pto.vnot¶
pto.vnot is part of the Unary Vector Instructions instruction set.
Summary¶
%result holds the lane-wise bitwise inversion.
Mechanism¶
pto.vnot computes the lane-wise bitwise inversion: dst[i] = ~src[i]. This inverts all bits in each element. Integer element types only. Inactive lanes leave the destination unchanged.
Syntax¶
PTO Assembly Form¶
vnot %result, %input, %mask
AS Level 1 (SSA)¶
%result = pto.vnot %input, %mask : !pto.vreg<NxT>, !pto.mask<G> -> !pto.vreg<NxT>
Documented A5 types or forms: all integer types.
Inputs¶
| Operand | Type | Description |
|---|---|---|
%input |
!pto.vreg<NxT> |
Source vector register; read at each active lane i |
%mask |
!pto.mask<G> |
Predicate mask; lanes where mask bit is 1 (true) are active |
Expected Outputs¶
| Result | Type | Description |
|---|---|---|
%result |
!pto.vreg<NxT> |
Lane-wise bitwise inversion: dst[i] = ~src[i] on active lanes; inactive lanes are unmodified |
Side Effects¶
This operation has no architectural side effect beyond producing its SSA results. It does not implicitly reserve buffers, signal events, or establish memory fences unless the form says so.
Constraints¶
Constraints
Integer element types only.
Exceptions¶
Exceptions
- The verifier rejects illegal operand shapes, unsupported element types, and attribute combinations that are not valid for the selected instruction set or target profile.
- Any additional illegality stated in the constraints section is also part of the contract.
Target-Profile Restrictions¶
Target-Profile Restrictions
- Documented A5 coverage:
all integer types. - A5 is the most detailed concrete profile in the current manual; CPU simulation and A2/A3-class targets may support narrower subsets or emulate the behavior while preserving the visible PTO contract.
- Code that depends on an instruction-set-specific type list, distribution mode, or fused form should treat that dependency as target-profile-specific unless the PTO manual states cross-target portability explicitly.
Performance¶
Timing Disclosure¶
The current public VPTO timing material for PTO micro instructions remains limited.
For pto.vnot, those public sources describe the instruction semantics, operand legality, and pipeline placement, but they do not publish a numeric latency or steady-state throughput.
| Metric | Status | Source Basis |
|---|---|---|
| A5 latency | Not publicly published | Current public VPTO timing material |
| Steady-state throughput | Not publicly published | Current public VPTO timing material |
If software scheduling or performance modeling depends on the exact cost of pto.vnot, treat that cost as target-profile-specific and measure it on the concrete backend rather than inferring a manual constant.
Examples¶
for (int i = 0; i < N; i++)
dst[i] = ~src[i];
Related Ops / Instruction Set Links¶
- Instruction set overview: Unary Vector Instructions
- Previous op in instruction set: pto.vrelu
- Next op in instruction set: pto.vbcnt