TANDS¶

Tile Operation Diagram¶

TANDS tile operation

Introduction¶

Elementwise bitwise AND of a tile and a scalar.

Math Interpretation¶

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

\[ \mathrm{dst}_{i,j} = \mathrm{src}_{i,j} \;\&\; \mathrm{scalar} \]

Assembly Syntax¶

PTO-AS form: see PTO-AS Specification.

Synchronous form:

%dst = tands %src, %scalar : !pto.tile<...>, i32

IR Level 1 (SSA)¶

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

IR Level 2 (DPS)¶

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

C++ Intrinsic¶

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

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

Constraints¶

Intended for integral element types.
The op iterates over dst.GetValidRow() / dst.GetValidCol().
Setting the source Tile and destination Tile to the same memory is Unsupported.

Examples¶

#include <pto/pto-inst.hpp>

using namespace pto;

void example() {
  using TileDst = Tile<TileType::Vec, uint16_t, 16, 16>;
  using TileSrc = Tile<TileType::Vec, uint16_t, 16, 16>;
  TileDst dst;
  TileSrc src;
  TANDS(dst, src, 0xffu);
}

ASM Form Examples¶

Auto Mode¶

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

PTO Assembly Form¶

%dst = tands %src, %scalar : !pto.tile<...>, i32
# IR Level 2 (DPS)
pto.tands ins(%src, %scalar : !pto.tile_buf<...>, dtype) outs(%dst : !pto.tile_buf<...>)