Tung Le Duc e5957ac3d7 [mlir] Fix the wrong computation of dynamic strides for lowering AllocOp to LLVM ... Leftover change from before the MLIR merge, reviewed at accepted at https://github.com/tensorflow/mlir/pull/338.		2019-12-28 23:33:28 +01:00
..
AffineToStandard	NFC: Replace ValuePtr with Value and remove it now that Value is value-typed.	2019-12-23 16:36:53 -08:00
GPUCommon	NFC: Replace ValuePtr with Value and remove it now that Value is value-typed.	2019-12-23 16:36:53 -08:00
GPUToCUDA	NFC: Replace ValuePtr with Value and remove it now that Value is value-typed.	2019-12-23 16:36:53 -08:00
GPUToNVVM	NFC: Replace ValuePtr with Value and remove it now that Value is value-typed.	2019-12-23 16:36:53 -08:00
GPUToROCDL	Adjust License.txt file to use the LLVM license	2019-12-23 15:33:37 -08:00
GPUToSPIRV	Refactor the way that pass options are specified.	2019-12-23 16:48:22 -08:00
LinalgToLLVM	NFC: Replace ValuePtr with Value and remove it now that Value is value-typed.	2019-12-23 16:36:53 -08:00
LoopToStandard	NFC: Replace ValuePtr with Value and remove it now that Value is value-typed.	2019-12-23 16:36:53 -08:00
LoopsToGPU	NFC: Replace ValuePtr with Value and remove it now that Value is value-typed.	2019-12-23 16:36:53 -08:00
StandardToLLVM	[mlir] Fix the wrong computation of dynamic strides for lowering AllocOp to LLVM	2019-12-28 23:33:28 +01:00
StandardToSPIRV	[mlir] Convert std.and/std.or ops to spv.LogicalAnd/spv.LogicalOr	2019-12-27 11:33:17 -08:00
VectorToLLVM	NFC: Replace ValuePtr with Value and remove it now that Value is value-typed.	2019-12-23 16:36:53 -08:00
VectorToLoops	Adjust License.txt file to use the LLVM license	2019-12-23 15:33:37 -08:00
CMakeLists.txt	Refactor dependencies to expose Vector transformations as patterns - NFC	2019-12-03 17:52:10 -08:00