HJHaipeng Jia

Haipeng Jia

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Haipeng Jia has a total of 46 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    PyramidFFT: Rearchitecting FFT with Matrix-Aligned Nested-Radix for Hierarchical Scratchpad Memory on AI Accelerators

    by Xiang Zhao, Ruge Zhang, Haipeng Jia, Kun Li, Jianliang Xu, Ting Cao, Yunxin Liu, Yunquan Zhang

    Emerging AI accelerators equipped with large-capacity scratchpad memory (SPM) provide high computational throughput and large on-chip storage capacity. However, for memory-bound HPC algorithms such as Fast Fourier Transform (FFT), the hierarchical SPM organization cannot be fully exploited, leading to underutilized compute resources and exacerbated bandwidth bottlenecks. In this paper, we propose PyramidFFT, a memory-efficient FFT system co-designed for AI accelerators with large-capacity SPM. PyramidFFT leverages large-capacity SPM to address the memory-bound problem of FFT through three key techniques: Memory-Aware Nested Network Design tightly couples FFT computation with the memory hierarchy to reduce memory access frequency; Matrix-Aligned Butterfly Layout Optimization, which dynamically adjusts butterfly parallelism and transforms the FFT data layout to better utilize Tensor Core Units (TCUs); Symmetry-Driven Real FFT Compression, which removes conjugate symmetric components in real FFT to further ease memory pressure. The results demonstrate that PyramidFFT mitigates memory-bound limitations, achieving up to an 8.2× efficiency improvement over the baseline without memory-hierarchy mapping. By aligning with the structural characteristics of large-capacity SPM, PyramidFFT bridges the gap between FFT’s memory-bound behavior and the compute-dense design of modern AI accelerators, demonstrating the effectiveness of architecture-aware FFT co-design on SPM-based systems.


  • Open Access

    MatXtract: Sparsity-Aware Matrix Transformation via Cascaded Compute Density EXtraction for SpMV

    by Luhan Wang, Kun Li, Yifeng Chen, Haipeng Jia, Yunquan Zhang, Ting Cao, Yunxin Liu

    Sparse Matrix-Vector multiplication (SpMV) is a fundamental kernel across scientific computing and graph analytics. Modern GPUs feature specialized processing units such as Tensor Core Units (TCUs) for accelerating dense matrix operations. While recent efforts leverage TCUs for SpMV acceleration, direct TCU-only mappings suffer from poor cache utilization and limited performance generalization across diverse sparse matrices. This article presents MatXtract, 1 a sparsity-aware matrix transformation framework that restructures sparse matrices through cascaded compute density extraction, enabling efficient TCU-accelerated SpMV. MatXtract introduces three key components: (1) Compute Density Extraction optimizes memory hierarchy utilization while creating Tensor Core- and CUDA core-friendly computation substrates to enhance TCU compute density and CUDA core load balancing; (2) Cascaded Execution Kernel employs a two-stage cascaded compression that systematically exploits hierarchical sparsity to maximize GPU computational throughput; and (3) Sparsity-Aware Predictor mitigates the mismatch between fixed TCU computation and diverse sparsity through Bayesian optimization for enhanced performance generalization. Extensive evaluations on 2,059 matrices show that MatXtract outperforms cuSPARSE, DASP, CSR5, and Merge-SpMV, achieving higher performance on 96.64% of matrices, with an average 1.98× and up to 8.83× speedup over cuSPARSE on NVIDIA A100 GPUs.


  • CGA: Accelerating BFS Through an Sparsity-Aware Adaptive Framework on Heterogeneous Platforms

    by Lei Xu, Haipeng Jia, Yunquan Zhang

    Direction optimization determines whether to use Sparse Matrix-Sparse Vector Multiplication (SpMSpV) or Sparse Matrix-Dense Vector Multiplication (SpMV) based on the input vector’s sparsity at each iteration of Breadth-First Search (BFS), aiming to achieve the fastest graph traversal. Although prior work on direction optimization has achieved state-of-the-art performance on either CPUs or GPUs, it has not fully leveraged the capabilities of modern heterogeneous platforms. This is because SpMSpV/SpMV execution times on GPUs do not consistently outperform those on CPUs, particularly for SpMSpV. In response, this paper introduces CGA, a machine learning-based adaptive framework for BFS that optimally selects between CPU and GPU kernels, effectively Adapting to diverse real-world graphs, vectors, and computing platforms. Our contributions include a novel set of bucket-based SpMSpV algorithms that significantly enhance kernel performance in high-sparsity scenarios, along with a low-overhead decision tree model and reduced CPU-GPU data transfers. Experimental results show that our framework outperforms previous state-of-the-art methods, achieving up to a 4.91x speedup over CPU-only baseline and 3.27x speedup over GPU-only baseline.


  • IrGEMM: An Input-Aware Tuning Framework for Irregular GEMM on ARM and X86 CPUs

    by Cunyang Wei, Haipeng Jia, Yunquan Zhang, Jianyu Yao, Chendi Li, Wenxuan Cao

    The matrix multiplication algorithm is a fundamental numerical technique in linear algebra and plays a crucial role in many scientific computing applications. Despite the high performance of mainstream basic linear algebra libraries for large-scale dense matrix multiplications, they exhibit poor performance when applied to matrix multiplication with irregular input. This paper proposes an input-aware tuning framework that accounts for application scenarios and computer architectures to provide high-performance irregular matrix multiplication on ARMv8 and X86 CPUs. The framework comprises two stages: the install-time stage and the run-time stage. The install-time stage utilizes our proposed computational template to generate high-performance kernels for general data layout and SIMD-friendly data layout. The run-time stage utilizes a tiling algorithm suitable for irregular GEMM to select the optimal kernel and link as an execution plan. Additionally, load-balanced multi-threaded optimization algorithms are defined to exploit the multi-threading capability of modern processors. Experiments demonstrate that the proposed IrGEMM framework can achieve significant performance improvements for irregular GEMM on both ARMv8 and X86 CPUs compared to other mainstream BLAS libraries.


  • Open Access

    HAM-SpMSpV: an Optimized Parallel Algorithm for Masked Sparse Matrix-Sparse Vector Multiplications on multi-core CPUs

    by Lei Xu, Haipeng Jia, Yunquan Zhang, Luhan Wang, Xianmeng Jiang

    The efficiency of Sparse Matrix-Sparse Vector Multiplication (SpM-SpV) is critically important in fields such as machine learning and graph analytics. In certain algorithms, masked SpMSpV computes only a subset of the result entries. Despite its significance, this selective computation poses unique challenges, and existing algorithms often struggle to exploit the sparsity of the input and the mask vectors concurrently. To boost the efficiency of masked SpMSpV on shared memory architectures, we introduce a hybrid adaptive masked SpMSpV algorithm (HAM-SpMSpV) designed to select the efficient kernel automatically based on input features. This approach builds upon the foundation of a conventional algorithm, incorporating two novel masked SpMSpVs: the pre-bucketing masked SPA-based algorithm and the pre-masking bucketed hash-based algorithm. The newly proposed algorithms significantly expedite computation, especially in scenarios with high sparsity in input vectors and masks. Our evaluation involved extensive testing across a diverse range of real-world graphs, utilizing various sparsity of input vectors and masks. This rigorous testing confirmed that our approach notably outperforms existing solutions. Specifically, it achieves a speedup of up to 1.96 times compared to SuiteSparse:GraphBLAS and a remarkable 6.28 times relative to MKL Graph, demonstrating significant advancements in SpMSpV efficiency.


  • SA_TRSM: A Shape-Aware Auto-Tuning Framework for Small-Scale Irregular-Shaped TRSM

    by Rongyuan Guo, Haipeng Jia, Yunquan Zhang, Mingsen Deng, Cunyang Wei, Wenbin Chang, Xiang Zhao

    TRSM (Triangular Solve with Matrix) is an algorithm in the BLAS library for efficiently solving systems of linear equations, which is widely used in scientific computing, engineering computing, and machine learning. The traditional TRSM algorithm performs well in solving large-scale converging squareshaped matrices but is inefficient in solving small-scale irregularshaped matrices. In this paper, we propose SATRSM, a Shape-Aware auto-tuning framework that is aware of scale size and irregularity, aiming to improve performance on small-scale irregular-shaped TRSM computations. SA TRSM consists of the install-time stage and the run-time stage. In the install-time stage, we designed five components for generating high-performance kernels. In the run-time stage, we designed the Shape-Aware tiling algorithm and Plan Generator for generating an efficient execution plan. The experimental results show that the average performance of SA TRSM in this paper improves by 29.4,16.1,24.6 times, and 7.8 times on double-precision real, single-precision real, doubleprecision complex, and single-precision complex in turn, relative to the algorithms in MKL.


  • Open Access

    OpenFFT: An Adaptive Tuning Framework for 3D FFT on ARM Multicore CPUs

    by Tun Chen, Haipeng Jia, Yunquan Zhang, Kun Li, Zhihao Li, Xiang Zhao, Jianyu Yao, Chendi Li

    The sophisticated hierarchy and shared characteristics of cache in multicore CPU architectures bring challenges to the performance improvement of fundamental algorithms, especially in implementing and optimizing 3D FFT. 3D FFT is a memory-bounded algorithm that contains many highly discretized memory accesses. With the working set scaling, the data locality becomes poor, which is prone to cause serious memory access overhead, especially for high-dimensional data transposition. This paper proposes a 3D FFT optimization framework named OpenFFT. This framework optimizes the memory access of 3D FFT by the following methods, including 1) A novel tiling algorithm, Z-OpenFFT, based on the column-order algorithm for high-dimensional vectorization to improve data locality and eliminate transposition; 2) An efficient search algorithm Section-cache-aware algorithm to optimize the memory access of butterfly network of 1D FFT; 3) A multi-thread allocation model by analyzing the characteristics of cache hierarchy and task size to allocate threads adaptively. Experiments demonstrate that OpenFFT could obtain a more competitive performance than the best configuration of FFTW and ARMPL on ARM CPUs.


  • Open Access

    Abstract 6203: Evaluating cost-effectiveness and clinical utility of a blood-based colorectal cancer (CRC) early detection assay, ColonAiQ࣪, through a real-world study in average-risk population (PreC)

    by Yanbing Ding, Jun Liu, Yongsheng Li, Cuiping Wang, Huisong Luo, Yang Li, Tingdong Tang, Hui Wang, Wenjun Pan, Huimin Yang, et al.

    Background: Effective non-invasive colorectal cancer (CRC) screening assays, with high sensitivity and specificity, are desired to increase patient compliance, improve early detection, and reduce CRC mortality. Current stool-based tests suffer with the handling difficulties with specimen, while blood-based tests that rely on single gene methylation have limited sensitivity. We have developed a multi-locus blood-based assay targeting circulating tumor DNA methylation, ColonAiQ, which was demonstrated the ability of early detection for CRC and advanced adenoma (AA) [1]. Study Design: We further organized a real-world cohort aiming for recruiting 120,000 average-risk population to evaluate ColonAiQ’s cost-effectiveness and clinical utility over a 3-year period. This Prospective evaluation of ColonAiQ, PreC study, is organized in Yangzhou city in China being supported by the local government and hospitals. Results: From Jan. 2021 to Aug. 2021, 21,735 apparently healthy volunteers aging from 40 to 80 (median 61.8) were recruited with 10ml blood draw to process with ColonAiQ assay. One thousand six hundred and thirty (7.5%) were tested positive in ColonAiQ, among which 650 were further examined by colonoscopy followed by pathological diagnosis on the biopsy specimen. We successfully identified 330 patients with neoplasm, including 14 (4.3%) asymptomatic CRC, 99 (30%) AA, 184 (43.9%) multi-adenoma or non-advanced adenoma, 33 (10%) polyps, together with 19 patients with non-neoplastic GI disorders. The positive predictive value (PPV) is primarily estimated as 2.2% for CRC and 15.2% for AA (43.5% for adenoma), although these numbers can be largely influenced by the scale of the sample size. Among those 14 identified CRC cases, none of them were tested positive in fecal immunochemical test (FIT), the current screening method locally available. Conclusion: Results from this real-world analysis of ColonAiQ performance, although a preliminary subset, demonstrates the assay robustness, tester compliance, patient adherence to the test result, substantially maximizing its potential benefits for average-risk CRC screening. ColonAiQ significantly increases the detection rate for precancerous adenomas and early-stage CRC when compared to existing molecular screening tests, which could greatly improve preventative care and CRC patient survival. Citation Format: Yanbing Ding, Jun Liu, Yongsheng Li, Cuiping Wang, Huisong Luo, Yang Li, Tingdong Tang, Hui Wang, Wenjun Pan, Huimin Yang, Haipeng Jia, Yunzhi Zhang, Rui Liu. Evaluating cost-effectiveness and clinical utility of a blood-based colorectal cancer (CRC) early detection assay, ColonAiQ࣪, through a real-world study in average-risk population (PreC) [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 6203.

  • Open Access

    Automatic Generation of High-Performance FFT Kernels on Arm and X86 CPUs

    by Zhihao Li, Haipeng Jia, Yunquan Zhang, Tun Chen, Liang Yuan, Richard Vuduc

    This paper presents AutoFFT, a template-based code generation framework that can automatically generate high-performance FFT kernels for all natural-number radices. AutoFFT is based on the Cooley-Tukey FFT algorithm, which exploits the symmetric and periodic properties of the DFT matrix, as the outer parallelization framework. Because butterflies are the core operations of the Cooley-Tukey algorithm, we explore additional symmetric and periodic properties of the DFT matrix and formulate multiple optimized calculation templates to further reduce the number of floating-point operations for butterflies of arbitrary natural numbers. To fully exploit hardware resources, we encapsulate a series of optimizations in an assembly template optimizer. Given any DFT problem, AutoFFT automatically generates C FFT kernels using these calculation templates and converts them into efficient assembly kernels using the template optimizer. Through a series of experiments on Arm, Intel, and AMD processors, we show that AutoFFT-generated kernels can outperform those in Fastest Fourier Transform in the West (FFTW), the Arm Performance Libraries (ARMPL), and the Intel Math Kernel Library (MKL).