Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

SIMD #12

Merged
merged 55 commits into from
Nov 27, 2023
Merged

SIMD #12

merged 55 commits into from
Nov 27, 2023

Commits on Nov 7, 2023

  1. use loop pragmas

    @chriselrod
    chriselrod committed Nov 7, 2023
    Configuration menu
    Copy the full SHA
    545a550 View commit details
    Browse the repository at this point in the history

  2. polymathnovec check

    @chriselrod
    chriselrod committed Nov 7, 2023
    Configuration menu
    Copy the full SHA
    e92701f View commit details
    Browse the repository at this point in the history

Commits on Nov 8, 2023

  1. some exerpimentation

    @chriselrod
    chriselrod committed Nov 8, 2023
    Configuration menu
    Copy the full SHA
    e207808 View commit details
    Browse the repository at this point in the history

  2. Minor progress; need to decide should I bite the bullet and switch to… 

    … column major?
    @chriselrod
    chriselrod committed Nov 8, 2023
    Configuration menu
    Copy the full SHA
    c17dcce View commit details
    Browse the repository at this point in the history

Commits on Nov 9, 2023

  1. Some progress updating RowVectors to be the default

    @chriselrod
    chriselrod committed Nov 9, 2023
    Configuration menu
    Copy the full SHA
    eca5570 View commit details
    Browse the repository at this point in the history

  2. SArray updates, and requires singleline seems to muck up some other f… 

    …ormatting options, so remove it again
    @chriselrod
    chriselrod committed Nov 9, 2023
    Configuration menu
    Copy the full SHA
    7c02a34 View commit details
    Browse the repository at this point in the history

Commits on Nov 10, 2023

  1. tests compile but fail

    @chriselrod
    chriselrod committed Nov 10, 2023
    Configuration menu
    Copy the full SHA
    b680baa View commit details
    Browse the repository at this point in the history

  2. tests pass

    @chriselrod
    chriselrod committed Nov 10, 2023
    Configuration menu
    Copy the full SHA
    be6ec98 View commit details
    Browse the repository at this point in the history

  3. add benchmarks

    @chriselrod
    chriselrod committed Nov 10, 2023
    Configuration menu
    Copy the full SHA
    e9d5787 View commit details
    Browse the repository at this point in the history

  4. some benchmarking progress

    @chriselrod
    chriselrod committed Nov 10, 2023
    Configuration menu
    Copy the full SHA
    adb44bd View commit details
    Browse the repository at this point in the history

  5. fix introduced test failures

    @chriselrod
    chriselrod committed Nov 10, 2023
    Configuration menu
    Copy the full SHA
    a1b9e7a View commit details
    Browse the repository at this point in the history

  6. move donotopt

    @chriselrod
    chriselrod committed Nov 10, 2023
    Configuration menu
    Copy the full SHA
    ac43898 View commit details
    Browse the repository at this point in the history

Commits on Nov 11, 2023

  1. start adding SIMD using gnu vector builtins

    @chriselrod
    chriselrod committed Nov 11, 2023
    Configuration menu
    Copy the full SHA
    b208ed6 View commit details
    Browse the repository at this point in the history

Commits on Nov 12, 2023

  1. Next thing to do is move indexing implementation more fully into `Ind… 

    …exing.hpp`, so we call it with ptr, dimension, and index args.
    @chriselrod
    chriselrod committed Nov 12, 2023
    Configuration menu
    Copy the full SHA
    d7630a5 View commit details
    Browse the repository at this point in the history

  2. some intrinsic progress

    @chriselrod
    chriselrod committed Nov 12, 2023
    Configuration menu
    Copy the full SHA
    cea8fab View commit details
    Browse the repository at this point in the history

Commits on Nov 13, 2023

  1. minor progress on simd

    @chriselrod
    chriselrod committed Nov 13, 2023
    Configuration menu
    Copy the full SHA
    0cd1bd3 View commit details
    Browse the repository at this point in the history

  2. add a transpose method

    @chriselrod
    chriselrod committed Nov 13, 2023
    Configuration menu
    Copy the full SHA
    06c7365 View commit details
    Browse the repository at this point in the history

  3. minor progress

    @chriselrod
    chriselrod committed Nov 13, 2023
    Configuration menu
    Copy the full SHA
    5f69375 View commit details
    Browse the repository at this point in the history

Commits on Nov 14, 2023

  1. minor progress

    @chriselrod
    chriselrod committed Nov 14, 2023
    Configuration menu
    Copy the full SHA
    5199ca0 View commit details
    Browse the repository at this point in the history

  2. tests in a passing state, but not actually using SIMD yet (making thi… 

    …s a good checkpoint for starting to turn it on and debug).
    @chriselrod
    chriselrod committed Nov 14, 2023
    Configuration menu
    Copy the full SHA
    95ab0cb View commit details
    Browse the repository at this point in the history

Commits on Nov 15, 2023

  1. Clang passes tests, GCC can't compile

    @chriselrod
    chriselrod committed Nov 15, 2023
    Configuration menu
    Copy the full SHA
    34acd5a View commit details
    Browse the repository at this point in the history

  2. Both GCC and Clang compile, and tests pass

    @chriselrod
    chriselrod committed Nov 15, 2023
    Configuration menu
    Copy the full SHA
    557ba0b View commit details
    Browse the repository at this point in the history

  3. matrix impl

    @chriselrod
    chriselrod committed Nov 15, 2023
    Configuration menu
    Copy the full SHA
    82fb670 View commit details
    Browse the repository at this point in the history

Commits on Nov 16, 2023

  1. initial matrix impl

    @chriselrod
    chriselrod committed Nov 16, 2023
    Configuration menu
    Copy the full SHA
    9924bf1 View commit details
    Browse the repository at this point in the history

  2. Currently in broken state

    @chriselrod
    chriselrod committed Nov 16, 2023
    Configuration menu
    Copy the full SHA
    8ed1281 View commit details
    Browse the repository at this point in the history

  3. one vcopyTo method

    @chriselrod
    chriselrod committed Nov 16, 2023
    Configuration menu
    Copy the full SHA
    51d2efb View commit details
    Browse the repository at this point in the history

  4. one scopyTo method

    @chriselrod
    chriselrod committed Nov 16, 2023
    Configuration menu
    Copy the full SHA
    57310ea View commit details
    Browse the repository at this point in the history

  5. further consolidation

    @chriselrod
    chriselrod committed Nov 16, 2023
    Configuration menu
    Copy the full SHA
    2cd9ccc View commit details
    Browse the repository at this point in the history

Commits on Nov 17, 2023

  1. Some debugging progress

    @chriselrod
    chriselrod committed Nov 17, 2023
    Configuration menu
    Copy the full SHA
    337922a View commit details
    Browse the repository at this point in the history

  2. tests pass

    @chriselrod
    chriselrod committed Nov 17, 2023
    Configuration menu
    Copy the full SHA
    1e7f839 View commit details
    Browse the repository at this point in the history

  3. avx512 bug fixes

    @chriselrod
    chriselrod committed Nov 17, 2023
    Configuration menu
    Copy the full SHA
    323d67b View commit details
    Browse the repository at this point in the history

Commits on Nov 18, 2023

  1. minor progress; in broken state, adding SIMD array

    @chriselrod
    chriselrod committed Nov 18, 2023
    Configuration menu
    Copy the full SHA
    aec9ec0 View commit details
    Browse the repository at this point in the history

Commits on Nov 19, 2023

  1. Some progress, tests currently don't compile.

    @chriselrod
    chriselrod committed Nov 19, 2023
    Configuration menu
    Copy the full SHA
    a60c925 View commit details
    Browse the repository at this point in the history

  2. Add mask comparisons

    @chriselrod
    chriselrod committed Nov 19, 2023
    Configuration menu
    Copy the full SHA
    8e47067 View commit details
    Browse the repository at this point in the history

  3. deduction doesn't work for builtin vvectors

    @chriselrod
    chriselrod committed Nov 19, 2023
    Configuration menu
    Copy the full SHA
    e790497 View commit details
    Browse the repository at this point in the history

  4. tests pass

    @chriselrod
    chriselrod committed Nov 19, 2023
    Configuration menu
    Copy the full SHA
    9d0e0e1 View commit details
    Browse the repository at this point in the history

Commits on Nov 20, 2023

  1. minor progress; currently broken. Plan here is to make compression op… 

    …toinal for `Array` so views of decompressed static arrays will work.
    @chriselrod
    chriselrod committed Nov 20, 2023
    Configuration menu
    Copy the full SHA
    dde1923 View commit details
    Browse the repository at this point in the history

Commits on Nov 21, 2023

  1. tests pass

    @chriselrod
    chriselrod committed Nov 21, 2023
    Configuration menu
    Copy the full SHA
    79fe5a1 View commit details
    Browse the repository at this point in the history

  2. add more benchmarks

    @chriselrod
    chriselrod committed Nov 21, 2023
    Configuration menu
    Copy the full SHA
    e28ceec View commit details
    Browse the repository at this point in the history

  3. Use explicit Compress template value instead of an alignment value … 

    …that implies compression. Also separate `Dual` impl between compressed and uncompressed to undefine most operations on the compressed version. TODO: separate non-pow-2-multiple implementation for Dual, and allow iterating.
    @chriselrod
    chriselrod committed Nov 21, 2023
    Configuration menu
    Copy the full SHA
    e4413c9 View commit details
    Browse the repository at this point in the history

  4. Updates, perf looking good

    @chriselrod
    chriselrod committed Nov 21, 2023
    Configuration menu
    Copy the full SHA
    25fa838 View commit details
    Browse the repository at this point in the history

  5. add comments, trivial change to index::Unroll cmp ops

    @chriselrod
    chriselrod committed Nov 21, 2023
    Configuration menu
    Copy the full SHA
    fd0a0fe View commit details
    Browse the repository at this point in the history

Commits on Nov 22, 2023

  1. Add tuple tests

    @chriselrod
    chriselrod committed Nov 22, 2023
    Configuration menu
    Copy the full SHA
    b07139c View commit details
    Browse the repository at this point in the history

  2. Some progress on implementing fused array ops

    @chriselrod
    chriselrod committed Nov 22, 2023
    Configuration menu
    Copy the full SHA
    5c219d1 View commit details
    Browse the repository at this point in the history

  3. some progress implementing fused exprs

    @chriselrod
    chriselrod committed Nov 22, 2023
    Configuration menu
    Copy the full SHA
    c39f66d View commit details
    Browse the repository at this point in the history

Commits on Nov 23, 2023

  1. some further updates

    @chriselrod
    chriselrod committed Nov 23, 2023
    Configuration menu
    Copy the full SHA
    6e0c755 View commit details
    Browse the repository at this point in the history

  2. add some static asserts

    @chriselrod
    chriselrod committed Nov 23, 2023
    Configuration menu
    Copy the full SHA
    e95dcc0 View commit details
    Browse the repository at this point in the history

  3. fix static assert

    @chriselrod
    chriselrod committed Nov 23, 2023
    Configuration menu
    Copy the full SHA
    bb96451 View commit details
    Browse the repository at this point in the history

  4. implement flattening, but no perf benefit observed yet, so commented … 

    …out for now
    @chriselrod
    chriselrod committed Nov 23, 2023
    Configuration menu
    Copy the full SHA
    b13a032 View commit details
    Browse the repository at this point in the history

Commits on Nov 25, 2023

  1. Some fixes, the reinterpret may be broken because of UB?

    @chriselrod
    chriselrod committed Nov 25, 2023
    Configuration menu
    Copy the full SHA
    69adf9d View commit details
    Browse the repository at this point in the history

  2. some improvements and fixes

    @chriselrod
    chriselrod committed Nov 25, 2023
    Configuration menu
    Copy the full SHA
    d1ae306 View commit details
    Browse the repository at this point in the history

  3. a couple bug fixes and layout fixes for duals

    @chriselrod
    chriselrod committed Nov 25, 2023
    Configuration menu
    Copy the full SHA
    2c5fa0b View commit details
    Browse the repository at this point in the history

  4. fix Dual

    @chriselrod
    chriselrod committed Nov 25, 2023
    Configuration menu
    Copy the full SHA
    30a98ae View commit details
    Browse the repository at this point in the history

Commits on Nov 26, 2023

  1. simplify expm impl a little

    @chriselrod
    chriselrod committed Nov 26, 2023
    Configuration menu
    Copy the full SHA
    884fdc4 View commit details
    Browse the repository at this point in the history

Commits on Nov 27, 2023

  1. fix-format

    @chriselrod
    chriselrod committed Nov 27, 2023
    Configuration menu
    Copy the full SHA
    1eef35b View commit details
    Browse the repository at this point in the history