pto.tand¶
pto.tand is part of the Elementwise Tile Tile instruction set.
Summary¶
Elementwise bitwise AND of two tiles.
Mechanism¶
Elementwise bitwise AND of two tiles.
For each element (i, j) in the valid region:
\[ \mathrm{dst}_{i,j} = \mathrm{src0}_{i,j} \;\&\; \mathrm{src1}_{i,j} \]
Syntax¶
Textual spelling is defined by the PTO ISA syntax-and-operands pages.
Synchronous form:
%dst = tand %src0, %src1 : !pto.tile<...>
AS Level 1 (SSA)¶
%dst = pto.tand %src0, %src1 : (!pto.tile<...>, !pto.tile<...>) -> !pto.tile<...>
AS Level 2 (DPS)¶
pto.tand ins(%src0, %src1 : !pto.tile_buf<...>, !pto.tile_buf<...>) outs(%dst : !pto.tile_buf<...>)
C++ Intrinsic¶
Declared in include/pto/common/pto_instr.hpp:
template <typename TileData, typename... WaitEvents>
PTO_INST RecordEvent TAND(TileData &dst, TileData &src0, TileData &src1, WaitEvents &... events);
Inputs¶
| Operand | Role | Description |
|---|---|---|
%src0 |
Left tile | First source tile; read at (i, j) for each (i, j) in dst valid region |
%src1 |
Right tile | Second source tile; read at (i, j) for each (i, j) in dst valid region |
WaitEvents... |
Optional synchronisation | RecordEvent tokens to wait on before issuing the operation |
Expected Outputs¶
| Result | Type | Description |
|---|---|---|
%dst |
!pto.tile<...> |
Destination tile; all (i, j) in its valid region contain src0[i,j] & src1[i,j] after the operation |
Side Effects¶
No architectural side effects beyond producing the destination tile. Does not implicitly fence unrelated traffic.
Constraints¶
Constraints
- Valid region:
- The op uses
dst.GetValidRow()/dst.GetValidCol()as the iteration domain.
- The op uses
Exceptions¶
Exceptions
- Illegal operand tuples, unsupported types, invalid layout combinations, or unsupported target-profile modes are rejected by the verifier or by the selected backend instruction set.
- Programs must not rely on behavior outside the documented legal domain of this operation, even if one backend currently accepts it.
Performance¶
A2/A3 Throughput¶
TAND compiles to CCE vector instructions via the TBinOp.hpp performance model. The throughput is identical to TADD (binary arithmetic):
| Metric | Value (FP) | Value (INT) |
|---|---|---|
| Startup latency | 14 | 14 |
| Completion latency | 19 | 17 |
| Per-repeat throughput | 2 | 2 |
| Pipeline interval | 18 | 18 |
Target-Profile Restrictions¶
Target-Profile Restrictions
-
Implementation checks (A2A3):
- Supported element types are 1-byte or 2-byte integral types.
dst,src0, andsrc1must use the same element type.dst,src0, andsrc1must be row-major.- Runtime:
src0.GetValidRow()/GetValidCol()andsrc1.GetValidRow()/GetValidCol()must matchdst.
-
Implementation checks (A5):
- Supported element types are 1-byte, 2-byte, or 4-byte integral types.
dst,src0, andsrc1must use the same element type.dst,src0, andsrc1must be row-major.- Runtime:
src0.GetValidRow()/GetValidCol()andsrc1.GetValidRow()/GetValidCol()must matchdst.
Examples¶
#include <pto/pto-inst.hpp>
using namespace pto;
void example() {
using TileT = Tile<TileType::Vec, int32_t, 16, 16>;
TileT a, b, out;
TAND(out, a, b);
}
Auto Mode¶
# Auto mode: compiler/runtime-managed placement and scheduling.
%dst = pto.tand %src0, %src1 : (!pto.tile<...>, !pto.tile<...>) -> !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.tand %src0, %src1 : (!pto.tile<...>, !pto.tile<...>) -> !pto.tile<...>
PTO Assembly Form¶
%dst = tand %src0, %src1 : !pto.tile<...>
# AS Level 2 (DPS)
pto.tand ins(%src0, %src1 : !pto.tile_buf<...>, !pto.tile_buf<...>) outs(%dst : !pto.tile_buf<...>)
Related Ops / Instruction Set Links¶
- Instruction set overview: Elementwise Tile Tile
- Previous op in instruction set: pto.tabs
- Next op in instruction set: pto.tor