srkreddy1238 opened a new pull request, #18523: URL: https://github.com/apache/tvm/pull/18523
Introduces the below features over texture annotation - Lowering, codegen and runtime for texture. - image2d_array_t support - Added depth dimension allows more allocations using texture instead of falling back to buffer when the texture limits exceeds. - A comprehensive set of schedules for Adreno textures. - Texture packing of arbitrary types up to 128 bit (FP16-NCHW8c, INT8-NCHW16c ...etc.). - A clBufferDescriptor debug dump controlled by cmake options. While covering these features the below interfaces or passes or enhanced which need a review. - alloc_tensor: VDevice information is passed across these API's. The way of texture allocation is ```alloc_storage``` allocates buffer/image objects as requested followed by alloc_tensor being a view of any scope. This takes care of optimum utilization backing memory across different image objects or scopes. - Constants Saving: The memory scope information for model params is saved alont with ```runtime.Tensor```. This added 2 methods ``SetScope``` and ```GetScope``` to ```runtime::Tensor```. Accordingly Save/Load gets different magic to keep backward compatibility. - Static Memory Planing: Mostly port from Relay static memory planner with mixed mode allocator. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
