Mahesh Ravishankar 4ced99c085 Enhance GPU To SPIR-V conversion to support builtins and load/store ops. ... To support a conversion of a simple load-compute-store kernel from GPU dialect to SPIR-V dialect, the conversion of operations like "gpu.block_dim", "gpu.thread_id" which allow threads to get the launch conversion is needed. In SPIR-V these are specified as global variables with builin attributes. This CL adds support to specify builtin variables in SPIR-V conversion framework. This is used to convert the relevant operations from GPU dialect to SPIR-V dialect. Also add support for conversion of load/store operation in Standard dialect to SPIR-V dialect. To simplify the conversion add a method to build a spv.AccessChain operation that automatically determines the return type based on the base pointer type and the indices provided. PiperOrigin-RevId: 265718525		2019-08-27 10:50:23 -07:00
..
GPUToCUDA	ConvertLaunchFuncToCudaCalls: use LLVM dialect globals	2019-08-20 07:52:01 -07:00
GPUToNVVM	Change the attribute dictionary syntax to separate name and value with '='.	2019-06-25 19:06:34 -07:00
GPUToSPIRV	Enhance GPU To SPIR-V conversion to support builtins and load/store ops.	2019-08-27 10:50:23 -07:00
LoopsToGPU	Replace linalg.for by loop.for	2019-07-16 13:44:57 -07:00
VectorToLLVM	LLVM dialect: prefix operations that correspond to intrinsics with "intr."	2019-08-20 06:38:52 -07:00
convert-to-cfg.mlir	Extract std.for std.if and std.terminator in their own dialect	2019-07-16 13:43:18 -07:00