TPRINT¶

指令示意图¶

TPRINT tile operation

简介¶

调试/打印 Tile 中的元素（实现定义）。

Print the contents of a Tile or GlobalTensor for debugging purposes directly from device code.

The TPRINT instruction outputs the logical view of data stored in a Tile or GlobalTensor. It supports common data types (e.g., float, half, int8, uint32) and multiple memory layouts (ND, DN, NZ for GlobalTensor; vector tiles for on-chip buffers).

Important: - This instruction is for development and debugging ONLY. - It incurs significant runtime overhead and must not be used in production kernels. - Output may be truncated if it exceeds the internal print buffer. - Requires CCE compilation option -D_DEBUG --cce-enable-print (see Behavior).

数学语义¶

除非另有说明, semantics are defined over the valid region and target-dependent behavior is marked as implementation-defined.

汇编语法¶

PTO-AS 形式：参见 PTO-AS Specification.

tprint %src : !pto.tile<...> | !pto.global<...>

AS Level 1 (SSA)¶

pto.tprint %src : !pto.tile<...> | !pto.partition_tensor_view<MxNxdtype> -> ()

AS Level 2 (DPS)¶

pto.tprint ins(%src : !pto.tile_buf<...> | !pto.partition_tensor_view<MxNxdtype>)

AS Level 1（SSA）¶

pto.tprint %src : !pto.tile<...> | !pto.partition_tensor_view<MxNxdtype> -> ()

AS Level 2（DPS）¶

pto.tprint ins(%src : !pto.tile_buf<...> | !pto.partition_tensor_view<MxNxdtype>)

C++ 内建接口¶

声明于 include/pto/common/pto_instr.hpp:

template <typename TileData, typename... WaitEvents>
PTO_INST RecordEvent TPRINT(TileData &src, WaitEvents &... events);

Supported Types for T¶

Tile: Must be a vector tile (TileType::Vec) with supported element type.
GlobalTensor: Must use layout ND, DN, or NZ, and have a supported element type.

约束¶

Supported element type:
- Floating-point: float, half
- Signed integers: int8_t, int16_t, int32_t
- Unsigned integers: uint8_t, uint16_t, uint32_t
For Tiles: TileData::Loc == TileType::Vec (only vector tiles are printable).
For GlobalTensor: Layout must be one of Layout::ND, Layout::DN, or Layout::NZ.

示例¶

Print a Tile¶

#include <pto/pto-inst.hpp>

PTO_INTERNAL void DebugTile(__gm__ float *src) {
  using ValidSrcShape = TileShape2D<float, 16, 16>;
  using NDSrcShape = BaseShape2D<float, 32, 32>;
  using GlobalDataSrc = GlobalTensor<float, ValidSrcShape, NDSrcShape>;
  GlobalDataSrc srcGlobal(src);

  using srcTileData = Tile<TileType::Vec, float, 16, 16>;
  srcTileData srcTile;
  TASSIGN(srcTile, 0x0);

  TLOAD(srcTile, srcGlobal);
  TPRINT(srcTile);
}

Print a GlobalTensor¶

#include <pto/pto-inst.hpp>

PTO_INTERNAL void DebugGlobalTensor(__gm__ float *src) {
  using ValidSrcShape = TileShape2D<float, 16, 16>;
  using NDSrcShape = BaseShape2D<float, 32, 32>;
  using GlobalDataSrc = GlobalTensor<float, ValidSrcShape, NDSrcShape>;
  GlobalDataSrc srcGlobal(src);

  TPRINT(srcGlobal);
}