Vivek Sarkar
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
Research Subjects
Vivek Sarkar has a total of 87 co-authors. Here are the top co-authors by number of shared publications:
- Jun Shirako
Georgia Institute of Technology
6 shared publications - Akihiro Hayashi
Georgia Institute of Technology
5 shared publications - Oscar Hernandez
Oak Ridge National Laboratory, Oak Ridge, USA
5 shared publications - Sri Raj Paul
Intel Corporation
4 shared publications - Aaron Welch
Oak Ridge National Laboratory, Oak Ridge, USA
3 shared publications - Akihiro Hayashi
Georgia Institute of Technology, Atlanta, USA
3 shared publications
Latest Publications
- Open Access
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 620-627
Performance Analysis of Conveyors: Memory Dominates?
Small-message aggregation is critical for scaling irregular, communication intensive applications in high-performance computing. In this paper, contrary to conventional wisdom, we present the first systematic study showing that memory contention, not network bandwidth, is the dominant bottleneck in message aggregation runtimes. Using the state-of-the-art conveyors library as our reference implementation, we conducted extensive experiments on HPC systems featuring Slingshot 11 and InfiniBand interconnects, scaling to 16k cores (256 nodes) and processing 10s–100s GB of data. Our measurements reveal that interference between user data and aggregation buffers drives LLC miss rates to 77%, inflating memory costs by 2–3× over the algorithmic baseline. Consequently, we advocate for dedicated near-memory subsystems to improve the scalability and performance of message aggregation runtimes. This paper also demonstrates up to an order of magnitude higher latency for conveyor termination compared to a traditional HPC barrier, and it examines the impact of communication context isolation and the critical challenge of programmability.
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 620-627
Open AccessPerformance Analysis of Conveyors: Memory Dominates?
Small-message aggregation is critical for scaling irregular, communication intensive applications in high-performance computing. In this paper, contrary to conventional wisdom, we present the first systematic study showing that memory contention, not network bandwidth, is the dominant bottleneck in message aggregation runtimes. Using the state-of-the-art conveyors library as our reference implementation, we conducted extensive experiments on HPC systems featuring Slingshot 11 and InfiniBand interconnects, scaling to 16k cores (256 nodes) and processing 10s–100s GB of data. Our measurements reveal that interference between user data and aggregation buffers drives LLC miss rates to 77%, inflating memory costs by 2–3× over the algorithmic baseline. Consequently, we advocate for dedicated near-memory subsystems to improve the scalability and performance of message aggregation runtimes. This paper also demonstrates up to an order of magnitude higher latency for conveyor termination compared to a traditional HPC barrier, and it examines the impact of communication context isolation and the critical challenge of programmability.
- Open Access
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 238-252
Toward a Unified GPU-Aware OpenSHMEM Specification
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 238-252
Open AccessToward a Unified GPU-Aware OpenSHMEM Specification
- Open Access
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 217-228
Heading Towards Energy Savings or Just Performance: Case-Study on Message Aggregation-Based Runtimes
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 217-228
Open AccessHeading Towards Energy Savings or Just Performance: Case-Study on Message Aggregation-Based Runtimes
- Open Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 8 (OOPSLA2) , 791-816
Fully Verified Instruction Scheduling
CompCert project, the state-of-the-art compiler that achieves the first end-to-end formally verified C compiler, does not support fully verified instruction scheduling. Instead, existing research that works on such topics only implements translation validation. This means they do not have direct formal proof that the scheduling algorithm is correct, but only a posterior validation to check each compiling case. Using such a method, CompCert accepts a valid C program and compiles correctly only when the untrusted scheduler generates a correct result. However, it does not guarantee the complete correctness of the scheduler. It also causes compile-time validation overhead in the view of runtime performance. In this work, we present the first achievement in developing a mechanized library for fully verified instruction scheduling while keeping the proof workload acceptably lightweight. The idea to reduce the proof length is to exploit a simple property that the topological reordering of a topological sorted list is equal to a sequence of swapping adjacent unordered elements. Together with the transitivity of semantic simulation relation, the only burden will become proving the semantic preservation of a transition that only swaps two adjacent independent instructions inside one block. After successfully proving this result, proving the correctness of any new instruction scheduling algorithm only requires proof that it preserved the syntax-level dependence among instructions, instead of reasoning about semantics details every time. We implemented a mechanized library of such methods in the Coq proof assistant based on CompCert’s library as a framework and used the list scheduling algorithm as a case study to show the correctness can be formally proved using our theory. We show that with our method that abstracts away the semantics details, it is flexible to implement any scheduler that reorders instructions with little extra proof burden. Our scheduler in the case study also abstracts away the outside scheduling heuristic as a universal parameter so it is flexible to modify without touching any correctness proof.
- 8 October 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 8 (OOPSLA2) , 791-816
Open AccessFully Verified Instruction Scheduling
CompCert project, the state-of-the-art compiler that achieves the first end-to-end formally verified C compiler, does not support fully verified instruction scheduling. Instead, existing research that works on such topics only implements translation validation. This means they do not have direct formal proof that the scheduling algorithm is correct, but only a posterior validation to check each compiling case. Using such a method, CompCert accepts a valid C program and compiles correctly only when the untrusted scheduler generates a correct result. However, it does not guarantee the complete correctness of the scheduler. It also causes compile-time validation overhead in the view of runtime performance. In this work, we present the first achievement in developing a mechanized library for fully verified instruction scheduling while keeping the proof workload acceptably lightweight. The idea to reduce the proof length is to exploit a simple property that the topological reordering of a topological sorted list is equal to a sequence of swapping adjacent unordered elements. Together with the transitivity of semantic simulation relation, the only burden will become proving the semantic preservation of a transition that only swaps two adjacent independent instructions inside one block. After successfully proving this result, proving the correctness of any new instruction scheduling algorithm only requires proof that it preserved the syntax-level dependence among instructions, instead of reasoning about semantics details every time. We implemented a mechanized library of such methods in the Coq proof assistant based on CompCert’s library as a framework and used the list scheduling algorithm as a case study to show the correctness can be formally proved using our theory. We show that with our method that abstracts away the semantics details, it is flexible to implement any scheduler that reorders instructions with little extra proof burden. Our scheduler in the case study also abstracts away the outside scheduling heuristic as a universal parameter so it is flexible to modify without touching any correctness proof.
- 16 September 2024
- Published by Springer Nature
- p. 161-175
Visualizing Correctness Issues in OpenMP Programs
- 16 September 2024
- Published by Springer Nature
- p. 161-175
Visualizing Correctness Issues in OpenMP Programs
- Open Access
- 17 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 113-125
APPy: Annotated Parallelism for Python on GPUs
GPUs are increasingly being used used to speed up Python applications in the scientific computing and machine learning domains. Currently, the two common approaches to leveraging GPU acceleration in Python are 1) create a custom native GPU kernel, and import it as a function that can be called from Python; 2) use libraries such as CuPy, which provides pre-defined GPU-implementation-backed tensor operators. The first approach is very flexible but requires tremendous manual effort to create a correct and high performance GPU kernel. While the second approach dramatically improves productivity, it is limited in its generality, as many applications cannot be expressed purely using CuPy’s pre-defined tensor operators. Additionally, redundant memory access can often occur between adjacent tensor operators due to the materialization of intermediate results. In this work, we present APPy (Annotated Parallelism for Python), which enables users to parallelize generic Python loops and tensor expressions for execution on GPUs by adding simple compiler directives (annotations) to Python code. Empirical evaluation on 20 scientific computing kernels from the literature on a server with an AMD Ryzen 7 5800X 8-Core CPU and an NVIDIA RTX 3090 GPU demonstrates that with simple pragmas APPy is able to generate more efficient GPU code and achieves significant geometric mean speedup relative to CuPy (30× on average), and to three state-of-the-art Python compilers, Numba (8.3× on average), DaCe-GPU (3.1× on average) and JAX-GPU (18.8× on average).
- 17 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 113-125
Open AccessAPPy: Annotated Parallelism for Python on GPUs
GPUs are increasingly being used used to speed up Python applications in the scientific computing and machine learning domains. Currently, the two common approaches to leveraging GPU acceleration in Python are 1) create a custom native GPU kernel, and import it as a function that can be called from Python; 2) use libraries such as CuPy, which provides pre-defined GPU-implementation-backed tensor operators. The first approach is very flexible but requires tremendous manual effort to create a correct and high performance GPU kernel. While the second approach dramatically improves productivity, it is limited in its generality, as many applications cannot be expressed purely using CuPy’s pre-defined tensor operators. Additionally, redundant memory access can often occur between adjacent tensor operators due to the materialization of intermediate results. In this work, we present APPy (Annotated Parallelism for Python), which enables users to parallelize generic Python loops and tensor expressions for execution on GPUs by adding simple compiler directives (annotations) to Python code. Empirical evaluation on 20 scientific computing kernels from the literature on a server with an AMD Ryzen 7 5800X 8-Core CPU and an NVIDIA RTX 3090 GPU demonstrates that with simple pragmas APPy is able to generate more efficient GPU code and achieves significant geometric mean speedup relative to CuPy (30× on average), and to three state-of-the-art Python compilers, Numba (8.3× on average), DaCe-GPU (3.1× on average) and JAX-GPU (18.8× on average).
- Open Access
- 16 October 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 7 (OOPSLA2) , 773-800
Concrete Type Inference for Code Optimization using Machine Learning with SMT Solving
Despite the widespread popularity of dynamically typed languages such as Python, it is well known that they pose significant challenges to code optimization due to the lack of concrete type information. To overcome this limitation, many ahead-of-time optimizing compiler approaches for Python rely on programmers to provide optional type information as a prerequisite for extensive code optimization. Since few programmers provide this information, a large majority of Python applications are executed without the benefit of code optimization, thereby contributing collectively to a significant worldwide wastage of compute and energy resources. In this paper, we introduce a new approach to concrete type inference that is shown to be effective in enabling code optimization for dynamically typed languages, without requiring the programmer to provide any type information. We explore three kinds of type inference algorithms in our approach based on: 1) machine learning models including GPT-4, 2) constraint-based inference based on SMT solving, and 3) a combination of 1) and 2). Our approach then uses the output from type inference to generate multi-version code for a bounded number of concrete type options, while also including a catch-all untyped version for the case when no match is found. The typed versions are then amenable to code optimization. Experimental results show that the combined algorithm in 3) delivers far superior precision and performance than the separate algorithms for 1) and 2). The performance improvement due to type inference, in terms of geometric mean speedup across all benchmarks compared to standard Python, when using 3) is 26.4× with Numba as an AOT optimizing back-end and 62.2× with the Intrepydd optimizing compiler as a back-end. These vast performance improvements can have a significant impact on programmers’ productivity, while also reducing their applications’ use of compute and energy resources.
- 16 October 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 7 (OOPSLA2) , 773-800
Open AccessConcrete Type Inference for Code Optimization using Machine Learning with SMT Solving
Despite the widespread popularity of dynamically typed languages such as Python, it is well known that they pose significant challenges to code optimization due to the lack of concrete type information. To overcome this limitation, many ahead-of-time optimizing compiler approaches for Python rely on programmers to provide optional type information as a prerequisite for extensive code optimization. Since few programmers provide this information, a large majority of Python applications are executed without the benefit of code optimization, thereby contributing collectively to a significant worldwide wastage of compute and energy resources. In this paper, we introduce a new approach to concrete type inference that is shown to be effective in enabling code optimization for dynamically typed languages, without requiring the programmer to provide any type information. We explore three kinds of type inference algorithms in our approach based on: 1) machine learning models including GPT-4, 2) constraint-based inference based on SMT solving, and 3) a combination of 1) and 2). Our approach then uses the output from type inference to generate multi-version code for a bounded number of concrete type options, while also including a catch-all untyped version for the case when no match is found. The typed versions are then amenable to code optimization. Experimental results show that the combined algorithm in 3) delivers far superior precision and performance than the separate algorithms for 1) and 2). The performance improvement due to type inference, in terms of geometric mean speedup across all benchmarks compared to standard Python, when using 3) is 26.4× with Numba as an AOT optimizing back-end and 62.2× with the Intrepydd optimizing compiler as a back-end. These vast performance improvements can have a significant impact on programmers’ productivity, while also reducing their applications’ use of compute and energy resources.
- 2 May 2023
- Published by Springer Nature
- p. 197-210
HIPLZ: Enabling Performance Portability for Exascale Systems
- 2 May 2023
- Published by Springer Nature
- p. 197-210
HIPLZ: Enabling Performance Portability for Exascale Systems
- Open Access
Enabling Multi-threading in Heterogeneous Quantum-Classical Programming Models
In this paper, we address some of the key limitations to realizing a generic heterogeneous parallel programming model for quantum-classical heterogeneous platforms. We discuss our experience in enabling user-level multi-threading in QCOR as well as challenges that need to be addressed for programming future quantum-classical systems. Specifically, we discuss our design and implementation of introducing C++-based parallel constructs to enable 1) parallel execution of a quantum kernel with std::thread and 2) asynchronous execution with std::async. To do so, we provide a detailed overview of the current implementation of the QCOR programming model and runtime, and discuss how we add 1) thread-safety to some of its user-facing API routines, and 2) increase parallelism in QCOR by removing data races that inhibit multi-threading so as to better utilize available computing resources. We also present preliminary performance results with the Quantum++ back end on a single-node Ryzen9 3900X machine that has 12 physical cores (24 hardware threads) with 128GB of RAM. The results show that running two Bell kernels with 12 threads per kernel in parallel outperforms running the kernels one after the other each with 24 threads (1.63x improvement). In addition, we observe the same trend when running two Shor's algorthm kernels in parallel (1.22x faster than executing the kernels one after the other). Furthermore, the parallel version is better in terms of strong scalability. We believe that our design, implementation, and results will open up an opportunity not only for 1) enabling quicker prototyping of parallel/asynchrony-aware quantum-classical algorithms on quantum circuit simulators in the short-term, but also for 2) realizing a generic heterogeneous parallel programming model for quantum-classical heterogeneous platforms in the long-term.
Open AccessEnabling Multi-threading in Heterogeneous Quantum-Classical Programming Models
In this paper, we address some of the key limitations to realizing a generic heterogeneous parallel programming model for quantum-classical heterogeneous platforms. We discuss our experience in enabling user-level multi-threading in QCOR as well as challenges that need to be addressed for programming future quantum-classical systems. Specifically, we discuss our design and implementation of introducing C++-based parallel constructs to enable 1) parallel execution of a quantum kernel with std::thread and 2) asynchronous execution with std::async. To do so, we provide a detailed overview of the current implementation of the QCOR programming model and runtime, and discuss how we add 1) thread-safety to some of its user-facing API routines, and 2) increase parallelism in QCOR by removing data races that inhibit multi-threading so as to better utilize available computing resources. We also present preliminary performance results with the Quantum++ back end on a single-node Ryzen9 3900X machine that has 12 physical cores (24 hardware threads) with 128GB of RAM. The results show that running two Bell kernels with 12 threads per kernel in parallel outperforms running the kernels one after the other each with 24 threads (1.63x improvement). In addition, we observe the same trend when running two Shor's algorthm kernels in parallel (1.22x faster than executing the kernels one after the other). Furthermore, the parallel version is better in terms of strong scalability. We believe that our design, implementation, and results will open up an opportunity not only for 1) enabling quicker prototyping of parallel/asynchrony-aware quantum-classical algorithms on quantum circuit simulators in the short-term, but also for 2) realizing a generic heterogeneous parallel programming model for quantum-classical heterogeneous platforms in the long-term.
- 1 August 2022
- Published by Springer Nature
- p. 350-366
Automatic Parallelization of Python Programs for Distributed Heterogeneous Computing
- 1 August 2022
- Published by Springer Nature
- p. 350-366
Automatic Parallelization of Python Programs for Distributed Heterogeneous Computing