TDIVS

Tile Operation Diagram

TDIVS tile operation

Introduction

Elementwise division with a scalar (tile/scalar or scalar/tile).

Math Interpretation

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

  • Tile/scalar:

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

  • Scalar/tile:

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

Assembly Syntax

PTO-AS form: see PTO-AS Specification.

Tile/scalar form:

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

Scalar/tile form:

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

IR Level 1 (SSA)

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

IR Level 2 (DPS)

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

C++ Intrinsic

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

template <typename TileData, typename... WaitEvents>
PTO_INST RecordEvent TDIVS(TileData& dst, TileData& src0, typename TileData::DType scalar, WaitEvents&... events);

template <typename TileData, typename... WaitEvents>
PTO_INST RecordEvent TDIVS(TileData& dst, typename TileData::DType scalar, TileData& src0, WaitEvents&... events);

Constraints

  • Implementation checks (A2A3) (both overloads):
  • TileData::DType must be one of: int32_t, int, int16_t, half, float16_t, float, float32_t.
  • Tile location must be vector (TileData::Loc == TileType::Vec).
  • Static valid bounds: TileData::ValidRow <= TileData::Rows and TileData::ValidCol <= TileData::Cols.
  • Runtime: src0.GetValidRow() == dst.GetValidRow() and src0.GetValidCol() == dst.GetValidCol().
  • Tile layout must be row-major (TileData::isRowMajor).
  • Implementation checks (A5) (both overloads):
  • TileData::DType must be one of: uint8_t, int8_t, uint16_t, int16_t, uint32_t, int32_t, half, float.
  • Tile location must be vector (TileData::Loc == TileType::Vec).
  • Static valid bounds: TileData::ValidRow <= TileData::Rows and TileData::ValidCol <= TileData::Cols.
  • Runtime: src0.GetValidRow() == dst.GetValidRow() and src0.GetValidCol() == dst.GetValidCol().
  • Tile layout must be row-major (TileData::isRowMajor).
  • Valid region:
  • The op uses dst.GetValidRow() / dst.GetValidCol() as the iteration domain.
  • Division-by-zero:
  • Behavior is target-defined; on A5 the tile/scalar form maps to multiply-by-reciprocal and uses 1/0 -> +inf for scalar == 0.

Examples

Auto

#include <pto/pto-inst.hpp>

using namespace pto;

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

ASM Form Examples

Auto Mode

# Auto mode: compiler/runtime-managed placement and scheduling.
%dst = pto.tdivs %src, %scalar : (!pto.tile<...>, dtype) -> !pto.tile<...>

Manual Mode

# Manual mode: bind resources explicitly before issuing the instruction.
# Optional for tile operands:
# pto.tassign %arg0, @tile(0x1000)
# pto.tassign %arg1, @tile(0x2000)
%dst = pto.tdivs %src, %scalar : (!pto.tile<...>, dtype) -> !pto.tile<...>

PTO Assembly Form

%dst = pto.tdivs %src, %scalar : (!pto.tile<...>, dtype) -> !pto.tile<...>
# IR Level 2 (DPS)
pto.tdivs ins(%src, %scalar : !pto.tile_buf<...>, dtype) outs(%dst : !pto.tile_buf<...>)