TMULS

Instruction Diagram

Introduction

Performs element-wise multiplication of a tile by a scalar.

Mathematical Semantics

For each element (i, j) within the valid region:

$$\mathrm{dst}_{i,j} = \mathrm{src}_{i,j} \cdot \mathrm{scalar}$$

Assembly Syntax

Synchronous form:

%dst = tmuls %src, %scalar : !pto.tile<...>, f32

AS Level 1 (SSA)

%dst = pto.tmuls %src, %scalar : (!pto.tile<...>, dtype) -> !pto.tile<...>

AS Level 2 (DPS)

pto.tmuls ins(%src, %scalar : !pto.tile_buf<...>, dtype) outs(%dst : !pto.tile_buf<...>)

C++ Built-in APIs

Declared in include/pto/common/pto_instr.hpp:

The public include header is <pto/pto-inst.hpp>, and the internal declaration is located in pto/common/pto_instr.hpp.

template <typename TileDataDst, typename TileDataSrc, typename... WaitEvents>
PTO_INST RecordEvent TMULS(TileDataDst &dst, TileDataSrc &src0, typename TileDataSrc::DType scalar, WaitEvents &... events);

Constraints

• Implementation check (Atlas A2/A3 training products/Atlas A2/A3 inference products):
  • TileData::DType must be one of the following: int32_t, int16_t, half, float.
  • The tile position must be a vector (TileData::Loc == TileType::Vec).
  • Static valid boundary: TileData::ValidRow <= TileData::Rows and TileData::ValidCol <= TileData::Cols.
  • Runtime: src0.GetValidRow() == dst.GetValidRow() and src0.GetValidCol() == dst.GetValidCol().
  • The tile layout must be row-major (TileData::isRowMajor).
• Implementation check (Ascend 950PR/Ascend 950DT):
  • TileData::DType must be one of the following: uint16_t, int16_t, uint32_t, int32_t, half, float, bfloat16_t.
  • The tile position must be a vector (TileData::Loc == TileType::Vec).
  • Static valid boundary: TileData::ValidRow <= TileData::Rows and TileData::ValidCol <= TileData::Cols.
  • Runtime: src0.GetValidCol() == dst.GetValidCol().
  • The tile layout must be row-major (TileData::isRowMajor).
• Valid region:
  • This operation uses dst.GetValidRow()/dst.GetValidCol() as the iteration domain.

Examples

Automatic

#include <pto/pto-inst.hpp>

using namespace pto;

void example_auto() {
  using TileT = Tile<TileType::Vec, float, 16, 16>;
  TileT src, dst;
  TMULS(dst, src, 2.0f);
}

Manual

#include <pto/pto-inst.hpp>

using namespace pto;

void example_manual() {
  using TileT = Tile<TileType::Vec, float, 16, 16>;
  TileT src, dst;
  TASSIGN(src, 0x1000);
  TASSIGN(dst, 0x2000);
  TMULS(dst, src, 2.0f);
}

ASM Examples

Automatic Mode

# Automatic mode: the compiler/runtime handles resource placement and scheduling.
%dst = pto.tmuls %src, %scalar : (!pto.tile<...>, dtype) -> !pto.tile<...>

Manual Mode

# Manual mode: explicitly bind resources first, then issue the instruction.
# Optional (when the instruction contains tile operands):
# pto.tassign %arg0, @tile(0x1000)
# pto.tassign %arg1, @tile(0x2000)
%dst = pto.tmuls %src, %scalar : (!pto.tile<...>, dtype) -> !pto.tile<...>

PTO Assembly Form

%dst = tmuls %src, %scalar : !pto.tile<...>, f32
# AS Level 2 (DPS)
pto.tmuls ins(%src, %scalar : !pto.tile_buf<...>, dtype) outs(%dst : !pto.tile_buf<...>)