Age | Commit message (Collapse) | Author | |
---|---|---|---|
2021-07-22 | vk_scheduler: Use locks instead of SPSC a queue | ReinUsesLisp | |
This tries to fix a data race where we'd wait forever for the GPU. | |||
2021-07-22 | vk_query_cache: Wait before reading queries | ReinUsesLisp | |
2021-07-22 | vk_master_semaphore: Use fetch_add to increase master semaphore tick | ReinUsesLisp | |
2021-07-22 | glasm: Add GLASM backend infrastructure | ReinUsesLisp | |
2021-07-22 | shader: ISET.X implementation | ameerj | |
2021-07-22 | gl_shader_cache: Remove code unintentionally committed | ReinUsesLisp | |
2021-07-22 | shader: Fixup SPIR-V emit header namespaces | ReinUsesLisp | |
2021-07-22 | Move SPIR-V emission functions to their own header | ReinUsesLisp | |
2021-07-22 | shader: Optimize NVN Fallthrough | FernandoS27 | |
2021-07-22 | shader: Stub SR_AFFINITY | FernandoS27 | |
2021-07-22 | shader: Implement Int32 SUATOM/SURED | ameerj | |
2021-07-22 | shader: Initial OpenGL implementation | ReinUsesLisp | |
2021-07-22 | spirv: Be aware of NAN unaware drivers | ReinUsesLisp | |
2021-07-22 | spirv: Add SSBO read fallbacks when no aliasing is available | ReinUsesLisp | |
2021-07-22 | spirv: Add OpKill fallback to demote | ReinUsesLisp | |
2021-07-22 | spirv: Do not enable ShaderLayer | ReinUsesLisp | |
This is enabled by an extension instead of the capability. | |||
2021-07-22 | spirv: Enable DemoteToHelperInvocationEXT only when supported | ReinUsesLisp | |
2021-07-22 | spirv: Use OriginLowerLeft when requested | ReinUsesLisp | |
2021-07-22 | spirv: Only add image operands mask when needed | ReinUsesLisp | |
2021-07-22 | spirv: Workaround image unsigned offset bug | ReinUsesLisp | |
Workaround bug on Nvidia's OpenGL SPIR-V compiler when using unsigned texture offsets. | |||
2021-07-22 | spirv: Add int8 and int16 capabilities only when supported | ReinUsesLisp | |
2021-07-22 | spirv: Add integer clamping workarounds | ReinUsesLisp | |
Workaround more bugs on Nvidia's OpenGL SPIR-V compiler. | |||
2021-07-22 | spirv: Implement int8 and int16 conversion fallbacks | ReinUsesLisp | |
2021-07-22 | spirv: Support OpenGL uniform buffers and change bindings | ReinUsesLisp | |
2021-07-22 | spirv: Desambiguate descriptor names | ReinUsesLisp | |
Worksaround a bug on Nvidia's OpenGL SPIR-V compiler where names are used for name matching. | |||
2021-07-22 | shader: Add OpenGL shader profile options | ReinUsesLisp | |
2021-07-22 | shader: Remove shader util | ReinUsesLisp | |
2021-07-22 | shader: Address feedback | FernandoS27 | |
2021-07-22 | shader: Implement VertexA stage | FernandoS27 | |
2021-07-22 | shader: Implement delegation of Exit to dispatcher on CFG | FernandoS27 | |
2021-07-22 | vk_graphics_pipeline: Fix texture buffer descriptors | ReinUsesLisp | |
2021-07-22 | shader: Fix IADD3.CC | ameerj | |
2021-07-22 | vk_scheduler: Allow command submission on worker thread | ReinUsesLisp | |
This changes how Scheduler::Flush works. It queues the current command buffer to be sent to the GPU but does not do it immediately. The Vulkan worker thread takes care of that. Users will have to use Scheduler::Flush + Scheduler::WaitWorker to get the previous behavior. Scheduler::Finish is unchanged. To avoid waiting on work never queued, Scheduler::Wait sends the current command buffer if that's what the caller wants to wait. | |||
2021-07-22 | vk_compute_pass: Fix -Wshadow warning | ReinUsesLisp | |
2021-07-22 | shader: Move pipeline cache logic to separate files | ReinUsesLisp | |
Move code to separate files to be able to reuse it from OpenGL. This greatly simplifies the pipeline cache logic on Vulkan. Transform feedback state is not yet abstracted and it's still intrusively stored inside vk_pipeline_cache. It will be moved when needed on OpenGL. | |||
2021-07-22 | vulkan: Defer descriptor set work to the Vulkan thread | ReinUsesLisp | |
Move descriptor lookup and update code to a separate thread. Delaying this removes work from the main GPU thread and allows creating descriptor layouts on another thread. This reduces a bit the workload of the main thread when new pipelines are encountered. | |||
2021-07-22 | vulkan: Rework descriptor allocation algorithm | ReinUsesLisp | |
Create multiple descriptor pools on demand. There are some degrees of freedom what is considered a compatible pool to avoid wasting large pools on small descriptors. | |||
2021-07-22 | vk_graphics_pipeline: Generate specialized pipeline config functions and ↵ | ReinUsesLisp | |
improve code | |||
2021-07-22 | shader: Accelerate pipeline transitions and use dirty flags for shaders | ReinUsesLisp | |
2021-07-22 | shader: Fix BFE s32 undefined check | ameerj | |
Our unit tests were hitting this exception. | |||
2021-07-22 | vk_compute_pipeline: Fix index comparison oversight on compute texture buffers | ReinUsesLisp | |
2021-07-22 | shader: Fix error checking in bitfieldExtract and implement bitfieldInsert ↵ | ReinUsesLisp | |
folding | |||
2021-07-22 | vulkan_device: Require shaderClipDistance and shaderCullDistance features | ReinUsesLisp | |
2021-07-22 | vk_graphics_pipeline: Guard against non-tessellation pipelines using patches | ReinUsesLisp | |
2021-07-22 | shader: Fix storage type when reading patches on tess control | ReinUsesLisp | |
2021-07-22 | shader: Fix VMNMX selector B | ReinUsesLisp | |
2021-07-22 | shader: Fix bugs and build issues on GCC | Rodrigo Locatti | |
2021-07-22 | shader: Fix render targets with null attachments | ReinUsesLisp | |
2021-07-22 | shader: Increase the maximum number of storage buffers | ReinUsesLisp | |
Compute shaders spill uniform buffers on storage buffers, increasing the expected number. | |||
2021-07-22 | shader: Remove identity removal pass for better build times | ReinUsesLisp | |