llvm-project/mlir/test/Dialect/GPU
Christian Sigg a79b26db0e [mlir] Fix for gpu-async-region pass.
- the !gpu.async.token is the second result of 'gpu.alloc async', not the first.
- async.execute construction takes operand types not yet wrapped in !async.value.
- fix typo

Reviewed By: herhut

Differential Revision: https://reviews.llvm.org/D93156
2020-12-16 19:08:10 +01:00
..
all-reduce-max.mlir [mlir][gpu] NFC: Make room for more than one GPU rewrite pattern. 2020-10-19 07:52:47 +02:00
all-reduce.mlir [mlir][gpu] NFC: Make room for more than one GPU rewrite pattern. 2020-10-19 07:52:47 +02:00
async-region.mlir [mlir] Fix for gpu-async-region pass. 2020-12-16 19:08:10 +01:00
invalid.mlir [mlir][gpu] Allow gpu.launch_func to be async. 2020-10-29 21:48:38 +01:00
mapping.mlir [mlir][AsmPrinter] Refactor printing to only print aliases for attributes/types that will exist in the output. 2020-11-09 21:54:47 -08:00
multiple-all-reduce.mlir [mlir] switch the modeling of LLVM types to use the new mechanism 2020-08-04 14:29:25 +02:00
ops.mlir [mlir] Add gpu.allocate, gpu.deallocate ops with LLVM lowering to runtime function calls. 2020-11-27 09:40:59 +01:00
outlining.mlir [mlir][gpu] Add customer printer/parser for gpu.launch_func. 2020-10-21 18:19:00 +02:00
promotion.mlir [mlir] Change dialect namespace loop->scf 2020-05-13 19:20:21 +02:00