Skip to content

TCOLPROD.md

Latest commit

 

History

History
127 lines (86 loc) · 2.66 KB

TCOLPROD.md

File metadata and controls

127 lines (86 loc) · 2.66 KB
Raw

TCOLPROD

Tile Operation Diagram

TCOLPROD tile operation

Introduction

Reduce each column by multiplying across rows.

Math Interpretation

Let R = src.GetValidRow() and C = src.GetValidCol(). For 0 <= j < C:

$$ \mathrm{dst}_{0,j} = \prod_{i=0}^{R-1} \mathrm{src}_{i,j} $$

Assembly Syntax

Synchronous form:

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

AS Level 1 (SSA)

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

AS Level 2 (DPS)

pto.tcolprod ins(%src : !pto.tile_buf<...>) outs(%dst : !pto.tile_buf<...>)

C++ Intrinsic

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

template <typename TileDataOut, typename TileDataIn, typename... WaitEvents>
PTO_INST RecordEvent TCOLPROD(TileDataOut &dst, TileDataIn &src, WaitEvents &... events);

Constraints

General constraints / checks

  • dst and src must be TileType::Vec.
  • dst and src must use standard ND layout: row-major and non-fractal (BLayout::RowMajor, SLayout::NoneBox).
  • dst and src must use the same element type.
  • Runtime checks:
    • src.GetValidCol() == dst.GetValidCol()
  • If src.GetValidRow() == 0 or src.GetValidCol() == 0, the implementation returns early.

A2A3 implementation checks

  • Supported element types: half, float, int16_t, int32_t.

A5 implementation checks

  • Supported element types: half, float, bfloat16_t, int16_t, uint16_t, int32_t, uint32_t.

Examples

Auto

#include <pto/pto-inst.hpp>

using namespace pto;

void example_auto() {
  using SrcT = Tile<TileType::Vec, float, 16, 16>;
  using DstT = Tile<TileType::Vec, float, 1, 16>;
  SrcT src;
  DstT dst;
  TCOLPROD(dst, src);
}

Manual

#include <pto/pto-inst.hpp>

using namespace pto;

void example_manual() {
  using SrcT = Tile<TileType::Vec, float, 16, 16>;
  using DstT = Tile<TileType::Vec, float, 1, 16>;
  SrcT src;
  DstT dst;
  TASSIGN(src, 0x1000);
  TASSIGN(dst, 0x2000);
  TCOLPROD(dst, src);
}

ASM Form Examples

Auto Mode

# Auto mode: compiler/runtime-managed placement and scheduling.
%dst = pto.tcolprod %src : !pto.tile<...> -> !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.tcolprod %src : !pto.tile<...> -> !pto.tile<...>

PTO Assembly Form

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