Making it easier to work with shaders https://git.yummers.dev/slang.git/atom?h=master 2025-10-10T17:09:24+00:00 2025-10-10T17:09:24+00:00 16-Bit-Dog 67922228+16-Bit-Dog@users.noreply.github.com 2025-10-10T17:09:24+00:00 urn:sha1:1e0908bd7107dfbdac912b693c3ab9bd6e1dc8b3 Fixes: https://github.com/shader-slang/slang/issues/7634 Duplicate of PR https://github.com/shader-slang/slang/pull/8052 Primary Changes: * Added `storeCoherent` and `loadCoherent` for coherent load/store via pointers. This is backed by `IRMemoryScopeAttr` which is an `IRAttr` attached to `IRLoad` and `IRStore` * Logic in `source\slang\slang-emit-spirv.cpp` for load/store emitting has been reworked to be less messy and more maintainable * Add to `hlsl.meta.slang` coop vector and coop matrix coherent load/store operations Secondary Changes: * Added a missing load/store test for coop matrix: `tests\cooperative-matrix\load-store-pointer.slang` --------- Co-authored-by: ArielG-NV <aglasroth@nvidia.com> Co-authored-by: ArielG-NV <159081215+ArielG-NV@users.noreply.github.com> Co-authored-by: slangbot <186143334+slangbot@users.noreply.github.com> Co-authored-by: Nathan V. Morrical <natemorrical@gmail.com> 2025-09-25T17:06:29+00:00 Jay Kwak 82421531+jkwak-work@users.noreply.github.com 2025-09-25T17:06:29+00:00 urn:sha1:f55f669d1badc94eb4eabf77a22a5994acca7a89 It appears that the inputType of the coopvec-mat-mul cannot be signed int32. It could be floating types or signed int32. Changing the tests to use uint32 instead of int32. The spec guarantees the following combinations and the rest should be queried at the runtime if it is supported by the HW. https://registry.khronos.org/vulkan/specs/latest/man/html/VkCooperativeVectorPropertiesNV.html#_description inputType | inputInterpretation | matrixInterpretation | biasInterpretation | resultType -- | -- | -- | -- | -- FLOAT16 | FLOAT16 | FLOAT16 | FLOAT16 | FLOAT16 UINT32 | SINT8_PACKED | SINT8 | SINT32 | SINT32 SINT8 | SINT8 | SINT8 | SINT32 | SINT32 FLOAT32 | SINT8 | SINT8 | SINT32 | SINT32 FLOAT16 | FLOAT_E4M3 | FLOAT_E4M3 | FLOAT16 | FLOAT16 FLOAT16 | FLOAT_E5M2 | FLOAT_E5M2 | FLOAT16 | FLOAT16 2025-09-02T23:43:48+00:00 James Helferty (NVIDIA) jhelferty@nvidia.com 2025-09-02T23:43:48+00:00 urn:sha1:f02b08490aa905f42a8d90381db84b1f8e409c0c Changes default for render-test to sm_6_5. Since sm_6_5 is the new default, remove the -use-dxil option, add -use-dxcb option Remove -use-dxil option from all test cases. Add -use-dxcb to two tests that needed it. Fixes #7611 2025-07-27T16:57:30+00:00 Jay Kwak 82421531+jkwak-work@users.noreply.github.com 2025-07-27T16:57:30+00:00 urn:sha1:d311efd9d6ddc620f5960c6fc10f25daa628df6c CPU tests were invalid because CPU target doesn't support float16_t. CUDA tests were failing due to minor precision error. 2025-07-16T00:48:30+00:00 ArielG-NV 159081215+ArielG-NV@users.noreply.github.com 2025-07-16T00:48:30+00:00 urn:sha1:439e025c1d3c58cc261c36f1e8d804a403b2856a * Changes Fix a coop-vec bug, fix incorrect test synax, clean up test, comment why some coop-vec tests are stil disabled * Changes Fix a coop-vec bug, fix incorrect test synax, clean up test, comment why some coop-vec tests are stil disabled * disable failing tests * push changes * add to failing GLSL test list 2025-07-11T23:39:21+00:00 ArielG-NV 159081215+ArielG-NV@users.noreply.github.com 2025-07-11T23:39:21+00:00 urn:sha1:d8d0b8969f731990820f25812f3d90ee4dd1ee75 * enable coop vec tests * disable tests which fail with reason * disable other failing tests * disable failing test * add to expected fail list * sort list 2025-06-26T03:09:57+00:00 Gangzheng Tong tonggangzheng@gmail.com 2025-06-26T03:09:57+00:00 urn:sha1:5afebcf02748384471a98858eedb685024f7f854 * Add matrix operand for OpCooperativeVectorMatrixMulAddNV * update tests to use the supported UINT32 input component type * Add MatrixCSignedComponentsKHR for coopVecMatMulAddPacked --------- Co-authored-by: Jay Kwak <82421531+jkwak-work@users.noreply.github.com> 2025-06-18T23:36:47+00:00 Yong He yonghe@outlook.com 2025-06-18T23:36:47+00:00 urn:sha1:777ac6cae9776cd2d28bd5a9f627261ba9740153 * Fix coopvector neg intrinsic. * Add test case. 2025-06-10T04:48:24+00:00 Mukund Keshava mkeshava@nvidia.com 2025-06-10T04:48:24+00:00 urn:sha1:d70da65a90ccd73439895a43b3958c0ea1441f35 * WiP: Add coopvec support for Optix * format code * fix minor issues * Fix review comments --------- Co-authored-by: slangbot <186143334+slangbot@users.noreply.github.com> 2025-06-06T16:26:02+00:00 Jay Kwak 82421531+jkwak-work@users.noreply.github.com 2025-06-06T16:26:02+00:00 urn:sha1:2203df78332f155374866b172887d2568422ed76 * Disable coopvec tests until we have the driver support * Remove conflicting agility sdk binaries