mirror of
https://github.com/ROCm/ROCm.git
synced 2026-02-21 03:00:39 -05:00
f1512bded1
The initial code merge of Nvidia Hopper features support. Please be aware that the code merge is not finished yet and the trouble-shooting is still ongoing. The new hardware features (GMMA, TMA, STMATRIX etc.) and automatic warp-specialization are experimental for now and turned off by default. It is recommended for a trial when version 3.0 is released. The work is contributed by: ben-zhang-609, bealwang, donproc, qliu93, jsh20, allatit23, LyricZhao, ivanyinwz, goostavz & yangjunpro from Nvidia, in cooperation with: ptillet, Jokeren, ThomasRaoux & zahimoud from OpenAI. Co-authored-by: Goostav Zhu <gzhu@nvidia.com>
18 lines
616 B
C++
18 lines
616 B
C++
#ifndef TRITON_CONVERSION_TRITONGPU_TO_LLVM_LOAD_STORE_OP_H
|
|
#define TRITON_CONVERSION_TRITONGPU_TO_LLVM_LOAD_STORE_OP_H
|
|
|
|
#include "TritonGPUToLLVMBase.h"
|
|
|
|
using namespace mlir;
|
|
using namespace mlir::triton;
|
|
|
|
void populateLoadStoreOpToLLVMPatterns(
|
|
TritonGPUToLLVMTypeConverter &typeConverter, RewritePatternSet &patterns,
|
|
int numWarps, ModuleAxisInfoAnalysis &axisInfoAnalysis,
|
|
ModuleAllocation &allocation,
|
|
ConvertTritonGPUOpToLLVMPatternBase::IndexCacheInfo &indexCacheInfo,
|
|
mlir::triton::gpu::TMAMetadataTy *tmaMetadata,
|
|
const TensorPtrMapT *tensorPtrMap, PatternBenefit benefit);
|
|
|
|
#endif
|