b6a68c1e6098915ac128db2dae945194bbe6f52b to main · Andreas Klöckner / loopy · GitLab

Commits on Source 6229

6c3d59be Be less boring in assigning instruction names.
Nov 02, 2011
f0c9980a Only assign axis 0 based on real array access. Document, speed up auto axis assignment.
Nov 02, 2011
3953ff82 New syntax for CSEs and reduction iname duplication.
Nov 02, 2011
be5f165f Add a force flag to tag_dimensions.
Nov 02, 2011
7690a127 Add a switch for annotation in the CCodeMapper.
Nov 02, 2011
04cd0ac6 Generate the shapes of ILP accumulators in the correct type.
Nov 02, 2011
984ca646 Some mucking around with the image ILP test.
Nov 02, 2011
bba4f50a Remove manual test from transpose.
Nov 02, 2011
d25ec07f Add Tim's SEM tests.
Nov 02, 2011
e64156dc Merge branch 'master' of http://git.tiker.net/trees/loopy
Nov 02, 2011
3afae933 Support image arguments in automated tests.
Nov 02, 2011
1eeffebe Fix code generation for floordiv.
Nov 02, 2011
6efeee7c Use static value for lower bound in hw axis setup.
Nov 02, 2011
78ec206c Change mechanism for specifying default tag in CSEs/prefetches.
Nov 02, 2011
f868f6f4 Defer decision on whether variables are local to preprocessing.
Nov 02, 2011
dfb03bb6 Be a bit laxer about PwAffs and Affs.
Nov 02, 2011
2c5b310a Be more rigorous about length-1 axes (don't insert them, don't ignore them).
Nov 02, 2011
38b23406 Fix linalg tests, move some of them towards the automated tests.
Nov 02, 2011
f2887fc1 Merge branch 'master' of git://localhost/loopy
Nov 02, 2011
a2eab227 New syntax in SEM test.
Nov 02, 2011
26107a94 Merge branch 'master' of git://localhost/loopy
Nov 02, 2011
0ec159e1 Make sure domain of map_space is correctly ordered in finding CSE lead index domain.
Nov 03, 2011
b37aaaf7 Deal with @-signs of iname-duplicating reductions in more places.
Nov 03, 2011
d183034b Refactor CSE handling to allow the user to specify the lead expression.
Nov 03, 2011
9956ff05 Find insn iname deps by fixed point iteration. Dot dependency graphing. Schedule improvements.
Nov 03, 2011
9d7b6802 Scheduler: Better notion of 'useful' for boostable instructions.
Nov 03, 2011
0d31c6a8 Make it ok to retag l.auto inames.
Nov 04, 2011
b4019d56 Add variable substitution.
Nov 05, 2011
0a9f6ed2 Add support for constant array arguments.
Nov 05, 2011
0171e5d8 Add simple FEM assembly test without prefetch.
Nov 05, 2011
da8d7c8e Some code rearrangement.
Nov 07, 2011
98395146 Scheduler: be less eager about entering loops, more eager about leaving them.
Nov 07, 2011
30e44717 Barrier Insertion: Be less strict in dep checking when checking for pre-barriers.
Nov 07, 2011
5485e575 Rewrite CSEs in terms of unification templates.
Nov 07, 2011
65312cd5 CSEs: Remove Gaussian elimination/affine eqn solving. Turns out not to be needed.
Nov 07, 2011
d72f97d2 Scheduler debugging.
Nov 08, 2011
bb11a67a A few CSE fixes, plus new error checks.
Nov 08, 2011
b8a175df Add remove_cses().
Nov 08, 2011
38ba6c3c Improve scheduler heuristics. Limit boostability to specific inames.
Nov 08, 2011
803791f3 Use loop nest maps to simplify scheduler.
Nov 08, 2011
618cc903 Pick not just axis 0, but all auto axes by lowest available stride.
Nov 08, 2011
8d248de6 Improve dep barrier insertion before loops.
Nov 08, 2011
715fd101 Test updates.
Nov 08, 2011
8f088865 SEM test updates.
Nov 08, 2011
ee602dc2 Merge git://github.com/inducer/loopy
Nov 08, 2011
6ef2c660 Add edit_code flag to automated testing harness.
Nov 08, 2011
b5d7ff2d Move CSE check to scheduling entrypoint.
Nov 08, 2011
41a88c2c Properly recurse in CSE expansion.
Nov 08, 2011
7c8dcfa0 Give a better error message for non-matching matching variables.
Nov 08, 2011
be92e8ba Test hackery.
Nov 09, 2011
5d0d02c8 Add lmem SEM Laplacian back to code.
Nov 09, 2011
73b991f1 Try to schedule entirely without boosting first before allowing it.
Nov 09, 2011
12452330 Cache result of dim_{max,min}.
Nov 09, 2011
1af94f84 An initial attempt at dealing with equality constraints.
Nov 09, 2011
abbded75 Kill CSEs. Add substitution rules, precomputes.
Nov 10, 2011
69bd5756 Fixes for the subst rule/precompute rewrite.
Nov 10, 2011
6f7ba19a Many more fixes to subst-precompute.
Nov 11, 2011
3a86e395 Attempt simple hull if outcome of get_footprint is not convex.
Nov 11, 2011
bfd2cc5f Expand reductions outer-to-inner using a queue.
Nov 11, 2011
7f257cfb Adapt iname dependency finding to properly exclude reduction inames.
Nov 11, 2011
de8e8429 Improvements to FEM assembly.
Nov 11, 2011
e9baab6d Preserve tags when duplicating reduction inames, plus more FEM assembly fixes.
Nov 11, 2011
9ad444e6 Pick (more) sensible names for reduction inames. Remove non-ND FEM quadrature.
Nov 11, 2011
3cd2819c Add some documentation. Expose 'with_annotation' flag.
Nov 11, 2011
2f5da323 Add a better output format for kernels.
Nov 11, 2011
847ffd67 Upgrade precomputation to make storage dims and sweep dims independent, allow iname sweeps.
Nov 11, 2011
e2e48066 Fix exposure of with_annotation flag.
Nov 11, 2011
c700eb6d Switch ill-advised outer 'unroll' on split automatic axis back to sequential.
Nov 11, 2011
8fe68119 Fix doc upload script.
Nov 11, 2011
6d6de311 Many scattered fixes. Full-prefetch SEM with ILP generates code.
Nov 12, 2011
c05844ee Fix up FEM quadrature example.
Nov 12, 2011
c7913fcf One more FEM tweak.
Nov 12, 2011
421c41d9 Make better message about device used for ref calculation.
Nov 12, 2011
ac02f82d Only include floor_div code if needed.
Nov 20, 2011
bf38b67c First shot at instance-based subst rule precomputation.
Nov 20, 2011
0d8961db Tim's SEM tweaks.
Nov 20, 2011
04ff7222 Merge branch 'master' of ssh://forge.tiker.net:2234/loopy
Nov 20, 2011
0327e979 Use PyOpenCL to translate dtypes into C types.
Jan 16, 2012
5e72d5e3 Hack auto test rig to support vector types, add flag about output filling.
Jan 16, 2012
4b34ba94 Parse vectorized reductions. Spelling: 'sum_vec_float4'
Jan 16, 2012
26a50987 Test float4 functionality.
Jan 16, 2012
9e2640d2 Fix prefill criterion.
Jan 17, 2012
c8064886 Fix FEM assembly code.
Jan 17, 2012
8ba555dc Expose reduction realization to the user. Add more notes.
Jan 18, 2012
0902408b Fix Fig 3.3 variant of FEM assembly.
Jan 18, 2012
72fdc4d2 Provide interactive assistance if the scheduler fails.
Jan 18, 2012
9e30e55e Implement complex-valued arithmetic.
Jan 23, 2012
8dd4ed28 Meeting notes w/ Tim at Reagan.
Feb 05, 2012
ea359a6a Make switch to turn off complex-valued expression codegen.
Feb 05, 2012
ff0933a5 "Properly" parse instructions with multiple equal signs.
Feb 05, 2012
59587042 Add parsing for "if()".
Feb 05, 2012
cda499e4 Add some doc hints that I'm likely to forget.
Feb 05, 2012
3933b49a Provide a better error message for inappropriate assignment lhs.
Feb 05, 2012
8e4493cd Default sweep_dims kwarg on add_prefetch() to empty.
Feb 05, 2012
b16f4dc8 Parse "N" as a shape/stride spec in kernel input.
Feb 12, 2012
04e4ee91 Before ILP refactor.
Feb 20, 2012
de71343d Make ILP go through regular loop emission, implement ilp.seq.
Feb 21, 2012
fd78a38d Remove TODO from FEM assembly ilp.seq example.
Feb 21, 2012
d20e0267 Add footprint generators for prefetch.
Mar 02, 2012
d68e69a8 Add SEM test case from Reagan airport with Tim.
Mar 02, 2012

6,129 additional commits have been omitted to prevent performance issues.