TROWSUM¶

指令示意图¶

简介¶

通过对列求和来归约每一行。

数学语义¶

Let R = src.GetValidRow() and C = src.GetValidCol(). For 0 <= i < R:

汇编语法¶

PTO-AS 形式：参见 PTO-AS Specification.

同步形式：

%dst = trowsum %src : !pto.tile<...> -> !pto.tile<...>

Lowering may introduce internal scratch tiles; the C++ intrinsic requires an explicit tmp operand.

AS Level 1 (SSA)¶

%dst = pto.trowsum %src, %tmp : (!pto.tile<...>, !pto.tile<...>) -> !pto.tile<...>

AS Level 2 (DPS)¶

pto.trowsum ins(%src, %tmp : !pto.tile_buf<...>, !pto.tile_buf<...>) outs(%dst : !pto.tile_buf<...>)

AS Level 1（SSA）¶

%dst = pto.trowsum %src, %tmp : (!pto.tile<...>, !pto.tile<...>) -> !pto.tile<...>

AS Level 2（DPS）¶

pto.trowsum ins(%src, %tmp : !pto.tile_buf<...>, !pto.tile_buf<...>) outs(%dst : !pto.tile_buf<...>)

C++ 内建接口¶

声明于 include/pto/common/pto_instr.hpp:

template <typename TileDataOut, typename TileDataIn, typename TileDataTmp, typename... WaitEvents>
PTO_INST RecordEvent TROWSUM(TileDataOut &dst, TileDataIn &src, TileDataTmp &tmp, WaitEvents &... events);

约束¶

实现检查 (NPU):

• A2A3:
  • Tile location: dst and src must be TileType::Vec.
  • Tile 布局 of src: ND fractal (isRowMajor and SLayout::NoneBox).
  • Tile 布局 of dst:
  • 推荐: DN layout Tile of 1D, e.g., Tile<TileType::Vec, T, ROWS, 1, BLayout::ColMajor, ValidRows, 1>
  • 将移除: ND layout Tile of 2D, e.g., Tile<TileType::Vec, T, ROWS, COLS, BLayout::RowMajor, ValidRows, 1>
  • 数据类型: half or float.
  • 数据类型一致性: dst.DType == src.DType.
  • 运行期有效区域检查:
  • srcValidCol != 0 and srcValidRow != 0.
  • srcValidRow == dstValidRow (the output valid row must match the input valid row).
• A5:
  • 数据类型: half or float.
  • 数据类型一致性: dst.DType == src.DType.
  • No explicit runtime assertions on validRow/validCol in the implementation; the loops use src.GetValidRow() and src.GetValidCol().

示例¶

自动（Auto）¶

#include <pto/pto-inst.hpp>

using namespace pto;

void example_auto() {
  using SrcT = Tile<TileType::Vec, float, 16, 16>;
  using DstT = Tile<TileType::Vec, float, 16, 1, BLayout::ColMajor>;
  using TmpT = Tile<TileType::Vec, float, 16, 16>;
  SrcT src;
  DstT dst;
  TmpT tmp;
  TROWSUM(dst, src, tmp);
}

手动（Manual）¶

#include <pto/pto-inst.hpp>

using namespace pto;

void example_manual() {
  using SrcT = Tile<TileType::Vec, float, 16, 16>;
  using DstT = Tile<TileType::Vec, float, 16, 1, BLayout::ColMajor>;
  using TmpT = Tile<TileType::Vec, float, 16, 16>;
  SrcT src;
  DstT dst;
  TmpT tmp;
  TASSIGN(src, 0x1000);
  TASSIGN(dst, 0x2000);
  TASSIGN(tmp, 0x3000);
  TROWSUM(dst, src, tmp);
}