45bd98f8ae8cd8e752783f88a586dd3055056da1 to main · Andreas Klöckner / loopy · GitLab

Commits on Source 4605

0494c442 replaced consec, uniform, and nonconsec subscript types with DataAccess class
Mar 12, 2016
09420000 subscript counter only looking for lid0 now, if not found, setting stride to maxsize
Mar 13, 2016
2dbeb387 now calculating strides greater than 1
Mar 15, 2016
0573d545 added StridedGmemAccess class, now used as key in gmem access dicts
Mar 15, 2016
c0dcf557 replaced operation tuples with TypedOp class
Mar 15, 2016
0f2a2519 Merge remote-tracking branch 'upstream/master'
Mar 16, 2016
b3d9498c temporary fix for stride counting when min tag axis >0, and added variable...
Apr 01, 2016
138c0b1e added variable name to StridedGmemAccess (still work to do)
Apr 01, 2016
e16469d7 adding local mem access counter
Apr 01, 2016
3d5ac249 Fix test_kernel_splitting_with_loop_and_private_temporary()
Jun 07, 2016
0e6f47fa Add support for local temporary spills / loads.
Jun 07, 2016
21e91413 Fix off-by-one error (yikes).
Jun 07, 2016
0386f584 Device mapper: Add a comment describing the current temporary variable
Jun 07, 2016
e816facf Fix typo.
Jun 07, 2016
52b9aa84 Merge branch 'gl-barrier-hacks' of gitlab.tiker.net:mattwala/loopy-gl-barrier into gl-barrier-hacks
Jun 07, 2016
e64ec000 Fix domain changing bug that used previous versions of the kernel.
Jun 07, 2016
cfe1f948 Test save/restore of private arrays.
Jun 07, 2016
6ab79dd2 Fix spelling error.
Jun 08, 2016
a0d26fb3 Fix comment.
Jun 09, 2016
bc324c37 Fix reduce() silliness.
Jun 09, 2016
442bc423 Add check for identifiers allowed in subst rules
Jul 28, 2016
87f29122 Fix pymbolic maxima interop import
Jul 28, 2016
61b7296f Avoid printing output in test kernels
Jul 28, 2016
76842320 Detect and eliminate identical subst rules even if they use differing arg names
Jul 28, 2016
5caed497 Allow emitting ISPC streaming stores (using https://github.com/ispc/ispc/pull/1181 )
Jul 28, 2016
0584893e Fix: library functions in test scripts are non-picklable
Jul 31, 2016
0bc8b18f Fix atomic update codegen in C target
Jul 31, 2016
706788d1 Fix processing of substitution rules after arg-indep join fix
Jul 31, 2016
26d0cfeb Allow parsing of instructions with no LHS (Fixes #33)
Aug 01, 2016
4bbe3318 Update error message to reflect preferred way of iname annotation
Aug 01, 2016
6577b16b Update make_assignment to allow for 0 LHSs
Aug 01, 2016
8575b294 Fix mis-nested loop in kernel arg guessing
Aug 01, 2016
5c852e5e Fix, test code generation for reduction in 0 LHS instructions (Fixes #32)
Aug 01, 2016
2a6baacb Merge branch 'matt-temporary-saving' into 'master'
Aug 01, 2016
0930839b CallInstruction: check type of assignees constructor arg
Aug 01, 2016
e5bf0630 Don't replace expressions with None in check_bounds
Aug 01, 2016
dc0d166b Fix construction of CallInstruction in test_call_with_no_returned_value
Aug 01, 2016
c10fa90b Do not pass None for expressions in IndexRankFinder in arg guessing
Aug 01, 2016
dc7b6c95 Add add_inames_to_insn
Aug 02, 2016
88e55cff Fix tests to not require boostability
Aug 02, 2016
303cd7f8 Deprecate 'boostability'
Aug 02, 2016
86af14d2 Improve scheduler diagnostics
Aug 02, 2016
200c1922 Give better error for 'for' without inames
Aug 02, 2016
e2c6e5cc Add support for 'if' blocks
Aug 02, 2016
00a46117 Fix get_image_arg_decl signature in CUDA backend
Aug 02, 2016
9b5b7f8e Fix OpenCL image arg access code gen
Aug 02, 2016
c4f5dff8 Remove stray pu.db
Aug 02, 2016
51367a35 Instructions implicitly use all inames that they contain
Aug 02, 2016
ffec02f7 Error msg fixes
Aug 02, 2016
8bd5e17d Add globbing to tag_inames
Aug 02, 2016
4020c09d Fix iname duplication during creation
Aug 02, 2016
58d10adb Rename forced_iname_deps -> within_inames
Aug 03, 2016
40237ff4 Add compat goop for forced_iname_deps -> within_inames rename
Aug 03, 2016
d4270094 Add some initial insn creation sanity checks
Aug 03, 2016
b704f1ad Bump data model for forced_iname_deps -> within_inames rename
Aug 08, 2016
96b47361 Add doc acknowledgments
Aug 08, 2016
23b7d216 Add doc autobuild
Aug 08, 2016
6c2a80d4 Ignore pytest's cache directory
Aug 09, 2016
e0a92bea Pre-schedule check: fix log order
Aug 09, 2016
73b3c172 Demote cache hit messages to debug log
Aug 09, 2016
10ee010b Don't show progress during doc upload
Aug 10, 2016
2d27fa30 Use both plain and non-plain set euqality in LoopKernel.__eq__
Aug 10, 2016
4084d5ca collect_common_factors_on_increment: Complain if no common factors found
Aug 12, 2016
e2f169bd set_loop_priority: Allow comma-sep string with empty bits
Aug 12, 2016
9a3d248a precompute: allow comma-sep for precompute_outer_inames, add storage_axes to...
Aug 12, 2016
909ad171 Gnuma test: stop using deprecated bits
Aug 12, 2016
f9e9030b Fix parameter passing in CL target
Aug 12, 2016
922ea6c0 Merge porter:src/loopy
Aug 12, 2016
f50b087b gmem_access_poly: Use simplify_using_aff on indices
Aug 13, 2016
f6e33619 Fix preprocessing logic in gather_access_footprints (and related)
Aug 13, 2016
d12d2102 Fix assignment tracing
Aug 13, 2016
83213136 Subscript codegen: Do not forget to apply offset if shape is None
Aug 14, 2016
2c66f36d Merge branch 'master' of ssh://github.com/inducer/loopy
Aug 16, 2016
410792ec Remove arguments from, simplify aff_from_expr
Aug 16, 2016
ae71983b Fix aff_to_expr to correctly interpret divs
Aug 16, 2016
75f730c3 Add a purpose-built eval mapper for aff_from_expr
Aug 16, 2016
237de765 Revert "Fix aff_to_expr to correctly interpret divs"
Aug 16, 2016
4f497ccd Fix compat goop for forced_iname_deps -> within_inames
Aug 16, 2016
35241a0a First discard parallel inames, then try use_boostable_into
Aug 19, 2016
56001eae Discard duplication options that do not affect an instruction
Aug 19, 2016
f1e4852c Emit a warning if falling into boostable_into branch
Aug 19, 2016
07fb77a1 Only build CentOS binaries for master [ci skip]
Aug 19, 2016
81e86ded Sort domain parameters on kernel creation for better determinism
Aug 27, 2016
0d069a65 commenting out debug print
Sep 01, 2016
8011a92f Fix loopy type handling in type inference
Sep 08, 2016
fc19d7c9 Make kernel execution a function of the target
Sep 14, 2016
94361fd7 Add loopy.compiled compatibility shim
Sep 14, 2016
6a0a8039 Stop using CompiledKernel.code in auto_test
Sep 14, 2016
42de8af3 Fix target replacement logic for kernel arg workarounds
Sep 14, 2016
87b722a3 Fix target execution prototype
Sep 14, 2016
b104125d Merge branch 'master' into detect-fix-unschedulable
Sep 14, 2016
fc14cb71 Restore library_for_test (oops) (!2)
Sep 16, 2016
0616712d Reset kernel executor cache after unpickling
Sep 18, 2016
2edb8713 Fix SEM Laplacian test with detect-fix-unschedulable
Sep 21, 2016
3653cffa Merge branch 'master' into detect-fix-unschedulable
Sep 21, 2016
68b6e6d2 Merge branch 'detect-fix-unschedulable' into 'master'
Sep 21, 2016
4b6e9645 Fix kernel unpickling wrt _kernel_executor_cache
Sep 21, 2016
279b7949 Fix missing cases in make_options
Sep 28, 2016
5f4ff941 Make get_required_predicates succeed even for empty kernels
Sep 29, 2016
393a11cc Fix interaction between CSE expansion and iname duplication
Oct 04, 2016

4,505 additional commits have been omitted to prevent performance issues.