sub GPU Virtual ISA NVIDIA
Subtract Arithmetic
sub.type d, a, b;
Subtract the second operand from the first, with optional saturation for signed 32-bit integers.
Encoding
PTX is a virtual instruction set. It has no single, stable native
binary encoding — the compiler lowers this instruction to different native machine
code depending on the selected NVIDIA target architecture (compute capability).
This page intentionally shows no bit-diagram; see the target/version requirements
below for what governs how this instruction compiles.
Syntax Forms
One mnemonic covers many type / state-space / scope / modifier combinations — each row below is an independently valid form.
| Syntax | Data Types | State Space(s) | Modifiers | Min. Target | Description |
|---|---|---|---|---|---|
| sub.type d, a, b; | s16, s32, s64, u16, u32, u64, f32, f64 | sm_10 | Generic subtract across integer and floating-point types. | ||
| sub.sat.s32 d, a, b; | s32 | sat | sm_10 | Signed 32-bit subtract with saturation. |
Operands
-
d
Destination register -
a
Minuend -
b
Subtrahend
At a Glance
Reference
NVIDIA PTX ISA
Semantics
d = a - b.
Sources
- Parallel Thread Execution ISA ↗ — NVIDIA Corporation, Chapter 9 — Instruction Set