KernelGen.h

浏览该文件的文档.

 
#include "common/Export.h"
#ifndef EVE_TENSOR_KERNELGEN_H
#define EVE_TENSOR_KERNELGEN_H
 
#include "tensor/Optimizer.h"
 
#include <string>
#include <vector>
 
namespace eve::tensor {
 
struct KernelSpec {
    std::string pass1;   // empty when single-pass
    std::string pass2;   // always set
    int groupsX1 = 0, groupsY1 = 1, groupsZ1 = 1;
    int groupsX2 = 0, groupsY2 = 1, groupsZ2 = 1;
    std::vector<int> inputRepresentatives;
    int inputCount = 0;          // total group input buffers
    int inputsReadPass1 = 0;     // leading inputs bound in pass1
    int statsCount = 0;          // per-row stats buffers (allocated by the runtime)
    int statsSize = 0;           // elements per stats buffer (rows)
    bool twoPass = false;
 
    // Weight-only quantization of a matmul B / embedding table input.
    // qDtype == 0 means fp32 storage. int8/int4 add a per-group scales buffer.
    int qDtype = 0;              // static_cast<int>(DType)
    int qGroup = 0;              // elements per scale group
    int scalesBinding = -1;      // storage binding of the scales buffer
    int outputBinding = -1;      // storage binding of the output (override)
};
 
EVENGINE_API_DOMAINS bool generateKernel(const Graph &graph, const FusedGroup &group, KernelSpec &out);
 
bool generateMatMulVariant(const Graph &graph, const FusedGroup &group, bool tiled,
                           KernelSpec &out);
 
constexpr int kMaxKernelBindings = 8;
 
}  // namespace eve::tensor
 
#endif  // EVE_TENSOR_KERNELGEN_H