Jiyuan Wang

Compiler technologies in deep learning and domain-specific hardware acceleration are increasingly adopting extensible compiler frameworks such as Multi-Level Intermediate Representation (MLIR) to facilitate more efficient development. With MLIR, compiler developers can easily define their own custom IRs in the form of MLIR dialects. However, the diversity and rapid evolution of such custom IRs make it impractical to manually write a custom test generator for each dialect. To address this problem, we design a new test generator called SYNTHFUZZ that combines grammar-based fuzzing with custom mutation synthesis. The key essence of SYNTHFUZZ is two fold: (1) It automatically infers parameterized context-dependent custom mutations from existing test cases. (2) It then concretizes the mutation’s content depending on the target context and reduces the chance of inserting invalid edits by performing k-ancestor and prefix/postfix matching. It obviates the need to manually define custom mutation operators for each dialect. We compare SYNTHFUZZ to three baselines: Grammarinator—a grammar-based fuzzer without custom mutations, MLIRSmith—a custom test generator for MLIR core dialects, and NeuRI—a custom test generator for ML models with parameterization of tensor shapes. We conduct this comprehensive comparison on four different MLIR projects. Each project defines a new set of MLIR dialects where manually writing a custom test generator would take weeks of effort. Our evaluation shows that SYNTHFUZZ on average improves MLIR dialect pair coverage by 1.75×, which increases branch coverage by 1.22×. Further, we show that our context dependent custom mutation increases the proportion of valid tests by up to 1.11×, indicating that SYNTHFUZZ correctly concretizes its parameterized mutations with respect to the target context. Parameterization of the mutations reduces the fraction of tests violating the base MLIR constraints by 0.57×, increasing the time spent fuzzing dialect-specific code

Data & code for replication

There is a growing interest in the computer architecture community to incorporate heterogeneity and specialization to improve performance. Developers can create heterogeneous applications that consist of both host code and kernel code, where compute-intensive kernels can be offloaded from CPU to hardware accelerators. Testing such applications on real heterogeneous architectures is extremely challenging as kernels are black boxes, providing no information about the kernels’ internal execution to diagnose issues such as silent hangs or unexpected results. Additionally, inputs for heterogeneous applications are often large matrices, leading to a vast search space for identifying bug-revealing inputs. We propose a novel fuzz testing technique, HFuzz, to enable efficient testing on real heterogeneous architectures. HFuzz aims to increase both the observability of hardware kernels and testing efficiency through a three-pronged approach. First, HFuzz automatically generates test guidance by inserting device-side in-kernel hardware probes in addition to host-side software monitors. Second, it performs rapid input space exploration by offloading computeintensive input mutations to hardware kernels. Third, HFuzz parallelizes fuzzing and enables fast on-chip memory access, by utilizing four FPGA-level optimizations including loop unrolling, shannonization, data preloading, and dynamic kernel sharing. We evaluate HFuzz on seven open-source OneAPI subjects from Intel. HFuzz speeds up fuzz testing by 4.7× with HW-accelerated input space exploration. By incorporating HW probes in tandem with SW monitors, HFuzz finds 33 defects within 4 hours and reveals 25 unique, unexpected behavior symptoms that could not be found by SW-based monitoring alone. HFuzz is the first to design hardware optimizations to accelerate fuzz testing.

Data & code for replication

Despite the trend of incorporating heterogeneity and specialization in hardware, the development of heterogeneous applications is limited to a handful of engineers with deep hardware expertise. We propose HeteroGen that takes C/C++ code as input and automatically generates an HLS version with test behavior preservation and better performance. Key to the success of HeteroGen is adapting the idea of search-based program repair to the heterogeneous computing domain, while addressing two technical challenges. First, the turn-around time of HLS compilation and simulation is much longer than the usual C/C++ compilation and execution time; therefore, HeteroGen applies pattern-oriented program edits guided by common fix patterns and their dependences. Second, behavior and performance checking requires testing, but test cases are often unavailable. Thus, HeteroGen auto-generates test inputs suitable for checking C to HLS-C conversion errors, while providing high branch coverage for the original C code.

Data & code for replication

The past few years have witnessed the proliferation of quantum software stacks (QSS) developed in response to rapid hardware advances in quantum computing. A QSS includes a quantum programming language, an optimizing compiler that compiles a quantum algorithm expressed in a high-level language into quantum gate instructions, a quantum simulator that emu- lates these instructions on a classical device, the control software that turns circuits into analog signals sent to the quantum computer, and execution on very expensive quantum hardware. In comparison to traditional compilers and architecture simulators, QSSes are difficult to tests due to the probabilistic nature of results, the lack of clear hardware specifications, and quantum programming complexity. This work devises a novel differential testing approach for QSSes, named QDIFF with three major innovations: (1) We generate input programs to be tested via semantics-preserving, source to source transformation to explore program variants. (2) We speed up differential testing by filtering out quantum circuits that are not worthwhile to execute on quantum hardware by analyzing static characteristics such as circuit depth, 2-gate operations, gate error rates, and T1 relaxation time. (3) We design an extensible equivalence checking mechanism via distribution comparison functions such as Kolmogorov–Smirnov test and cross entropy.

Data & code for replication

Slides

Slides for ASE

We propose a novel fuzz testing technique, called heterofuzz, designed to specifically target heterogeneous applications and to detect platform-dependent divergence. The key essence of heterofuzz is that it uses three-pronged approaches to reduce the long latency of repetitively invoking a hardware simulator on a heterogeneous application. First, in addition to monitoring code coverage as a fuzzing guidance mechanism, we analyze synthesis pragmas in kernel code and monitor accelerator-relevant value spectra. Second, we design dynamic probabilistic mutations to increase the chance of hitting divergent behavior under different platforms. Third, we memorize the boundaries of seen kernel inputs and skip HLS simulator invocation if it can expose only redundant divergent behavior. We evaluate heterofuzz on seven real-world heterogeneous applications with FPGA kernels. heterofuzz is 754X faster in exposing the same set of distinct divergence symptoms than naive fuzzing. Probabilistic mutations contribute to 17.5X speed up than the one without. Selective invocation of HLS simulation contributes to 8.8X speed up than the one without.

arXiv (Oct 2018)

Tool paper for BigFuzz

Data & code for replication

video

We propose a novel coverage-guided fuzz testing tool for big data analytics, called BigFuzz. The key essence of our approach is that: (a) we focus on exercising application logic as opposed to increasing framework code coverage by abstracting the DISC framework using specifications. BigFuzz performs automated source to source transformations to construct an equivalent DISC application suitable for fast test generation, and (b) we design schema-aware data mutation operators based on our in-depth study of DISC application error types. BigFuzz speeds up the fuzzing time by 78 to 1477X compared to random fuzzing, improves application code coverage by 20% to 271%, and achieves 33% to 157% improvement in detecting application errors. When compared to the state of the art that uses symbolic execution to test big data analytics, BigFuzz is applicable to twice more programs and can find 81% more bugs.

Data & code for replication

video

We want to use pattern-based approach to automatically generate desired FPGA code.

In this paper, we present QuanFuzz, a search-based test input generator for quantum program. We define the quantum sensitive information to evaluate test input for quantum program and use matrix generator to generate test cases with higher coverage. First, we extract quantum sensitive information -- measurement operations on those quantum registers and the sensitive branches associated with those measurement results, from the quantum source code. Then, we use the sensitive information guided algorithm to mutate the initial input matrix and select those matrices which improve the probability weight for a value of the quantum register to trigger the sensitive branch. The process keeps iterating until the sensitive branch triggered. We tested QuanFuzz on benchmarks and acquired 20% - 60% more coverage compared to traditional testing input generation.

arXiv (Oct 2018)