TMINS

Tile Operation Diagram

Introduction

Elementwise minimum of a tile and a scalar.

Math Interpretation

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

$${\mathrm{d}\mathrm{s}\mathrm{t}}_{i,j}=\min ({\mathrm{s}\mathrm{r}\mathrm{c}}_{i,j},\mathrm{s}\mathrm{c}\mathrm{a}\mathrm{l}\mathrm{a}\mathrm{r})$$

Assembly Syntax

Synchronous form:

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

AS Level 1 (SSA)

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

AS Level 2 (DPS)

pto.tmins 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 TMINS(TileDataDst &dst, TileDataSrc &src, typename TileDataSrc::DType scalar, WaitEvents &... events);

Constraints

• Implementation checks (A2A3):
  • TileData::DType must be one of: int32_t, int, int16_t, half, float16_t, float, float32_t.
  • Runtime: src.GetValidRow() == dst.GetValidRow() and src.GetValidCol() == dst.GetValidCol().
• Implementation checks (A5):
  • TileData::DType must be one of: uint8_t, int8_t, uint16_t, int16_t, uint32_t, int32_t, half, float, bfloat16_t.
  • Runtime: src.GetValidCol() == dst.GetValidCol().
• Common constraints:
  • dst and src must use the same element type.
  • Scalar type must match the tile data type.
  • Tile location must be vector (TileData::Loc == TileType::Vec).
• Valid region:
  • The op uses dst.GetValidRow() / dst.GetValidCol() as the iteration domain.

Examples

Auto

#include <pto/pto-inst.hpp>

using namespace pto;

void example_auto() {
  using TileT = Tile<TileType::Vec, float, 16, 16>;
  TileT src, dst;
  TMINS(dst, src, 0.0f);
}

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);
  TMINS(dst, src, 0.0f);
}

ASM Form Examples

Auto Mode

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

Manual Mode

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

PTO Assembly Form

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