summaryrefslogtreecommitdiff
path: root/source/slang/slang-ir-autodiff-unzip.cpp
AgeCommit message (Collapse)Author
2025-02-25Fix `UseGraph::replace` (#6395)Sai Praveen Bangaru
* Fix `UseGraph::isTrivial()` test. * Fix. * Fix. * Refactor `UseGraph` and `UseChain` * Update slang-ir-autodiff-primal-hoist.cpp * Update all auto-diff locations that handle pointers to treat user pointers as regular values * Update test to use direct-SPIRV only --------- Co-authored-by: Yong He <yonghe@outlook.com>
2025-01-10Fix `markNonContextParamsAsSideEffectFree`. (#6054)Yong He
2025-01-09[Auto-diff] Overhaul auto-diff type tracking + Overhaul dynamic dispatch for ↵Sai Praveen Bangaru
differentiable functions (#5866) * Overhauled the auto-diff system for dynamic dispatch * More fixes * remove intermediate dumps * Update slang-ast-type.h * More fixes + add a workaround for existential no-diff * Update reverse-control-flow-3.slang * remove dumps * remove more dumps * Delete working-reverse-control-flow-3.hlsl * Cleanup comments + unused variables * More comment cleanup * Add support for lowering `DiffPairType(TypePack)` & `MakePair(MakeValuePack, MakeValuePack)` * Fix array of issues in Falcor tests. * Update slang-ir-autodiff-pairs.cpp * More fixes for Falcor image tests * Small fixups. --------- Co-authored-by: Yong He <yonghe@outlook.com>
2024-11-05Move switch statement bodies to their own lines (#5493)Ellie Hermaszewska
* Move switch statement bodies to their own lines * format --------- Co-authored-by: Yong He <yonghe@outlook.com>
2024-10-29formatEllie Hermaszewska
* format * Minor test fixes * enable checking cpp format in ci
2024-10-28Assorted auto-diff enhancements for increased performance & more streamlined ↵Sai Praveen Bangaru
auto-diff results (#5394) * Various AD enhancements * Fix issue with pt-loop test * Update pt-loop.slang * More fixes for perf. Final minimal context test now passes. * Fix issue with loop-elimination pass not running after dce * Try fix wgpu test by removing select operator * Disable wgpu * Delete out.wgsl * Remove comments * Update slang-ir-util.cpp * Fix header relative paths for slang-embed * Disbale wgpu for a few other tests * Better way of determining which params to ignore for side-effects * Update slang-ir-dce.cpp * Fix issue with circular reference from previous AD pass being left behind for the next AD pass * Update slang-ir-dce.cpp
2024-09-19Support `IDifferentiablePtrType` (#5031)Sai Praveen Bangaru
* initial diff-ref-type interface * Initial support for `IDifferentiablePtrType` * Fix unused vars * More tests + fix switch case fallthrough. * Update slang-ir-autodiff.cpp * Update diff-ptr-type-loop.slang * Add optimization to allow more complex pair types * Update slang-ir-autodiff-primal-hoist.cpp * Update diff-ptr-type-loop.slang * Update slang-ir-autodiff-primal-hoist.cpp * More fixes to address reviews * Update slang-check-expr.cpp * Optimizations + rename `differentiableRefInterfaceType` -> `differentiablePtrInterfaceType` * Move pair logic to ir-builder, unify the type dictionaries. --------- Co-authored-by: Yong He <yonghe@outlook.com>
2024-09-18Report AD checkpoint contexts (#5058)venkataram-nv
* Transferring source locations when creating phi instructions * Tracking for simple variables * Deriving source locations for loop counters * Printing checkpoint structure breakdown * More readable output format * Special behavior for loop counters * Writing report to file * Add slangc option to enable checkpoint reports * Display types of checkpointed fields * Message in case there are no checkpointing contexts * Catch source locations for function calls * Source cleanup * Fix compilation warnings * Remove stray dump() * Provide the report through diagnostic notes * Add missing path for sourceLoc during unzip pass * Add tests for reporting intermediates * Include more transfer cases for source locations * Fix ordering in address elimination * Fill in more holes with source location transfer * Remove debugging line * Reverting changes to diagnostic sink * Simplify address elimination using source location RAII contexts * Eliminating manual source loc transfers in forward transcription * Fix local var adaptation to use RAII location setter * Simplify primal hoisting logic for source location transfer * Simplify unzipping with RAII location scopes * Simplify transpose logic * Cleaning up for rev.cpp * Reverting spacing changes * Fix mistake with source loc RAII instantiation * Fix formatting issues
2024-08-06Fix auto-diff synthesized method naming conventions (#4714)Sai Praveen Bangaru
* Fix auto-diff synthesized method naming conventions * Update tests; remove unused var
2023-09-21Various slangpy fixes. (#3227)Yong He
* Make dynamic cast transparent through `IRAttributedType`. * Add [CUDAXxx] variant of attributes. * Support marshaling of vector types. * Wrap cuda kernels in `extern "C"` block. --------- Co-authored-by: Yong He <yhe@nvidia.com>
2023-08-23Misc. SPIRV Fixes. (#3146)Yong He
* Lower all ByteAddressBuffer uses for SPIRV. * Misc. SPIRV Fixes. --------- Co-authored-by: Yong He <yhe@nvidia.com> Co-authored-by: Ellie Hermaszewska <ellieh@nvidia.com>
2023-08-17Initial support for differentiating existential types (#3111)Sai Praveen Bangaru
* Merge * WIP: Complete auto-diff logic for existential types * Revert "Add compiler option for generating representative hash" This reverts commit 13b09ef4621e73844c96d64d9c111a8ed0d45aae. * More fixes for fwd-mode AD on existential types * Add anyValueSize inference pass * Fix checking of `Differential.Differential==Differential` * In-progress: infer any-value-size for existential types * Existentials now work in forward-mode * Overhaul handling of existential AD types. Fwd-mode works, reverse-mode requires front-end changes * Reverse-mode now works on existentials * Cleanup * Remove diff rules for create existential object for now * Revert treat-as-differentiable changes * Fixes * More fixes * Cleanup * more cleanup * signed/unsigned * Revert "Cleanup" This reverts commit e4f7d71f07bb207736f90708961eeecd09a1b652. * Cleanup (again) * Remove public/export/keep-alive on null differential after AD pass * Minor fix * Update dictionary accessors * Keep export decoration * More fixes + Support for `kIROp_PackAnyValue` * Merge upstream * Update expected-failure.txt
2023-08-16Use ankerl/unordered_dense as a hashmap implementation (#3036)Ellie Hermaszewska
* Correct namespace for getClockFrequency * missing const * Add missing assignment operator * Remove unused variables * Return correct modified variable * Use stable hash code for file system identity * terse static_assert * Structured binding for map iteration * Make (==) and getHashCode const on many structs * Add ConstIterator for LinkedList * Replace uses of ItemProxy::getValue with Dictionary::at * Extract list of loads from gradientsMap before updating it * Const correctness in type layout * Add unordered_dense hashmap submodule * Use wyhash or getHashCode in slang-hash.h * refactor slang-hash.h * Use ankerl/unordered_dense as a hashmap implementation Notable changes: - The subscript operator returns a reference directly to the value, rather than a lazy ItemProxy (pair of dict pointer and key) slang-profile time (95% over 10 runs): - Before: 6.3913906 (±0.0746) - After: 5.9276123 (±0.0964) * 64 bit hash for strings So they have the same hash as char buffers with the same contents * Narrowing warnings for gcc to match msvc * revert back to c++17 * Correct c++ version for msvc * Use path to unordered_dense which keeps tests happy * Do not assign to and read from map in same expression * Remove redundant map operations in primal-hoist * Split out stable hash functions into slang-stable-hash.h * 64 bit hash by default * regenerate vs projects * Correct return type from HashSetBase::getCount() * correct width for call to Dictionary::reserve * Use stable hash for obfuscated module ids * Signed int for reserve * clearer variable naming * Parameterize Dictionary on hash and equality functors * Allow heterogenous lookup for Dictionary * missing const * Use set over operator[] in some places * Remove unused function * s/at/getValue
2023-04-27Prevent storing loads of global parameters. (#2850)Yong He
Co-authored-by: Yong He <yhe@nvidia.com>
2023-04-25Dictionary using lowerCamel (#2835)jsmall-nvidia
* #include an absolute path didn't work - because paths were taken to always be relative. * WIP lowerCamel Dictionary. * WIP more lowerCamel fixes for Dictionary. * Add/Remove/Clear * GetValue/Contains * Fix tabs in dictionary. Count -> getCount * Fix fields with caps. * Key -> key Value -> value Use m_ for members where appropriate. Use lowerCamel in linked list. * Some small fixes/improvements to Dictionary. * Kick CI.
2023-04-24Change AD checkpointing policy to recompute more. (#2836)Yong He
Co-authored-by: Yong He <yhe@nvidia.com>
2023-04-21Refactor checkpointing policy and availability pass. (#2826)Yong He
Co-authored-by: Yong He <yhe@nvidia.com>
2023-04-21AD: Various fixes around dynamic dispatch (#2820)Sai Praveen Bangaru
* Add a test for the new diff material system * Various fixes for AD - inout primal context params converted to out params, - added attributed types to list of stored types - used differentiated primal func type instead of type of differentiated func to avoid tangling with user-code differential types. --------- Co-authored-by: Lifan Wu <lifanw@nvidia.com>
2023-03-29Update checkpoint policy to make obvious recompute decisions. (#2753)Yong He
* Update checkpoint policy to make obvious recompute decisions. Also adds an optimization to fold updateElement chains on the same array or struct into a single makeArray or makeStruct. * Bug fixes around array types with different int typed count. * change test. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com>
2023-03-16Fix Phi simplification bug. (#2710)Yong He
* Fix Phi simplification bug. * Fix up. * Fix. * Fix. * Fix. * Fix. * Fix. * Fix test. * Fix test. --------- Co-authored-by: Yong He <yhe@nvidia.com>
2023-03-15Extend DCE to handle pure function calls that returns via `inout` ↵Yong He
parameters. (#2700)
2023-03-15AD: Primal-Hoisting Rework + Checkpoint Policy Framework (#2702)Sai Praveen Bangaru
2023-03-15Properly implement differential witness of intermediate context type. (#2699)Yong He
* Properly implement differential witness of intermediate context type. * Modify test to include a loop. --------- Co-authored-by: Yong He <yhe@nvidia.com>
2023-03-14Support `fwd_diff(bwd_diff(f))`. (#2697)Yong He
* Support `fwd_diff(bwd_diff(f))`. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com>
2023-03-08Add support for `[PrimalSubstitute]` and `[PrimalSubstituteOf]`. (#2691)Yong He
* Add support for `[PrimalSubstitute]` and `[PrimalSubstituteOf]`. * Fix * Fix. * Cleanup. --------- Co-authored-by: Yong He <yhe@nvidia.com>
2023-02-24More control flow simplifications. (#2673)Yong He
* More control flow and Phi param simplifications. * Fix. * Fix gcc error. * Fix. * More IR cleanup. * Fix bug in phi param dce + ifelse simplify. * Propagate and DCE side-effect-free functions. * Enhance CFG simplifcation to remove loops with no side effects. * Fix. * Fixes. * Fix tests. Add [__AlwaysFoldIntoUseSite] for rayPayloadLocation. * More cleanup. * Fixes. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com>
2023-02-22Fixed hoisting of intermediate array & context vars (#2674)Sai Praveen Bangaru
Also added legalization for loops
2023-02-22Reverse-mode AD fixes for loops with non-trivial break region (#2671)Sai Praveen Bangaru
* Fix crash when applying autodiff to functions with no arguments * Fixes for loops where the break region is non-trivial * Minor fix * Implement array legalization correctly. * Fix array legalization. --------- Co-authored-by: Yong He <yhe@nvidia.com>
2023-02-20Miscellaneous backward autodiff fixes. (#2665)Yong He
* Fix differentiable type registration * Fix use of non-differentiable return value in a differentiable func. * Fix use of primal inst that does not dominate the diff block. * Fix primal inst hoisting, and add missing type legalization logic. * Make `detach` defined on all differentiable T. --------- Co-authored-by: Yong He <yhe@nvidia.com>
2023-02-16Remove `SharedIRBuilder`. (#2657)Yong He
Co-authored-by: Yong He <yhe@nvidia.com>
2023-02-10Fix several autodiff bugs. (#2643)Yong He
2023-02-10Fix checking of `[BackwardDerivativeOf]` attribute. (#2640)Yong He
* Fix checking of `[BackwardDerivativeOf]` attribute. * Fix crash in `canInstHaveSideEffectAtAddress`. * Fix. * Revert fix. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com>
2023-02-07Arithmetic simplifications and more IR clean up logic. (#2632)Yong He
2023-02-03Overhaul `transposeParameterBlock` to support `inout` params. (#2621)Yong He
* Overhaul `transposeParameterBlock` to support `inout` params. * Small bug fixes. * Bug fix on differentiable intrinsic specialization. * Fixes. * Run autodiff tests on CPU. * Clean up. * More bug fixes., * Add test coverage on inout param. * Fix language server hinting for transcribed mutable params. --------- Co-authored-by: Yong He <yhe@nvidia.com>
2023-02-01Support `out` parameters in backward differentiation. (#2619)Yong He
* Support `out` parameters in backward differentiation. * Fixes. * Fix cleanup. --------- Co-authored-by: Yong He <yhe@nvidia.com>
2023-01-31Patched support for multi-return and fallthrough if-else with break stmts ↵Sai Praveen Bangaru
(#2617)
2023-01-25Unify UpdateField and UpdateElement with access chain. (#2611)Yong He
* Unify UpdateField and UpdateElement with access chain. * Fix warnings. Co-authored-by: Yong He <yhe@nvidia.com>
2023-01-24Reimplement address elimination. (#2605)Yong He
* Reimplement address elimination pass. * Fix error. * Update test references. Co-authored-by: Yong He <yhe@nvidia.com>
2023-01-17First custom backward-derivative test case working. (#2598)Yong He
2023-01-14Support custom backward derivative attribute. (#2594)Yong He
2023-01-11Make backward differentiation work with generics. (#2586)Yong He
* Make backward differentiation work with generics. * Fix. * Another fix. * More fix. Co-authored-by: Yong He <yhe@nvidia.com>
2023-01-10Nested bwd-diff func call context save/restore. (#2584)Yong He
Co-authored-by: Yong He <yhe@nvidia.com>
2023-01-06Split bwd_diff op into separate ops for primal and propagate func. (#2582)Yong He
* Split bwd_diff op into separate ops for primal and propagate func. * Fix. * Download swiftshader with github actions instead of curl on linux. * Fix github action. Co-authored-by: Yong He <yhe@nvidia.com>
2023-01-04Multi-block reverse-mode autodiff (#2576)Sai Praveen Bangaru
* Initial multi-block implementation * Implemented multi-block reverse-mode (without loops) * Added logic to remove block-level decorations to avoid confusing IR simplification passes * Fixed issues with block-level decorations during IR simplification by removing them prior to simplification. Co-authored-by: Yong He <yonghe@outlook.com>
2022-12-21Further unify the autodiff passes. (#2574)Yong He
* Further unify the autodiff passes. * Fix clang compilation error. * Rename ForwardDerivativeTranscriber->ForwardDiffTranscriber. * Remove unused fields from Transcriber classes. * More small cleanups. * Cleanup. Co-authored-by: Yong He <yhe@nvidia.com>
2022-12-19Separate primal computations from unzipped function into an explicit ↵Yong He
function. (#2569) Co-authored-by: Yong He <yhe@nvidia.com>
generated by cgit v1.2.3 (git 2.39.1) at 2026-08-03 03:59:41 +0000