| efeda20 | Yong He | 30 March 2023, 21:34:54 UTC | Fix stdlib definitions for tensor interlocked methods. (#2761) Co-authored-by: Yong He <yhe@nvidia.com> | 30 March 2023, 21:34:54 UTC |
| 917416f | Yong He | 30 March 2023, 19:50:02 UTC | More builtin library support in torch backend. (#2760) Co-authored-by: Yong He <yhe@nvidia.com> | 30 March 2023, 19:50:02 UTC |
| e3b701c | Ellie Hermaszewska | 30 March 2023, 19:48:02 UTC | Enable CUDA render api on unix (#2757) * Remove extra qualification in cuda device impl Only MSVC accepts this illegal code * Enable CUDA render api on unix --------- Co-authored-by: Yong He <yonghe@outlook.com> | 30 March 2023, 19:48:02 UTC |
| 72f7928 | Ellie Hermaszewska | 30 March 2023, 19:46:27 UTC | Fix mismatched malloc/delete[] in toWString (#2758) Co-authored-by: Yong He <yonghe@outlook.com> | 30 March 2023, 19:46:27 UTC |
| d01e28a | Yong He | 30 March 2023, 18:41:54 UTC | Fix autodiff pass duplicates exported functions. (#2759) Co-authored-by: Yong He <yhe@nvidia.com> | 30 March 2023, 18:41:54 UTC |
| 37594df | Yong He | 30 March 2023, 04:06:23 UTC | Update TOC (#2756) Co-authored-by: Yong He <yhe@nvidia.com> | 30 March 2023, 04:06:23 UTC |
| 6fa4edb | Yong He | 30 March 2023, 01:23:21 UTC | Convert tensor types in `make_tensor_view`. (#2755) Co-authored-by: Yong He <yhe@nvidia.com> | 30 March 2023, 01:23:21 UTC |
| af062bf | Yong He | 30 March 2023, 01:00:34 UTC | Fix IRArrayType emit logic. (#2754) * Fix IRArrayType emit logic. * Fix test. * Fix ast constant folding. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 30 March 2023, 01:00:34 UTC |
| 082c48d | Yong He | 30 March 2023, 00:05:07 UTC | Update checkpoint policy to make obvious recompute decisions. (#2753) * 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> | 30 March 2023, 00:05:07 UTC |
| a862f5b | Yong He | 29 March 2023, 17:00:48 UTC | Update a1-02-slangpy.md | 29 March 2023, 17:00:48 UTC |
| bbf12c2 | Ellie Hermaszewska | 29 March 2023, 16:25:15 UTC | Add missing initializer in json source map decoding (#2752) | 29 March 2023, 16:25:15 UTC |
| 64fe75c | Yong He | 29 March 2023, 01:01:42 UTC | Update a1-02-slangpy.md | 29 March 2023, 01:01:42 UTC |
| 87d331c | Yong He | 29 March 2023, 00:28:38 UTC | Update a1-02-slangpy.md | 29 March 2023, 00:28:38 UTC |
| 102702c | Yong He | 29 March 2023, 00:20:54 UTC | Update a1-02-slangpy.md | 29 March 2023, 00:20:54 UTC |
| cce9094 | Yong He | 29 March 2023, 00:20:36 UTC | Update a1-02-slangpy.md | 29 March 2023, 00:20:36 UTC |
| 3ca504f | Yong He | 29 March 2023, 00:16:07 UTC | Update a1-02-slangpy.md | 29 March 2023, 00:16:07 UTC |
| 0ea68f2 | Yong He | 28 March 2023, 23:55:34 UTC | Update a1-02-slangpy.md | 28 March 2023, 23:55:34 UTC |
| 1f9f604 | Yong He | 28 March 2023, 23:51:56 UTC | Update a1-02-slangpy.md | 28 March 2023, 23:51:56 UTC |
| 240a29b | Yong He | 28 March 2023, 23:33:50 UTC | Update a1-02-slangpy.md | 28 March 2023, 23:33:50 UTC |
| dba963d | Yong He | 28 March 2023, 23:27:45 UTC | Update toc (#2749) Co-authored-by: Yong He <yhe@nvidia.com> | 28 March 2023, 23:27:45 UTC |
| 92ba905 | Yong He | 28 March 2023, 23:26:42 UTC | Update a1-02-slangpy.md | 28 March 2023, 23:26:42 UTC |
| a61f089 | Yong He | 28 March 2023, 22:19:03 UTC | Add slangpy doc, fix cuda prelude. (#2748) * Add slangpy doc, fix cuda prelude. * more bug fix. * fix. * fix. * More fix. * fix. * f * fix prelude. * update prelude. * update doc * Update prelude. * add zeros_like * update doc. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 28 March 2023, 22:19:03 UTC |
| 8f03af5 | Sai Praveen Bangaru | 28 March 2023, 19:39:52 UTC | AD: Warped-Area-Sampling test works now. (#2742) * Create render.slang * Added higher-order differentiability decorators for built-ins + preliminary tests * Update diff.meta.slang * Copy over conformance synthesis code to `DifferentiableTypeConformanceContext` * Update render.slang * Fixed 1D warped-area sampling test * Update warped-sampling-1d.slang * Remove commented line. * Change WAS test to use fixed point * Replaced InterlockedCmpExchange with InterlockedAdd * Increase fixed point precision * Reduce floating-point precision by 2 digits to avoid platform-specific problems * Dropped another digit (just to be safe) --------- Co-authored-by: Yong He <yonghe@outlook.com> | 28 March 2023, 19:39:52 UTC |
| e22b4db | Yong He | 28 March 2023, 18:12:40 UTC | Small fixes and cleanups on CUDA/CPP codegen. (#2746) * Small fixes and cleanups on CUDA/CPP codegen. * Disable `legalizeEmptyTypes` for now. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 28 March 2023, 18:12:40 UTC |
| 0a69260 | Yong He | 28 March 2023, 06:00:42 UTC | Translate all composed types into tuple types in pyBind. (#2744) * Translate all composed types into tuple types in pyBind. * Delete temp file. * Fix get tuple element code emit logic. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 28 March 2023, 06:00:42 UTC |
| d120fec | jsmall-nvidia | 28 March 2023, 02:52:48 UTC | Upgrade `slang-llvm` (#2741) * #include an absolute path didn't work - because paths were taken to always be relative. * Fix SlangCompileTarget to keep ordering. * Add test. Remove V2 version of interface to access IDownstreamCompiler Update to slang-llvm which has _chkstk support. * Update slang.h Co-authored-by: Ellie Hermaszewska <github@sub.monoid.al> --------- Co-authored-by: Yong He <yonghe@outlook.com> Co-authored-by: Ellie Hermaszewska <github@sub.monoid.al> | 28 March 2023, 02:52:48 UTC |
| 579870b | Yong He | 28 March 2023, 02:51:21 UTC | Apply IR simplifcation immediately after specialization to avoid duplicates. (#2739) * Apply IR simplifcation immediately after specialization to avoid duplicates. * Update source/slang/slang-ir-specialize.cpp Co-authored-by: Ellie Hermaszewska <github@sub.monoid.al> --------- Co-authored-by: Yong He <yhe@nvidia.com> Co-authored-by: Ellie Hermaszewska <github@sub.monoid.al> | 28 March 2023, 02:51:21 UTC |
| 84dc318 | Yong He | 28 March 2023, 01:39:44 UTC | Don't touch output file if content did not change. (#2738) Co-authored-by: Yong He <yhe@nvidia.com> | 28 March 2023, 01:39:44 UTC |
| ca1f93a | jsmall-nvidia | 27 March 2023, 17:57:42 UTC | Using SourceMap for location output (#2736) * #include an absolute path didn't work - because paths were taken to always be relative. * WIP using SourceMap with SourceManager. * Add a test to check obfuscation map is working. --------- Co-authored-by: Yong He <yonghe@outlook.com> | 27 March 2023, 17:57:42 UTC |
| 2179480 | Yong He | 27 March 2023, 17:05:07 UTC | Fix lowering crash in [BackwardDerivativeOf]. (#2737) Co-authored-by: Yong He <yhe@nvidia.com> | 27 March 2023, 17:05:07 UTC |
| 333968a | Ellie Hermaszewska | 27 March 2023, 09:48:46 UTC | Use c++17 standard (#2686) * Use c++17 standard * regenerate VS projects * Switch to using std::invoke | 27 March 2023, 09:48:46 UTC |
| ffa7d05 | Yong He | 26 March 2023, 23:39:51 UTC | Update slang-llvm (#2735) | 26 March 2023, 23:39:51 UTC |
| d64ee86 | Yong He | 26 March 2023, 20:59:11 UTC | Add PyTorch C++ binding generation. (#2734) * Add PyTorch C++ binding generation. * fix --------- Co-authored-by: Yong He <yhe@nvidia.com> | 26 March 2023, 20:59:11 UTC |
| 666af09 | Yong He | 25 March 2023, 03:17:46 UTC | Switch to short circuiting semantics for scalar `?:` operator. (#2733) | 25 March 2023, 03:17:46 UTC |
| 7292edb | Sai Praveen Bangaru | 24 March 2023, 23:50:51 UTC | Added `[BackwardDifferentiable]` tags for intrinsic + builtin methods (#2732) * Added higher-order differentiability decorators for built-ins + preliminary tests * Update diff.meta.slang | 24 March 2023, 23:50:51 UTC |
| e794de0 | jsmall-nvidia | 24 March 2023, 13:56:59 UTC | Obfuscated source map writing (#2727) * #include an absolute path didn't work - because paths were taken to always be relative. * WIP produce obfuscated source map and write when container is specified. * Make the sourcemap generated name stable. | 24 March 2023, 13:56:59 UTC |
| 03c1083 | Yong He | 24 March 2023, 11:33:51 UTC | Fix nested bwdContextType lowering. (#2731) Co-authored-by: Yong He <yhe@nvidia.com> | 24 March 2023, 11:33:51 UTC |
| 56a84a0 | Yong He | 24 March 2023, 05:42:59 UTC | Fix various autodiff crashes related to interface usage. (#2730) * Fix crash. * Fix `[ForwradDerivative]` on member functions. * Update comments. * Fix crash when [BackwardDerivative] is provided but not [ForwardDerivative]. * Allow calling dynamic dispatched generic method from differentiable func. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 24 March 2023, 05:42:59 UTC |
| e004511 | Sai Praveen Bangaru | 24 March 2023, 02:27:30 UTC | AD: Fix type checking for higher-order custom derivatives definitions (#2729) * Fixed type coercion issue with higher-order user defined methods * Placed associated type lookup method in a loop * Update high-order-user-defined-derivative.slang * Revert changes to associated type lookup method | 24 March 2023, 02:27:30 UTC |
| 6e4eae1 | Yong He | 24 March 2023, 00:16:32 UTC | Hack handling of primal insts that has a function type. (#2728) * Update diff-bwd material test * Minor update * Hack handling of primal insts that has a function type. --------- Co-authored-by: winmad <winmad.wlf@gmail.com> Co-authored-by: Yong He <yhe@nvidia.com> | 24 March 2023, 00:16:32 UTC |
| 50e7d97 | Yong He | 23 March 2023, 23:59:02 UTC | Fix optimization pass not converging. (#2725) * Fix optimization pass not converging. * Fix. * Fix tests. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 23 March 2023, 23:59:02 UTC |
| 85f0058 | Yong He | 23 March 2023, 18:37:29 UTC | Fix scope fixing for address insts. (#2724) Co-authored-by: Yong He <yhe@nvidia.com> | 23 March 2023, 18:37:29 UTC |
| 34acec2 | Yong He | 23 March 2023, 06:59:22 UTC | Fix generic lowering regression due to IR deduplication. (#2723) * Fix generic lowering. * Fix generic lowering regression due to IR deduplication. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 23 March 2023, 06:59:22 UTC |
| 44ab095 | winmad | 23 March 2023, 05:04:28 UTC | Create a simplified Falcor material system in slang test (#2721) * Duplicate an example of differentiating Falcor's material system * Add a second BSDF * WIP: update test; grad didn't pass through * Finalize test --------- Co-authored-by: Lifan Wu <lifanw@nvidia.com> | 23 March 2023, 05:04:28 UTC |
| 259a015 | Yong He | 23 March 2023, 04:16:35 UTC | Type legalization and autodiff bug fixes. (#2722) * Bug fixes. * Fix. * Only perform autodiff for functions whose derivative is actually used. * Fix loop optimize bug. * Fix high order diff. * Fix trivial diff func generation. * Fixes. * Cleanup. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 23 March 2023, 04:16:35 UTC |
| d4f99c8 | jsmall-nvidia | 22 March 2023, 16:04:33 UTC | Source map obfuscation (#2717) * #include an absolute path didn't work - because paths were taken to always be relative. * WIP source map. * Split out handling of RttiTypeFuncs to a map type. * Make RttiTypeFuncsMap hold default impls. * Slightly more sophisticated RttiTypeFuncsMap * Source map decoding. * Fix tabs. * Fix asserts due to negative values. * Use less obscure mechanisms in SourceMap. * Source map decoding. Simplifying SourceMap usage. * First attempt at ouputting a source map as part of emit. * Added support for -source-map option. SourceMap is added to the artifact. * Small improvements around column calculation in SourceWriter. * Source Loc obuscation WIP. * Fix some issues around SourceMap obfuscation. * Split out obfuscation into its own file. * Keep obfuscated SourceMap even through serialization bottleneck. | 22 March 2023, 16:04:33 UTC |
| d8a40ab | Yong He | 22 March 2023, 04:29:13 UTC | [TreatAsDifferentiable] functions. (#2720) | 22 March 2023, 04:29:13 UTC |
| 8387673 | Yong He | 22 March 2023, 03:03:12 UTC | Fix associated type resolution bug. (#2719) * Fix associated type resolution bug. * Fix. * Fix language server hinting messed up by breadcrumb nodes. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 22 March 2023, 03:03:12 UTC |
| 5d2c5dd | Yong He | 21 March 2023, 22:44:43 UTC | Fix IntVal type check. (#2718) * Fix IntVal type check. * add test case result. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 21 March 2023, 22:44:43 UTC |
| 96caba7 | Yong He | 21 March 2023, 22:44:21 UTC | Add texture tri-linear autodiff example. (#2715) * Add quad texture example. * delete output image * remove irrelavent files * update project files * fix * Update example. * Fix. * remove out-texture --------- Co-authored-by: Yong He <yhe@nvidia.com> | 21 March 2023, 22:44:21 UTC |
| 7f11f88 | Yong He | 17 March 2023, 22:57:22 UTC | Add support for emitting cuda kernel and host functions. (#2712) * Add support for emitting cuda kernel and host functions. * Update test. * Fix cuda preamble emit. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 17 March 2023, 22:57:22 UTC |
| 4b55bf6 | Yong He | 17 March 2023, 22:14:44 UTC | Rework differentiability dataflow check. (#2711) Co-authored-by: Yong He <yhe@nvidia.com> | 17 March 2023, 22:14:44 UTC |
| 29abe39 | Yong He | 17 March 2023, 17:53:48 UTC | Update 07-autodiff.md | 17 March 2023, 17:53:48 UTC |
| 8a61b9d | jsmall-nvidia | 17 March 2023, 15:05:15 UTC | Support for producing SourceMap on emit (#2707) * #include an absolute path didn't work - because paths were taken to always be relative. * WIP source map. * Split out handling of RttiTypeFuncs to a map type. * Make RttiTypeFuncsMap hold default impls. * Slightly more sophisticated RttiTypeFuncsMap * Source map decoding. * Fix tabs. * Fix asserts due to negative values. * Use less obscure mechanisms in SourceMap. * Source map decoding. Simplifying SourceMap usage. * First attempt at ouputting a source map as part of emit. * Added support for -source-map option. SourceMap is added to the artifact. | 17 March 2023, 15:05:15 UTC |
| 9476d45 | Yong He | 17 March 2023, 06:46:14 UTC | Fix Phi simplification bug. (#2710) * Fix Phi simplification bug. * Fix up. * Fix. * Fix. * Fix. * Fix. * Fix. * Fix test. * Fix test. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 17 March 2023, 06:46:14 UTC |
| 77d3630 | Yong He | 17 March 2023, 05:17:51 UTC | Fix name mangling of `FuncCallIntVal` in func signatures. (#2709) * Fix name mangling of `FuncCallIntVal` in func signatures. * Enhance the test. * Fix. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 17 March 2023, 05:17:51 UTC |
| fc9cba5 | Yong He | 17 March 2023, 05:17:34 UTC | Add `[CudaDeviceExport]` to allow exporting CUDA device functions. (#2708) * Add `[CudaDeviceExport]` to allow exporting CUDA device functions. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 17 March 2023, 05:17:34 UTC |
| 2fd1ac6 | jsmall-nvidia | 17 March 2023, 05:13:59 UTC | SourceMap encoding (#2706) * #include an absolute path didn't work - because paths were taken to always be relative. * WIP source map. * Split out handling of RttiTypeFuncs to a map type. * Make RttiTypeFuncsMap hold default impls. * Slightly more sophisticated RttiTypeFuncsMap * Source map decoding. * Fix tabs. * Fix asserts due to negative values. * Use less obscure mechanisms in SourceMap. * Source map decoding. Simplifying SourceMap usage. | 17 March 2023, 05:13:59 UTC |
| 4cb899f | jsmall-nvidia | 16 March 2023, 19:19:20 UTC | Preliminary SourceMap support (#2701) * #include an absolute path didn't work - because paths were taken to always be relative. * WIP source map. * Split out handling of RttiTypeFuncs to a map type. * Make RttiTypeFuncsMap hold default impls. * Slightly more sophisticated RttiTypeFuncsMap * Source map decoding. * Fix tabs. * Fix asserts due to negative values. * Use less obscure mechanisms in SourceMap. | 16 March 2023, 19:19:20 UTC |
| 1036d1a | Yong He | 16 March 2023, 18:06:01 UTC | Add test case for `makeStruct` transcription. (#2705) * Add test case for `makeStruct` transcription. * Update documentation on `no_diff`. * Update toc --------- Co-authored-by: Yong He <yhe@nvidia.com> | 16 March 2023, 18:06:01 UTC |
| b92f280 | Samuel Kogler | 16 March 2023, 18:05:33 UTC | Support GL_EXT_fragment_shader_barycentric (#2704) * Support GL_EXT_fragment_shader_barycentric * Support pervertex with GL_EXT_fragment_shader_barycentric | 16 March 2023, 18:05:33 UTC |
| e960534 | Yong He | 16 March 2023, 06:31:09 UTC | Update 07-autodiff.md | 16 March 2023, 06:31:09 UTC |
| f7431f9 | Yong He | 16 March 2023, 06:26:14 UTC | Fix `transcribeConstruct` for `makeStruct`. (#2703) Co-authored-by: Yong He <yhe@nvidia.com> | 16 March 2023, 06:26:14 UTC |
| 3a1a6c4 | Yong He | 16 March 2023, 03:53:48 UTC | Extend DCE to handle pure function calls that returns via `inout` parameters. (#2700) | 16 March 2023, 03:53:48 UTC |
| 71efd94 | Sai Praveen Bangaru | 16 March 2023, 02:26:58 UTC | AD: Primal-Hoisting Rework + Checkpoint Policy Framework (#2702) | 16 March 2023, 02:26:58 UTC |
| 38e6219 | Yong He | 15 March 2023, 18:12:15 UTC | Update 07-autodiff.md | 15 March 2023, 18:12:15 UTC |
| bf30824 | Yong He | 15 March 2023, 16:39:21 UTC | Properly implement differential witness of intermediate context type. (#2699) * Properly implement differential witness of intermediate context type. * Modify test to include a loop. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 15 March 2023, 16:39:21 UTC |
| 176eaa9 | Yong He | 14 March 2023, 16:33:16 UTC | Update 07-autodiff.md | 14 March 2023, 16:33:16 UTC |
| e291f60 | Yong He | 14 March 2023, 16:31:51 UTC | Support `fwd_diff(bwd_diff(f))`. (#2697) * Support `fwd_diff(bwd_diff(f))`. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 14 March 2023, 16:31:51 UTC |
| a911ca6 | Yong He | 13 March 2023, 17:57:28 UTC | Support high order diff pattern: `bwd_diff(fwd_diff(f))`. (#2695) * Support high order diff pattern: `bwd_diff(fwd_diff(f))`. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 13 March 2023, 17:57:28 UTC |
| 3fea56e | jsmall-nvidia | 10 March 2023, 19:19:48 UTC | Support for PDB output from DXC (#2693) * #include an absolute path didn't work - because paths were taken to always be relative. * Add versioning to CompileOptions for DownstreamCompiler so we can add new options without breaking binary interface. * Add support for debug info format to API/command line processing. * Small simplification. * Add support for adding PDB output from a compilation. * Use builtin offset of directly. * Fix typo in debug. | 10 March 2023, 19:19:48 UTC |
| e39893e | jsmall-nvidia | 10 March 2023, 17:24:51 UTC | Add struct version to DownstreamCompiler::CompileOptions interface (#2692) * #include an absolute path didn't work - because paths were taken to always be relative. * Add versioning to CompileOptions for DownstreamCompiler so we can add new options without breaking binary interface. * Use builtin offset of directly. | 10 March 2023, 17:24:51 UTC |
| e06cfb3 | Yong He | 09 March 2023, 23:53:51 UTC | Update restrictions sections in autodiff doc. (#2694) * Update restrictions section in autodiff doc. * Update restrictions sections in autodiff doc. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 09 March 2023, 23:53:51 UTC |
| a611d4b | Yong He | 09 March 2023, 23:18:36 UTC | Update user guide on `[PrimalSubstitute]` | 09 March 2023, 23:18:36 UTC |
| 86fc50c | Yong He | 09 March 2023, 05:52:34 UTC | Add support for `[PrimalSubstitute]` and `[PrimalSubstituteOf]`. (#2691) * Add support for `[PrimalSubstitute]` and `[PrimalSubstituteOf]`. * Fix * Fix. * Cleanup. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 09 March 2023, 05:52:34 UTC |
| 257733f | Yong He | 07 March 2023, 19:22:32 UTC | Reuse higher-order `ResolveInvoke` logic to resolve func refs in `[*DerivativeOf]` attribs. (#2688) * Reuse higher-order `ResolveInvoke` logic to resolve func refs in [*DerivativeOf] attribs. * Add diff implementation matrix versions of binary and ternary intrinsics. * Add diff impl for legacy intrinsics. * Fix diagnostics of using non-differentiable function in a diff operator. * Add diff implementation for `determinant`. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 07 March 2023, 19:22:32 UTC |
| 6f31eae | Yong He | 01 March 2023, 21:19:33 UTC | Implement derivatives for HLSL intrinsics. (#2684) * Implement derivatives for HLSL intrinsics. * Vector intrinsics. * Add all intrinsics. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 01 March 2023, 21:19:33 UTC |
| 6c26aa1 | Yong He | 01 March 2023, 20:59:51 UTC | Improve diagnostic on differentiablitiy check. (#2687) Co-authored-by: Yong He <yhe@nvidia.com> | 01 March 2023, 20:59:51 UTC |
| 3c32dd9 | Sai Praveen Bangaru | 01 March 2023, 02:24:24 UTC | AD: Fixed do-while loops (#2683) * WIP: Fix for do-while loops * Added a somewhat hacky fix for do-while loops * Redid the indexed region map builder step to fix issue with the nested loops test * rename * Used managed pointers | 01 March 2023, 02:24:24 UTC |
| 7eeda30 | Theresa Foley | 28 February 2023, 23:10:14 UTC | Fixes to GitHub Windows CI build (#2664) | 28 February 2023, 23:10:14 UTC |
| f7db44a | Yong He | 28 February 2023, 23:09:19 UTC | Add `SourceBlobWithPathInfoArtifactRepresentation`. (#2682) | 28 February 2023, 23:09:19 UTC |
| f23e362 | Yong He | 28 February 2023, 05:21:39 UTC | Diagnose on storing differentiable value into non-differentiable location. (#2681) | 28 February 2023, 05:21:39 UTC |
| 10e2d9c | Sai Praveen Bangaru | 28 February 2023, 04:42:06 UTC | More fixes for reverse-mode on complicated loops (#2675) * Multiple fixes to get various loop tests to pass. * Create reverse-nested-loop.slang * Fix for variables becoming inaccessible during cfg normalization * Removed comments and moved break-branch-normalization to eliminateMultiLevelBreaks * Fix. * Override liveness tests | 28 February 2023, 04:42:06 UTC |
| a3ba22b | Yong He | 27 February 2023, 23:18:07 UTC | Detect and deduplicate read-only resource access. (#2680) * Detect and deduplicate read-only resource access. * Fix tests. * Fix tests. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 27 February 2023, 23:18:07 UTC |
| b1b76f0 | Sai Praveen Bangaru | 25 February 2023, 07:23:41 UTC | Added support for `kIROp_Select` (#2679) | 25 February 2023, 07:23:41 UTC |
| 85c1569 | Yong He | 24 February 2023, 22:33:32 UTC | Support dynamic dispatch a backward differentiable function. (#2678) Co-authored-by: Yong He <yhe@nvidia.com> | 24 February 2023, 22:33:32 UTC |
| 91694da | Yong He | 24 February 2023, 21:22:07 UTC | Fix differential type registration through non-differentiable type. (#2677) * Fix differential type registration through non-differentiable type. * More fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 24 February 2023, 21:22:07 UTC |
| bd6306c | Yong He | 24 February 2023, 18:01:47 UTC | More control flow simplifications. (#2673) * 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> | 24 February 2023, 18:01:47 UTC |
| e8c08e7 | Sai Praveen Bangaru | 23 February 2023, 03:22:26 UTC | Fixed hoisting of intermediate array & context vars (#2674) Also added legalization for loops | 23 February 2023, 03:22:26 UTC |
| 6eb0b4d | Sai Praveen Bangaru | 23 February 2023, 00:33:42 UTC | Reverse-mode AD fixes for loops with non-trivial break region (#2671) * 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> | 23 February 2023, 00:33:42 UTC |
| 0ef7aa8 | Yong He | 21 February 2023, 20:51:46 UTC | Fix transposeCall. (#2669) * Modify control-flow test case * Update reverse-control-flow-3.slang * Fix `transposeCall`. * Fix. --------- Co-authored-by: Sai Praveen Bangaru <31557731+saipraveenb25@users.noreply.github.com> Co-authored-by: Yong He <yhe@nvidia.com> | 21 February 2023, 20:51:46 UTC |
| 6bca0ec | Sai Praveen Bangaru | 21 February 2023, 16:37:15 UTC | Added support for simple while loops (#2667) * Added support for simple while loops * Fix support for while loops by changing logic to grab the loop update block | 21 February 2023, 16:37:15 UTC |
| e5bec2f | Ellie Hermaszewska | 21 February 2023, 03:46:21 UTC | Take into account the optimization level requested in TargetDesc (#2649) * Take into account the optimization level requested in TargetDesc Combines conflicting optimization levels by taking the maximum between them; as such they now each represent the lower bound on the eventual optimization level. Most of the changes are making this clear by s/optimizationLevel/minimumOptimizationLevel Closes https://github.com/shader-slang/slang/issues/2324 * Remove optimization level from TargetDesc | 21 February 2023, 03:46:21 UTC |
| 47715e6 | Yong He | 20 February 2023, 22:42:50 UTC | Miscellaneous backward autodiff fixes. (#2665) * 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> | 20 February 2023, 22:42:50 UTC |
| 8b05df4 | Yong He | 20 February 2023, 18:17:00 UTC | Add static for loop iteration inference. (#2659) | 20 February 2023, 18:17:00 UTC |
| a8da735 | Sai Praveen Bangaru | 18 February 2023, 00:03:52 UTC | Allocate N+1 arrays instead of N to avoid out-of-bounds access when unzipping loops (#2663) | 18 February 2023, 00:03:52 UTC |
| 92ccc8f | Sai Praveen Bangaru | 17 February 2023, 23:02:58 UTC | AD: More legacy type handling cleanup + user-defined reverse-mode fix (#2662) * WIP: Remove all legacy type checking * Fixed issue with user-defined backward derivatives not bypassing the AD process --------- Co-authored-by: Yong He <yonghe@outlook.com> | 17 February 2023, 23:02:58 UTC |
| 5cd39d1 | Sai Praveen Bangaru | 17 February 2023, 22:56:07 UTC | AD: Remove the original loop condition upon inversion (#2661) * Remove the original condition upon loop inversion (it's redundant, and causes out-of-bounds accesses) * minor fix (also removed the first loop check skip) * Cleanup unused insts * minor comment fix | 17 February 2023, 22:56:07 UTC |
| 0516073 | Yong He | 17 February 2023, 21:23:27 UTC | Fixed crash when lowering IR for no_diff struct member. (#2658) * Fixed crash when lowering IR for no_diff struct member. * Improve `setInsertBeforeOrdinaryInst` and `setInsertAfterOrdinaryInst`. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 17 February 2023, 21:23:27 UTC |
| 79049bc | Sai Praveen Bangaru | 17 February 2023, 21:22:47 UTC | Cleaned up legacy differential type handling + type casting bugfixes (#2660) | 17 February 2023, 21:22:47 UTC |
