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

Add Armv7M support for Cortex-M4 and Cortex-M7 #61

Draft
wants to merge 246 commits into
base: main
Choose a base branch
from
Draft

Add Armv7M support for Cortex-M4 and Cortex-M7 #61

wants to merge 246 commits into from

Commits on Aug 7, 2024

  1. Very early armv7m support 

    * Basic parsing functionality
* A few instructions modeled for M4
* Extend helper to resolve .if/.else directives
    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    4e5d9fb View commit details
    Browse the repository at this point in the history

  2. Cortex-M4 adjustments for Keccak 

    * NOT tested for functional correctness
* Parsing Keccak works, "optimizing" small parts as well
    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    9529353 View commit details
    Browse the repository at this point in the history

  3. Allow .w/.n annotation for instructions as "width"

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    0870d09 View commit details
    Browse the repository at this point in the history

  4. Fix bug in condition parsing

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    15b5055 View commit details
    Browse the repository at this point in the history

  5. Add Cortex-M7 Model

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    834d91c View commit details
    Browse the repository at this point in the history

  6. Enhance Armv7M and M7 model

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    b8360c0 View commit details
    Browse the repository at this point in the history

  7. rm useless M7 constraint

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    17903a0 View commit details
    Browse the repository at this point in the history

  8. Fix to str in Armv7M

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    59eef53 View commit details
    Browse the repository at this point in the history

  9. Fix bug in .if ... .else parsing

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    f7b79b4 View commit details
    Browse the repository at this point in the history

  10. Update Cortex-M7 model with new instructions and some fixes

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    b8e4728 View commit details
    Browse the repository at this point in the history

  11. FIx in_out decl for ldr Armv7M

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    5f8ee70 View commit details
    Browse the repository at this point in the history

  12. Add naive example code for Keccak M7

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    b287000 View commit details
    Browse the repository at this point in the history

  13. Fix in_out declaration for {ldr,str}_with_postinc in Armv7M

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    8a25456 View commit details
    Browse the repository at this point in the history

  14. Update Example for Keccak

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    4a01d61 View commit details
    Browse the repository at this point in the history

  15. Fix Armv7M model

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    2db7e1b View commit details
    Browse the repository at this point in the history

  16. Add read/write annotations to Keccak code

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    2616dea View commit details
    Browse the repository at this point in the history

  17. Opt Keccak M4/7

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    acabe5f View commit details
    Browse the repository at this point in the history

  18. Fix register type for Armv7m

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    29522fc View commit details
    Browse the repository at this point in the history

  19. Add support for Arm Cortex-M4 and Cortex-M7 targets to query

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    ea4bfbc View commit details
    Browse the repository at this point in the history

  20. Update Cortex-M7 model with new instructions and fix load latency

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    372288a View commit details
    Browse the repository at this point in the history

  21. Add naive code for small part of keccak (for debugging)

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    e852163 View commit details
    Browse the repository at this point in the history

  22. Fix example.py

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    d0a98e2 View commit details
    Browse the repository at this point in the history

  23. add example

    @mkannwischer @dop-amin
    mkannwischer authored and dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    409ae35 View commit details
    Browse the repository at this point in the history

  24. re-add asm

    @mkannwischer @dop-amin
    mkannwischer authored and dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    0f31b18 View commit details
    Browse the repository at this point in the history

  25. port han's additions to slothy

    @mkannwischer @dop-amin
    mkannwischer authored and dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    2d7c733 View commit details
    Browse the repository at this point in the history

  26. fix ldr latency

    @mkannwischer @dop-amin
    mkannwischer authored and dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    09c8420 View commit details
    Browse the repository at this point in the history

  27. relax output register constraints

    @mkannwischer @dop-amin
    mkannwischer authored and dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    cd38a9c View commit details
    Browse the repository at this point in the history

  28. add renaming of other function in dilithium

    @mkannwischer @dop-amin
    mkannwischer authored and dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    1403445 View commit details
    Browse the repository at this point in the history

  29. Two load units on M7

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    0664db0 View commit details
    Browse the repository at this point in the history

  30. Example Keccak Part

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    cb84ca2 View commit details
    Browse the repository at this point in the history

  31. make clang like the dilithium NTT

    @mkannwischer @dop-amin
    mkannwischer authored and dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    82f2018 View commit details
    Browse the repository at this point in the history

  32. enable mca for dilithium ntt

    @mkannwischer @dop-amin
    mkannwischer authored and dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    9a1f462 View commit details
    Browse the repository at this point in the history

  33. make dilithium code work in with mca

    @mkannwischer @dop-amin
    mkannwischer authored and dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    c4fe685 View commit details
    Browse the repository at this point in the history

  34. [Experimental] Refine M7 model 

    * Use w-form
* Model shift unit
* Tweak str tp/latency
* Handle eor with shift as "special case"
    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    bc2adc4 View commit details
    Browse the repository at this point in the history

  35. M7 special latencies 

    * ldr -> arith fwd
* 2c latency if consumer has barrell shift
    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    03f2052 View commit details
    Browse the repository at this point in the history

  36. Generalize ldr->arith/log. fwd

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    617ad4f View commit details
    Browse the repository at this point in the history

  37. Add MAC fwd

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    77f7a76 View commit details
    Browse the repository at this point in the history

  38. Fix vmov latency, own subclass for multiplications

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    d087c21 View commit details
    Browse the repository at this point in the history

  39. Fix shifted operand latency special case

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    27f3753 View commit details
    Browse the repository at this point in the history

  40. Add eor_short

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    baa526c View commit details
    Browse the repository at this point in the history

  41. [experimental] Add vmov cycle restriction

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    c423d0f View commit details
    Browse the repository at this point in the history

  42. Modify naive code to be parsable by slothy

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    f60c213 View commit details
    Browse the repository at this point in the history

  43. Progress Keccak optimization

    @dop-amin
    dop-amin committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    355bf02 View commit details
    Browse the repository at this point in the history

Commits on Aug 13, 2024

  1. Add sources to model

    @dop-amin
    dop-amin committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    d13a73d View commit details
    Browse the repository at this point in the history

Commits on Oct 1, 2024

  1. Add absorb_spills configuration controlling merge of stack spills

    @hanno-becker
    hanno-becker committed Oct 1, 2024
    Configuration menu
    Copy the full SHA
    0a104de View commit details
    Browse the repository at this point in the history

  2. Add 'altnerating' strategy for naive interleaving 

    When `split_heuristic_preprocess_naive_interleaving` is enabled,
SLOTHY preprocesses the input by naively reordering instructions
according to their depths in the computational flow graph.

This commit introduces another naive interleaving strategy
"alternate" which will make SLOTHY alternate evenly between
instructions tagged with `interleaving_class=0/1`. This is
useful when two sequential blocks of code are to be interleaved
as evenly as possible, which is common in scalar/Neon hybrids.
    @hanno-becker
    hanno-becker committed Oct 1, 2024
    Configuration menu
    Copy the full SHA
    4e7c974 View commit details
    Browse the repository at this point in the history

Commits on Oct 2, 2024

  1. add Kyber NTT (functional only)

    @mkannwischer
    mkannwischer committed Oct 2, 2024
    Configuration menu
    Copy the full SHA
    ff26548 View commit details
    Browse the repository at this point in the history

  2. Add llvm to CI run 

    Add llvm to CI run to allow mca in example script.
    @dop-amin
    dop-amin authored Oct 2, 2024
    Configuration menu
    Copy the full SHA
    0b14cfa View commit details
    Browse the repository at this point in the history

  3. Merge branch 'main' into armv7m

    @dop-amin
    dop-amin authored Oct 2, 2024
    Configuration menu
    Copy the full SHA
    92e3ee5 View commit details
    Browse the repository at this point in the history

  4. llvm-14 -> llvm

    @dop-amin
    dop-amin authored Oct 2, 2024
    Configuration menu
    Copy the full SHA
    e59851d View commit details
    Browse the repository at this point in the history

  5. remove vmov constraint

    @dop-amin
    dop-amin committed Oct 2, 2024
    Configuration menu
    Copy the full SHA
    b590b34 View commit details
    Browse the repository at this point in the history

  6. Fix Dilithium example

    @dop-amin
    dop-amin committed Oct 2, 2024
    Configuration menu
    Copy the full SHA
    0e5001e View commit details
    Browse the repository at this point in the history

  7. Modify Kyber NTT example

    @dop-amin
    dop-amin committed Oct 2, 2024
    Configuration menu
    Copy the full SHA
    c518581 View commit details
    Browse the repository at this point in the history

Commits on Oct 7, 2024

  1. Add dilithium intt (functional only)

    @dop-amin
    dop-amin committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    bf6534b View commit details
    Browse the repository at this point in the history

  2. Add dilithium pointwise (functional only)

    @dop-amin
    dop-amin committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    c2179c6 View commit details
    Browse the repository at this point in the history

  3. Add dilithium 257 NTT, iNTT, basemul (functional only) 

    * Includes addition to the parser that allows register ranges (e.g., for vldm)
    @dop-amin
    dop-amin committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    3c3da5f View commit details
    Browse the repository at this point in the history

  4. Add dilithium 769 NTT, iNTT, pointwise (functional only)

    @dop-amin
    dop-amin committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    d1c1c12 View commit details
    Browse the repository at this point in the history

  5. Add dilithium reduce32 (functional only)

    @dop-amin
    dop-amin committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    c8ba40c View commit details
    Browse the repository at this point in the history

  6. Add dilithium caddq (functional only)

    @dop-amin
    dop-amin committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    5ee5867 View commit details
    Browse the repository at this point in the history

  7. Add kyber NTT, iNTT, basemul (functional only)

    @dop-amin
    dop-amin committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    bed4961 View commit details
    Browse the repository at this point in the history

  8. Add kyber frombytes mul (functional only)

    @dop-amin
    dop-amin committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    2218a95 View commit details
    Browse the repository at this point in the history

  9. Add kyber pointwise add/sub (functional only)

    @dop-amin
    dop-amin committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    ad93f7e View commit details
    Browse the repository at this point in the history

  10. Unify barrel shift notation

    @dop-amin
    dop-amin committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    bad9bcd View commit details
    Browse the repository at this point in the history

  11. Add kyber reductions (functional only)

    @dop-amin
    dop-amin committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    3ad74e9 View commit details
    Browse the repository at this point in the history

  12. Consider increment for load/store-multiple instructions

    @dop-amin
    dop-amin committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    bbf5c66 View commit details
    Browse the repository at this point in the history

  13. Rename dilithium ntt example

    @dop-amin
    dop-amin committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    fae0590 View commit details
    Browse the repository at this point in the history

  14. Unify more barrel shift notation

    @dop-amin
    dop-amin committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    0936a8b View commit details
    Browse the repository at this point in the history

  15. Draft uArch model for new instructions 

    * All uArch details for examples should be present
* Lots of guessing involved, scepticism is advised
    @dop-amin
    dop-amin committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    d5b933d View commit details
    Browse the repository at this point in the history

Commits on Oct 10, 2024

  1. Small fixes to naive dilithium examples

    @dop-amin
    dop-amin committed Oct 10, 2024
    Configuration menu
    Copy the full SHA
    06f8f12 View commit details
    Browse the repository at this point in the history

  2. Add optimized dilithium code

    @dop-amin
    dop-amin committed Oct 10, 2024
    Configuration menu
    Copy the full SHA
    eebebf8 View commit details
    Browse the repository at this point in the history

Commits on Oct 11, 2024

  1. fix kyber ntt (functional only)

    @mkannwischer
    mkannwischer committed Oct 11, 2024
    Configuration menu
    Copy the full SHA
    77395e5 View commit details
    Browse the repository at this point in the history

  2. fix ldm and stm models

    @mkannwischer
    mkannwischer committed Oct 11, 2024
    Configuration menu
    Copy the full SHA
    5138f24 View commit details
    Browse the repository at this point in the history

  3. fix

    @mkannwischer
    mkannwischer committed Oct 11, 2024
    Configuration menu
    Copy the full SHA
    480ab47 View commit details
    Browse the repository at this point in the history

  4. fix again

    @mkannwischer
    mkannwischer committed Oct 11, 2024
    Configuration menu
    Copy the full SHA
    e44ed0f View commit details
    Browse the repository at this point in the history

  5. Kyber: add intt and add

    @mkannwischer
    mkannwischer committed Oct 11, 2024
    Configuration menu
    Copy the full SHA
    2be055f View commit details
    Browse the repository at this point in the history

  6. More general structure for loop parsing

    @dop-amin
    dop-amin committed Oct 11, 2024
    Configuration menu
    Copy the full SHA
    f5fba20 View commit details
    Browse the repository at this point in the history

Commits on Oct 12, 2024

  1. Fix load/store multiple register range

    @dop-amin
    dop-amin committed Oct 12, 2024
    Configuration menu
    Copy the full SHA
    d937396 View commit details
    Browse the repository at this point in the history

  2. Add some optimized code

    @dop-amin
    dop-amin committed Oct 12, 2024
    Configuration menu
    Copy the full SHA
    3691093 View commit details
    Browse the repository at this point in the history

  3. Fix dilithium intt

    @dop-amin
    dop-amin committed Oct 12, 2024
    Configuration menu
    Copy the full SHA
    9c4b121 View commit details
    Browse the repository at this point in the history

  4. Remove .rept for dilithium

    @dop-amin
    dop-amin committed Oct 12, 2024
    Configuration menu
    Copy the full SHA
    887489d View commit details
    Browse the repository at this point in the history

  5. re-enable labels in dilithium ntt

    @dop-amin
    dop-amin committed Oct 12, 2024
    Configuration menu
    Copy the full SHA
    65a62be View commit details
    Browse the repository at this point in the history

  6. optimize more kyber code

    @mkannwischer
    mkannwischer committed Oct 12, 2024
    Configuration menu
    Copy the full SHA
    36e5843 View commit details
    Browse the repository at this point in the history

Commits on Oct 13, 2024

  1. TEST: Demonstrate how to potentially do instruction-splitting

    @hanno-becker
    hanno-becker committed Oct 13, 2024
    Configuration menu
    Copy the full SHA
    d1a075f View commit details
    Browse the repository at this point in the history

  2. Merge remote-tracking branch 'upstream/eor2_split_experiment' into ar… 

    …mv7m
    @dop-amin
    dop-amin committed Oct 13, 2024
    Configuration menu
    Copy the full SHA
    2339b19 View commit details
    Browse the repository at this point in the history

  3. Add fusion cbs for splitting ldm and stm

    @dop-amin
    dop-amin committed Oct 13, 2024
    Configuration menu
    Copy the full SHA
    a819050 View commit details
    Browse the repository at this point in the history

  4. fix cb typo

    @dop-amin
    dop-amin committed Oct 13, 2024
    Configuration menu
    Copy the full SHA
    670fb3d View commit details
    Browse the repository at this point in the history

  5. Add ldm postinc cb 

    * Re-optimize add_kyber
    @dop-amin
    dop-amin committed Oct 13, 2024
    Configuration menu
    Copy the full SHA
    68a4b65 View commit details
    Browse the repository at this point in the history

  6. rm fusion from aarch64_simple0 example

    @dop-amin
    dop-amin committed Oct 13, 2024
    Configuration menu
    Copy the full SHA
    0e67046 View commit details
    Browse the repository at this point in the history

  7. Add vldm cb 

    * Applied in Kyber intt
    @dop-amin
    dop-amin committed Oct 13, 2024
    Configuration menu
    Copy the full SHA
    92514ff View commit details
    Browse the repository at this point in the history

Commits on Oct 14, 2024

  1. Add missing vldr parsers

    @dop-amin
    dop-amin committed Oct 14, 2024
    Configuration menu
    Copy the full SHA
    64946f3 View commit details
    Browse the repository at this point in the history

  2. Add vldr to M7 uArch model

    @dop-amin
    dop-amin committed Oct 14, 2024
    Configuration menu
    Copy the full SHA
    4fa7ba9 View commit details
    Browse the repository at this point in the history

  3. Add ldrd splitting

    @dop-amin
    dop-amin committed Oct 14, 2024
    Configuration menu
    Copy the full SHA
    41025f6 View commit details
    Browse the repository at this point in the history

  4. Add heuristic to more examples

    @dop-amin
    dop-amin committed Oct 14, 2024
    Configuration menu
    Copy the full SHA
    0b02149 View commit details
    Browse the repository at this point in the history

  5. Add fusion to fnt example

    @dop-amin
    dop-amin committed Oct 14, 2024
    Configuration menu
    Copy the full SHA
    93b0b68 View commit details
    Browse the repository at this point in the history

Commits on Oct 15, 2024

  1. fix syntax+cpu

    @mkannwischer
    mkannwischer committed Oct 15, 2024
    Configuration menu
    Copy the full SHA
    3b1cc1c View commit details
    Browse the repository at this point in the history

  2. Fix vmov dual args out

    @dop-amin
    dop-amin committed Oct 15, 2024
    Configuration menu
    Copy the full SHA
    27cea57 View commit details
    Browse the repository at this point in the history

  3. Move Loop class 

    * Add file for common code between models
    @dop-amin
    dop-amin committed Oct 15, 2024
    Configuration menu
    Copy the full SHA
    7aede50 View commit details
    Browse the repository at this point in the history

  4. Improve documentation for loop abstraction

    @dop-amin
    dop-amin committed Oct 15, 2024
    Configuration menu
    Copy the full SHA
    7d457e8 View commit details
    Browse the repository at this point in the history

  5. Add examples for loop types

    @dop-amin
    dop-amin committed Oct 15, 2024
    Configuration menu
    Copy the full SHA
    397685f View commit details
    Browse the repository at this point in the history

  6. Merge branch 'flexible_loops' into armv7m

    @dop-amin
    dop-amin committed Oct 15, 2024
    Configuration menu
    Copy the full SHA
    a56cf5b View commit details
    Browse the repository at this point in the history

  7. Fix duplicate examples

    @dop-amin
    dop-amin committed Oct 15, 2024
    Configuration menu
    Copy the full SHA
    6be707f View commit details
    Browse the repository at this point in the history

  8. Add Loop parser + examples for armv7m

    @dop-amin
    dop-amin committed Oct 15, 2024
    Configuration menu
    Copy the full SHA
    fac21e2 View commit details
    Browse the repository at this point in the history

  9. Add option to give factor for loops with non-one in/decrements

    @dop-amin
    dop-amin committed Oct 15, 2024
    Configuration menu
    Copy the full SHA
    3a3e255 View commit details
    Browse the repository at this point in the history

  10. Merge branch 'flexible_loops' into armv7m

    @dop-amin
    dop-amin committed Oct 15, 2024
    Configuration menu
    Copy the full SHA
    9f9f567 View commit details
    Browse the repository at this point in the history

Commits on Oct 16, 2024

  1. symbolic Kyber NTT

    @mkannwischer
    mkannwischer committed Oct 16, 2024
    Configuration menu
    Copy the full SHA
    0474979 View commit details
    Browse the repository at this point in the history

  2. fix _add_objective spills

    @mkannwischer
    mkannwischer committed Oct 16, 2024
    Configuration menu
    Copy the full SHA
    69d500c View commit details
    Browse the repository at this point in the history

  3. minimize spills: do not set variable_size

    @mkannwischer
    mkannwischer committed Oct 16, 2024
    Configuration menu
    Copy the full SHA
    89328ab View commit details
    Browse the repository at this point in the history

  4. SLOTHY: add config.objective_lower_bound option

    @mkannwischer
    mkannwischer committed Oct 16, 2024
    Configuration menu
    Copy the full SHA
    2d1b1c1 View commit details
    Browse the repository at this point in the history

  5. adjust example to use objective_lower_bound

    @mkannwischer
    mkannwischer committed Oct 16, 2024
    Configuration menu
    Copy the full SHA
    35f7029 View commit details
    Browse the repository at this point in the history

  6. cleanup

    @mkannwischer
    mkannwischer committed Oct 16, 2024
    Configuration menu
    Copy the full SHA
    ab88970 View commit details
    Browse the repository at this point in the history

  7. fix log stmt

    @mkannwischer
    mkannwischer committed Oct 16, 2024
    Configuration menu
    Copy the full SHA
    120db9f View commit details
    Browse the repository at this point in the history

  8. clean up symbolic NTT

    @mkannwischer
    mkannwischer committed Oct 16, 2024
    Configuration menu
    Copy the full SHA
    40f3385 View commit details
    Browse the repository at this point in the history

  9. attempt to fix CI

    @mkannwischer
    mkannwischer committed Oct 16, 2024
    Configuration menu
    Copy the full SHA
    52c1ddb View commit details
    Browse the repository at this point in the history

  10. remove broken example

    @mkannwischer
    mkannwischer committed Oct 16, 2024
    Configuration menu
    Copy the full SHA
    27b0851 View commit details
    Browse the repository at this point in the history

  11. Switch strategy for loop counter offset modification

    @dop-amin
    dop-amin committed Oct 16, 2024
    Configuration menu
    Copy the full SHA
    23d13a9 View commit details
    Browse the repository at this point in the history

  12. Merge branch 'flexible_loops' into armv7m

    @dop-amin
    dop-amin committed Oct 16, 2024
    Configuration menu
    Copy the full SHA
    ccaf7fb View commit details
    Browse the repository at this point in the history

  13. Make additional loop data part of class

    @dop-amin
    dop-amin committed Oct 16, 2024
    Configuration menu
    Copy the full SHA
    8664fc7 View commit details
    Browse the repository at this point in the history

  14. Merge remote-tracking branch 'origin/flexible_loops' into armv7m

    @dop-amin
    dop-amin committed Oct 16, 2024
    Configuration menu
    Copy the full SHA
    01aab7b View commit details
    Browse the repository at this point in the history

  15. Make cmp loops work with sw pipelining

    @dop-amin
    dop-amin committed Oct 16, 2024
    Configuration menu
    Copy the full SHA
    f580564 View commit details
    Browse the repository at this point in the history

Commits on Oct 17, 2024

  1. fix ntt_kyber_symbolic example

    @mkannwischer
    mkannwischer committed Oct 17, 2024
    Configuration menu
    Copy the full SHA
    4146e14 View commit details
    Browse the repository at this point in the history

  2. remove some labels that are not longer needed

    @mkannwischer
    mkannwischer committed Oct 17, 2024
    Configuration menu
    Copy the full SHA
    1bd31b2 View commit details
    Browse the repository at this point in the history

  3. Fix typo in fusion_loop

    @dop-amin
    dop-amin committed Oct 17, 2024
    Configuration menu
    Copy the full SHA
    8d68d58 View commit details
    Browse the repository at this point in the history

  4. model bank conflicts

    @mkannwischer
    mkannwischer committed Oct 17, 2024
    Configuration menu
    Copy the full SHA
    b5f0aa9 View commit details
    Browse the repository at this point in the history

  5. rename doubly defined .equ's

    @mkannwischer
    mkannwischer committed Oct 17, 2024
    Configuration menu
    Copy the full SHA
    df1be44 View commit details
    Browse the repository at this point in the history

  6. fix equ in more examples

    @mkannwischer
    mkannwischer committed Oct 17, 2024
    Configuration menu
    Copy the full SHA
    614f4af View commit details
    Browse the repository at this point in the history

  7. remove more labels that are no longer needed

    @mkannwischer
    mkannwischer committed Oct 17, 2024
    Configuration menu
    Copy the full SHA
    39c9c80 View commit details
    Browse the repository at this point in the history

  8. allow more powerful expressions in immediate

    @mkannwischer
    mkannwischer committed Oct 17, 2024
    Configuration menu
    Copy the full SHA
    6c88fdf View commit details
    Browse the repository at this point in the history

  9. split dry run CI by target

    @mkannwischer
    mkannwischer committed Oct 17, 2024
    Configuration menu
    Copy the full SHA
    31434ec View commit details
    Browse the repository at this point in the history

  10. switch some kyber examples to sw pipelining

    @mkannwischer
    mkannwischer committed Oct 17, 2024
    Configuration menu
    Copy the full SHA
    6888a7b View commit details
    Browse the repository at this point in the history

  11. optimize_loop for Dilithium examples 

    * Introduces loop class for loops that restore the compare-to pointer using a vmov
* Modifies mode of operation for loop extraction: The loop instructions need to appear in sequence
    @dop-amin
    dop-amin committed Oct 17, 2024
    Configuration menu
    Copy the full SHA
    c69ad9c View commit details
    Browse the repository at this point in the history

  12. Fix frombytes_mul_acc_32_16_kyber loop 

    * Slight code modification to make loop parsable
    @dop-amin
    dop-amin committed Oct 17, 2024
    Configuration menu
    Copy the full SHA
    f8550a0 View commit details
    Browse the repository at this point in the history

  13. Slight tweaks to example config

    @dop-amin
    dop-amin committed Oct 17, 2024
    Configuration menu
    Copy the full SHA
    5d34476 View commit details
    Browse the repository at this point in the history

Commits on Oct 18, 2024

  1. make .equ regex more general

    @mkannwischer
    mkannwischer committed Oct 18, 2024
    Configuration menu
    Copy the full SHA
    3c00fc8 View commit details
    Browse the repository at this point in the history

  2. symbolic Kyber NTT: switch stack locations from #define to .equ

    @mkannwischer
    mkannwischer committed Oct 18, 2024
    Configuration menu
    Copy the full SHA
    4bbf1a1 View commit details
    Browse the repository at this point in the history

  3. debug symbolic NTT

    @mkannwischer
    mkannwischer committed Oct 18, 2024
    Configuration menu
    Copy the full SHA
    8df6444 View commit details
    Browse the repository at this point in the history

  4. re-add ldrd splitting for symbolic NTT

    @mkannwischer
    mkannwischer committed Oct 18, 2024
    Configuration menu
    Copy the full SHA
    f75fc14 View commit details
    Browse the repository at this point in the history

  5. switch ntt_kyber to sw pipelining

    @mkannwischer
    mkannwischer committed Oct 18, 2024
    Configuration menu
    Copy the full SHA
    a29d5f5 View commit details
    Browse the repository at this point in the history

  6. Kyber intt: add sw pipelining

    @mkannwischer
    mkannwischer committed Oct 18, 2024
    Configuration menu
    Copy the full SHA
    631bca2 View commit details
    Browse the repository at this point in the history

  7. change config for Kyber intt

    @mkannwischer
    mkannwischer committed Oct 18, 2024
    Configuration menu
    Copy the full SHA
    f49e7ce View commit details
    Browse the repository at this point in the history

  8. model bank conflicts using execution units

    @mkannwischer
    mkannwischer committed Oct 18, 2024
    Configuration menu
    Copy the full SHA
    65b37d6 View commit details
    Browse the repository at this point in the history

  9. fix kyber ntt configs

    @mkannwischer
    mkannwischer committed Oct 18, 2024
    Configuration menu
    Copy the full SHA
    24f09c2 View commit details
    Browse the repository at this point in the history

  10. Add some optimized code

    @dop-amin
    dop-amin committed Oct 18, 2024
    Configuration menu
    Copy the full SHA
    e51f423 View commit details
    Browse the repository at this point in the history

Commits on Oct 19, 2024

  1. fix symbolic NTT

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    606251b View commit details
    Browse the repository at this point in the history

  2. loop opt: do not count empty lines for instruction count

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    fc8a963 View commit details
    Browse the repository at this point in the history

  3. Merge branch 'main' into armv7m

    @mkannwischer
    mkannwischer authored Oct 19, 2024
    Configuration menu
    Copy the full SHA
    0dfdfd3 View commit details
    Browse the repository at this point in the history

  4. fix Dilithium NTT

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    9310140 View commit details
    Browse the repository at this point in the history

  5. fix typo

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    6a2898f View commit details
    Browse the repository at this point in the history

  6. fix writing of instructions with offset fixup

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    fd5dbbc View commit details
    Browse the repository at this point in the history

  7. use simplify instead of eval

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    f9d1a06 View commit details
    Browse the repository at this point in the history

  8. re-optimized Dilithium NTT

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    00c9e74 View commit details
    Browse the repository at this point in the history

  9. correctly handle virtual instructions for boundary_reserved_regs

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    bb552ac View commit details
    Browse the repository at this point in the history

  10. fix fixup for ldr+str without offset

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    6b235d3 View commit details
    Browse the repository at this point in the history

  11. correctly label load and store instructions

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    ebc3140 View commit details
    Browse the repository at this point in the history

  12. fix address fix-up for split ldm/stm/ldrd/strd

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    8068757 View commit details
    Browse the repository at this point in the history

  13. change config for dilithium intt to make it work

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    421686e View commit details
    Browse the repository at this point in the history

  14. tweak dilithium intt to not use explicit pointer increments

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    5c656b9 View commit details
    Browse the repository at this point in the history

  15. fix typo

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    ab006b2 View commit details
    Browse the repository at this point in the history

  16. intt769 config (not producing working code)

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    f316565 View commit details
    Browse the repository at this point in the history

  17. Add loop counter fixup due to pipelining

    @dop-amin
    dop-amin committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    09b30bf View commit details
    Browse the repository at this point in the history

  18. partially revert e51f423 (remove 769 ntt+intt)

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    d1371d7 View commit details
    Browse the repository at this point in the history

  19. Unify cmp argument order in naive intt dilithium

    @dop-amin
    dop-amin committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    6946572 View commit details
    Browse the repository at this point in the history

  20. Adapt other loop types to new arguments, account for loops that use r… 

    …egister arguments
    @dop-amin
    dop-amin committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    fda002a View commit details
    Browse the repository at this point in the history

  21. Add missing default value for new_fixup

    @dop-amin
    dop-amin committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    6eb04b2 View commit details
    Browse the repository at this point in the history

  22. fix broken naive implementation of frombytes_mul_acc_32_16_kyber

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    602810f View commit details
    Browse the repository at this point in the history

  23. frombytes_mul_acc_32_16_kyber: config

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    fb530f2 View commit details
    Browse the repository at this point in the history

  24. add frombytes code that at least works

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    0bd930a View commit details
    Browse the repository at this point in the history

  25. set inputs are outputs

    @mkannwischer
    mkannwischer committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    89bad81 View commit details
    Browse the repository at this point in the history

  26. Re-introduce in_out args for postinc

    @dop-amin
    dop-amin committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    a0fe5b2 View commit details
    Browse the repository at this point in the history

  27. Make address offset fixup configurable 

    (cherry picked from commit dcb4f07)
    @hanno-becker @dop-amin
    hanno-becker authored and dop-amin committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    19bc582 View commit details
    Browse the repository at this point in the history

  28. Fix in->in_out in fusion for ldrd

    @dop-amin
    dop-amin committed Oct 19, 2024
    Configuration menu
    Copy the full SHA
    8dff93f View commit details
    Browse the repository at this point in the history

Commits on Oct 20, 2024

  1. fix

    @mkannwischer
    mkannwischer committed Oct 20, 2024
    Configuration menu
    Copy the full SHA
    fcba26c View commit details
    Browse the repository at this point in the history

  2. add ldrd_imm for experiments

    @mkannwischer
    mkannwischer committed Oct 20, 2024
    Configuration menu
    Copy the full SHA
    47556ae View commit details
    Browse the repository at this point in the history

  3. Update unfold_all_aliases

    @dop-amin
    dop-amin committed Oct 20, 2024
    Configuration menu
    Copy the full SHA
    c39ac3c View commit details
    Browse the repository at this point in the history

Commits on Oct 21, 2024

  1. Fix splitting of ldrd 

    This previously mixed up the target registers, leading to
functionally incorrect code.
    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    f315126 View commit details
    Browse the repository at this point in the history

  2. Add support for spilling to FPR in Armv7-M model

    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    1118952 View commit details
    Browse the repository at this point in the history

  3. Improve debuggabiliity by adding line numbers to code dump

    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    d86c27e View commit details
    Browse the repository at this point in the history

  4. Clear trailing whitespaces from Armv7-M and AArch64 model

    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    e2f1795 View commit details
    Browse the repository at this point in the history

  5. Fix typo in pretty-printing of orig<->opt permutation

    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    23044f8 View commit details
    Browse the repository at this point in the history

  6. Bump to max number of solutions to 128 

    Prevent surprise-stop of long-running SLOTHY optimizations because
they have bumped into the max nubmer of solutions.
    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    055d62a View commit details
    Browse the repository at this point in the history

  7. Add support for is_spill annotations for inputs 

    Previously, SLOTHY would fail when a global input was spilled via
an instruction annotated with `// @slothy:is_spill`.

This commit fixes this by ad-hoc creating a VirtualInstruction node
for the input in this case -- as is done during ordinary DFG parsing
already.
    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    18fb4f1 View commit details
    Browse the repository at this point in the history

  8. Add first optimized version of NTT-769

    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    d65c7cb View commit details
    Browse the repository at this point in the history

  9. Dilithium-NTT-769: Spill twiddle_ptr to FPR during L1234

    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    06c455c View commit details
    Browse the repository at this point in the history

  10. remove ntt_769_dilithium_opt_m7 -- it's never used

    @mkannwischer
    mkannwischer committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    58b87f8 View commit details
    Browse the repository at this point in the history

  11. Dilithium-NTT-769: Allow SLOTHY to revisit choice of spill

    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    5b93e74 View commit details
    Browse the repository at this point in the history

  12. Dilithium-NTT-769: Minor improvement

    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    807f66d View commit details
    Browse the repository at this point in the history

  13. diable unsafe address fixup for intt_769_dilithium

    @mkannwischer
    mkannwischer committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    d269844 View commit details
    Browse the repository at this point in the history

  14. disable unsafe_address_offset_fixup for fusion

    @mkannwischer
    mkannwischer committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    9a5a592 View commit details
    Browse the repository at this point in the history

  15. Optimized FNT

    @dop-amin
    dop-amin committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    c203b5d View commit details
    Browse the repository at this point in the history

  16. Allow boolean SLOTHY tags within macros 

    Previously, a boolean tag (like `// @slothy:core=True`) inside a
macro would lead to failure upon trying to unfold macro arguments.

This commit fixes this.
    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    69d4133 View commit details
    Browse the repository at this point in the history

  17. Optimize frombytes_mul_16_32_kyber

    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    6eec797 View commit details
    Browse the repository at this point in the history

  18. Fix core tag for frombytes_16_32

    @dop-amin
    dop-amin committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    3a538d0 View commit details
    Browse the repository at this point in the history

  19. Separately handle log_or_shifted in uArch model

    @dop-amin
    dop-amin committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    5437631 View commit details
    Browse the repository at this point in the history

  20. Updated opt frombytes_mul_16_32 code

    @dop-amin
    dop-amin committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    c94efbb View commit details
    Browse the repository at this point in the history

  21. Fix assignment of functional units

    @dop-amin
    dop-amin committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    eab6e95 View commit details
    Browse the repository at this point in the history

  22. Make intt_769_dilithium work and add opt

    @dop-amin
    dop-amin committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    33c8768 View commit details
    Browse the repository at this point in the history

  23. Make ifnt_257_dilithium work and add opt

    @dop-amin
    dop-amin committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    be844bd View commit details
    Browse the repository at this point in the history

  24. Add b to vmovcmp loop label output

    @dop-amin
    dop-amin committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    5e7c0ef View commit details
    Browse the repository at this point in the history

  25. Arm-v7m: Output register and input register for ldr can't match

    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    e191670 View commit details
    Browse the repository at this point in the history

  26. Add optimized code + script for frombytes_mul_acc_32_16_kyber

    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    db6db95 View commit details
    Browse the repository at this point in the history

  27. Add optimized code + script for frombytes_mul_acc_32_32_kyber

    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    d7b2d30 View commit details
    Browse the repository at this point in the history

  28. optimize + code invntt_fast_opt_m7

    @dop-amin
    dop-amin committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    258ce88 View commit details
    Browse the repository at this point in the history

  29. Update basemul_acc_32_32_kyber

    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    5ededbb View commit details
    Browse the repository at this point in the history

  30. Re-optimize fromplant_kyber_opt_m7 with SW pipelining

    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    06261e0 View commit details
    Browse the repository at this point in the history

  31. Re-optimize barrett_reduce_kyber

    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    568283e View commit details
    Browse the repository at this point in the history

  32. Re-optimize pointwise_769_dilithium

    @hanno-becker
    hanno-becker committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    7de2bb6 View commit details
    Browse the repository at this point in the history

  33. Revert "Re-optimize pointwise_768_dilithium" 

    This reverts commit 7de2bb6.
    @dop-amin
    dop-amin committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    8ba5dc0 View commit details
    Browse the repository at this point in the history

  34. Add swpipelining to fnt 1st loop

    @dop-amin
    dop-amin committed Oct 21, 2024
    Configuration menu
    Copy the full SHA
    b33eebe View commit details
    Browse the repository at this point in the history

Commits on Oct 22, 2024

  1. Re-optimize pointwise_769_dilithium

    @hanno-becker
    hanno-becker committed Oct 22, 2024
    Configuration menu
    Copy the full SHA
    593924f View commit details
    Browse the repository at this point in the history

  2. add slot constaint + extra shift latency for pkhbt/pkhtb

    @mkannwischer
    mkannwischer committed Oct 22, 2024
    Configuration menu
    Copy the full SHA
    5b0925a View commit details
    Browse the repository at this point in the history

  3. re-optimize fromplant

    @mkannwischer
    mkannwischer committed Oct 22, 2024
    Configuration menu
    Copy the full SHA
    7e4afcb View commit details
    Browse the repository at this point in the history

  4. Fix pointwise_769_dilithium

    @hanno-becker
    hanno-becker committed Oct 22, 2024
    Configuration menu
    Copy the full SHA
    d294eaa View commit details
    Browse the repository at this point in the history

  5. Add latest Keccak 

    * Includes .w modification in naive
    @dop-amin
    dop-amin committed Oct 22, 2024
    Configuration menu
    Copy the full SHA
    41c7f87 View commit details
    Browse the repository at this point in the history

  6. Fix typo in uArch

    @dop-amin
    dop-amin committed Oct 22, 2024
    Configuration menu
    Copy the full SHA
    e358ae6 View commit details
    Browse the repository at this point in the history

  7. Add slightly faster FNT 

    * Ran with more repeats on server
    @dop-amin
    dop-amin committed Oct 22, 2024
    Configuration menu
    Copy the full SHA
    df73ad1 View commit details
    Browse the repository at this point in the history

  8. Make model more realistic (?) 

    * Restrict shifted instructions more to SHIFT0
* Add 1 cycle extra latency for pk... and ubfx
    @dop-amin
    dop-amin committed Oct 22, 2024
    Configuration menu
    Copy the full SHA
    5461aa2 View commit details
    Browse the repository at this point in the history

Commits on Oct 23, 2024

  1. rename add_dsp_mul_slot_constraint -> add_dsp_slot_constraint

    @mkannwischer
    mkannwischer committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    e90fe64 View commit details
    Browse the repository at this point in the history

  2. force dsp/bitmanip instructions to slot0

    @mkannwischer
    mkannwischer committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    a81bee4 View commit details
    Browse the repository at this point in the history

  3. model MAC forwarding path

    @mkannwischer
    mkannwischer committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    a73d750 View commit details
    Browse the repository at this point in the history

  4. re-opt frombytes_mul functions

    @mkannwischer
    mkannwischer committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    d56d65e View commit details
    Browse the repository at this point in the history

  5. remove symbolic NTT from CI

    @mkannwischer
    mkannwischer committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    eb02647 View commit details
    Browse the repository at this point in the history

  6. Re-opt 769 pointmul 

    * IPC fits perfectly
    @dop-amin
    dop-amin committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    74d355e View commit details
    Browse the repository at this point in the history

  7. fix basemul_acc_32_16_kyber example + re-opt basemul

    @mkannwischer
    mkannwischer committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    161e376 View commit details
    Browse the repository at this point in the history

  8. change str latency

    @mkannwischer
    mkannwischer committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    a9f2fb9 View commit details
    Browse the repository at this point in the history

  9. add comment about 0-cycle latency

    @mkannwischer
    mkannwischer committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    19a6078 View commit details
    Browse the repository at this point in the history

  10. basemul_acc_32_32_kyber: only use one post-inc per iteration

    @mkannwischer
    mkannwischer committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    628df26 View commit details
    Browse the repository at this point in the history

  11. str fix confusion of latency and throughput

    @mkannwischer
    mkannwischer committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    ae15c46 View commit details
    Browse the repository at this point in the history

  12. Kyber: add missing asms

    @mkannwischer
    mkannwischer committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    2b79bdb View commit details
    Browse the repository at this point in the history

  13. Kyber: add mising asms to examples.py (plain copy)

    @mkannwischer
    mkannwischer committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    78098ef View commit details
    Browse the repository at this point in the history

  14. ocd

    @mkannwischer
    mkannwischer committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    1d2fb43 View commit details
    Browse the repository at this point in the history

  15. re-optimize 769 NTT

    @mkannwischer
    mkannwischer committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    bc8d17f View commit details
    Browse the repository at this point in the history

  16. fix some mistakes in the basemul+frombytes

    @mkannwischer
    mkannwischer committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    a3c7da0 View commit details
    Browse the repository at this point in the history

  17. cleanup matacc functions

    @mkannwischer
    mkannwischer committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    3d1ced7 View commit details
    Browse the repository at this point in the history

  18. Optimize Kyber NTT 

    * Naive implementation has 2 more vreg pushes in the beginning
    @dop-amin
    dop-amin committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    edd5bd1 View commit details
    Browse the repository at this point in the history

  19. Add optimized Kyber NTT 

    * Script & naive unchanged!
    @dop-amin
    dop-amin committed Oct 23, 2024
    Configuration menu
    Copy the full SHA
    70f93d2 View commit details
    Browse the repository at this point in the history

Commits on Oct 24, 2024

  1. optimize basemul_kyber and basemul_acc_kyber

    @mkannwischer
    mkannwischer committed Oct 24, 2024
    Configuration menu
    Copy the full SHA
    b0156a3 View commit details
    Browse the repository at this point in the history

  2. optimize frombytes_mul_kyber and frombytes_mul_acc_kyber

    @mkannwischer
    mkannwischer committed Oct 24, 2024
    Configuration menu
    Copy the full SHA
    2f9d7ff View commit details
    Browse the repository at this point in the history

  3. Update Keccak asm

    @dop-amin
    dop-amin committed Oct 24, 2024
    Configuration menu
    Copy the full SHA
    adfafaa View commit details
    Browse the repository at this point in the history

  4. Fix Keccak part asm example to work

    @dop-amin
    dop-amin committed Oct 24, 2024
    Configuration menu
    Copy the full SHA
    b61987b View commit details
    Browse the repository at this point in the history

  5. Remove rept from keccak part example

    @dop-amin
    dop-amin committed Oct 24, 2024
    Configuration menu
    Copy the full SHA
    f8e5e28 View commit details
    Browse the repository at this point in the history

  6. Add type to keccak old function

    @dop-amin
    dop-amin committed Oct 24, 2024
    Configuration menu
    Copy the full SHA
    29b213c View commit details
    Browse the repository at this point in the history

  7. Modification to ldr latency override

    @dop-amin
    dop-amin committed Oct 24, 2024
    Configuration menu
    Copy the full SHA
    70edca6 View commit details
    Browse the repository at this point in the history

  8. Add st hazard constraint

    @dop-amin
    dop-amin committed Oct 24, 2024
    Configuration menu
    Copy the full SHA
    a14e1c4 View commit details
    Browse the repository at this point in the history

  9. Remove shift pipes

    @dop-amin
    dop-amin committed Oct 24, 2024
    Configuration menu
    Copy the full SHA
    75bf1d4 View commit details
    Browse the repository at this point in the history

  10. rm ldr latency increase

    @dop-amin
    dop-amin committed Oct 24, 2024
    Configuration menu
    Copy the full SHA
    882b83f View commit details
    Browse the repository at this point in the history

Commits on Nov 6, 2024

  1. Merge branch 'main' into armv7m

    @mkannwischer
    mkannwischer committed Nov 6, 2024
    Configuration menu
    Copy the full SHA
    9354c57 View commit details
    Browse the repository at this point in the history

Commits on Nov 8, 2024

  1. Merge branch 'main' into armv7m

    @mkannwischer
    mkannwischer authored Nov 8, 2024
    Configuration menu
    Copy the full SHA
    bba8088 View commit details
    Browse the repository at this point in the history