TABS

Instruction Diagram

Introduction

Element-wise absolute value of a tile.

Mathematical Semantics

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

$$\mathrm{dst}_{i,j} = \left|\mathrm{src}_{i,j}\right|$$

Assembly Syntax

Synchronous form:

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

AS Level 1 (SSA)

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

AS Level 2 (DPS)

pto.tabs ins(%src : !pto.tile_buf<...>) 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 TABS(TileDataDst &dst, TileDataSrc &src, WaitEvents &... events);

Constraints

• Implementation check (CPU sim):
  • TileData::DType must be one of the following: int32_t, int, int16_t, half, float.
  • The implementation iterates over dst.GetValidRow()/dst.GetValidCol().
• Implementation check (Costmodel):
  • TileData::DType must be one of the following: int32_t, int16_t, int8_t, uint8_t, half, float.
• Implementation check (NPU):
  • For Atlas A3 training products/Atlas A3 inference products, TileData::DType must be one of the following: float or half.
  • For Ascend 950PR/Ascend 950DT, TileData::DType must be one of the following: int32_t, int16_t, int8_t, half, float.
  • The tile position must be a vector (TileData::Loc == TileType::Vec).
  • Static valid bounds: TileData::ValidRow <= TileData::Rows and TileData::ValidCol <= TileData::Cols.
  • Runtime: src.GetValidRow() == dst.GetValidRow() and src.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;
  TABS(dst, src);
}

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);
  TABS(dst, src);
}

ASM Examples

Automatic Mode

# Automatic mode: the compiler/runtime is responsible for resource placement and scheduling.
%dst = pto.tabs %src : !pto.tile<...> -> !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.tabs %src : !pto.tile<...> -> !pto.tile<...>

PTO Assembly Form

%dst = tabs %src : !pto.tile<...> -> !pto.tile<...>
# AS Level 2 (DPS)
pto.tabs ins(%src : !pto.tile_buf<...>) outs(%dst : !pto.tile_buf<...>)