Skip to content

issues Search Results · repo:DLTcollab/sse2neon language:C++

Filter by

118 results
 (85 ms)

118 results

inDLTcollab/sse2neon (press backspace or delete to remove)

I encountered some error possibly related to sse2neon when trying to port some SSE code to apple soc. ../src/SmoothUV.cpp:73:17: error: argument to __builtin_neon_vgetq_lane_i16 must be a constant integer ...
  • yuygfgg
  • 2
  • Opened 
    on Jan 10
  • #660

Reproducing https://github.com/DLTcollab/sse2neon/pull/657#issuecomment-2564587426 here: If an alignment of 1 is passed to _mm_malloc(), this implementation will allocate with malloc() and then _mm_free() ...
  • invertego
  • 1
  • Opened 
    on Jan 5
  • #658

clang supports some of these 512bit builtins - do you have support for them? __builtin_ia32_pshufb512 __builtin_ia32_permvarqi512 __builtin_ia32_permvarsi512 __builtin_ia32_cvtb2mask512 __builtin_ia32_cvtd2mask512 ...
  • anujgoyal
  • Opened 
    on Nov 22, 2024
  • #655

The current source file is harder to follow than it should be. Splitting off the arm7 code into it s own header would help. Then all those fallbacks can be jettisoned. Apple Silicon, iPhone 5S, and all ...
  • alecazam
  • 2
  • Opened 
    on Sep 18, 2024
  • #649

_MM_SET_ROUNDING_MODE is declared as FORCE_INLINE_OPTNONE, which lowers performance. Unless I m missing something, wouldn t it be better to define the r union as volatile instead?
  • jmather-sesi
  • 5
  • Opened 
    on Sep 4, 2024
  • #648

Currently, the pre-built GNU toolchain for Arm-based CPUs used in our GitHub Actions is version GCC 11.2-2022.02, sourced from the Arm Developer website. Given that a more recent version, 13.3.Rel1, is ...
  • jserv
  • 2
  • Opened 
    on Aug 16, 2024
  • #647

When we run CI with optimization options, compiler would warn that the codebase break strict-aliasing rules. see the CI https://github.com/DLTcollab/sse2neon/actions/runs/9658424846/job/26639574270?pr=638 ...
  • howjmay
  • 1
  • Opened 
    on Jun 25, 2024
  • #639

After having a little more of a dig in relation to #633 - it appears that tests are failing on all platforms, including linux, when using newer versions of clang (tested against LLVM 14 through to LLVM ...
  • anthony-linaro
  • 16
  • Opened 
    on May 29, 2024
  • #635

I m using sse2neon with Agner Fogs VCL. In this article I read that the the SSE ordering of the vector in the SIMD type is the reverse of Neon. https://developer.arm.com/documentation/102581/0200/Port-with-SSE2Neon-and-SIMDe ...
  • dtxpression
  • 2
  • Opened 
    on May 24, 2024
  • #634

I am trying to compile a project using sse2neon.h inside a docker container from the base image balenalib/raspberrypi3-debian:bookworm, using QEMU for armv7 virtualization. Here is some info as printed ...
  • ankith26
  • 2
  • Opened 
    on Apr 18, 2024
  • #629
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue search results · GitHub