IntelLabs/encrypted-computing-sdk
Intel’s HERACLES accelerator introduces a new set of fundamental instructions, the Polynomial Instructions Set Architecture (P-ISA) that operates directly on polynomials requiring a completely new programming environment. This open-source project aims at developing the building blocks for a compiler toolchain for HERACLES.
The SDK implements a modular, LLVM-inspired compiler pipeline with language-independent intermediate representations (IRs) that decompose large polynomial computations into abstraction layers, enabling target-agnostic FHE scheme development and third-party library integration. It includes P-ISA tools and an assembler targeting Intel's HERACLES accelerator, which accelerates polynomial operations via SIMD instructions while minimizing memory-compute data movement—a key bottleneck in traditional FHE implementations. Currently in Phase 1 with functional prototypes, the project aims to reduce the performance overhead confining FHE to specialized use cases.
Stars
61
Forks
4
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 23, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ai-coding/IntelLabs/encrypted-computing-sdk"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ash-project/igniter
A code generation and project patching framework.
hypergol/hypergol
Hypergol is a Data Science/Machine Learning productivity toolkit to accelerate any projects into...
d-led/gen_server_virtual_time
virtual time-based extension to the GenServer behavior that allows testing time-based processes...
hyperpolymath/anvomidaviser
Convert ISU notation to formal figure skating programs via Anvomidav
hyperpolymath/atsiser
Wrap C codebases in ATS linear types for zero-cost memory safety