about summary refs log tree commit diff
path: root/library/stdarch
AgeCommit message (Collapse)AuthorLines
2023-10-31Refactor some loops to avoid indexingEduardo Sánchez Muñoz-211/+48
2023-10-31Simplify some expressions with pointers and referencesEduardo Sánchez Muñoz-12/+12
2023-10-31Avoid constans that are too close to `PI` or `TAU`Eduardo Sánchez Muñoz-8/+8
2023-10-31Fuse multiple `str::replace` invocations into a single oneEduardo Sánchez Muñoz-3/+1
2023-10-31Convert `while` loop to `for`Eduardo Sánchez Muñoz-1/+1
2023-10-31Derive `Default` for `Initializer` in std_detectEduardo Sánchez Muñoz-8/+3
2023-10-31Simplify a `cfg`Eduardo Sánchez Muñoz-2/+2
2023-10-31Do not deny `clippy::missing_inline_in_public_items` in std_detectEduardo Sánchez Muñoz-1/+0
2023-10-31Replace some `x >= LO && x <= HI` with `matches!(x, LO..=HI)`Eduardo Sánchez Muñoz-5/+5
2023-10-31Change `x <= y - 1` to `x < y` in `static_assert_{u,s}imm_bits`Eduardo Sánchez Muñoz-2/+2
2023-10-31Silence four additional clippy warnings and sort them alphabeticallyEduardo Sánchez Muñoz-2/+6
2023-10-31Drop old link from intrinsic-test README.Jacob Bramley-4/+0
Now, the README approximately matches the `--help` output.
2023-10-30Add `#[cfg_attr(miri, ignore)]` to tests of functions that cannot be ↵Eduardo Sánchez Muñoz-0/+27
supported by Miri This includes functions that use inline assemby or that do certains operations such as saving/restoring the processor state.
2023-10-30Improve _mm_round_ss/_mm_round_sd testsEduardo Sánchez Muñoz-10/+38
* Do not use deprecated CSR access functions * Test different rounding modes
2023-10-30Extend _mm_minpos_epu16 test to check case where minimum value is repeatedEduardo Sánchez Muñoz-0/+9
2023-10-30Extend _mm_insert_ps test to check zeroing priority over copyingEduardo Sánchez Muñoz-0/+7
2023-10-30Extend _mm_mulhrs_epi16 test to check large valuesEduardo Sánchez Muñoz-0/+7
2023-10-30Extend _mm_maddubs_epi16 test to check widening and saturating behaviorEduardo Sánchez Muñoz-0/+21
2023-10-30Extend SSSE3 hadd/hsub tests to check overflow behavior (wrapping or saturating)Eduardo Sánchez Muñoz-0/+78
2023-10-30Extend _mm_shuffle_epi8 test to check index wrappingEduardo Sánchez Muñoz-0/+5
2023-10-30Extend _mm_madd_epi16 test to check cases with large values.Eduardo Sánchez Muñoz-0/+26
2023-10-29Fix various compilation errorsAmanieu d'Antras-17/+36
2023-10-29Fix more missing/incorrect feature specificationsAmanieu d'Antras-12/+76
2023-10-29Cleanup last uses of the stdsimd featureAmanieu d'Antras-11/+8
2023-10-29Add tracking issue for 32-bit ARM DSP instrinsicsAmanieu d'Antras-2/+51
2023-10-29Remove ARM udf and dbg intrinsicsAmanieu d'Antras-32/+0
These have already been removed for AArch64
2023-10-29Add tracking issue for all remaining unstable NEON intrinsicsAmanieu d'Antras-33/+149
2023-10-29Add tracking issue for ARM barrier intrinsicsAmanieu d'Antras-25/+29
2023-10-29Add tracking issue for ARM hint intrinsicsAmanieu d'Antras-0/+7
2023-10-29Add tracking issue for AArch64 prefetch intrinsicAmanieu d'Antras-0/+8
2023-10-29Add tracking issue for AArch64 TME intrinsicsAmanieu d'Antras-0/+17
2023-10-29Add tracking issue for ARM CRC32 intrinsicsAmanieu d'Antras-2/+10
2023-10-29Add stability attributes for re-exports of AArch64 NEON intrinsicsAmanieu d'Antras-0/+3
2023-10-29Fix 'since' in simd_avx512_types stability attributeAmanieu d'Antras-3/+3
2023-10-29Fix stability attributes for ARM crypto intrinsicsAmanieu d'Antras-56/+78
2023-10-29Add tracking issue for ARM NEON instructionsAmanieu d'Antras-6/+3835
2023-10-29Add tracking issue for NVPTX intrinsicsAmanieu d'Antras-1/+19
2023-10-29Add tracking issues for feature detectionAmanieu d'Antras-77/+89
2023-10-29Add tracking issue for MIPS intrinsicsAmanieu d'Antras-56/+595
2023-10-29Add tracking issues for WebAssemblyAmanieu d'Antras-0/+27
2023-10-29Add tracking issue for `_MM_SHUFFLE`Amanieu d'Antras-1/+1
2023-10-29Check for missing stability attributes when building outside coreAmanieu d'Antras-2/+4
2023-10-29Add tracking issue for PowerPC intrinsicsAmanieu d'Antras-2/+185
2023-10-29Add tracking issue for RISC-V intrinsicsAmanieu d'Antras-47/+169
2023-10-29Revert accidental stabilization of `_mm512_storeu_ps`Amanieu d'Antras-1/+0
2023-10-29Add tracking issue on `has_cpuid`Amanieu d'Antras-0/+1
2023-10-29Add stability attributes on x86 re-exportsAmanieu d'Antras-13/+58
2023-10-29Add tracking issue for RTMAmanieu d'Antras-0/+12
2023-10-29Add tracking issue for AVX-512Amanieu d'Antras-0/+3943
2023-10-21Disable NEON intrinsics on big-endian ARMAmanieu d'Antras-98/+14
These are currently broken because the order of elements inside vectors is reversed on big-endian systems: the ARM ABI requires that element 0 is located at the highest address of the vector type. However LLVM intrinsics expect element 0 to be located at the lowest address. See https://llvm.org/docs/BigEndianNEON.html and `arm_neon.h` in Clang for more details. Although this is a breaking change, this is acceptable for 2 reasons: - big endian ARM targets are only tier 3. - it is preferable to stop existing code from compiling than to let it run and produce incorrect results.
generated by cgit-pink 1.4.1-3-g733a5 (git 2.37.1) at 2026-04-24 03:00:13 +0000