mirror of
https://github.com/ROCm/ROCm.git
synced 2026-04-05 03:01:17 -04:00
20100a7254
This PR merges the `triton-mlir` branch, in which we have been quietly rewriting the Triton backend from scratch to increase maintainability, stability and ultimately performance. Changes to the runtime are minimal, and this new version aims to remain backward-compatible with the previous commit. The legacy backend is now officially deprecated, but can still be accessed via the `legacy-backend` tag. Co-authored-by: Keren Zhou <kerenzhou@openai.com> Co-authored-by: Yan Chunwei <yanchunwei@outlook.com> Co-authored-by: goostavz <109190422+goostavz@users.noreply.github.com> Co-authored-by: Shintaro Iwasaki <siwasaki@fb.com> Co-authored-by: Yan Da <dyanab@connect.ust.hk> Co-authored-by: Jun Yang <yangjunpro@gmail.com> Co-authored-by: Ian Bearman <ianb@microsoft.com> Co-authored-by: Jason Ansel <jansel@jansel.net> Co-authored-by: Qingyi Liu <qingyil@nvidia.com> Co-authored-by: ben-zhang-609 <110140741+ben-zhang-609@users.noreply.github.com> Co-authored-by: Chenggang Zhao <lyricz@yeah.net> Co-authored-by: ben-zhang-609 <benzh609@gmail.com> Co-authored-by: dongdongl <dongdongl@nvidia.com>
47 lines
1.3 KiB
C++
47 lines
1.3 KiB
C++
#ifndef TRITON_DIALECT_TRITONGPU_IR_DIALECT_H_
|
|
#define TRITON_DIALECT_TRITONGPU_IR_DIALECT_H_
|
|
|
|
#include "mlir/Dialect/GPU/GPUDialect.h"
|
|
#include "mlir/Dialect/Tensor/IR/Tensor.h"
|
|
#include "mlir/IR/BuiltinOps.h"
|
|
#include "mlir/IR/Dialect.h"
|
|
|
|
// TritonGPU depends on Triton
|
|
#include "triton/Dialect/Triton/IR/Dialect.h"
|
|
|
|
#include "triton/Dialect/TritonGPU/IR/Dialect.h.inc"
|
|
#include "triton/Dialect/TritonGPU/IR/Traits.h"
|
|
|
|
#define GET_ATTRDEF_CLASSES
|
|
#include "triton/Dialect/Triton/IR/AttrInterfaces.h.inc"
|
|
#include "triton/Dialect/TritonGPU/IR/TritonGPUAttrDefs.h.inc"
|
|
|
|
#define GET_OP_CLASSES
|
|
#include "triton/Dialect/TritonGPU/IR/Ops.h.inc"
|
|
|
|
namespace mlir {
|
|
namespace triton {
|
|
namespace gpu {
|
|
|
|
unsigned getElemsPerThread(Type type);
|
|
|
|
SmallVector<unsigned> getThreadsPerWarp(const Attribute &layout);
|
|
|
|
SmallVector<unsigned> getWarpsPerCTA(const Attribute &layout);
|
|
|
|
SmallVector<unsigned> getSizePerThread(const Attribute &layout);
|
|
|
|
SmallVector<unsigned> getContigPerThread(Attribute layout);
|
|
|
|
SmallVector<unsigned> getThreadsPerCTA(const Attribute &layout);
|
|
|
|
SmallVector<unsigned> getShapePerCTA(const Attribute &layout);
|
|
|
|
SmallVector<unsigned> getOrder(const Attribute &layout);
|
|
|
|
} // namespace gpu
|
|
} // namespace triton
|
|
} // namespace mlir
|
|
|
|
#endif // TRITON_DIALECT_TRITONGPU_IR_DIALECT_H_
|