George Mitenkov 2ad7e1a301 [MLIR][SPIRVToLLVM] Conversion for global and addressof ...

Inital conversion of `spv._address_of` and `spv.globalVariable`.
In SPIR-V, the global returns a pointer, whereas in LLVM dialect
the global holds an actual value. This difference is handled by
`spv._address_of` and `llvm.mlir.addressof`ops that both return
a pointer. Moreover, only current invocation is in conversion's
scope.

Reviewed By: antiagainst, mravishankar

Differential Revision: https://reviews.llvm.org/D84626

2020-08-12 09:41:14 +03:00

..

AffineToStandard

…

AVX512ToLLVM

…

GPUCommon

[MLIR] Adding gpu.host_register op and lower it to a runtime call.

2020-08-10 22:46:17 +02:00

GPUToNVVM

[mlir] take MLIRContext instead of LLVMDialect in getters of LLVMType's

2020-08-06 11:05:40 +02:00

GPUToROCDL

…

GPUToSPIRV

[mlir][spirv] Add correct handling of Kernel and Addresses capabilities

2020-08-07 12:29:21 -07:00

GPUToVulkan

[mlir] take MLIRContext instead of LLVMDialect in getters of LLVMType's

2020-08-06 11:05:40 +02:00

LinalgToLLVM

…

LinalgToSPIRV

…

LinalgToStandard

[mlir][Linalg] Conv ops lowering to std calls added.

2020-08-04 07:12:58 +00:00

SCFToGPU

…

SCFToSPIRV

…

SCFToStandard

…

ShapeToSCF

[MLIR][Shape] Lower shape.broadcast to scf

2020-08-03 08:20:14 +00:00

ShapeToStandard

[MLIR][Shape] Limit shape.rank lowering to its extent tensor variant

2020-07-30 11:43:08 +00:00

SPIRVToLLVM

[MLIR][SPIRVToLLVM] Conversion for global and addressof

2020-08-12 09:41:14 +03:00

StandardToLLVM

[MLIR] Adding gpu.host_register op and lower it to a runtime call.

2020-08-10 22:46:17 +02:00

StandardToSPIRV

[mlir][StandardToSPIRV] Use spv.UMod for index re-calculation

2020-08-05 14:52:04 -04:00

VectorToLLVM

[mlir] Fix mlir build break due to warning when NDEBUG is not set

2020-08-10 15:35:02 -07:00

VectorToROCDL

[mlir] Remove most uses of LLVMDialect::getModule

2020-08-06 10:54:30 +02:00

VectorToSCF

…

CMakeLists.txt

…

PassDetail.h

…