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

Optimize/add static math functions #354

Merged
merged 147 commits into from
Mar 20, 2022
Merged

Optimize/add static math functions #354

merged 147 commits into from
Mar 20, 2022

Conversation

runer112
Copy link
Member

@runer112 runer112 commented Jan 23, 2022 •
edited by jacobly0
Loading

Adds or optimizes static versions of many math functions. Most notably, implements the full suite of 64-bit integer (long long) support.

Partially addresses #276.

TODO:

  • This description.
  • Autotester config for math_test.
  • Confirm that no more integer math functions are missing.
  • Optimize static short division family of functions.
  • Verify all functions over many inputs.

@runer112
Improve cpp_tireal_pi_montecarlo
9f00417
@runer112
Provide optimized static versions of __smuls and __smulu
48f64cb
@runer112
Touch up smulu.src
d61333f
@runer112
Provide optimized static versions of __imuls and __imulu
8db0d93
@runer112
Rework doc in smulu.src and imulu.src
508fa7a
@runer112
Mark static versions of __smuls and __smulu as "fast"
51130a7
@runer112
Reimplement proper static versions of __smuls and __smulu
4dc950e
@runer112
Mark static versions of __imuls and __imulu as "fast"
76980b9
@runer112
Reimplement proper static versions of __imuls and __imulu
76f2366
@runer112
Fix some docs
370c07f
@runer112
Reformat asm
41aaf2c
@runer112
This looks nicer
0e7425d
@runer112
Implement __lmuls_fast and __lmulu_fast
857a45c
@runer112
Provide optimized static versions of __lmuls and __lmulu
9326b14
@runer112
Provide optimized versions of __sand, __sor, and __sxor
36ebb4b
@runer112
This order may eventually better allow for hijacking
62f6507
@runer112
Provide optimized versions of __iand, __ior, and __ixor
becfdac
@runer112
Provide optimized versions of __land, __lor, and __lxor
7312406
@runer112
Provide optimized versions of __scmpzero, __icmpzero, __lcmpzero, and…
f9e57aa 
… __llcmpzero
@runer112
Provide optimized versions of __ladd and __lladd
f6f95e2
@runer112
Don't forget to propagate carry
2da942f
@runer112
Provide optimized versions of __lsub and __llsub
d1337cd
@runer112
Optimize __lladd_fast
8a37d3f
@runer112
Fix stack frame bugs
673ba00
@runer112
Provide optimized versions of __lland, __llor, and __llxor
dfa34fd
@runer112
Implement enough junk for my long long test program to link
c5ca508
@runer112
Fix __llsub
ba8d751
@runer112
Fix __lldivu_b and __llmulu_b
e7d9047
@runer112
Fix __llcmpu and __llcmpzero
9f0220c
@runer112
Optimize __bpopcnt, __spopcnt, __ipopcnt, and __lpopcnt
1217ded
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 13:40 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 13:40 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 13:40 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 13:40 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 13:40 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 13:40 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 13:40 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 13:40 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 13:40 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 13:40 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 13:40 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 13:40 Inactive
jacobly0
jacobly0 approved these changes Mar 20, 2022
View reviewed changes
Copy link
Member

@jacobly0 jacobly0 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, all tests are passing.

@runer112 runer112 temporarily deployed to Autotester March 20, 2022 21:57 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 21:57 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 21:57 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 21:57 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 21:57 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 21:57 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 21:57 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 21:57 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 21:57 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 21:57 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 21:57 Inactive
@runer112 runer112 temporarily deployed to Autotester March 20, 2022 21:57 Inactive
@mateoconlechuga mateoconlechuga merged commit d857bcd into master Mar 20, 2022
@mateoconlechuga mateoconlechuga deleted the opt-static-math branch March 20, 2022 22:07
@adriweb adriweb mentioned this pull request May 16, 2022
Open
@adriweb adriweb linked an issue May 16, 2022 that may be closed by this pull request
Add support for double / long double #276
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@mateoconlechuga mateoconlechuga mateoconlechuga left review comments

@jacobly0 jacobly0 jacobly0 approved these changes

Assignees
No one assigned
Labels
feature optimization
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Add support for double / long double
4 participants
@runer112 @mateoconlechuga @jacobly0 @adriweb