://github.com/DLTcollab/sse2neon/pull/545
• Improve performance of various intrinsics by @AymenQ in https://github.com/DLTcollab/sse2neon/pull/549
• Vectorize _mm_minpos_epu16 by @AymenQ in https://github.com/DLTcollab/sse2neon/pull/551
• Align _mm_prefetch behavior to document by @howjmay in https://github.com/DLTcollab/sse2neon/pull/550
• Add clang/Windows build by @invertego in https://github.com/DLTcollab/sse2neon/pull/556
• Test all valid immediates in _mm_dp_pd by @Cuda-Chen in https://github.com/DLTcollab/sse2neon/pull/557
• Optimize _mm_aesenclast_si128 for Arm64 by @howjmay in https://github.com/DLTcollab/sse2neon/pull/561
• Implement _mm_aesdec_si128 by @howjmay in https://github.com/DLTcollab/sse2neon/pull/559
• Implement _mm_aesdeclast_si128 by @howjmay in https://github.com/DLTcollab/sse2neon/pull/565
• Implement _mm_aesimc_si128 by @howjmay in https://github.com/DLTcollab/sse2neon/pull/567
• Optimize aeskeygenassist_si128 for Arm64 by @howjmay in https://github.com/DLTcollab/sse2neon/pull/569
• Update Intel intrinsics document links by @howjmay in https://github.com/DLTcollab/sse2neon/pull/570

New Contributors

• @Cuda-Chen made their first contribution in https://github.com/DLTcollab/sse2neon/pull/532
• @Developer-Ecosystem-Engineering made their first contribution in https://github.com/DLTcollab/sse2neon/pull/533
• @balister made their first contribution in https://github.com/DLTcollab/sse2neon/pull/535
• @invertego made their first contribution in https://github.com/DLTcollab/sse2neon/pull/541
• @AymenQ made their first contribution in https://github.com/DLTcollab/sse2neon/pull/543

Full Changelog: https://github.com/DLTcollab/sse2neon/compare/v1.5.1...v1.6.0

What's Changed

• fix: Fix dividing zero error in validateFloatError by @HowJMay in https://github.com/DLTcollab/sse2neon/pull/515
• Fix compilation with standardized C compilers by @jserv in https://github.com/DLTcollab/sse2neon/pull/516
• Fix _mm_storel_epi64 by @andrewevstyukhin in https://github.com/DLTcollab/sse2neon/pull/517
• Add support for 32-bit targets on ARMv8 architectures by @jonathanhue in https://github.com/DLTcollab/sse2neon/pull/520
• Use CRC and directed rounding intrinsics on A32 by @jonathanhue in https://github.com/DLTcollab/sse2neon/pull/522
• fix: Fix alignment in tests by @HowJMay in https://github.com/DLTcollab/sse2neon/pull/523

New Contributors

• @sleepybishop made their first contribution in https://github.com/DLTcollab/sse2neon/pull/508
• @luzpaz made their first contribution in https://github.com/DLTcollab/sse2neon/pull/509
• @andrewevstyukhin made their first contribution in https://github.com/DLTcollab/sse2neon/pull/517
• @jonathanhue made their first contribution in https://github.com/DLTcollab/sse2neon/pull/520

Full Changelog: https://github.com/DLTcollab/sse2neon/compare/v1.5.0...v1.5.1

Around 94% of the SSE intrinsics are implemented in the release.
The rest of the unimplemented intrinsics are:

• Exception related macros
• _mm_clflush()
• Memory barrier intrinsics
• String comparison intrinsics