summaryrefslogtreecommitdiffstats
path: root/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
Commit message (Expand)AuthorAgeFilesLines
* Revert "[mlir] Create a gpu.module operation for the GPU Dialect."Benjamin Kramer2020-01-161-10/+11
* [mlir] Create a gpu.module operation for the GPU Dialect.Tres Popp2020-01-141-11/+10
* Unbreak the mlir build after 202ab273e6eca134b69882f100c666fcd3affbcfBenjamin Kramer2020-01-131-1/+1
* [mlir] Added missing GPU lowering ops.Julian Gross2020-01-131-1/+8
* [mlir] NFC: Remove Value::operator* and Value::operator-> now that Value is p...River Riddle2020-01-111-13/+13
* NFC: Replace ValuePtr with Value and remove it now that Value is value-typed.River Riddle2019-12-231-108/+107
* Adjust License.txt file to use the LLVM licenseMehdi Amini2019-12-231-13/+4
* NFC: Introduce new ValuePtr/ValueRef typedefs to simplify the transition to V...River Riddle2019-12-221-108/+109
* Add gpu.shuffle op.Christian Sigg2019-12-201-2/+60
* NFC: Remove unnecessary 'llvm::' prefix from uses of llvm symbols declared in...River Riddle2019-12-181-3/+3
* Harden the requirements to memory attribution types in gpu.funcAlex Zinenko2019-12-181-2/+25
* Plug gpu.func into the GPU lowering pipelinesAlex Zinenko2019-12-161-3/+37
* Fix maskAndClamp in gpu.all_reduce.Christian Sigg2019-12-131-2/+5
* Automated rollback of commit f68ac464d818629e0fe10c23b44ac782d64a12d2Christian Sigg2019-12-121-2/+2
* Switch from shfl.bfly to shfl.down.Christian Sigg2019-12-121-2/+2
* NFC: Fix naming inconsistency: FuncOpLowering -> GPUFuncOpLowering.Christian Sigg2019-12-111-7/+3
* Add a function to get lowering patterns from GPU to NVVM.Stephan Herhut2019-12-111-13/+18
* Update the builder API to take ValueRange instead of ArrayRef<Value *>River Riddle2019-12-071-4/+3
* LLVM::GlobalOp: take address space as builder argumentAlex Zinenko2019-12-061-7/+2
* Add conversions of GPU func with memory attributions to LLVM/NVVMAlex Zinenko2019-12-061-1/+144
* Introduce Linkage attribute to the LLVM dialectAlex Zinenko2019-12-021-2/+2
* Rename CLI flags -lower-gpu-ops-to-*-ops to -convert-gpu-to-*Alex Zinenko2019-11-181-2/+1
* Add custom lowering of ExpOp for NVVM and ROCM.Alexander Belyaev2019-10-241-1/+4
* Unify GPU op definition names with other dialects.Christian Sigg2019-10-211-9/+10
* Get active source lane predicate from shuffle instruction.Christian Sigg2019-10-191-18/+20
* Add gpu.barrier op to synchronize invocations of a local workgroup.Christian Sigg2019-10-181-0/+4
* Support custom accumulator provided as region to gpu.all_reduce.Christian Sigg2019-10-161-8/+105
* Mark GPU dialect as illegal when lowering to NVVM.Christian Sigg2019-10-101-0/+1
* Use llvm.func to define functions with wrapped LLVM IR function typeAlex Zinenko2019-10-101-2/+0
* Change to doxygen comments. NFC.Christian Sigg2019-10-091-63/+63
* Support reduction of partial warps.Christian Sigg2019-10-071-88/+159
* Moving the GPUIndexIntrinsicOpLowering template to a common locationDeven Desai2019-10-041-70/+1
* Fix typos, NFC.Christian Sigg2019-10-041-1/+1
* Change all_reduce lowering to support 2D and 3D blocks.Christian Sigg2019-10-011-43/+124
* Switch comments from GPU dialect terms to CUDA terms (NFC).Christian Sigg2019-09-301-8/+7
* Add AllReduceOp to GPU dialect with lowering to NVVM.Christian Sigg2019-09-261-2/+169
* Outline GPU kernel function into a nested module.Christian Sigg2019-09-231-38/+17
* Automated rollback of commit 5684a12434f923d03b6870f2aa16226bfb0b38b6George Karpenkov2019-09-191-17/+38
* Outline GPU kernel function into a nested module.MLIR Team2019-09-191-38/+17
* NFC: Finish replacing FunctionPassBase/ModulePassBase with OpPassBase.River Riddle2019-09-131-1/+1
* Port mlir-cuda-runner to use dialect conversion framework.Stephan Herhut2019-08-281-66/+98
* NFC: Move LLVMIR, SDBM, and StandardOps to the Dialect/ directory.River Riddle2019-08-191-2/+2
* Change from llvm::make_unique to std::make_uniqueJacques Pienaar2019-08-171-1/+1
* Express ownership transfer in PassManager API through std::unique_ptr (NFC)Mehdi Amini2019-08-121-2/+2
* Move GPU dialect to {lib,include/mlir}/DialectAlex Zinenko2019-07-251-1/+1
* GPUtoNVVM: adjust integer bitwidth when lowering special register opsAlex Zinenko2019-06-251-6/+27
* Fix GPUToNVVM naming: NNVM should have been NVVMAlex Zinenko2019-06-191-1/+1
* Use llvm::StringSwitch in lowering of GPU ops to NVVM ops.Stephan Herhut2019-06-191-9/+8
* Add lowering pass from GPU dialect operations to LLVM/NVVM intrinsics.Stephan Herhut2019-06-191-0/+119
OpenPOWER on IntegriCloud