Lei Zhang 399887c9e4 [mlir][spirv] Add resource limits into target environment ...

This commit adds two resource limits, max_compute_workgroup_size
and max_compute_workgroup_invocations as resource limits to
the target environment. They are not used at the current moment,
but they will affect the SPIR-V CodeGen. Adding for now to have
a proper target environment modelling.

Differential Revision: https://reviews.llvm.org/D73905

2020-02-04 08:35:19 -05:00

..

GPUToCUDA

Create a gpu.module operation for the GPU Dialect.

2020-01-21 14:05:03 +01:00

GPUToNVVM

Add tanh lowering from Standard dialect to NVVM and ROCDL.

2020-01-28 11:01:10 +01:00

GPUToROCDL

Changed wrong ROCDL instructions in GPU lowering.

2020-01-30 15:37:00 +01:00

GPUToSPIRV

Create a gpu.module operation for the GPU Dialect.

2020-01-21 14:05:03 +01:00

LinalgToSPIRV

[mlir][spirv] Add resource limits into target environment

2020-02-04 08:35:19 -05:00

LoopsToGPU

[MLIR] Make gpu.launch implicitly capture uses of values defined above.

2020-02-03 10:08:48 +01:00

StandardToLLVM

[mlir] Introduce bare ptr calling convention for MemRefs in LLVM dialect

2020-01-31 15:19:38 -08:00

StandardToSPIRV

[mlir][spirv] Add lowering for composite std.constant.

2020-01-22 08:25:00 -05:00

VectorToLLVM

[mlir] [VectorOps] fixed bug in vector.insert_strided_slice lowering

2020-01-31 11:29:46 -08:00

VectorToLoops

[mlir] Change the syntax of AffineMapAttr and IntegerSetAttr to avoid conflicts with function types.

2020-01-13 13:24:39 -08:00

convert-to-cfg.mlir

Add lowering for loop.parallel to cfg.

2020-01-28 11:55:51 +01:00