simde

simde copied to clipboard

_mm_malloc and _mm_free (feature request)

6

Many codes that use SSE and friends also use `_mm_{malloc,realloc,free}`. SSE2Neon supports these (https://github.com/DLTcollab/sse2neon/pull/25/files). The implementation is simple and I will try to contribute if no one else does it...

jeffhammond

I saw that apple has a fork of sse2neon here: https://github.com/Developer-Ecosystem-Engineering/sse2neon/commit/0478ed66e6142b33af881d94c420574ea51b6762 They might have some useful arm64 implementations that could be ported to SIMDe.

milot-mirdita

- [ ] a Markdown file named `paper.md`structured like [this](https://joss.readthedocs.io/en/latest/submitting.html#example-paper-and-bibliography) and compiles properly using this [preview service](https://whedon.theoj.org/) - [ ] Including all [required sections](https://joss.readthedocs.io/en/latest/submitting.html#what-should-my-paper-contain) - [ ] A list of...

mr-c

Hi, there is a [bug report](https://bugs.debian.org/1002223) of the Debian packaged simde version which results in: Summary of Failures: 7/874 x86/avx512/abs/emul/c ERROR 0.01s exit status 1 8/874 x86/avx512/abs/native/c ERROR 0.01s exit...

tillea

Native aliases for `_mm512_setzero_ps` and `_mm512_setzero_pd` were copy-pasted from `_mm512_setzero_si512` without modification. This pull request fixes the issue.

EleonoreMizo

The float versions below already have `static const` so I assume these should be too.

sbc100

I'm having difficulty understanding how to build the tests I want. I'd like to build tests for native x86 SIMD sets, one at a time, with the CMake file that's...

seanbaxter

Fixed _mm_insert_ps in correct translation of the function.

6

The issue was a wrong copy and incorrect masking. https://github.com/simd-everywhere/simde/issues/931 I haven't fixed the unit test as I don't have the dev setup of the library (I am working on...

MirJawadMairaj

_mm_insert_ps is broken on ARM processor

2

Hi, I noticed that _mm_insert_ps is broken on 0.7.2 (and I noticed still on master as well). I have a fix that worked for me looking at: https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#techs=SSE4_1&ig_expand=4048 ``` SIMDE_FUNCTION_ATTRIBUTES...

MirJawadMairaj

neon/mla_lane: initial implementation using mla+dup

2

ngzhian