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.

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

OpenCL: cleanup and rev support for add_diag, unary +-, mean, sub_col, sub_row, segment #2272

Merged
merged 20 commits into from
Dec 28, 2020

Conversation

rok-cesnovar
Copy link
Member

Summary

This PR does dome minor cleanup of /opencl and adds support for a few simple functions. In detail:

  • removes copy_triangular, diagonal_multiply, identity and sub_block. The first was not used, other were replaced by k.g.
  • added rev support for add_diag, unary operator+ (and plus()), unary operator- (and minus()), mean, sub_col, sub_row, segment

Tests

All new functions are tested

Side Effects

/

Release notes

OpenCL: added rev support for add_diag, unary operator+ (and plus()), unary operator- (and minus()), mean, sub_col, sub_row and segment.

Checklist

@rok-cesnovar
Copy link
Member Author

Ready for review.

@stan-buildbot
Copy link
Contributor


Name Old Result New Result Ratio Performance change( 1 - new / old )
gp_pois_regr/gp_pois_regr.stan 3.55 3.45 1.03 2.91% faster
low_dim_corr_gauss/low_dim_corr_gauss.stan 0.02 0.02 0.95 -5.38% slower
eight_schools/eight_schools.stan 0.11 0.11 1.0 -0.39% slower
gp_regr/gp_regr.stan 0.15 0.15 1.0 -0.02% slower
irt_2pl/irt_2pl.stan 5.2 5.24 0.99 -0.74% slower
performance.compilation 89.6 88.77 1.01 0.93% faster
low_dim_gauss_mix_collapse/low_dim_gauss_mix_collapse.stan 8.63 8.63 1.0 -0.06% slower
pkpd/one_comp_mm_elim_abs.stan 28.65 30.01 0.95 -4.74% slower
sir/sir.stan 139.02 135.15 1.03 2.78% faster
gp_regr/gen_gp_data.stan 0.04 0.04 0.98 -1.64% slower
low_dim_gauss_mix/low_dim_gauss_mix.stan 3.04 3.05 1.0 -0.16% slower
pkpd/sim_one_comp_mm_elim_abs.stan 0.37 0.39 0.97 -3.03% slower
arK/arK.stan 2.53 2.51 1.01 0.57% faster
arma/arma.stan 0.61 0.6 1.02 1.52% faster
garch/garch.stan 0.68 0.67 1.01 1.31% faster
Mean result: 0.996466358781

Jenkins Console Log
Blue Ocean
Commit hash: af0df52


Machine information ProductName: Mac OS X ProductVersion: 10.11.6 BuildVersion: 15G22010

CPU:
Intel(R) Xeon(R) CPU E5-1680 v2 @ 3.00GHz

G++:
Configured with: --prefix=/Applications/Xcode.app/Contents/Developer/usr --with-gxx-include-dir=/usr/include/c++/4.2.1
Apple LLVM version 7.0.2 (clang-700.1.81)
Target: x86_64-apple-darwin15.6.0
Thread model: posix

Clang:
Apple LLVM version 7.0.2 (clang-700.1.81)
Target: x86_64-apple-darwin15.6.0
Thread model: posix

@stan-buildbot
Copy link
Contributor


Name Old Result New Result Ratio Performance change( 1 - new / old )
gp_pois_regr/gp_pois_regr.stan 3.41 3.36 1.02 1.53% faster
low_dim_corr_gauss/low_dim_corr_gauss.stan 0.02 0.02 1.02 2.26% faster
eight_schools/eight_schools.stan 0.11 0.11 1.02 2.24% faster
gp_regr/gp_regr.stan 0.15 0.15 0.98 -1.93% slower
irt_2pl/irt_2pl.stan 5.19 5.14 1.01 1.02% faster
performance.compilation 89.72 88.65 1.01 1.2% faster
low_dim_gauss_mix_collapse/low_dim_gauss_mix_collapse.stan 8.66 8.66 1.0 0.02% faster
pkpd/one_comp_mm_elim_abs.stan 29.97 30.3 0.99 -1.07% slower
sir/sir.stan 135.07 138.93 0.97 -2.86% slower
gp_regr/gen_gp_data.stan 0.04 0.04 1.0 -0.41% slower
low_dim_gauss_mix/low_dim_gauss_mix.stan 3.04 3.07 0.99 -0.95% slower
pkpd/sim_one_comp_mm_elim_abs.stan 0.39 0.4 0.98 -2.31% slower
arK/arK.stan 2.53 2.54 0.99 -0.52% slower
arma/arma.stan 0.6 0.61 0.99 -0.66% slower
garch/garch.stan 0.67 0.67 1.0 -0.06% slower
Mean result: 0.998549810769

Jenkins Console Log
Blue Ocean
Commit hash: 1e2793a


Machine information ProductName: Mac OS X ProductVersion: 10.11.6 BuildVersion: 15G22010

CPU:
Intel(R) Xeon(R) CPU E5-1680 v2 @ 3.00GHz

G++:
Configured with: --prefix=/Applications/Xcode.app/Contents/Developer/usr --with-gxx-include-dir=/usr/include/c++/4.2.1
Apple LLVM version 7.0.2 (clang-700.1.81)
Target: x86_64-apple-darwin15.6.0
Thread model: posix

Clang:
Apple LLVM version 7.0.2 (clang-700.1.81)
Target: x86_64-apple-darwin15.6.0
Thread model: posix

@rok-cesnovar rok-cesnovar merged commit 6067103 into develop Dec 28, 2020
@rok-cesnovar rok-cesnovar deleted the opencl/cleanup branch December 28, 2020 17:01
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants