Cheng Tan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Cheng Tan has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Ang Li
Pacific Northwest National Laboratory
3 shared publications - Anqi Guo
Department of Electrical & Computer Engineering, Boston University, Boston, Massachusetts, USA
2 shared publications - Anthony Skjellum
Tennessee Technological University
2 shared publications - Chunshu Wu
Pacific Northwest National Laboratory
2 shared publications - Jeff Zhang
Arizona State University, Tempe, AZ, USA
2 shared publications - Lei Ju
Shandong University
2 shared publications
Latest Publications
- Open Access
- 8 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 10 (PLDI) , 953-979
NEURA: A Unified and Retargetable Compilation Framework for Coarse-Grained Reconfigurable Architectures
Coarse-Grained Reconfigurable Architectures (CGRAs) are a promising and versatile accelerator platform, offering a balance between the performance and efficiency of specialized accelerators and software programmability. However, their full potential is severely hindered by control flow in accelerated kernels, as control flow (e.g., loops, branches) is fundamentally incompatible with the parallel, data-driven CGRA fabric. Prior strategies to resolve this mismatch in CGRA kernel acceleration are either inefficient, sacrificing performance for generality, or lack generality due to the difficulty of adapting them across different execution models. Thus, a general and unified solution for efficient CGRA kernel acceleration remains elusive. This paper introduces NEURA, a unified and retargetable compilation framework that systematically resolves the control-dataflow mismatch in CGRAs. NEURA's core innovation is a novel, pure dataflow intermediate representation (IR) built on a predicated type system. In this IR, control contexts are embedded as a predicate within each data, making control an intrinsic property of data. This mechanism enables NEURA to systematically flatten complex control flow into a single unified dataflow graph. This unified representation decouples kernel representation from hardware, empowering NEURA to retarget diverse CGRAs with different execution models and microarchitectural features. When targeted to a high-performance spatio-temporal CGRA, NEURA delivers a 2.20x speedup on kernel benchmarks and up to 2.71x geometric mean speedup on real-world applications over state-of-the-art (SOTA) high-performance baselines. It also provides a competitive solution against the SOTA low-power CGRA when retargeted to a spatial-only CGRA. NEURA is open-source and available at https://github.com/coredac/neura.
- 8 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 10 (PLDI) , 953-979
Open AccessNEURA: A Unified and Retargetable Compilation Framework for Coarse-Grained Reconfigurable Architectures
Coarse-Grained Reconfigurable Architectures (CGRAs) are a promising and versatile accelerator platform, offering a balance between the performance and efficiency of specialized accelerators and software programmability. However, their full potential is severely hindered by control flow in accelerated kernels, as control flow (e.g., loops, branches) is fundamentally incompatible with the parallel, data-driven CGRA fabric. Prior strategies to resolve this mismatch in CGRA kernel acceleration are either inefficient, sacrificing performance for generality, or lack generality due to the difficulty of adapting them across different execution models. Thus, a general and unified solution for efficient CGRA kernel acceleration remains elusive. This paper introduces NEURA, a unified and retargetable compilation framework that systematically resolves the control-dataflow mismatch in CGRAs. NEURA's core innovation is a novel, pure dataflow intermediate representation (IR) built on a predicated type system. In this IR, control contexts are embedded as a predicate within each data, making control an intrinsic property of data. This mechanism enables NEURA to systematically flatten complex control flow into a single unified dataflow graph. This unified representation decouples kernel representation from hardware, empowering NEURA to retarget diverse CGRAs with different execution models and microarchitectural features. When targeted to a high-performance spatio-temporal CGRA, NEURA delivers a 2.20x speedup on kernel benchmarks and up to 2.71x geometric mean speedup on real-world applications over state-of-the-art (SOTA) high-performance baselines. It also provides a competitive solution against the SOTA low-power CGRA when retargeted to a spatial-only CGRA. NEURA is open-source and available at https://github.com/coredac/neura.
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1285-1300
Neura: A Unified Framework for Hierarchical and Adaptive CGRAs
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1285-1300
Open AccessNeura: A Unified Framework for Hierarchical and Adaptive CGRAs
- Top Cited PapersOpen Access
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 845-861
PICACHU: Plug-In CGRA Handling Upcoming Nonlinear Operations in LLMs
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 845-861
Top Cited PapersOpen AccessPICACHU: Plug-In CGRA Handling Upcoming Nonlinear Operations in LLMs
- Open Access
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 410-425
Enhancing CGRA Efficiency Through Aligned Compute and Communication Provisioning
Coarse-grained Reconfigurable Arrays (CGRAs) are domain-agnostic accelerators that enhance the energy efficiency of resource-constrained edge devices. The CGRA landscape is diverse, exhibiting trade-offs between performance, efficiency, and architectural specialization. However, CGRAs often overprovision communication resources relative to their modest computing capabilities. This occurs because the theoretically provisioned programmability for CGRAs often proves superfluous in practical implementations. In this paper, we propose Plaid, a novel CGRA architecture and compiler that aligns compute and communication capabilities, thereby significantly improving energy and area efficiency while preserving its generality and performance. We demonstrate that the dataflow graph, representing the target application, can be decomposed into smaller, recurring communication patterns called motifs. The primary contribution is the identification of these structural motifs within the dataflow graphs and the development of an efficient collective execution and routing strategy tailored to these motifs. The Plaid architecture employs a novel collective processing unit that can execute multiple operations of a motif and route related data dependencies together. The Plaid compiler can hierarchically map the dataflow graph and judiciously schedule the motifs. Our design achieves a 43% reduction in power consumption and 46% area savings compared to the baseline high-performance spatio-temporal CGRA, all while preserving its generality and performance levels. In comparison to the baseline energy-efficient spatial CGRA, Plaid offers a 1.4× performance improvement and a 48% area savings, with almost the same power.
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 410-425
Open AccessEnhancing CGRA Efficiency Through Aligned Compute and Communication Provisioning
Coarse-grained Reconfigurable Arrays (CGRAs) are domain-agnostic accelerators that enhance the energy efficiency of resource-constrained edge devices. The CGRA landscape is diverse, exhibiting trade-offs between performance, efficiency, and architectural specialization. However, CGRAs often overprovision communication resources relative to their modest computing capabilities. This occurs because the theoretically provisioned programmability for CGRAs often proves superfluous in practical implementations. In this paper, we propose Plaid, a novel CGRA architecture and compiler that aligns compute and communication capabilities, thereby significantly improving energy and area efficiency while preserving its generality and performance. We demonstrate that the dataflow graph, representing the target application, can be decomposed into smaller, recurring communication patterns called motifs. The primary contribution is the identification of these structural motifs within the dataflow graphs and the development of an efficient collective execution and routing strategy tailored to these motifs. The Plaid architecture employs a novel collective processing unit that can execute multiple operations of a motif and route related data dependencies together. The Plaid compiler can hierarchically map the dataflow graph and judiciously schedule the motifs. Our design achieves a 43% reduction in power consumption and 46% area savings compared to the baseline high-performance spatio-temporal CGRA, all while preserving its generality and performance levels. In comparison to the baseline energy-efficient spatial CGRA, Plaid offers a 1.4× performance improvement and a 48% area savings, with almost the same power.
- Open Access
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
FHE-CGRA: Enable Efficient Acceleration of Fully Homomorphic Encryption on CGRAs
Fully Homomorphic Encryption (FHE) is an attractive privacy-preserving technique that allows computation directly on encrypted data without decryption. However, it incurs significant performance and memory costs due to intensive computations. In this work, we investigate the execution of FHE-enabled machine learning (ML) applications. We show that the runtime hardware reconfigurability of the underlying execution units of homomorphic operations is highly desirable for efficient hardware resource utilization during FHE-ML execution, due to the changing FHE encryption variants across different ML stages (e.g., the multiplicative level of the ciphertext) and corresponding optimal execution unit design. Based on the observation, we propose FHE-CGRA, a coarse-grained re-configurable architecture (CGRA) acceleration framework with an MLIR-based compiler toolchain for end-to-end homomorphic applications. The experiment shows that FHE-CGRA achieves up-to 8.15× speedup against a conventional CGRA baseline for accelerating the inference of FHE-encrypted convolution neural network (FHE-CNN) models, and up-to 16.48× power efficiency w.r.t. the state-of-the-art FPGA-based FHE-CNN accelerator design.
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessFHE-CGRA: Enable Efficient Acceleration of Fully Homomorphic Encryption on CGRAs
Fully Homomorphic Encryption (FHE) is an attractive privacy-preserving technique that allows computation directly on encrypted data without decryption. However, it incurs significant performance and memory costs due to intensive computations. In this work, we investigate the execution of FHE-enabled machine learning (ML) applications. We show that the runtime hardware reconfigurability of the underlying execution units of homomorphic operations is highly desirable for efficient hardware resource utilization during FHE-ML execution, due to the changing FHE encryption variants across different ML stages (e.g., the multiplicative level of the ciphertext) and corresponding optimal execution unit design. Based on the observation, we propose FHE-CGRA, a coarse-grained re-configurable architecture (CGRA) acceleration framework with an MLIR-based compiler toolchain for end-to-end homomorphic applications. The experiment shows that FHE-CGRA achieves up-to 8.15× speedup against a conventional CGRA baseline for accelerating the inference of FHE-encrypted convolution neural network (FHE-CNN) models, and up-to 16.48× power efficiency w.r.t. the state-of-the-art FPGA-based FHE-CNN accelerator design.
- Open Access
- 30 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 413-425
SmartFuse: Reconfigurable Smart Switches to Accelerate Fused Collectives in HPC Applications
Communication switches have sometimes been augmented to process collectives, e.g., in the IBM BlueGene and Mellanox SHArP switches. In this work, we find that there is a great acceleration opportunity through the further augmentation of switches to accelerate more complex functions that combine communication with computation. We consider three types of such functions. The first is fully-fused collectives built by fusing multiple existing collectives like Allreduce with Alltoall. The second is semi-fused collectives built by combining a collective with another computation. The third are higher-order collectives built by combining multiple computations and communications, such as to perform matrix-matrix multiply (PGEMM). In this work, we propose a framework called SmartFuse to accelerate fused collective functions. The core of SmartFuse is a reconfigurable smart switch to support these operations. The semi/fully fused collectives are implemented with a CGRA-like architecture, while higher-order collectives are implemented with a more specialized computational unit that can also schedule communication. Supporting our framework is software to evaluate and translate relevant parts of the input program, compile them into a control data flow graph, and then map this graph to the switch hardware. The proposed framework, once deployed, has the strong potential to accelerate existing HPC applications transparently by encapsulation within an MPI implementation. Experimental results show that this approach improves the performance of the PGEMM kernel, miniFE, and AMG by, on average, 94%, 15%, and 13%, respectively.
- 30 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 413-425
Open AccessSmartFuse: Reconfigurable Smart Switches to Accelerate Fused Collectives in HPC Applications
Communication switches have sometimes been augmented to process collectives, e.g., in the IBM BlueGene and Mellanox SHArP switches. In this work, we find that there is a great acceleration opportunity through the further augmentation of switches to accelerate more complex functions that combine communication with computation. We consider three types of such functions. The first is fully-fused collectives built by fusing multiple existing collectives like Allreduce with Alltoall. The second is semi-fused collectives built by combining a collective with another computation. The third are higher-order collectives built by combining multiple computations and communications, such as to perform matrix-matrix multiply (PGEMM). In this work, we propose a framework called SmartFuse to accelerate fused collective functions. The core of SmartFuse is a reconfigurable smart switch to support these operations. The semi/fully fused collectives are implemented with a CGRA-like architecture, while higher-order collectives are implemented with a more specialized computational unit that can also schedule communication. Supporting our framework is software to evaluate and translate relevant parts of the input program, compile them into a control data flow graph, and then map this graph to the switch hardware. The proposed framework, once deployed, has the strong potential to accelerate existing HPC applications transparently by encapsulation within an MPI implementation. Experimental results show that this approach improves the performance of the PGEMM kernel, miniFE, and AMG by, on average, 94%, 15%, and 13%, respectively.
- Open Access
- 21 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 450-462
FLASH: FPGA-Accelerated Smart Switches with GCN Case Study
Some communication switches, e.g., the Mellanox SHArP and those in the IBM BlueGene clusters, are augmented to process packets at the application level with fixed-function collectives. This approach, however, lacks flexibility, which limits their applicability in diverse and dynamic workloads. Recently, a new type of programmable packet processor, which uses high-level languages, e.g., P4, has emerged as a possible candidate. P4-based switches, however, fall short in certain applications, including machine learning, where capabilities not currently supported by P4 are needed. These include more complex calculation, such as sparse computation and fused multiply-accumulate, data-intensive floating point operations, data reuse, and significant memory. The problem addressed here is that such a switch augmentation needs to support: a large amount of state, significant flexible compute capability, and ease of programming, all while maintaining full functionality, including ensuring high throughput, and demonstrating utility. In this work, we propose a programmable look-aside-type accelerator that can be embedded into, or attached to, existing communication switch pipelines and that is capable of processing packets at line rate. The proposed in-switch accelerator is based on mixing an ISA (subset of RISC-V instructions) with dataflow graphs (found in CGRAs). To augment performance, vector instructions are also supported. To facilitate usability, we have developed a complete toolchain to compile user-provided C/C++ codes to appropriate back-end instructions for configuring the accelerator. While this approach is flexible enough to support various workloads, in this paper, we consider Graph Convolutional Networks (GCNs) as a case study. Experimental results show that this approach considerably improves the performance of distributed GCN applications.
- 21 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 450-462
Open AccessFLASH: FPGA-Accelerated Smart Switches with GCN Case Study
Some communication switches, e.g., the Mellanox SHArP and those in the IBM BlueGene clusters, are augmented to process packets at the application level with fixed-function collectives. This approach, however, lacks flexibility, which limits their applicability in diverse and dynamic workloads. Recently, a new type of programmable packet processor, which uses high-level languages, e.g., P4, has emerged as a possible candidate. P4-based switches, however, fall short in certain applications, including machine learning, where capabilities not currently supported by P4 are needed. These include more complex calculation, such as sparse computation and fused multiply-accumulate, data-intensive floating point operations, data reuse, and significant memory. The problem addressed here is that such a switch augmentation needs to support: a large amount of state, significant flexible compute capability, and ease of programming, all while maintaining full functionality, including ensuring high throughput, and demonstrating utility. In this work, we propose a programmable look-aside-type accelerator that can be embedded into, or attached to, existing communication switch pipelines and that is capable of processing packets at line rate. The proposed in-switch accelerator is based on mixing an ISA (subset of RISC-V instructions) with dataflow graphs (found in CGRAs). To augment performance, vector instructions are also supported. To facilitate usability, we have developed a complete toolchain to compile user-provided C/C++ codes to appropriate back-end instructions for configuring the accelerator. While this approach is flexible enough to support various workloads, in this paper, we consider Graph Convolutional Networks (GCNs) as a case study. Experimental results show that this approach considerably improves the performance of distributed GCN applications.
- 19 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 32 (12) , 2880-2892
ARENA: Asynchronous Reconfigurable Accelerator Ring to Enable Data-Centric Parallel Computing
The next generation HPC and data centers are likely to be reconfigurable and data-centric due to the trend of hardware specialization and the emergence of data-driven applications. In this article, we propose ARENA - an asynchronous reconfigurable accelerator ring architecture as a potential scenario on how the future HPC and data centers will be like. Despite using the coarse-grained reconfigurable arrays (CGRAs) as the substrate platform, our key contribution is not only the CGRA-cluster design itself, but also the ensemble of a new architecture and programming model that enables asynchronous tasking across a cluster of reconfigurable nodes, so as to bring specialized computation to the data rather than the reverse. We presume distributed data storage without asserting any prior knowledge on the data distribution. Hardware specialization occurs at runtime when a task finds the majority of data it requires are available at the present node. In other words, we dynamically generate specialized CGRA accelerators where the data reside. The asynchronous tasking for bringing computation to data is achieved by circulating the task token, which describes the dataflow graphs to be executed for a task, among the CGRA cluster connected by a fast ring network. Evaluations on a set of HPC and data-driven applications across different domains show that ARENA can provide better parallel scalability with reduced data movement (53.9 percent). Compared with contemporary compute-centric parallel models, ARENA can bring on average 4.37× speedup. The synthesized CGRAs and their task-dispatchers only occupy 2.93mm$^2$2<; inline-graphic xlink:href="tan-ieq1-3081074.gif"/> chip area under 45nm process technology and can run at 800MHz with on average 759.8mW power consumption. ARENA also supports the concurrent execution of multi-applications, offering ideal architectural support for future high-performance parallel computing and data analytics systems.
- 19 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 32 (12) , 2880-2892
ARENA: Asynchronous Reconfigurable Accelerator Ring to Enable Data-Centric Parallel Computing
The next generation HPC and data centers are likely to be reconfigurable and data-centric due to the trend of hardware specialization and the emergence of data-driven applications. In this article, we propose ARENA - an asynchronous reconfigurable accelerator ring architecture as a potential scenario on how the future HPC and data centers will be like. Despite using the coarse-grained reconfigurable arrays (CGRAs) as the substrate platform, our key contribution is not only the CGRA-cluster design itself, but also the ensemble of a new architecture and programming model that enables asynchronous tasking across a cluster of reconfigurable nodes, so as to bring specialized computation to the data rather than the reverse. We presume distributed data storage without asserting any prior knowledge on the data distribution. Hardware specialization occurs at runtime when a task finds the majority of data it requires are available at the present node. In other words, we dynamically generate specialized CGRA accelerators where the data reside. The asynchronous tasking for bringing computation to data is achieved by circulating the task token, which describes the dataflow graphs to be executed for a task, among the CGRA cluster connected by a fast ring network. Evaluations on a set of HPC and data-driven applications across different domains show that ARENA can provide better parallel scalability with reduced data movement (53.9 percent). Compared with contemporary compute-centric parallel models, ARENA can bring on average 4.37× speedup. The synthesized CGRAs and their task-dispatchers only occupy 2.93mm$^2$2<; inline-graphic xlink:href="tan-ieq1-3081074.gif"/> chip area under 45nm process technology and can run at 800MHz with on average 759.8mW power consumption. ARENA also supports the concurrent execution of multi-applications, offering ideal architectural support for future high-performance parallel computing and data analytics systems.
- Open Access
- 1 January 2020
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Electronics Express
- Vol. 17 (4) , 20190714
Integrated design of X-band phased array antenna with LTCC 3D T/R module
In this paper, a novel design scheme of X-band phased array antenna is introduced. The antenna array is mainly composed of the 3D T/R module, which is based on LTCC technology, and the slotted waveguide antenna. The whole system adopts the vertical interconnected three-dimensional multi-layer technology for the spaceborne synthetic aperture radar (SAR) system. 3D T/R module greatly improves the integration of the system by assembling different multifunctional chips into a complete multi-layer LTCC substrate. The slotted waveguide antenna is connected vertically with the T/R module, the power divider, etc, implementing the integrated design. The test results of the antenna system show that the phased array antenna has a good performance in terms of gain, radiating patterns and so on, which provides a new idea for the integrated design of the phased array antenna.
- 1 January 2020
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Electronics Express
- Vol. 17 (4) , 20190714
Open AccessIntegrated design of X-band phased array antenna with LTCC 3D T/R module
In this paper, a novel design scheme of X-band phased array antenna is introduced. The antenna array is mainly composed of the 3D T/R module, which is based on LTCC technology, and the slotted waveguide antenna. The whole system adopts the vertical interconnected three-dimensional multi-layer technology for the spaceborne synthetic aperture radar (SAR) system. 3D T/R module greatly improves the integration of the system by assembling different multifunctional chips into a complete multi-layer LTCC substrate. The slotted waveguide antenna is connected vertically with the T/R module, the power divider, etc, implementing the integrated design. The test results of the antenna system show that the phased array antenna has a good performance in terms of gain, radiating patterns and so on, which provides a new idea for the integrated design of the phased array antenna.