bfd3f39 | Lin Hsu | 08 November 2023, 03:04:36 UTC | Fix HitObject::GetInstanceIndex/ID() for glsl/spirv (#3315) Co-authored-by: Yong He <yonghe@outlook.com> | 08 November 2023, 03:04:36 UTC |
0f2578d | Yong He | 08 November 2023, 03:03:52 UTC | Add `IRThisTypeWitness` to stand in for witness lookups inside an interface definition. (#3316) Co-authored-by: Yong He <yhe@nvidia.com> | 08 November 2023, 03:03:52 UTC |
4219419 | Neil Bickford | 07 November 2023, 19:47:18 UTC | CUDA: Fixes for NVRTC 12.x and warp mask ambiguity; adds CC 8.x warp reduction intrinsics. (#3314) * CUDA: Fixes for NVRTC 12.x, warp mask ambiguity; add reduction partial specializations. * Fixes running NVRTC on CUDA 12 without a specified profile (used in testing, e.g. `slang-test -api cuda -category wave`) * Fixes mask ambiguity between getting the lane index from threadId.x and a full mask of threads. * Adds partial specializations for compute capability 8.x warp reduction intrinsics. * Fix formatting | 07 November 2023, 19:47:18 UTC |
46529df | Yong He | 06 November 2023, 22:40:38 UTC | Fix ICE when lowering an associatedtype declref from an derived interface. (#3312) * Fix ICE when lowering an associatedtype declref from an derived interface. * Fixes. * Fix test. * Fix GLSL/SPIRV image subscript swizzle store regression. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 06 November 2023, 22:40:38 UTC |
da9e0ad | Ellie Hermaszewska | 06 November 2023, 21:21:49 UTC | Correctly pass values from the conditional block to the loop during inversion (#3311) Co-authored-by: Yong He <yonghe@outlook.com> | 06 November 2023, 21:21:49 UTC |
79677b8 | Yong He | 04 November 2023, 00:10:09 UTC | Add SubgroupQuad intrinsics for glsl/spirv. (#3310) * Add SubgroupQuad intrinsics for glsl/spirv. * Fix. * Add test for quad intrinsics. * fix. * improve diagnostics text. * Fix. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 04 November 2023, 00:10:09 UTC |
111de4d | Yong He | 03 November 2023, 21:40:18 UTC | Update 07-autodiff.md | 03 November 2023, 21:40:18 UTC |
cc22270 | Yong He | 03 November 2023, 19:49:23 UTC | Add more diagnostics on invalid custom derivative use. (#3309) * Add more diagnostics on invalid custom derivative use. * cleanup. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 03 November 2023, 19:49:23 UTC |
911a440 | Yong He | 02 November 2023, 21:54:22 UTC | Fix crash when writing to `no_diff` out parameter. (#3308) * Fix crash when writing to `no_diff` out parameter. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 02 November 2023, 21:54:22 UTC |
72e95f2 | Ellie Hermaszewska | 02 November 2023, 20:00:16 UTC | Several spirv intrinsics and small fix (#3307) * spirv intrinsic for faceforward * spirv intrinsic for fwidth * spirv intrinsic for modf * spirv intrinsic for nonuniformresourceindex * spirv intrinsic for transpose * Make sure address space matches for OpAccessChain * Correct placement for OpDecorate instructions in spirv asm blocks | 02 November 2023, 20:00:16 UTC |
e712ebd | Yong He | 02 November 2023, 05:49:30 UTC | Add mnemonic parsing for `intrinsic_type` modifier. (#3306) Co-authored-by: Yong He <yhe@nvidia.com> | 02 November 2023, 05:49:30 UTC |
6aca381 | Yong He | 02 November 2023, 04:42:12 UTC | Parameter binding and gfx fixes. (#3302) * Parameter binding and gfx fixes. * Add diagnostics on entry point parameters. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 02 November 2023, 04:42:12 UTC |
532c432 | Ellie Hermaszewska | 02 November 2023, 03:22:14 UTC | Add OpDot for spirv (#3304) Co-authored-by: Yong He <yonghe@outlook.com> | 02 November 2023, 03:22:14 UTC |
12e69ff | skallweitNV | 01 November 2023, 16:48:44 UTC | add support for dx 6.7 profiles (#3299) | 01 November 2023, 16:48:44 UTC |
1ac6638 | Yong He | 26 October 2023, 23:19:02 UTC | Disable frexp test on swiftshader. (#3294) * Disable frexp test on swiftshader. * Fix windows release script. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 26 October 2023, 23:19:02 UTC |
aed3bd6 | Yong He | 26 October 2023, 22:36:25 UTC | Remove use of `::set-output` in github actions. (#3293) Co-authored-by: Yong He <yhe@nvidia.com> | 26 October 2023, 22:36:25 UTC |
02e6c6b | Yong He | 26 October 2023, 22:04:25 UTC | Update to Bearer/tap/gon for macos notarization. (#3292) Co-authored-by: Yong He <yhe@nvidia.com> | 26 October 2023, 22:04:25 UTC |
41e17d3 | Ellie Hermaszewska | 26 October 2023, 22:03:34 UTC | Make the exponent return value from frexp int (#3284) * Make the exponent return value from frexp int Fixes https://github.com/shader-slang/slang/issues/3282 * Update slang-llvm. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 26 October 2023, 22:03:34 UTC |
bee74b1 | Yong He | 26 October 2023, 21:01:26 UTC | Add more diagnostics around use of custom derivatives. (#3291) Co-authored-by: Yong He <yhe@nvidia.com> | 26 October 2023, 21:01:26 UTC |
927d176 | Yong He | 26 October 2023, 17:45:08 UTC | Fix generic specialization bug. (#3290) * Fix generic specialization bug. * Update test. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 26 October 2023, 17:45:08 UTC |
4572976 | Sai Praveen Bangaru | 25 October 2023, 20:31:49 UTC | Update autodiff-texture example with one that auto-diffs a reference impl. (#3288) | 25 October 2023, 20:31:49 UTC |
1a8216b | Ellie Hermaszewska | 25 October 2023, 19:22:01 UTC | Fix warnings for gcc 12.3 (#3286) * Silence a few gcc out of bounds warnings * Search upwards from executable for prelude directory instead of assuming depth * comment wording * Check return values of read and write * Correct path to vulkan headers in gfx * Correct diagnostic on missing file in slang-embed * Do not use absolute path to libraries in test-context.cpp --------- Co-authored-by: Yong He <yonghe@outlook.com> | 25 October 2023, 19:22:01 UTC |
e04abb5 | Yong He | 25 October 2023, 19:21:35 UTC | Fix single iteration loop detection logic. (#3287) Co-authored-by: Yong He <yhe@nvidia.com> | 25 October 2023, 19:21:35 UTC |
0175346 | Yong He | 25 October 2023, 14:50:31 UTC | Use GLSL Scalar layout for vulkan device. (#3285) Co-authored-by: Yong He <yhe@nvidia.com> | 25 October 2023, 14:50:31 UTC |
5dc3c2f | Yong He | 25 October 2023, 14:50:14 UTC | Add `IArray`. (#3281) * Initial support for generic interfaces. * Cleanup. * Add generic syntax for interfaces. * Add `IArray`. * Fix. * Fix. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 25 October 2023, 14:50:14 UTC |
f8bf75c | Yong He | 25 October 2023, 14:45:23 UTC | Support generic interfaces. (#3278) * Initial support for generic interfaces. * Cleanup. * Add generic syntax for interfaces. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 25 October 2023, 14:45:23 UTC |
d8f4c94 | Sai Praveen Bangaru | 21 October 2023, 01:21:30 UTC | Fix issue with transposing `IRMakeVector` with non-singleton operands (#3280) | 21 October 2023, 01:21:30 UTC |
d001a7b | Yong He | 19 October 2023, 10:49:42 UTC | Add a tool to dump/replay compute pipeline creation from gfx. (#3275) * Add a tool to dump/replay compute pipeline creation from gfx. * Fix x86 build. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 19 October 2023, 10:49:42 UTC |
7826afc | Ellie Hermaszewska | 17 October 2023, 22:26:00 UTC | Type layouts for structured buffers with counters (#3269) * More tests for append structured buffer * Append and Consume structured buffer tests for DX12 * neaten * test wobble * Add counter layout information to append/consume structured buffers * add getRWStructuredBufferType * Correct definition of get size for append/consume structured buffers * tweak append structured buffer test * Allow initializing counter buffer in render test * vulkan test for consume structured buffer * Handle null counterVarLayout in getExplicitCounterBindingRangeOffset * remove dead code * Implement atomic counter increment/decrement for spirv * explicit spirv test * Add missing check on result * Hold on to counter resources --------- Co-authored-by: Yong He <yonghe@outlook.com> | 17 October 2023, 22:26:00 UTC |
0a3683d | Yong He | 16 October 2023, 23:17:56 UTC | Run Falcor Tests (#3270) * Run Falcor Tests * Update test config. * update config. * fix. * fix * fix. * skip slow test. * Fix ci config. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 16 October 2023, 23:17:56 UTC |
d4b8edf | Yong He | 13 October 2023, 20:49:02 UTC | Update a1-04-interop.md | 13 October 2023, 20:49:02 UTC |
edf90f5 | Yong He | 13 October 2023, 20:42:17 UTC | Update a1-04-interop.md (#3277) | 13 October 2023, 20:42:17 UTC |
078cf8e | Yong He | 13 October 2023, 20:30:57 UTC | Add documentation on target intrinsics. (#3276) Co-authored-by: Yong He <yhe@nvidia.com> | 13 October 2023, 20:30:57 UTC |
c701013 | Yong He | 12 October 2023, 19:20:34 UTC | Add HitObject.GetWorldToObject. (#3273) * Add HitObject.GetWorldToObject. * fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 12 October 2023, 19:20:34 UTC |
459572c | Ellie Hermaszewska | 11 October 2023, 17:53:00 UTC | Small warnings and bugs (#3272) * Correctly use removeTrivialSingleIterationLoops during simplification * remove unused variables * Fix invalid fallthrough --------- Co-authored-by: Yong He <yonghe@outlook.com> | 11 October 2023, 17:53:00 UTC |
61132c7 | Yong He | 11 October 2023, 05:07:56 UTC | Report spirv-opt time. (#3271) * Report spirv-opt time. * Removing timing logic in `loadModule`. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 11 October 2023, 05:07:56 UTC |
cd9a8b2 | Yong He | 11 October 2023, 00:35:26 UTC | Update README.md | 11 October 2023, 00:35:26 UTC |
fb91955 | Yong He | 09 October 2023, 23:53:51 UTC | Update slang-glslang binaries to v13.0.0.x-g (#3268) * Update slang-glslang binaries to v13.0.0.x-g * Update tests. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 09 October 2023, 23:53:51 UTC |
a83a8b6 | Yong He | 09 October 2023, 22:07:26 UTC | Update prebuilt glslang binaries. (#3267) * Update prebuilt glslang binaries. * Update spirv-disassembling logic in slang-glslang. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 09 October 2023, 22:07:26 UTC |
67e186f | Yong He | 09 October 2023, 21:03:43 UTC | Run curated spirv-opt passes through slang-glslang. (#3266) * Run curated spirv-opt passes through slang-glslang. * Cleanup. * Replace spirv-dis downstream compiler with glslang. * delete slang-spirv-opt.cpp. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 09 October 2023, 21:03:43 UTC |
17c7163 | Yong He | 06 October 2023, 21:03:18 UTC | Small type system fixes. (#3265) | 06 October 2023, 21:03:18 UTC |
4547125 | Yong He | 06 October 2023, 00:05:20 UTC | Add intellisense support for spirv_asm blocks. (#3264) Co-authored-by: Yong He <yhe@nvidia.com> | 06 October 2023, 00:05:20 UTC |
441e13e | Sai Praveen Bangaru | 05 October 2023, 16:52:49 UTC | Various AD Fixes (#3263) * Various fixes * Remove unused parameter * Update slang-ir-loop-unroll.cpp --------- Co-authored-by: Yong He <yonghe@outlook.com> | 05 October 2023, 16:52:49 UTC |
65751ce | Ellie Hermaszewska | 05 October 2023, 16:49:19 UTC | Check for extension support before enabling a feature (#3262) Co-authored-by: Yong He <yonghe@outlook.com> | 05 October 2023, 16:49:19 UTC |
8eb504f | Yong He | 05 October 2023, 16:45:54 UTC | Use designated compiler ID in SPIRV backend. (#3261) Co-authored-by: Yong He <yhe@nvidia.com> | 05 October 2023, 16:45:54 UTC |
9572c60 | Yong He | 04 October 2023, 19:16:35 UTC | Add `kIROp_BitOr` to known non-differentiable inst list. (#3259) Co-authored-by: Yong He <yhe@nvidia.com> | 04 October 2023, 19:16:35 UTC |
ac886fd | Yong He | 04 October 2023, 18:20:35 UTC | SPIRV compiler performance fixes. (#3258) * SPIRV compiler performance fixes. * Cleanup. * update project files * Cleanup debug code. * Make redundancy removal non-recursive. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 04 October 2023, 18:20:35 UTC |
d87493a | Yong He | 02 October 2023, 22:39:34 UTC | More direct-SPIRV fixes. (#3257) * More direct-SPIRV fixes. * Fix array-reg-to-mem. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 02 October 2023, 22:39:34 UTC |
cea230b | Ellie Hermaszewska | 02 October 2023, 16:05:39 UTC | Use const ref for mesh payload (#3254) * Use const ref for mesh payload * Test mesh payload hlsl output | 02 October 2023, 16:05:39 UTC |
ccf2611 | Yong He | 02 October 2023, 10:33:58 UTC | Add SPIRV intrinsics for ShaderExecutionReordering and RW/Buffer. (#3252) * Add SPIRV intrinsics for ShaderExecutionReordering. * Add intrinsics for `Buffer` and `RWBuffer`. * Various spirv fixes. * Marshal bool vector type. * Inline global constants + OpFOrdNotEqual->OpFUnordNotEqual. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 02 October 2023, 10:33:58 UTC |
6138de5 | jsmall-nvidia | 29 September 2023, 23:10:22 UTC | Fix for problem with OrderedHashSet causing crash (#3251) * Fix for problem with OrderedHashSet causing crashes during running tests on on g++ 7.3 * Fix typo | 29 September 2023, 23:10:22 UTC |
f20f4e2 | Yong He | 29 September 2023, 19:01:36 UTC | Add `requirePrelude()` intrinsic function. (#3250) * Add `requirePrelude()` intrinsic function. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 29 September 2023, 19:01:36 UTC |
af61737 | Yong He | 29 September 2023, 01:08:06 UTC | [Direct SPIRV]: ray tracing pipeline intrinsics. (#3244) * Use a dedicated inst opcode to retrieve ray payload locations. * [Direct SPIRV]: ray tracing pipeline intrinsics. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 29 September 2023, 01:08:06 UTC |
b7d318f | Yong He | 29 September 2023, 01:07:40 UTC | Support `constref` parameters passing. (#3249) * Support `constref` parameters passing. * Fix. * Fix. * Add test and diagnostic on mix use of __constref and no_diff. * check for [constref] on differentiable member method. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 29 September 2023, 01:07:40 UTC |
e723894 | Sai Praveen Bangaru | 28 September 2023, 06:19:54 UTC | Fix `TensorView.store()` definition (#3248) | 28 September 2023, 06:19:54 UTC |
e698b4a | Sai Praveen Bangaru | 28 September 2023, 05:45:09 UTC | Remove `[NoSideEffect]` from `DiffTensorView.store()` (#3247) Co-authored-by: Yong He <yonghe@outlook.com> | 28 September 2023, 05:45:09 UTC |
e710fac | Yong He | 28 September 2023, 05:39:22 UTC | Fix a bug in `canInstHaveSideEffectAtAddress`. (#3246) Co-authored-by: Yong He <yhe@nvidia.com> | 28 September 2023, 05:39:22 UTC |
12e8ce5 | Yong He | 28 September 2023, 05:35:58 UTC | Fix regression on no_diff type transcription. (#3245) Co-authored-by: Yong He <yhe@nvidia.com> | 28 September 2023, 05:35:58 UTC |
9833ff9 | Yong He | 27 September 2023, 18:46:29 UTC | Fix `isMovableInst`. (#3243) Co-authored-by: Yong He <yhe@nvidia.com> | 27 September 2023, 18:46:29 UTC |
8326248 | Ellie Hermaszewska | 27 September 2023, 18:46:03 UTC | WIP Mesh shaders for SPIR-V (#3226) * SPIR-V impl for SetMeshOutputCounts and DispatchMesh * Unsightly fix for legalization ordering differences between GLSL and SPIR-V * spelling * Start a new block after terminating one in the OpEmitMeshTasksExt SPIR-V asm block * Emit mesh shader decorations in SPIR-V * Mesh and task shader stages for spir-v * Output explicit gl builtins for spir-v * Be more hygenic when SOAizing mesh outputs * Do not create builtin paramter block for spirv mesh outputs * Pass mesh payloads around by ref * comment * less expected failure * remove unused * Add spirv op * Correct type query for default flat modifier --------- Co-authored-by: Yong He <yonghe@outlook.com> | 27 September 2023, 18:46:03 UTC |
771b3ef | Yong He | 27 September 2023, 18:36:31 UTC | Avoid make copies of __ref parameters when doing autodiff. (#3242) Co-authored-by: Yong He <yhe@nvidia.com> | 27 September 2023, 18:36:31 UTC |
ebe8dde | Yong He | 27 September 2023, 06:56:06 UTC | Various SPIRV fixes. (#3231) * Various SPIRV fixes. - Geometry shader support (WIP). - Fix texture get dimension and load. - Fold global GetElement(MakeArray/MakeVector) insts. - Call spvopt to inline all functions. - Translate OpImageSubscript. - Emit struct member names and global variable names. - Fix lowering of OpBitNot -> OpNot, instead of OpBitReverse. * Fix test. * Fix geometry shader. * Fix geometry shader emit. * Add atomic Image access test. * Fix tests. * don't fail if spirv-opt fails. * Update comments. * Fix test. * Cleanups. * indentation --------- Co-authored-by: Yong He <yhe@nvidia.com> Co-authored-by: Ellie Hermaszewska <ellieh@nvidia.com> | 27 September 2023, 06:56:06 UTC |
c5c8cfb | Sai Praveen Bangaru | 27 September 2023, 00:50:13 UTC | Handle the case where the parent if-else region's after-block is unreachable. (#3241) Also added a test for this. Co-authored-by: Yong He <yonghe@outlook.com> | 27 September 2023, 00:50:13 UTC |
a18dca2 | jsmall-nvidia | 26 September 2023, 19:40:22 UTC | Fix for epoch/ASTBuilder* nullptr issue (#3240) * Fix issue with failing tests tests/serialization/serialized-module-test.slang tests/serialization/extern/extern-test.slang * Fix issue with session destruction order on Session. * Improve comment. | 26 September 2023, 19:40:22 UTC |
6c99194 | Sai Praveen Bangaru | 25 September 2023, 22:30:34 UTC | Add test for vector-element contiguity error (#3235) | 25 September 2023, 22:30:34 UTC |
56c4a8c | Sai Praveen Bangaru | 25 September 2023, 22:29:35 UTC | Update a1-02-slangpy.md (#3237) | 25 September 2023, 22:29:35 UTC |
2e76151 | jsmall-nvidia | 25 September 2023, 15:52:18 UTC | Fix for threading issues around global session & epoch ids. (#3232) * Fix for threading issues around global session & epoch ids. * Make m_epochId atomic for thread visibility. | 25 September 2023, 15:52:18 UTC |
ab04bd0 | Sai Praveen Bangaru | 23 September 2023, 16:11:45 UTC | More `slangpy` features + polishing (#3233) * Update user-guide with new slangpy features * More polishing of new slangpy docs * Update a1-02-slangpy.md * Only require contiguity for vector element types * Added `loadOnce/storeOnce` and subscript operations * Added docs, `DiffTensorView.dims()` & `DiffTensorView.stride(uint)` * Add constructors, remove storeOnce/loadOnce test * Adjusted intrinsic definitions | 23 September 2023, 16:11:45 UTC |
263f807 | Yong He | 21 September 2023, 23:03:16 UTC | Update a1-02-slangpy.md (#3228) | 21 September 2023, 23:03:16 UTC |
e31a967 | Yong He | 21 September 2023, 23:02:04 UTC | Revert inlining change in #3217. (#3229) Co-authored-by: Yong He <yhe@nvidia.com> | 21 September 2023, 23:02:04 UTC |
5b2eb06 | Yong He | 21 September 2023, 21:00:48 UTC | Various slangpy fixes. (#3227) * 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> | 21 September 2023, 21:00:48 UTC |
af8ce68 | Yong He | 21 September 2023, 17:39:19 UTC | Misc SPIRV fixes. (#3220) Co-authored-by: Yong He <yhe@nvidia.com> | 21 September 2023, 17:39:19 UTC |
85d40ed | Ellie Hermaszewska | 21 September 2023, 16:45:53 UTC | Emit loads for array resources correctly (#3214) * Emit loads for array resources correctly * Put arrays of UniformConstant resources in UniformConstant * less expected failure * This code was actually used --------- Co-authored-by: Yong He <yonghe@outlook.com> | 21 September 2023, 16:45:53 UTC |
335ca78 | Ellie Hermaszewska | 21 September 2023, 16:43:15 UTC | move global initializers to entry point for spirv (#3225) * move global initializers to entry point for spirv * less expected failure --------- Co-authored-by: Yong He <yonghe@outlook.com> | 21 September 2023, 16:43:15 UTC |
4810dbd | Ellie Hermaszewska | 21 September 2023, 16:42:17 UTC | Do not move movable insts in fuse-satcoop (#3221) * Do not move movable insts in fuse-satcoop * Add case for IRCall in isMovableInst --------- Co-authored-by: Yong He <yonghe@outlook.com> | 21 September 2023, 16:42:17 UTC |
65e1a5b | Ellie Hermaszewska | 21 September 2023, 15:31:03 UTC | fix warnings (#3224) * Remove unused variable * Remove unused variable * Remove unused if bindings | 21 September 2023, 15:31:03 UTC |
c31f456 | Yong He | 21 September 2023, 05:28:51 UTC | Update a1-02-slangpy.md (#3223) | 21 September 2023, 05:28:51 UTC |
c04f5b4 | Sai Praveen Bangaru | 21 September 2023, 05:15:29 UTC | Update user-guide with new slangpy features (#3222) | 21 September 2023, 05:15:29 UTC |
29c318b | Sai Praveen Bangaru | 21 September 2023, 00:54:10 UTC | Move force inlining step to before `processAutodiffCalls` (and run in loop) (#3217) * Move auto-diff force inlining step to before `processAutodiffCalls` * Fix `replaceUsesWith` to handle existing inst defined after current use. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 21 September 2023, 00:54:10 UTC |
5b23870 | Sai Praveen Bangaru | 20 September 2023, 20:47:56 UTC | Redirect destination-driven lowering logic to regular lowering for `SelectExpr` (#3219) * Redirect destination-driven lowering logic to regular lowering for select expr * Add test | 20 September 2023, 20:47:56 UTC |
25c79ad | Sai Praveen Bangaru | 20 September 2023, 19:22:51 UTC | Fix `atan2` stdlib derivative + add tests. (#3218) * Fix atan2 stdlib derivative. Add tests for atan2 * Create dstdlib-atan2.slang.expected.txt * Update tests | 20 September 2023, 19:22:51 UTC |
73292d9 | Yong He | 20 September 2023, 10:30:27 UTC | Direct SPIRV: Rasterization pipeline tests. (#3216) * Direct SPIRV: Rasterization pipeline tests. * Fixup. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 20 September 2023, 10:30:27 UTC |
739c3a7 | Sai Praveen Bangaru | 19 September 2023, 22:51:24 UTC | Added `[AutoPyBindCUDA]` for automatic kernel binding + `[PyExport]` for exporting type information (#3209) * Initial: add a DiffTensor impl * Auto-binding and diff tensor implementations now work * Refactored diff-tensor implementation + added py-export for struct types * Cleanup * Update slang-ir-pytorch-cpp-binding.cpp * Updated test names * Update autodiff-data-flow.slang.expected * Add more versions of load/store & default generic args for DiffTensorView. * Add diagnostic for default generic arg and more tests * Add more `[AutoPyBind]` tests | 19 September 2023, 22:51:24 UTC |
359fdc9 | Ellie Hermaszewska | 19 September 2023, 16:56:12 UTC | Handle combined image and samplers in spirv (#3213) * Handle combined image and samplers in spirv * less expected failure --------- Co-authored-by: Yong He <yonghe@outlook.com> | 19 September 2023, 16:56:12 UTC |
da30696 | Ellie Hermaszewska | 19 September 2023, 16:47:53 UTC | Memoize types in spirv asm blocks (#3215) * Neaten emitInst * Memoize types in spirv asm blocks * less expected failure | 19 September 2023, 16:47:53 UTC |
6542d47 | Yong He | 19 September 2023, 14:21:17 UTC | Direct SPIRV ParameterBlock fix. (#3212) Co-authored-by: Yong He <yhe@nvidia.com> | 19 September 2023, 14:21:17 UTC |
d1efc69 | Yong He | 19 September 2023, 03:46:57 UTC | Use target-dependent pointer size in natural layout. (#3210) Co-authored-by: Yong He <yhe@nvidia.com> | 19 September 2023, 03:46:57 UTC |
95fcf65 | Sai Praveen Bangaru | 19 September 2023, 03:45:44 UTC | Fix loop inversion issue that caused ordinary blocks with multiple predecessors (#3211) * Add test case for while loop * Fix loop inversion issue that caused ordinary blocks with multiple predecessors The original version can leave the CFG in an invalid state with `e4` not being a break block or merge point, but having multiple predecessors. The updated version creates a separate jump block for each break instruction to avoid this issue. * Fixup tests | 19 September 2023, 03:45:44 UTC |
e884b15 | Yong He | 18 September 2023, 18:46:53 UTC | Fix highlighting of generic types without argument. (#3208) Co-authored-by: Yong He <yhe@nvidia.com> | 18 September 2023, 18:46:53 UTC |
8bcffcc | Yong He | 18 September 2023, 13:12:30 UTC | Use direct spirv in hello-world example. (#3207) * Use direct spirv in hello-world example. * Use vulkan 1.1 * Use vulkan 1.2. * fix. * Fix test. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 18 September 2023, 13:12:30 UTC |
95b470f | Yong He | 13 September 2023, 23:20:38 UTC | Add missing RayQuery intrinsics. (#3206) Co-authored-by: Yong He <yhe@nvidia.com> | 13 September 2023, 23:20:38 UTC |
c12779b | Ellie Hermaszewska | 13 September 2023, 16:56:53 UTC | Fix build with --enable-xlib=false (#3203) * Fix build with --enable-xlib=false * Correct brace location --------- Co-authored-by: Yong He <yonghe@outlook.com> | 13 September 2023, 16:56:53 UTC |
894237e | SirKero | 13 September 2023, 16:56:00 UTC | Add gfx d3d12 TextureCube UAV case (#3205) Co-authored-by: Yong He <yonghe@outlook.com> | 13 September 2023, 16:56:00 UTC |
d2466a6 | Yong He | 13 September 2023, 16:48:32 UTC | Add all RayQuery SPIRV Intrinsics. (#3204) * Add all RayQuery SPIRV Intrinsics. * Fix * Fix. * fix. * Fix. * Fix. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 13 September 2023, 16:48:32 UTC |
c0a77c3 | Yong He | 12 September 2023, 17:49:16 UTC | Direct SPIRV for RayTracing Inline. (#3201) * Direct SPIRV for RayTracing Inline. * Fix. * Cleanup. * Fix compile error. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 12 September 2023, 17:49:16 UTC |
3f4081d | Ellie Hermaszewska | 12 September 2023, 09:44:34 UTC | Correctly identify the number of operands to image sampling operands in SPIR-V (#3200) * Correctly identify the number of operands to image sampling operands in SPIR-V * Neaten imageoperands warning test * Neaten imageoperands warning test | 12 September 2023, 09:44:34 UTC |
09854a4 | Ellie Hermaszewska | 12 September 2023, 03:13:11 UTC | Add Mesh and Task shader support to GFX (#3190) * Bump vulkan headers Also just use vulkan-headers as a submodule * Add drawMeshTasks to gfx graphics pipelines * Add DispatchMesh overload with no payload, with GLSL intrinsic * Require spirv 1.4 for mesh shaders * Add vulkan mesh shader feature discovery * Add mesh shader stage bits to vk-util * Add mesh and task shader support to render-test * Add mesh and task tests * Preserve "payload" specifier in task shaders * Add mesh shader pipeline support to gfx * Add TODO * Add numThreads attribute for amplification stage * Add payload to task shader test * Drop dependency on d3dx12 * Allow passing payloads from task to mesh shaders * regenerate vs projects * check DispatchMesh name correctly * Add mesh shader tests to failing tests * Detect wave-ops feature on vulkan * Add fuse-product to expected failures This fails because the global varaible `count` is not initialized * Add required extension to WaveMaskMatch SPIR-V impl * Remove meshShader member from pipeline desc * Identify mesh shader support on d3d12 | 12 September 2023, 03:13:11 UTC |
87bb0b5 | Sai Praveen Bangaru | 09 September 2023, 00:12:25 UTC | Add check for contiguous tensors (#3199) Otherwise, this can lead to undetected scenario where the strides are incorrect for non-scalar types (`float2`, `float3`, etc..) Users must call `tensor = tensor.contiguous()` on the inputs to avoid this error. | 09 September 2023, 00:12:25 UTC |
26a0b3e | Yong He | 08 September 2023, 22:57:00 UTC | Fix attribute highlighting + language server crash. (#3198) * Fix attribute highlighting + language server crash. * Fix wave intrinsic. * Fix. * Fix. --------- Co-authored-by: Yong He <yhe@nvidia.com> | 08 September 2023, 22:57:00 UTC |
26a7cf7 | Sai Praveen Bangaru | 08 September 2023, 21:03:14 UTC | Remove unsupported torch types + add bool type. (#3197) Co-authored-by: Yong He <yonghe@outlook.com> | 08 September 2023, 21:03:14 UTC |