TQUANT

指令示意图

TQUANT tile operation

简介

量化 Tile(例如 FP32 到 FP8),生成指数/缩放/最大值输出。

数学语义

除非另有说明, semantics are defined over the valid region and target-dependent behavior is marked as implementation-defined.

汇编语法

PTO-AS 形式:参见 PTO-AS Specification.

AS Level 1 (SSA)

%dst = pto.tquant %src, %qp : (!pto.tile<...>, !pto.tile<...>) -> !pto.tile<...>

AS Level 2 (DPS)

pto.tquant ins(%src, %qp : !pto.tile_buf<...>, !pto.tile_buf<...>) outs(%dst : !pto.tile_buf<...>)

AS Level 1(SSA)

%dst = pto.tquant %src, %qp : (!pto.tile<...>, !pto.tile<...>) -> !pto.tile<...>

AS Level 2(DPS)

pto.tquant ins(%src, %qp : !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 <auto quant_type, typename TileDataOut, typename TileDataSrc, typename TileDataExp, typename TileDataMax,
          typename... WaitEvents>
PTO_INST RecordEvent TQUANT(TileDataOut &dst, TileDataSrc &src, TileDataExp *exp, TileDataMax *max, TileDataSrc *scaling, WaitEvents &... events);

template <auto quant_type, auto store_mode, typename TileDataOut, typename TileDataSrc, typename TileDataExp,
          typename TileDataMax, typename TileDataIdx, typename... WaitEvents>
PTO_INST RecordEvent TQUANT(TileDataOut &dst, TileDataSrc &src, TileDataExp *exp, TileDataMax *max, TileDataSrc *scaling, TileDataExp *exp_zz, TileDataIdx *vgather_idx, WaitEvents &... events);

template <auto quant_type, typename TileDataOut, typename TileDataSrc, typename TileDataPara, typename... WaitEvents>
PTO_INST RecordEvent TQUANT(TileDataOut &dst, TileDataSrc &src, TileDataPara &scale, TileDataPara *offset = nullptr, WaitEvents &... events);

约束

  • This instruction is currently implemented for specific targets (see include/pto/npu/*/TQuant.hpp).
  • Input type requirements and output tile types are mode/target-dependent.

示例

See related examples in docs/isa/ and docs/coding/tutorials/.