Compiler Management of Communication and Parallelism for Quantum Computation

Abstract

Quantum computing (QC) offers huge promise to accelerate a range of computationally intensive benchmarks. Quantum computing is limited, however, by the challenges of decoherence: i.e., a quantum state can only be maintained for short windows of time before it decoheres. While quantum error correction codes can protect against decoherence, fast execution time is the best defense against decoherence, so efficient architectures and effective scheduling algorithms are necessary. This paper proposes the Multi-SIMD QC architecture and then proposes and evaluates effective schedulers to map benchmark descriptions onto Multi-SIMD architectures. The Multi-SIMD model consists of a small number of SIMD regions, each of which may support operations on up to thousands of qubits per cycle. Efficient Multi-SIMD operation requires efficient scheduling. This work develops schedulers to reduce communication requirements of qubits between operating regions, while also improving parallelism.We find that communication to global memory is a dominant cost in QC. We also note that many quantum benchmarks have long serial operation paths (although each operation may be data parallel). To exploit this characteristic, we introduce Longest-Path-First Scheduling (LPFS) which pins operations to SIMD regions to keep data in-place and reduce communication to memory. The use of small, local scratchpad memories also further reduces communication. Our results show a 3% to 308% improvement for LPFS over conventional scheduling algorithms, and an additional 3% to 64% improvement using scratchpad memories. Our work is the most comprehensive software-to-quantum toolflow published to date, with efficient and practical scheduling techniques that reduce communication and increase parallelism for full-scale quantum code executing up to a trillion quantum gate operations.

OpenFermion: the electronic structure package for quantum computers

“…Moreover, to maximize usefulness within the field, every effort has been made to design OpenFermion as a modular library which is agnostic with respect to quantum programming language frameworks. Through its plugin system, OpenFermion is able to interface with, and benefit from, any of the frameworks being developed for both more abstract quantum software and hardware specific compilation [70][71][72][73][74][75][76][77][78][79][80].…”

Faster and More Reliable Quantum SWAPs via Native Gates

“…As indicated by the two dashed boxes in Figure 6, this concatenated view reveals new opportunities for optimization that are invisible when we consider the CNOT and NOTC as atomic basis gates. This observation is akin to interprocedural optimization in classical compilers [35,36] and to fine-grained scheduling in quantum compilers [37]. On the top qubit, the Ry(−90) Ry(180) sequence can be simplified into a single sequence.…”

Saqip

“…Heckey et al [50] proposed an ion trap multi-SIMD architecture composed of k SIMD operating regions each with a width or qubit capacity of d to execute many quantum applications written in Scaffold programming language. Its architecture model is so similar to QLA and has the same disadvantages.…”

“…All edges of the interaction graph should be examined in Step 3; therefore, this step needs O (n д ) examinations. The k-way multilevel partitioning algorithm (Step 4) computes a k-way partitioning of the interaction graph of qubits in O (n e ) = O (n д ) time [50] where n e is the number of edges of the interaction graph. The time complexity of Algorithm 2 (Line 6) is O ((…”