TCOLMAX¶
指令示意图¶
简介¶
通过取行间最大值来归约每一列。
数学语义¶
Let R = src.GetValidRow() and C = src.GetValidCol(). For 0 <= j < C:
\[ \mathrm{dst}_{0,j} = \max_{0 \le i < R} \mathrm{src}_{i,j} \]
汇编语法¶
PTO-AS 形式:参见 PTO-AS Specification.
同步形式:
%dst = tcolmax %src : !pto.tile<...> -> !pto.tile<...>
AS Level 1 (SSA)¶
%dst = pto.tcolmax %src : !pto.tile<...> -> !pto.tile<...>
AS Level 2 (DPS)¶
pto.tcolmax ins(%src : !pto.tile_buf<...>) outs(%dst : !pto.tile_buf<...>)
AS Level 1(SSA)¶
%dst = pto.tcolmax %src : !pto.tile<...> -> !pto.tile<...>
AS Level 2(DPS)¶
pto.tcolmax ins(%src : !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... WaitEvents>
PTO_INST RecordEvent TCOLMAX(TileDataOut &dst, TileDataIn &src, WaitEvents &... events);
约束¶
实现检查 (NPU):
- Tile location:
dstandsrcmust beTileType::Vec. - Tile 布局: both tiles must be ND fractal (
isRowMajorandSLayout::NoneBox). - 数据类型:
- A2A3:
half,float,int16_t,int32_t. - A5:
half,float,int8_t,uint8_t,int16_t,uint16_t,int32_t,uint32_t,bfloat16_t.
- A2A3:
- 数据类型一致性:
dst.DType == src.DType. - 运行期有效区域检查:
src.GetValidCol() == dst.GetValidCol().- If
src.GetValidRow() == 0orsrc.GetValidCol() == 0, the implementation returns early.
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, 1, 16>;
SrcT src;
DstT dst;
TCOLMAX(dst, src);
}
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, 1, 16>;
SrcT src;
DstT dst;
TASSIGN(src, 0x1000);
TASSIGN(dst, 0x2000);
TCOLMAX(dst, src);
}