The DOI matches its Crossref record; 199 of the 199 references it cites were found in a registry or an index; 5 of the 49 sources its claims cite were checked for support.
A Survey of CPU-GPU Heterogeneous Computing Techniques
Open accessAbstract
As both CPUs and GPUs become employed in a wide range of applications, it has been acknowledged that both of these Processing Units (PUs) have their unique features and strengths and hence, CPU-GPU collaboration is inevitable to achieve high-performance computing. This has motivated a significant amount of research on heterogeneous computing techniques, along with the design of CPU-GPU fused chips and petascale heterogeneous supercomputers. In this article, we survey Heterogeneous Computing Techniques (HCTs) such as workload partitioning that enable utilizing both CPUs and GPUs to improve performance and/or energy efficiency. We review heterogeneous computing approaches at runtime, algorithm, programming, compiler, and application levels. Further, we review both discrete and fused CPU-GPU systems and discuss benchmark suites designed for evaluating Heterogeneous Computing Systems (HCSs). We believe that this article will provide insights into the workings and scope of applications of HCTs to researchers and motivate them to further harness the computational powers of CPUs and GPUs to achieve the goal of exascale performance.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
This survey reviews CPU-GPU heterogeneous computing techniques (HCTs) that use both processing units to improve performance and/or energy efficiency. It classifies approaches across algorithm/runtime, programming/compiler, energy, fused-vs-discrete architecture, application-domain, and benchmark perspectives.
Key findings
- HCTs are classified by scheduling nature (dynamic vs. static) and workload-partitioning basis, including relative PU performance/load balancing, subtask parallelism or characteristics, floating-point precision, and GPU memory-size limits; pipelining and MapReduce use are also identified.
- Hardware trends show CPU core counts rising to 8–32 cores with >60 likely, CUDA cores increasing from 240 (GTX 280) to 3072 (GTX TITAN X), CPU LLC growing from 32MB (POWER7) to 96MB (POWER8), and GPU L2 caches from 768KB (Fermi) to 2048KB (Maxwell); NVLink promises 5–12× PCIe Gen3 bandwidth.
- Fused CPU-GPU systems reduce data-transfer overhead: Daga et al. report an AMD E-series Zacate APU with only 80 GPU cores providing >3× improvement over a discrete Radeon HD 5870 with 1600 more powerful GPU cores; Spafford et al. find fused systems can have better energy efficiency due to low transfer overhead, but higher CPU-GPU contention and lower compute-intensive CPU performance than discrete designs.
- Energy-saving approaches include intelligent workload partitioning, DVFS on CPU and/or GPU, and resource scaling/low-power modes; benchmark suites include SHOC, Parboil, Rodinia, and Valar. The June 2014 Green500 top 15 systems are all CPU-GPU heterogeneous, and Yang et al. achieve 0.8 PetaFLOP on Tianhe-1A for global atmospheric simulation.
Methods
- Literature survey of heterogeneous computing techniques using both CPU and GPU, covering discrete and fused CPU-GPU architectures; scope excludes FPGA-based heterogeneous systems, GPU-only performance works, load balancing within a single GPU or across multiple GPUs only, and circuit/device/microarchitectural research.
- Works are organized by abstraction level and theme: algorithm/runtime workload partitioning, programming languages/frameworks/compiler techniques, energy efficiency, fused CPU-GPU chips, application domains, and benchmark suites, with classification tables.
- No primary experiments are conducted; the paper synthesizes cited research and reports their evaluation platforms and performance/energy results where available.
Limitations
- The paper states scope limitations: it includes only CPU-GPU systems/techniques, excludes FPGA-based heterogeneous systems, GPU-only works, single-GPU or multi-GPU-only load balancing, and circuit/device/microarchitectural works; it focuses on key research ideas while only mentioning CPU/GPU platforms used in cited experiments.
- Evident from the text: as a survey, it provides no new experimental validation, and its classifications and conclusions depend on the selected literature and reported results, which may not generalize across all HCSs.
- The paper also identifies open needs: fully automatic toolchains, lower-overhead porting of existing CPU/GPU codes, order-of-magnitude energy-efficiency improvement for mobile systems, and more extensive evaluation/development of fused HCSs.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
5 of 49 cited sources checked · 4 supported · 0 flagged · accuracy not yet measured
Every source the paper cites for this claim was checked and supports it.
In the paper
“Due to this, different amount of work-divisions to CPU and GPU can lead to vastly different performance [Grewe and O'Boyle 2011].”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.3.4. Reaping the fruits of advancements in CPU design.
What the sources say
- Supportedcites Grewe and O'Boyle 2011 source
Section 3 (Motivation) compares different CPU–GPU workload splits and reports that assigning just 10% of one program’s work to CPUs makes it more than five times slower than GPU-only execution. It also shows that other programs perform best with different splits, directly supporting the claim. (LLM, conf=0.95)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Thus, a heterogeneous system can provide high performance for a much wider variety of applications and usage scenarios than using either of CPU or GPU alone [Vetter and Mittal 2015].”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.3.1. Acknowledging and leveraging unique architectural strengths of PUs.
What the sources say
- Partly supportedcites Vetter and Mittal 2015 sourceExperimental — accuracy not yet measured
The Introduction says heterogeneous computing has increased computational rates in leading supercomputers. Section 2 describes CPU-like and GPU-like cores whose balance depends on workload. Neither passage establishes that a combined system delivers high performance across a much wider variety of applications and usage scenarios than either CPU or GPU alone. (LLM, conf=0.84)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“It facilitates both task-parallelism and data-parallelism.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 4.4. Design of OpenCL and related frameworks
What the sources say
- Supportedcites Stone et al. 2010 source
The Introduction calls OpenCL a standard for task-parallel and data-parallel heterogeneous computing. The OpenCL programming model section also says it enables applications with either type of computation. (LLM, conf=0.95)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Supported
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“The importance of heterogeneous computing can be seen from the fact that an astonishingly large fraction of TOP500 and Green500 supercomputers now use both CPUs and GPUs [Green500 2014;Top500 2014].”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 1. INTRODUCTION
What the sources say
- Not matchedcites Green500 2014
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites Top500 2014
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:boosted· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Not matched
In the paper
“As a definite case in point, the June 2014 Green500 list of most energy efficient supercomputers shows that all the top 15 systems in the list are CPU-GPU heterogeneous systems [Green500 2014].”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.3.3. Improving resource utilization.
What the sources say
- Not matchedcites Green500 2014
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Not matched
In the paper
“With increasing number of cores, the size of last level cache (LLC) on CPU is also increasing [Mittal 2014b].”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.2.3. Cache size.
What the sources say
- Not matchedcites Mittal 2014b
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Fused HCSs (or APUs) replace the PCIe data transfer cost by fast memory block transfers between the CPU and GPU memory partitions.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 6. FUSED CPU-GPU CHIPS AND COMPARISON WITH DISCRETE SYSTEMS
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesNone of the sources cited for this claim have been checked yet.
In the paper
“The limited bandwidth of PCIe has conventionally remained a bottleneck in GPU performance, especially for applications which transfer large amount of data between CPU and GPU [Gregg and Hazelwood 2011;Lee et al. 2010].”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.2.5. Interconnect bandwidth.
What the sources say
- Not matchedcites Gregg and Hazelwood 2011
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked — no full text of the sourcecites Lee et al. 2010 source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These trends make it evident that the hardware architecture of both CPU and GPU has undergone and still undergoing a process of never-ending evolution.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.2.5. Interconnect bandwidth.
Strength:boosted· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesThe paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Both CPU and GPU possess distinct architectural features.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.3.1. Acknowledging and leveraging unique architectural strengths of PUs.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
- It may state two separate claims as one. 26
- Probably not a substantial claim. 27
Every source the paper cites for this claim was checked and supports it.
In the paper
“It provides a higher abstraction programming framework and hence, it enables the programmer to write programs which are portable across wide variety of processing units, although it may not be able to achieve the highest possible performance on a PU.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 4.4. Design of OpenCL and related frameworks
What the sources say
- Supportedcites Stone et al. 2010 source
The Introduction says OpenCL provides easy-to-use abstractions and guarantees portability and correctness across architectures. The OpenCL programming model says kernels are portable across a variety of hardware but are not guaranteed to achieve peak performance on different architectures. (LLM, conf=0.94)
Strength:hedged· not yet calibratedCausal:conditional· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“OpenCL [Stone et al. 2010] is an open standard and has been adopted by several vendors.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 4.4. Design of OpenCL and related frameworks
What the sources say
- Supportedcites Stone et al. 2010 source
The Introduction calls OpenCL a new industry standard. The Graphics Processing Units section reports that both AMD and NVIDIA had released OpenCL implementations, supporting adoption by multiple vendors. (LLM, conf=0.93)
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Supported
In the paper
“Earlier GPUs only provided softwaremanaged caches and not hardware-managed caches, however, as the GPUs move towards general-purpose computing, they are now featuring increasingly larger-sized hardware-managed caches.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.2.3. Cache size.
What the sources say
- Not matchedcites Mittal 2014a
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- Not matched
In the paper
“For example, GT200 architecture GPU did not have an L2 cache, the Fermi GPU has 768KB LLC, the Kepler GPU has 1536KB LLC and the Maxwell GPU has 2048KB LLC [Mittal 2014a].”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.2.3. Cache size.
What the sources say
- Not matchedcites Mittal 2014a
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Not matched
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“The 45nm POWER7 processor had 32MB eDRAM (embedded DRAM) LLC [Wendel et al. 2010], the 32nm POWER7+ processor had an 80MB eDRAM LLC [Zyuban et al. 2013], while the 22nm POWER8 processor has a 96MB eDRAM LLC [Fluhr et al. 2014].”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.2.3. Cache size.
What the sources say
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Few years ago, CPUs had nearly 1B transistors [Wendel et al. 2010] while the recently announced Oracle SPARC M7 CPU will have more than 10B transistors on chip [Morgan 2014].”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.2.1. Transistor count.
What the sources say
- Not checked — no full text of the sourcecites Wendel et al. 2010 source
- Not matchedcites Morgan 2014
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“From Table III, it is clear that for GPU programming, CUDA is most widely used, which is due to its similarity with C/C++ and ability to write optimized code.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 4.1. A classification of research works based on programming languages used
Strength:boosted· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“3D stacking facilitates high bandwidth and memory capacity [Poremba et al. 2015] and hence, both CPUs and GPUs are increasingly moving towards use of 3D stacking, for example, Intel's Knights Landing [Gardner 2014] and NVIDIA's Pascal GPU [Gupta 2014] will feature 3D stacked memory.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.2.4. 3D stacking.
What the sources say
- Not matchedcites Gardner 2014
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites Gupta 2014
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- Not matched
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“An even closer level of integration between CPU and GPU can be achieved by fabricating them on the same chip and many such processors have already been produced, such as AMD Llano [Branover et al. 2012], Intel Sandy Bridge [Yuffe et al. 2011], Ivy Bridge [Damaraju et al. 2012] etc.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 1. INTRODUCTION
What the sources say
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Earlier CPUs had only one or two cores, while as recent CPUs have 8 to 32 cores [Fluhr et al. 2014;Morgan 2014] and CPUs with more than 60 cores are likely to be available in near future [Gardner 2014].”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.2.2. Core count.
What the sources say
- Not checked — no full text of the sourcecites Fluhr et al. 2014 source
- Not matchedcites Morgan 2014
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites Gardner 2014
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:hedged· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“For CPU programming, OpenMP is most widely used due to its portability and ease of programming by virtue of use of compiler directives.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 4.1. A classification of research works based on programming languages used
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Similarly, the GT200 GPU (2008) had 1.4B transistors, while the recent Geforce GTX TITAN X GPU has 8B transistors [Pirzada 2015].”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.2.1. Transistor count.
What the sources say
- Not matchedcites Pirzada 2015
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Not matched
In the paper
“Along similar lines, the number of CUDA cores in GeForce GTX 280, GTX 480, GTX 680 and GTX TITAN X GPU is 240, 448, 1536 and3072, respectively [NVIDIA 2015].”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.2.2. Core count.
What the sources say
- Not matchedcites NVIDIA 2015
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Not matched
In the paper
“In contrast, GPUs use much larger number of cores, which are in-order cores that share their control unit.Also, GPU cores use lower frequency, and smaller sized caches [Mittal 2014a].”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.3.1. Acknowledging and leveraging unique architectural strengths of PUs.
What the sources say
- Not matchedcites Mittal 2014a
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While fused HCSs address several limitations of discrete HCSs, they also introduce new tradeoffs and require the design of suitable data-access strategies to take full advantage of their fast interconnection.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 8. CONCLUSION AND FUTURE DIRECTIONS
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As both CPU and GPU become employed in a wide range of applications, it has been acknowledged that both of these processing units (PUs) have their unique features and strengths and hence, CPU-GPU collaboration is inevitable to achieve high-performance computing.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > Abstract
Tests✓ Asserted: passes✗ Checkable: fails✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may be too vague to check against evidence.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Many algorithm-level techniques require the programmer to manually partition the workload between PUs, identify the subtasks suitable for each PU and/or profile the performance of each PU.This is a tedious process which does not scale well beyond small problems.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 8. CONCLUSION AND FUTURE DIRECTIONS
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This reduces their data transfer time which especially benefits the applications which require large communication between CPU and GPU.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 6. FUSED CPU-GPU CHIPS AND COMPARISON WITH DISCRETE SYSTEMS
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In systems with GPUs, CPUs have been conventionally used as host for GPU to manage I/O and scheduling, however, as continuing innovations improve CPU performance even further (refer Section 2.2), using their computation capabilities also has become more attractive.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.3.4. Reaping the fruits of advancements in CPU design.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Moreover, existing fused HCSs are not strictly superior to discrete GPUs on all parameters and hence, despite their potential, extensive evaluation and development on them has been lacking.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 8. CONCLUSION AND FUTURE DIRECTIONS
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclearIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“As both CPU and GPU become employed in a wide range of applications, it has been acknowledged that both of these processing units (PUs) have their unique features and strengths and hence, CPU-GPU collaboration is inevitable to achieve high-performance computing.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > Abstract
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“To meet the worse-case performance requirements, the CPU-only or GPU-only systems are usually over-provisioned, however, their average utilization remains low [Mittal 2012;Mittal and Vetter 2015].”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.3.3. Improving resource utilization.
What the sources say
- Not checked — no full text of the sourcecites Mittal 2012 source
- Not matchedcites Mittal and Vetter 2015
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Due to their unique characteristics, HCSs require special benchmarks to gain insights into their functioning.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 7.2. Benchmarks for Heterogeneous Computing
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“Further, while several initial works report that GPUs provide up to 100× to 1000× speedup, other researchers claim that on applying careful optimizations on both CPUs and GPUs; CPUs may equal or even outperform the performance of GPUs [Gummaraju et al. 2010;Lee et al. 2010].”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.3.4. Reaping the fruits of advancements in CPU design.
What the sources say
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The vastly different architectures and programming models of CPU and GPU, however, also present several challenges in achieving such collaborative computing.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 1. INTRODUCTION
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
In the paper
“Mobile computing systems, which now number nearly equal to the population of the earth [International Telecommunication Union 2012], generally provide multimedia services under real-time performance constraints and hence they are attractive targets for acceleration through the use of heterogeneous computing.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 8. CONCLUSION AND FUTURE DIRECTIONS
What the sources say
- Not matchedcites International Telecommunication Union 2012
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For applications where data transfers dominate execution time, or branch divergence does not allow for the uninterrupted execution on all GPU cores, CPUs can provide better performance than GPUs.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.3.2. Matching algorithmic requirements to features of PUs.
Strength:plain· not yet calibratedCausal:conditional· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The vastly different architecture, programming model and performance (for a given program) of CPU and GPU present unique challenges in heterogeneous computing.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.4. Factors and challenges involved in heterogeneous computing
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
In the paper
“For example, Ding et al. [2009] note that for a query processing application, CPUs are more efficient for queries involving short lists while GPUs are more efficient for those involving long lists.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.3.2. Matching algorithmic requirements to features of PUs.
What the sources say
- Not checked — no full text of the sourcecites Ding et al. 2009 source
Strength:plain· not yet calibratedCausal:correlational· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Significant amount of work needs to be done before recently introduced HCS programming frameworks can reach the level of maturity, robustness and popularity as enjoyed by the conventional CPU programming languages.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 8. CONCLUSION AND FUTURE DIRECTIONS
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✗ Checkable: fails✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“As a result, heterogeneous computing has been actively researched and utilized in variety of applications ranging from natural sciences to engineering etc.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 8. CONCLUSION AND FUTURE DIRECTIONS
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Several existing large-scale codes are written in either CPU or GPU languages.Porting them to HCSs will incur large overhead and is also error-prone.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 8. CONCLUSION AND FUTURE DIRECTIONS
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“However, given that CPU-GPU workload division based techniques on heterogeneous systems use CPU also to get performance gain (and not just as a host), sometimes CPU is also referred to as an accelerator [Sun et al. 2012].”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.1. Clarifying the terminology
What the sources say
- Not checked — no full text of the sourcecites Sun et al. 2012 source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“However, a recently proposed interconnect, called NVLink, promises to offer 5 to 12× bandwidth compared to PCIe Gen3 interconnect [Gupta 2014] and this is likely to offset the bandwidth limitation of conventional interconnects.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 2.2.5. Interconnect bandwidth.
What the sources say
- Not matchedcites Gupta 2014
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:hedged· not yet calibratedCausal:conditional· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“These domains are, by no means, exhaustive as heterogeneous computing can be applied in several other domains also which are computationally intensive and/or provide opportunity for parallelization.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 7.1. Application domains of heterogeneous computing
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Discrete GPUs have separate memory spaces from the CPU and hence, data transfer happens over a connection bus (e.g.PCIe bus), which incurs large overhead.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 6. FUSED CPU-GPU CHIPS AND COMPARISON WITH DISCRETE SYSTEMS
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Rests on an assumption: Discrete GPUs have separate memory spaces from the CPU.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Note that while many other techniques which aim to improve performance may also save energy, in this table we only show those techniques which have been evaluated on the basis of energy efficiency.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 5. TECHNIQUES FOR IMPROVING ENERGY EFFICIENCY
Strength:hedged· not yet calibratedCausal:conditional· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Notice that some of these benchmarks provide implementations in different languages which allow comparison using those programming models.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 7.2. Benchmarks for Heterogeneous Computing
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While the large cost and power consumption of HCSs may be acceptable in high-end computing systems, using them in mobile systems calls for an order-of-magnitude improvement in their energy efficiency.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 8. CONCLUSION AND FUTURE DIRECTIONS
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In recent years, CPUs and GPUs are increasingly being seen as indispensable coprocessors, instead of substitutes for each other.”
§ A Survey of CPU-GPU Heterogeneous Computing Techniques > 8. CONCLUSION AND FUTURE DIRECTIONS
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
The paper relies on this without support.
Modern multicore CPUs use up to a few tens of cores, which are typically out-of-order, multi-instruction issue cores; CPU cores run at high frequency and use large sized caches to minimize the latency of a single-thread.
“Modern multicore CPUs use upto a few tens of cores, which are typically out-of-order, multi-instruction issue cores.Also, CPU cores run at high-frequency and use large sized caches to minimize the latency of a single-thread.”
The paper relies on this without support.
After allocating a task to GPU (starting the kernel), CPU stays idle, leading to wastage of energy.
“Further, after allocating the task to GPU (i.e. starting the kernel), CPU stays idle which leads to wastage of energy.”
The authors state this as an assumption.
The different subtasks are of similar nature and can run on any of the PU.
“For example, assuming that the different subtasks are of similar nature and can run on any of the PU, the decision about where a subtask should be mapped depends on which PU provides higher performance and which mapping helps in achieving load-balancing.”
The paper relies on this without support.
Different languages offer different tradeoffs between ease of programming, ability to write optimized code, ability to target multiple PUs and products from different vendors etc.
“Different languages offer different tradeoffs between ease of programming, ability to write optimized code, ability to target multiple PUs and products from different vendors etc.”
The paper relies on this without support.
OpenCL can be used for both CPU and GPU, and hence, applications written in OpenCL can be easily scheduled on any PU.
“For example, OpenCL can be used for both CPU and GPU, and hence, applications written in OpenCL can be easily scheduled on any PU.”
The paper relies on this without support.
CUDA works only on NVIDIA GPUs.
“By comparison, CUDA works only on NVIDIA GPUs”
The paper relies on this without support.
ACML and Brook+ can be used to program AMD GPUs only.
“ACML (AMD Core Math Library) and Brook+ can be used to program AMD GPUs only.”
The paper relies on this without support.
OpenMP, Pthread, TBB and MKL are used to write parallel programs on CPUs.
“Similarly OpenMP, Pthread, TBB (thread building block) and MKL (math kernel library) are used to write parallel programs on CPUs.”
The paper relies on this without support.
MKL is internally parallelized by OpenMP threading.
“Note that MKL is internally parallelized by OpenMP threading; for sake of clarity, we mention it separately in Table III.”
The paper relies on this without support.
Small task sizes provide better load-balancing, while large task sizes provide better resource utilization and an optimal value of task sizes achieves a trade-off between these two factors.
“Small task sizes provide better load-balancing, while large task sizes provide better resource utilization and an optimal value of task sizes achieves a trade-off between these two factors.”
The paper relies on this without support.
HMMER algorithm has large memory requirement and thus, for large sized sequences, shared memory of GPU becomes unsuitable while global memory incurs large performance penalty.
“HMMER algorithm has large memory requirement and thus, for large sized sequences, shared memory of GPU becomes unsuitable while global memory incurs large performance penalty.”
The paper relies on this without support.
Discrete GPUs have separate memory spaces from the CPU.
“Discrete GPUs have separate memory spaces from the CPU and hence, data transfer happens over a connection bus (e.g.PCIe bus), which incurs large overhead.”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Dithering step 3 is assigned to both GPU and CPU
MinorThe handover description says step 3 runs on the GPU, but the subsequent description says the CPU performs steps 1 and 3. The account gives conflicting assignments for the final step.
“finally hands over the data back to GPU for doing last part of the algorithm (step 3).”
“Thus, CPU performs step 1 and 3 alone; and also shares the work in step 2.”
Citations
Cites
Lecture Notes in Computer Science 1205
(1999) · Industrial Robot the international journal of robotics research and application · doi:10.1108/ir.1999.04926fae.001 · Cited by 39,228
Rodinia: A benchmark suite for heterogeneous computing
Che, S., Boyer, M. J., Meng, J., Tarjan, D., Sheaffer, J. W., Lee, S.-H., & Kevin Skadron, Y. (2009) · IEEE International Symposium on Workload Characterization · doi:10.1109/iiswc.2009.5306797 · Cited by 3,100
The International Telecommunication Union
Jones, R. W. (2002) · Digest - IEEE Antennas and Propagation Society. International Symposium · doi:10.1109/aps.1997.631791 · Cited by 1,903
StarPU: a unified platform for task scheduling on heterogeneous multicore architectures
Augonnet, C., Thibault, S., Raymond Namyst, D., & Wacrenier, P. (2010) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.1631 · Cited by 1,372
OpenCL: A Parallel Programming Standard for Heterogeneous Computing Systems
Stone, J. E., Gohara, D., & Shi, G. (2010) · Computing in Science & Engineering · doi:10.1109/mcse.2010.69 · Cited by 1,086
Parboil: A Revised Benchmark Suite for Scientific and Commercial Throughput Computing
Stratton, J. A., Rodrigues, C. I., Sung, I.-J., Obeid, N., Chang, L., Anssari, N., Liu, G. D., & Hwu, W. (2012) · Cited by 707
The Scalable Heterogeneous Computing (SHOC) benchmark suite
Anthony Danalis, A., Marin, G., McCurdy, C., Meredith, J. S., Roth, P. C., Spafford, K. L., Tipparaju, V., & Vetter, J. S. (2010) · doi:10.1145/1735688.1735702 · Cited by 688
Self-citationDebunking the 100X GPU vs. CPU myth: an evaluation of throughput computing on CPU and GPU
Lee, V. W., Kim, C., Chhugani, J., Deisher, M., Kim, D., Nguyen, A. D., Satish, N., Smelyanskiy, M., Chennupaty, S., Hammarlund, P., et al. (2010) · Proceedings of the 37th annual international symposium on Computer architecture · doi:10.1145/1815961.1816021 · Cited by 640
Luk, C.-K., Hong, S., & Kim, H. (2009) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1145/1669112.1669121 · Cited by 501
Where is the data? Why you cannot debate CPU vs. GPU performance without the answer
Gregg, C., & Hazelwood, K. (2011) · IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) · doi:10.1109/ispass.2011.5762730 · Cited by 292
Efficient Parallel Graph Exploration on Multi-Core CPU and GPU
Hong, S., Oguntebi, T., & Olukotun, K. (2011) · International Conference on Parallel Architectures and Compilation Techniques (PACT) · doi:10.1109/pact.2011.14 · Cited by 271
Ishfaq Ahmad, D., Al‐Ayyoub, A., Avdelas, G. G., Avresky, D. R., Buyya, R., Cortés, T., de Sturler, E., Martino, B. D., Dickens, P. M., Drira, K., et al. (1999) · Cited by 249
A Survey of Methods for Analyzing and Improving GPU Energy Efficiency
Mittal, S., & Vetter, J. S. (2014) · ACM Computing Surveys · doi:10.1145/2636342 · Cited by 235
Self-citationPeta-scale phase-field simulation for dendritic solidification on the TSUBAME 2.0 supercomputer
Shimokawabe, T., Aoki, T., Takaki, T., Endo, T., Yamanaka, A., Maruyama, N., Nukada, A., & Matsuoka, S. (2011) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1145/2063384.2063388 · Cited by 196
A survey of techniques for improving energy efficiency in embedded computing systems
Mittal, S. (2014) · International Journal of Computer Aided Engineering and Technology · doi:10.1504/ijcaet.2014.065419 · Cited by 193
Self-citationKim, J., Seo, S., Lee, J., Nah, J., Jo, G., & Lee, J. (2012) · International Conference on Supercomputing · doi:10.1145/2304576.2304623 · Cited by 186
Diamos, G., & Yalamanchili, S. (2008) · ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC) · doi:10.1145/1383422.1383447 · Cited by 169
Multilevel summation of electrostatic potentials using graphics processing units
Hardy, D. J., Stone, J. E., & Schulten, K. J. (2008) · Parallel Computing · doi:10.1016/j.parco.2008.12.005 · Cited by 158
Tsoi, K. H., & Luk, W. W. (2010) · ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA) · doi:10.1145/1723112.1723134 · Cited by 146
Petascale Direct Numerical Simulation of Blood Flow on 200K Cores and Heterogeneous Architectures
Rahimian, A., Lashuk, I., Veerapaneni, S., Chandramowlishwaran, A. M., Malhotra, D., Moon, L., Sampath, R. S., Shringarpure, A., Vetter, J. S., Vuduc, R. W., et al. (2010) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1109/sc.2010.42 · Cited by 145
Self-citationA yoke of oxen and a thousand chickens for heavy lifting graph processing
Gharaibeh, A., Costa, L. B., Santos‐Neto, E., & Ripeanu, M. (2012) · International Conference on Parallel Architectures and Compilation Techniques (PACT) · doi:10.1145/2370816.2370866 · Cited by 142
GreenGPU: A Holistic Approach to Energy Efficiency in GPU-CPU Heterogeneous Architectures
Ma, K., Li, X., Chen, W., Zhang, C., & Wang, X. (2012) · Proceedings of the International Conference on Parallel Processing · doi:10.1109/icpp.2012.31 · Cited by 137
Predictive Runtime Code Scheduling for Heterogeneous Architectures
Jiménez, V., Vilanova, L., Gelado, I., Gil, M., Fursin, G., & Navarro, N. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-92990-1_4 · Cited by 132
Hong, C., Chen, D., Chen, W., Zheng, W., & Lin, H. (2010) · International Conference on Parallel Architectures and Compilation Techniques (PACT) · doi:10.1145/1854273.1854303 · Cited by 131
A survey of architectural techniques for improving cache power efficiency
Mittal, S. (2013) · Sustainable Computing Informatics and Systems · doi:10.1016/j.suscom.2013.11.001 · Cited by 129
Self-citationA new era in scientific computing: Domain decomposition methods in hybrid CPU–GPU architectures
Papadrakakis, M., Stavroulakis, G., & Karatarakis, A. (2011) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2011.01.013 · Cited by 112
A Static Task Partitioning Approach for Heterogeneous Systems Using OpenCL
Grewe, D., & O’Boyle, M. F. P. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-19861-8_16 · Cited by 109
On the limits of GPU acceleration
Vuduc, R. W., Chandramowlishwaran, A. M., Choi, J. W., Guney, M. E., & Shringarpure, A. (2010) · Cited by 108
Accelerating MapReduce on a coupled CPU-GPU architecture
Chen, L., Huo, X., & Agrawal, G. (2012) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1109/sc.2012.16 · Cited by 105
QR Factorization on a Multicore Node Enhanced with Multiple GPU Accelerators
Agullo, E., Augonnet, C., Dongarra, J. J., Mathieu Faverge, A., Ltaief, H., Thibault, S., & Tomov, S. Z. (2011) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps.2011.90 · Cited by 103
Ravi, V. T., Ma, W., Chiu, D., & Agrawal, G. (2010) · International Conference on Supercomputing · doi:10.1145/1810085.1810106 · Cited by 99
Transparent CPU-GPU collaboration for data-parallel kernels on heterogeneous systems
Lee, J., Samadi, M., Park, Y., & Mahlke, S. A. (2013) · doi:10.5555/2523721.2523756 · Cited by 98
Branover, A., Foley, D., & Steinman, M. (2012) · IEEE Micro · doi:10.1109/mm.2012.2 · Cited by 98
Characterizing and evaluating a key-value store application on heterogeneous CPU-GPU systems
Hetherington, T., Rogers, T. G., Hsu, L. R., O’Connor, M., & Aamodt, T. M. (2012) · IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) · doi:10.1109/ispass.2012.6189209 · Cited by 98
Opportunities for Nonvolatile Memory Systems in Extreme-Scale High-Performance Computing
Vetter, J. S., & Mittal, S. (2015) · Computing in Science & Engineering · doi:10.1109/mcse.2015.4 · Cited by 95
Self-citationBiomedical image analysis on a cooperative cluster of GPUs and multicores
Hartley, T. D. R., Çatalyürek, Ü. V., Ruiz, A., Igual, F. D., Mayo, R., & Ujaldón, M. (2008) · International Conference on Supercomputing · doi:10.1145/1375527.1375533 · Cited by 95
Coordinating the use of GPU and CPU for improving performance of compute intensive applications
Teodoro, G., Sachetto, R., Sertel, O., Gürcan, M. N., Meira, W., Çatalyürek, Ü. V., & Ferreira, R. (2009) · IEEE International Conference on Cluster Computing (CLUSTER) · doi:10.1109/clustr.2009.5289193 · Cited by 95
Pandit, P., & Govindarajan, R. (2014) · Proceedings of the CGO/Proceedings of the ... CGO · doi:10.1145/2544137.2544163 · Cited by 94
Scaling Hierarchical N-body Simulations on GPU Clusters
Jetley, P., Wesolowski, L., Gioachin, F., Kalé, L. V., & Quinn, T. (2010) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1109/sc.2010.49 · Cited by 94
Medical Ultrasound Imaging: To GPU or Not to GPU?
So, H. K., Chen, J., Yiu, B. Y. S., & Yu, A. C. H. (2011) · IEEE Micro · doi:10.1109/mm.2011.65 · Cited by 94
Multi-GPU and Multi-CPU Parallelization for Interactive Physics Simulations
Hermann, E., Raffin, B., Fauré, F., Gautier, T., & Allard, J. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15291-7_23 · Cited by 93
Dynamically managed data for CPU-GPU architectures
Jablin, T. B., Jablin, J. A., Prabhu, P., Liu, F., & August, D. I. (2012) · Proceedings of the CGO/Proceedings of the ... CGO · doi:10.1145/2259016.2259038 · Cited by 91
Accelerating MapReduce on a coupled CPU-GPU architecture
Chen, L., Huo, X., & Agrawal, G. (2012) · IEEE International Conference on High Performance Computing, Data, and Analytics · doi:10.5555/2388996.2389030 · Cited by 89
A dynamic self-scheduling scheme for heterogeneous multiprocessor architectures
Belviranli, M. E., Bhuyan, L. N., & Gupta, R. (2013) · ACM Transactions on Architecture and Code Optimization · doi:10.1145/2400682.2400716 · Cited by 88
An automatic input-sensitive approach for heterogeneous task partitioning
Kofler, K., Grasso, I., Cosenza, B., & Fahringer, T. (2013) · International Conference on Supercomputing · doi:10.1145/2464996.2465007 · Cited by 86
Adaptive Optimization for Petascale Heterogeneous CPU/GPU Computing
Yang, C., Wang, F., Du, Y., Chen, J., Liu, J., Yi, H., & Lü, K. (2010) · IEEE International Conference on Cluster Computing (CLUSTER) · doi:10.1109/cluster.2010.12 · Cited by 86
On the Efficacy of a Fused CPU+GPU Processor (or APU) for Parallel Computing
Daga, M., Aji, A. M., & Feng, W.-C. (2011) · 2011 Symposium on Application Accelerators in High-Performance Computing · doi:10.1109/saahpc.2011.29 · Cited by 84
Xu, M., Chen, F., Liu, X., Ge, W., & Li, J. (2012) · Chemical Engineering Journal · doi:10.1016/j.cej.2012.07.049 · Cited by 83
Tuned and wildly asynchronous stencil kernels for hybrid CPU/GPU systems
Venkatasubramanian, S., & Vuduc, R. W. (2009) · International Conference on Supercomputing · doi:10.1145/1542275.1542312 · Cited by 82
An efficient, model-based CPU-GPU heterogeneous FFT library
Ogata, Y., Endo, T., Maruyama, N., & Matsuoka, S. (2008) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps.2008.4536163 · Cited by 82
A Proposal to Extend the OpenMP Tasking Model for Heterogeneous Architectures
Ayguadé, E., Badia, R. M., Cabrera, D., Durán, A., González, M., Igual, F. D., Jiménez-González, D., Labarta, J., Martorell, X., Mayo, R., et al. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-02303-3_13 · Cited by 81
Portable performance on heterogeneous architectures
Phothilimthana, P. M., Ansel, J., Ragan‐Kelley, J., & Amarasinghe, S. P. (2013) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/2451116.2451162 · Cited by 80
Hybrid Map Task Scheduling for GPU-Based Heterogeneous Clusters
Shirahata, K., Sato, H., & Matsuoka, S. (2010) · IEEE International Conference on Cloud Computing Technology and Science · doi:10.1109/cloudcom.2010.55 · Cited by 79
Energy-aware high performance computing with graphic processing units
Rofouei, M., Stathopoulos, T., Ryffel, S., Kaiser, W., & Sarrafzadeh, M. (2008) · Cited by 73
Programming model for a heterogeneous x86 platform
Saha, B., Zhou, X., Chen, H., Gao, Y. L., Yan, S., Rajagopalan, M., Fang, J., Zhang, P., Ronen, R., & Mendelson, A. (2009) · ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI) · doi:10.1145/1542476.1542525 · Cited by 72
Using graphics processors for high-performance IR query processing
Ding, S., He, J., Yan, H., & Suel, T. (2008) · International World Wide Web Conference (WWW) · doi:10.1145/1367497.1367732 · Cited by 71
A 22nm IA multi-CPU and GPU System-on-Chip
Damaraju, S., George, V., Jahagirdar, S., Khondker, T., Milstrey, R., Sarkar, S., Siers, S., Stolero, I., & Subbiah, A. (2012) · 2012 IEEE International Solid-State Circuits Conference · doi:10.1109/isscc.2012.6176876 · Cited by 70
Tomov, S. Z., Nath, R., & Dongarra, J. J. (2010) · Parallel Computing · doi:10.1016/j.parco.2010.06.001 · Cited by 69
Heterogeneous Task Scheduling for Accelerated OpenMP
Scogland, T., Rountree, B., Feng, W.-C., & de Supinski, B. R. (2012) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps.2012.23 · Cited by 67
Maestro: Data Orchestration and Tuning for OpenCL Devices
Spafford, K. L., Meredith, J., & Vetter, J. S. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15291-7_26 · Cited by 66
Self-citationLoad balancing in a changing world
Boyer, M., Kevin Skadron, Y., Che, S., & Jayasena, N. (2013) · ACM International Conference on Computing Frontiers (CF) · doi:10.1145/2482767.2482794 · Cited by 65
A fully integrated multi-CPU, GPU and memory controller 32nm processor
Yuffe, M., Knoll, E., Mehalel, M., Shor, J., & Kurts, T. (2011) · 2011 IEEE International Solid-State Circuits Conference · doi:10.1109/isscc.2011.5746311 · Cited by 64
Proceedings of the 2014 Federated Conference on Computer Science and Information Systems
(2014) · Annals of Computer Science and Information Systems · doi:10.15439/978-83-60810-58-3 · Cited by 60
Power-efficient time-sensitive mapping in heterogeneous systems
Liu, C., Li, J., Huang, W., Rubio, J., Speight, E. W., & Lin, X. (2012) · International Conference on Parallel Architectures and Compilation Techniques (PACT) · doi:10.1145/2370816.2370822 · Cited by 59
Gummaraju, J., Morichetti, L., Houston, M., Sander, B., Gaster, B. R., & Zheng, B. (2010) · Proceedings of the 19th international conference on Parallel architectures and compilation techniques · doi:10.1145/1854273.1854302 · Cited by 59
A Scalable High Performant Cholesky Factorization for Multicore with GPU Accelerators
Ltaief, H., Tomov, S. Z., Nath, R., Du, P., & Dongarra, J. J. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19328-6_11 · Cited by 57
An efficient scheduling scheme using estimated execution time for heterogeneous computing systems
Choi, H., Son, D. O., Kang, S. G., Kim, J. M., Lee, H.-H. S., & Kim, C. H. (2013) · The Journal of Supercomputing · doi:10.1007/s11227-013-0870-6 · Cited by 56
Using graphics processors for high performance IR query processing
Ding, S., He, J., Yan, H., & Suel, T. (2009) · Proceedings of the 18th international conference on World wide web · doi:10.1145/1526709.1526766 · Cited by 56
Parallel Processing of Matrix Multiplication in a CPU and GPU Heterogeneous Environment
Ohshima, S., Kise, K., Katagiri, T., & Yuba, T. (2007) · Springer eBooks · doi:10.1007/978-3-540-71351-7_24 · Cited by 55
Efficient co-processor utilization in database query processing
Breß, S., Beier, F., Rauhe, H., Sattler, K.-U., Schallehn, E., & Saake, G. (2013) · Information Systems · doi:10.1016/j.is.2013.05.004 · Cited by 53
Data-aware scheduling of legacy kernels on heterogeneous platforms with distributed memory
Becchi, M., Byna, S., Cadambi, S., & Chakradhar, S. (2010) · ACM Symposium on Parallelism in Algorithms and Architectures (SPAA) · doi:10.1145/1810479.1810498 · Cited by 52
Zhong, Z., Rychkov, V., & Lastovetsky, A. (2012) · IEEE International Conference on Cluster Computing (CLUSTER) · doi:10.1109/cluster.2012.34 · Cited by 50
The tradeoffs of fused memory hierarchies in heterogeneous computing architectures
Spafford, K. L., Meredith, J. S., Lee, S., Li, D., Roth, P. C., & Vetter, J. S. (2012) · Proceedings of the 9th conference on Computing Frontiers · doi:10.1145/2212908.2212924 · Cited by 49
Self-citationProcessing data streams with hard real-time constraints on heterogeneous systems
Verner, U., Schuster, A., & Silberstein, M. (2011) · International Conference on Supercomputing · doi:10.1145/1995896.1995915 · Cited by 49
A peta-scalable CPU-GPU algorithm for global atmospheric simulations
Yang, C., Xue, W., Fu, H., Gan, L., Li, L., Xu, Y., Lu, Y., Sun, J., Yang, G., & Zheng, W. (2013) · ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming · doi:10.1145/2442516.2442518 · Cited by 48
A survey of architectural techniques for DRAM power management
Mittal, S. (2012) · International Journal of High Performance Systems Architecture · doi:10.1504/ijhpsa.2012.050990 · Cited by 46
Self-citationEfficient irregular wavefront propagation algorithms on hybrid CPU–GPU machines
Teodoro, G., Pan, T. C., Kurç, T., Kong, J., Cooper, L., & Saltz, J. H. (2013) · Parallel Computing · doi:10.1016/j.parco.2013.03.001 · Cited by 45
Linpack evaluation on a supercomputer with heterogeneous accelerators
Endo, T., Matsuoka, S., Nukada, A., & Maruyama, N. (2010) · 2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS) · doi:10.1109/ipdps.2010.5470353 · Cited by 43
Dynamic Heterogeneous Scheduling Decisions Using Historical Runtime Data
Gregg, C., Boyer, M., Hazelwood, K., & Kevin Skadron, Y. (2011) · Cited by 42
Noniterative Multireference Coupled Cluster Methods on Heterogeneous CPU–GPU Systems
Bhaskaran‐Nair, K., Ma, W., Krishnamoorthy, S., Villa, O., van Dam, H. J. J., Aprà, E., & Kowalski, K. (2013) · Journal of Chemical Theory and Computation · doi:10.1021/ct301130u · Cited by 41
A mixed-precision algorithm for the solution of Lyapunov equations on hybrid CPU–GPU platforms
Benner, P., Ezzatti, P., Kreßner, D., Quintana–Ort́ı, E. S., & Remón, A. (2010) · Parallel Computing · doi:10.1016/j.parco.2010.12.002 · Cited by 41
Radiation modeling using the Uintah heterogeneous CPU/GPU runtime system
Humphrey, A., Meng, Q., Berzins, M., & Harman, T. (2012) · Extreme Science and Engineering Discovery Environment · doi:10.1145/2335755.2335791 · Cited by 41
CPU/GPU computing for long-wave radiation physics on large GPU clusters
Lu, F., Song, J., Cao, X., & Zhu, X. (2011) · Computers & Geosciences · doi:10.1016/j.cageo.2011.08.007 · Cited by 41
Scalable fast multipole methods on distributed heterogeneous architectures
Hu, Q., Gumerov, N. A., & Ramani Duraiswami, B. (2011) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1145/2063384.2063432 · Cited by 41
SPRAT: Runtime processor selection for energy-aware computing
Takizawa, H., Sato, K., & Kobayashi, H. (2008) · IEEE International Conference on Cluster Computing (CLUSTER) · doi:10.1109/clustr.2008.4663799 · Cited by 40
Heterogeneous Computing for Vertebra Detection and Segmentation in X-Ray Images
Lecron, F., Mahmoudi, S. A., Benjelloun, M., Mahmoudi, S., & Manneback, P. (2011) · International Journal of Biomedical Imaging · doi:10.1155/2011/640208 · Cited by 39
GPU and APU computations of Finite Time Lyapunov Exponent fields
Conti, C., Rossinelli, D., & Koumoutsakos, P. (2011) · Journal of Computational Physics · doi:10.1016/j.jcp.2011.10.032 · Cited by 39
Accelerating Large Scale Image Analyses on Parallel, CPU-GPU Equipped Systems
Teodoro, G., Kurç, T., Pan, T. C., Cooper, L., Kong, J., Widener, P. M., & Saltz, J. H. (2012) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps.2012.101 · Cited by 39
Combinatorial Bidirectional Path‐Tracing for Efficient Hybrid CPU/GPU Rendering
Pajot, A., Barthe, L., Paulin, M., & Poulin, P. (2011) · Computer Graphics Forum · doi:10.1111/j.1467-8659.2011.01863.x · Cited by 39
Optimizing tensor contraction expressions for hybrid CPU-GPU execution
Ma, W., Krishnamoorthy, S., Villa, O., Kowalski, K., & Agrawal, G. (2011) · Cluster Computing · doi:10.1007/s10586-011-0179-2 · Cited by 37
Hybrid algorithms for list ranking and graph connected components
Banerjee, D. S., & Kothapalli, K. (2011) · International Conference on High Performance Computing (HiPC) · doi:10.1109/hipc.2011.6152655 · Cited by 37
Automatic compilation of MATLAB programs for synergistic execution on heterogeneous processors
Prasad, A., Anantpur, J., & Govindarajan, R. (2011) · ACM SIGPLAN Notices · doi:10.1145/1993316.1993517 · Cited by 36
Hybrid computing: CPU+GPU co-processing and its application to tomographic reconstruction
Agulleiro, J. I., Vázquez, F., Garzón, E. M., & Fernández, J. J. (2012) · Ultramicroscopy · doi:10.1016/j.ultramic.2012.02.003 · Cited by 34
Divide and Conquer on Hybrid GPU-Accelerated Multicore Systems
Christof Vömel, A., Tomov, S. Z., & Dongarra, J. J. (2012) · SIAM Journal on Scientific Computing · doi:10.1137/100806783 · Cited by 34
Automatic Dynamic Task Distribution between CPU and GPU for Real-Time Systems
Joselli, M., Zamith, M. P. D. M., Clua, E., Montenegro, A. A., Conci, A., Leal-Toledo, R. C. P., Valente, L., Feijó, B., d’Ornellas, M. C., & Pozzer, C. T. (2008) · IEEE International Conference on Computational Science and Engineering (CSE) · doi:10.1109/cse.2008.38 · Cited by 34
Practical Time Bundle Adjustment for 3D Reconstruction on the GPU
Choudhary, S., Gupta, S., & Narayanan, P. J. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-35740-4_33 · Cited by 33
Enabling task-level scheduling on heterogeneous platforms
Sun, E., Schaa, D., Bagley, R., Rubin, N., & Kaeli, D. (2012) · Proceedings of the 5th Annual Workshop on General Purpose Processing with Graphics Processing Units · doi:10.1145/2159430.2159440 · Cited by 33
Jiang, W., & Agrawal, G. (2012) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps.2012.65 · Cited by 33
Power-aware dynamic task scheduling for heterogeneous accelerated clusters
Hamano, T., Endo, T., & Matsuoka, S. (2009) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps.2009.5160977 · Cited by 32
Accelerating Protein Sequence Search in a Heterogeneous Computing System
Xiao, S., Lin, H., & Feng, W.-C. (2011) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps.2011.115 · Cited by 32
A SURVEY OF TECHNIQUES FOR MANAGING AND LEVERAGING CACHES IN GPUs
Mittal, S. (2014) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126614300025 · Cited by 31
Self-citationA dynamic scheduling framework for emerging heterogeneous systems
Ravi, V. T., & Agrawal, G. (2011) · IEEE International Conference on High Performance Computing, Data, and Analytics · doi:10.1109/hipc.2011.6152724 · Cited by 31
A Class of Hybrid LAPACK Algorithms for Multicore and GPU Architectures
Horton, M., Tomov, S. Z., & Dongarra, J. J. (2011) · Symposium on Application Accelerators in High-Performance Computing (SAAHPC) · doi:10.1109/saahpc.2011.18 · Cited by 31
Accelerating Kirchhoff Migration by CPU and GPU Cooperation
Panetta, J., Teixeira, T., Filho, P. R. P. D. S., Filho, C. A. D. C., Sotelo, D., da Motta, F., Pinheiro, S. S., Pedrosa, I., Rosa, A. L. R., Monnerat, L. R., et al. (2009) · International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD) · doi:10.1109/sbac-pad.2009.29 · Cited by 31
Performance evaluation of hybrid programming patterns for large CPU/GPU heterogeneous clusters
Lu, F., Song, J., Yin, F., & Zhu, X. (2012) · Computer Physics Communications · doi:10.1016/j.cpc.2012.01.019 · Cited by 30
Dziekonski, A., Lamęcki, A., & Mrozowski, M. (2011) · IEEE Antennas and Wireless Propagation Letters · doi:10.1109/lawp.2011.2159769 · Cited by 29
A Waterfall Model to Achieve Energy Efficient Tasks Mapping for Large Scale GPU Clusters
Liu, W., Du, Z., Xiao, Y., Bader, D. A., & Chen, X. (2011) · IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum · doi:10.1109/ipdps.2011.129 · Cited by 29
Using Hybrid CPU-GPU Platforms to Accelerate the Computation of the Matrix Sign Function
Benner, P., Ezzatti, P., Quintana–Ort́ı, E. S., & Remón, A. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-14122-5_17 · Cited by 28
Heterogeneous Systems for Energy Efficient Scientific Computing
Liu, Q., & Luk, W. W. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-28365-9_6 · Cited by 27
Pienaar, J. A., Raghunathan, A., & Chakradhar, S. (2011) · International Conference on Supercomputing · doi:10.1145/1995896.1995933 · Cited by 27
A Hybrid CPU-GPU Accelerated Framework for Fast Mapping of High-Resolution Human Brain Connectome
Wang, Y., Du, H., Xia, M., Ren, L., Xu, M., Xie, T., Gong, G., Xu, N., Yang, H., & Yong He, A. (2013) · PLoS ONE · doi:10.1371/journal.pone.0062789 · Cited by 27
Evaluating application performance and energy consumption on hybrid CPU+GPU architecture
Padoin, E. L., Pilla, L. L., Boito, F. Z., Kassick, R. V., Velho, P., & Navaux, P. O. A. (2012) · Cluster Computing · doi:10.1007/s10586-012-0219-6 · Cited by 27
Hybrid Core Acceleration of UWB SIRE Radar Signal Processing
Park, S. J., Ross, J. A., Shires, D. R., Richie, D. A., Henz, B. J., & Nguyen, L. (2010) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2010.117 · Cited by 26
5.1 POWER8TM: A 12-core server-class processor in 22nm SOI with 7.6Tb/s off-chip bandwidth
Fluhr, E. J., Friedrich, J., Dreps, D., Zyuban, V., Still, G., Gonzalez, C., Hall, A., Hogenmiller, D., Malgioglio, F., Nett, R., et al. (2014) · 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC) · doi:10.1109/isscc.2014.6757353 · Cited by 26
Synergistic execution of stream programs on multicores with accelerators
Udupa, A., Govindarajan, R., & Thazhuthaveetil, M. J. (2009) · ACM SIGPLAN/SIGBED Conference on Languages, Compilers, and Tools for Embedded Systems (LCTES) · doi:10.1145/1542452.1542466 · Cited by 26
An asymmetric distributed shared memory model for heterogeneous parallel systems
Gelado, I., Stone, J. E., Cabezas, J., Patel, S., Navarro, N., & Hwu, W.-M. W. (2010) · ACM SIGARCH Computer Architecture News · doi:10.1145/1735970.1736059 · Cited by 25
Shen, W., Wei, D., Xu, W., Zhu, X. Y., & Yuan, S. (2010) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2010.06.015 · Cited by 23
Shot boundary detection using Zernike moments in multi-GPU multi-CPU architectures
Toharia, P., Robles, Ó. D., Suárez, R., Bosque, J. L., & Pastor, L. (2011) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2011.10.011 · Cited by 23
Performance characterization of data-intensive kernels on AMD Fusion architectures
Lee, K., Lin, H., & Feng, W.-C. (2012) · Computer Science - Research and Development · doi:10.1007/s00450-012-0209-1 · Cited by 22
Advances in Intelligent Systems and Applications - Volume 2
Pan, J.-S., Lin, C.-C., & Yang, C.-N. (2012) · Smart innovation, systems and technologies · doi:10.1007/978-3-642-35473-1 · Cited by 22
Porting irregular reductions on heterogeneous CPU-GPU configurations
Huo, X., Ravi, V. T., & Agrawal, G. (2011) · IEEE International Conference on High Performance Computing, Data, and Analytics · doi:10.1109/hipc.2011.6152715 · Cited by 21
Task-based parallel breadth-first search in heterogeneous environments
Munguía, L.-M., Bader, D. A., & Ayguadé, E. (2012) · IEEE International Conference on High Performance Computing, Data, and Analytics · doi:10.1109/hipc.2012.6507474 · Cited by 21
Stefański, T. P. (2013) · Electromagnetic waves · doi:10.2528/pier12111702 · Cited by 21
Optimal Utilization of Heterogeneous Resources for Biomolecular Simulations
Hampton, S. S., Alam, S. R., Crozier, P., & Agarwal, P. K. (2010) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1109/sc.2010.37 · Cited by 21
Cooperative heterogeneous computing for parallel processing on CPU/GPU hybrids
Lee, C., Ro, W. W., & Gaudiot, J. (2012) · Workshop on Interaction between Compilers and Computer Architectures · doi:10.1109/interact.2012.6339624 · Cited by 20
Clarke, D., Ilić, A., Lastovetsky, A., & Sousa, L. A. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-32820-6_49 · Cited by 20
Dynamic load balancing on heterogeneous multicore/multiGPU systems
Acosta, A., Corujo, R., Blanco, V., & Almeida, F. (2010) · International Conference on High Performance Computing & Simulation (HPCS) · doi:10.1109/hpcs.2010.5547097 · Cited by 20
Gao, P. C., Tao, Y., Bai, Z. H., & Lin, H. (2011) · Electromagnetic waves · doi:10.2528/pier11092303 · Cited by 20
IBM POWER7+ design for higher frequency at fixed power
Zyuban, V., Taylor, S. A., Christensen, B., Hall, A. R., Gonzalez, C. J., Friedrich, J., Clougherty, F., Tetzloff, J., & Rao, R. (2013) · IBM Journal of Research and Development · doi:10.1147/jrd.2013.2279597 · Cited by 19
Real-Time Non-rigid Registration of Medical Images on a Cooperative Parallel Architecture
Liu, Y., Fedorov, A., Kikinis, R., & Chrisochoides, N. P. (2009) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm.2009.10 · Cited by 19
Binotto, A. P. D., Pereira, C. E., Kuijper, A., Stork, A., & Fellner, D. W. (2011) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc.2011.20 · Cited by 19
2011 18th International Conference on High Performance Computing
(2011) · doi:10.1109/hipc18761.2011 · Cited by 19
CoreTSAR: Adaptive Worksharing for Heterogeneous Systems
Scogland, T., Feng, W.-C., Rountree, B., & de Supinski, B. R. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-07518-1_11 · Cited by 18
Glinda: a framework for accelerating imbalanced applications on heterogeneous platforms
Shen, J., Varbanescu, A. L., Sips, H., Arntzen, M., & Simons, D. G. (2013) · Proceedings of the ACM International Conference on Computing Frontiers · doi:10.1145/2482767.2482785 · Cited by 18
Mistry, P., Ukidave, Y., Schaa, D., & Kaeli, D. R. (2013) · doi:10.1145/2458523.2458529 · Cited by 18
Anzt, H., Heuveline, V., Aliaga, J. I., Castillo, M., Fernandez, J. C., Mayo, R., & Quintana–Ort́ı, E. S. (2011) · International Green and Sustainable Computing Conference · doi:10.1109/igcc.2011.6008594 · Cited by 18
Chai, J., Su, H., Wen, M., Cai, X. H., Wu, N., & Zhang, C. (2013) · The Journal of Supercomputing · doi:10.1007/s11227-013-0911-1 · Cited by 17
Hybrid implementation of error diffusion dithering
Deshpande, A., Misra, I., & Narayanan, P. J. (2011) · IEEE International Conference on High Performance Computing, Data, and Analytics · doi:10.1109/hipc.2011.6152714 · Cited by 16
Wang, Z., Zheng, L., Chen, Q., & Guo, M. (2013) · International Workshop on Programming Models and Applications for Multicores and Manycores (PMAM) · doi:10.1145/2442992.2443004 · Cited by 16
Automatic generation of software pipelines for heterogeneous parallel systems
Pienaar, J. A., Chakradhar, S., & Raghunathan, A. (2012) · IEEE International Conference on High Performance Computing, Data, and Analytics · doi:10.5555/2388996.2389029 · Cited by 15
Lang, J., & Rünger, G. (2013) · Procedia Computer Science · doi:10.1016/j.procs.2013.05.193 · Cited by 15
Accelerating Smith-Waterman on Heterogeneous CPU-GPU Systems
Singh, J., & Aruni, I. (2011) · International Conference on Bioinformatics and Biomedical Engineering · doi:10.1109/icbbe.2011.5780005 · Cited by 15
An optimized large-scale hybrid DGEMM design for CPUs and ATI GPUs
Li, J., Li, X., Tan, G., Chen, M., & Sun, N. (2012) · International Conference on Supercomputing · doi:10.1145/2304576.2304626 · Cited by 15
Automatic dataflow application tuning for heterogeneous systems
Hartley, T. D. R., Saule, É., & Çatalyürek, Ü. V. (2010) · IEEE International Conference on High Performance Computing, Data, and Analytics · doi:10.1109/hipc.2010.5713173 · Cited by 15
Programming model for a heterogeneous x86 platform
Saha, B., Zhou, X., Chen, H., Gao, Y. L., Yan, S., Rajagopalan, M., Fang, J., Zhang, P., Ronen, R., & Mendelson, A. (2009) · ACM SIGPLAN Notices · doi:10.1145/1543135.1542525 · Cited by 15
CuHMMer: A load-balanced CPU-GPU cooperative bioinformatics application
Yao, P., An, H., Xu, M., Gu, L., Li, X., Wang, Y., & Han, W. (2010) · International Conference on High Performance Computing & Simulation (HPCS) · doi:10.1109/hpcs.2010.5547159 · Cited by 14
Optimization Techniques for 3D-FWT on Systems with Manycore GPUs and Multicore CPUs
Bernabé, G., Cuenca, J., & Domingo Giménez, C. (2013) · Procedia Computer Science · doi:10.1016/j.procs.2013.05.195 · Cited by 14
Experience of parallelizing cryo-EM 3D reconstruction on a CPU-GPU heterogeneous system
Li, L., Li, X., Tan, G., Chen, M., & Zhang, P. (2011) · ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC) · doi:10.1145/1996130.1996157 · Cited by 14
Iterative SLE Solvers over a CPU-GPU Platform
Binotto, A. P. D., Daniel, C., Weber, D., Kuijper, A., Stork, A., Pereira, C. E., & Fellner, D. W. (2010) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc.2010.40 · Cited by 13
Effective Kernel Mapping for OpenCL Applications in Heterogeneous Platforms
Albayrak, O. E., Aktürk, İ., & Öztürk, Ö. (2012) · International Conference on Parallel Processing Workshops (ICPPW) · doi:10.1109/icppw.2012.14 · Cited by 13
Quantifying the energy efficiency of FFT on heterogeneous platforms
Ukidave, Y., Ziabari, A. K., Mistry, P., Schirner, G., & Kaeli, D. R. (2013) · IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) · doi:10.1109/ispass.2013.6557174 · Cited by 13
Anzt, H., Castillo, M., Aliaga, J. I., Fernandez, J. C., Heuveline, V., Mayo, R., & Quintana–Ort́ı, E. S. (2011) · University Library Heidelberg · doi:10.11588/emclpp.2011.05.11693 · Cited by 13
Astrophysical Particle Simulations on Heterogeneous CPU-GPU SystemsPreprint
Nakasato, N., Ogiya, G., Miki, Y., Mori, M., & NOMOTO, K. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1206.1199 · Cited by 11
CPU and/or GPU: Revisiting the GPU Vs. CPU MythPreprint
Kothapalli, K., Banerjee, D. S., Narayanan, P. J., Sood, S., Bahl, A. K., Sharma, S., Lad, S., Singh, K. K., Matam, K. K., Indarapu, S. B., et al. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1303.2171 · Cited by 11
Accelerating inclusion-based pointer analysis on heterogeneous CPU-GPU systems
Su, Y., Ye, D., & Xue, J. (2013) · IEEE International Conference on High Performance Computing, Data, and Analytics · doi:10.1109/hipc.2013.6799110 · Cited by 11
X-device query processing by bitwise distribution
Pirk, H., Sellam, T., Manegold, S., & Kersten, M. L. (2012) · International Workshop on Data Management on New Hardware (DaMoN) · doi:10.1145/2236584.2236591 · Cited by 11
A Map-Reduce Based Framework for Heterogeneous Processing Element Cluster Environments
Tan, Y. S., Lee, B., He, B., & Campbell, R. H. (2012) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid.2012.35 · Cited by 11
Fluid Simulation with Two-Way Interaction Rigid Body Using a Heterogeneous GPU and CPU Environment
José Ricardo da, S., Clua, E., Montenegro, A. A., & Pagliosa, P. (2010) · Brazilian Symposium on Computer Games and Digital Entertainment (SBGames) · doi:10.1109/sbgames.2010.25 · Cited by 11
PLASMA: Portable Programming for SIMD Heterogeneous Accelerators
Pai, S., Govindarajan, R., & Thazhuthaveetil, M. J. (2010) · Cited by 10
CPU–GPU hybrid parallel strategy for cosmological simulations
Wang, Y., Dou, Y., Guo, S., Lei, Y., & Zou, D. (2013) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.3046 · Cited by 10
Efficient sparse matrix-matrix multiplication on heterogeneous high performance systems
Siegel, J., Villa, O., Krishnamoorthy, S., Tumeo, A., & Li, X. (2010) · IEEE International Conference on Cluster Computing Workshops (CLUSTER Workshops) · doi:10.1109/clusterwksp.2010.5613109 · Cited by 10
A compound OpenMP/MPI program development toolkit for hybrid CPU/GPU clusters
Li, H.-F., Liang, T., & Chiu, J.-Y. (2013) · The Journal of Supercomputing · doi:10.1007/s11227-013-0912-0 · Cited by 10
Wu, Q., Yang, C., Wang, F., & Xue, J. (2012) · IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum · doi:10.1109/ipdpsw.2012.13 · Cited by 10
A New Parallel Method of Smith-Waterman Algorithm on a Heterogeneous Platform
Chen, B., Xu, Y., Yang, J., & Jiang, H. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-13119-6_7 · Cited by 9
Sparse Matrix Matrix Multiplication on Hybrid CPU+GPU Platforms
Matam, K. K., Indarapu, S. B., & Kothapalli, K. (2012) · Cited by 9
Workload Balancing on Heterogeneous Systems: A Case Study of Sparse Grid Interpolation
Murarasu, A. F., Weidendorfer, J., & Bode, A. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-29740-3_39 · Cited by 8
GPU/CPU Work Sharing with Parallel Language XcalableMP-dev for Parallelized Accelerated Computing
Odajima, T., Boku, T., Hanawa, T., Lee, J., & Sato, M. (2012) · International Conference on Parallel Processing Workshops (ICPPW) · doi:10.1109/icppw.2012.16 · Cited by 8
An exact algorithm for energy-efficient acceleration of task trees on CPU/GPU architectures
Silberstein, M., & Maruyama, N. (2011) · doi:10.1145/1987816.1987826 · Cited by 8
Muramatsu, J.-I., Fukaya, T., Zhang, S.-L., Kimura, K., & Yamamoto, Y. (2011) · International Journal of Networking and Computing · doi:10.15803/ijnc.1.2_132 · Cited by 7
Wang, G., & Song, W. (2011) · International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT) · doi:10.1109/pdcat.2011.28 · Cited by 7
Garba, M. T., & González–Vélez, H. (2012) · Parallel Processing Letters · doi:10.1142/s0129626412400087 · Cited by 7
GPU-enabled efficient executions of radiation calculations in climate modeling
Korwar, S. K., Vadhiyar, S. S., & Nanjundiah, R. S. (2013) · IEEE International Conference on High Performance Computing, Data, and Analytics · doi:10.1109/hipc.2013.6799141 · Cited by 7
Enabling multiple accelerator acceleration for Java/OpenMP
Veldema, R., Blaß, T., & Philippsen, M. (2011) · Cited by 7
Using 1000+ GPUs and 10000+ CPUs for Sedimentary Basin Simulations
Wen, M., Su, H., Wei, W., Wu, N., Cai, X. H., & Zhang, C. (2012) · IEEE International Conference on Cluster Computing (CLUSTER) · doi:10.1109/cluster.2012.37 · Cited by 6
Simulating cortical networks on heterogeneous multi-GPU systems
Nere, A., Franey, S., Hashmi, A., & Lipasti, M. (2013) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2012.02.006 · Cited by 6
An Efficient Stream Buffer Mechanism for Dataflow Execution on Heterogeneous Platforms with GPUs
Balevic, A., & Kienhuis, B. (2011) · Workshop on Data-Flow Execution Models for Extreme Scale Computing (DFM) · doi:10.1109/dfm.2011.10 · Cited by 6
Hawick, K. A., & Playne, D. P. (2013) · Cited by 6
Parallel Sorting on the Heterogeneous AMD Fusion Accelerated Processing Unit
Delorme, M. (2013) · TSpace (University of Toronto) · Cited by 6
Boratto, M. D. C., Alonso, P., Ramiro, C., & Barreto, M. E. (2012) · Procedia Computer Science · doi:10.1016/j.procs.2012.04.006 · Cited by 5
A (ir)regularity-aware task scheduler for heterogeneous platforms
Mariano, A. M. M., Alves, R. N., Barbosa, J., Santos, L. P., & Proença, A. J. (2012) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) · Cited by 5
Compiler and runtime support for enabling reduction computations on heterogeneous systems
Ravi, V. T., Ma, W., Chiu, D., & Agrawal, G. (2011) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.1848 · Cited by 5
An On-Demand Fast Parallel Pseudo Random Number Generator with Applications
Banerjee, D. S., Bahl, A. K., & Kothapalli, K. (2012) · IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum · doi:10.1109/ipdpsw.2012.212 · Cited by 5
Performance Implications of Nonuniform Device Topologies in Scalable Heterogeneous Architectures
Meredith, J., Roth, P. C., Spafford, K. L., & Vetter, J. S. (2011) · IEEE Micro · doi:10.1109/mm.2011.79 · Cited by 5
Self-citation罗力, Yang, C. Q., 赵宇波, & Cai, X. (2011) · Cited by 5
Dynamically tuned push-relabel algorithm for the maximum flow problem on CPU-GPU-Hybrid platforms
He, Z., & Hong, B. (2010) · 2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS) · doi:10.1109/ipdps.2010.5470401 · Cited by 4
A Framework for Profiling and Performance Monitoring of Heterogeneous Applications
Mistry, P., Ukidave, Y., Schaa, D., & Kaeli, D. R. (2013) · Cited by 4
Hybrid ray tracing and path tracing of Bezier surfaces using a mixed hierarchy
Nigam, R., & Narayanan, P. J. (2012) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/2425333.2425368 · Cited by 3
A hybrid shared memory heterogeneous execution platform for PCIe-based GPGPUs
Shukla, S. K., & Bhuyan, L. N. (2013) · IEEE International Conference on High Performance Computing, Data, and Analytics · doi:10.1109/hipc.2013.6799140 · Cited by 3
Solving linear recurrences on hybrid GPU accelerated manycore systems
Stpiczyński, P. (2011) · Cited by 3
Solving a kind of BVP for ODEs on heterogeneous CPU + CUDA-enabled GPU systems
Stpiczyński, P., & Potiopa, J. (2010) · Proceedings of the International Multiconference on Computer Science and Information Technology · doi:10.1109/imcsit.2010.5680041 · Cited by 3
A Technique for Collision Detection and 3D Interaction Based on Parallel GPU and CPU Processing
Tsuda, F., & Nakamura, R. (2011) · Brazilian Symposium on Computer Games and Digital Entertainment (SBGames) · doi:10.1109/sbgames.2011.20 · Cited by 3
Fast Snippet Generation Based on CPU-GPU Hybrid System
Liu, D., Li, R., Gu, X., Wen, K., He, H., & Gao, G. (2011) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads.2011.63 · Cited by 2
Enhancing Cloud-Based Servers by GPU/CPU Virtualization Management
Wu, T., Lee, W., Duan, C.-Y., & Suen, T.-W. (2012) · Smart innovation, systems and technologies · doi:10.1007/978-3-642-35473-1_20 · Cited by 2
Hybrid-parallel Algorithms for 2D Green's Functions
Melcón, A. Á., Domingo Giménez, C., Quesada, F. D., & Ramírez, T. (2013) · Procedia Computer Science · doi:10.1016/j.procs.2013.05.218 · Cited by 1
Gpu Implementation Of The Dp Code
Sottile, F. (2013) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.831464 · Cited by 1
Synergistic execution of stream programs on multicores with accelerators
Udupa, A., Govindarajan, R., & Thazhuthaveetil, M. J. (2009) · ACM SIGPLAN Notices · doi:10.1145/1543136.1542466 · Cited by 1
Wendel, D., Kalla, R., Friedrich, J., Kahle, J., Leenstra, J., Lichtenau, C., Sinharoy, B., Starke, W., & Zyuban, V. (2010) · 2010 IEEE International Conference on Integrated Circuit Design and Technology · doi:10.1109/icicdt.2010.5510286
- Self-citation
Sparse matrix-matrix multiplication on modern architectures
Matam, K., Indarapu, S. R. K. B., & Kothapalli, K. (2012) · 2012 19th International Conference on High Performance Computing · doi:10.1109/hipc.2012.6507483
Flagged first, then by citations
Research works printed but not linked: 12
- Chris Gregg, Jeff Brantley, and Kim Hazelwood. 2010. Contention-aware scheduling of parallel code for heterogeneous systems. In Proceedings of the USENIX Workshop on Hot Topics in Parallelism (HotPar’10).
- 10.5555/2015039.2015535 · DOI
- 10.5555/1987237.1987259 · DOI
- 10.5555/1885276.1885302 · DOI
- 10.5555/1964238.1964251 · DOI
- 10.5555/1761728.1761755 · DOI
- Usman Pirzada. 2015. Nvidia Geforce GTX TITAN X Unveiled - GM200 ‘Big Daddy Maxwell’, 12GB VRam and 8 Billion Transistors. Retrieved from wccftech.com/nvidia-gtx-titan-x-revealed-gdc-2015/.
- 10.5555/1855610.1855621 · DOI
- 10.5555/1885276.1885305 · DOI
- 10.5555/2001252.2001258 · DOI
- 10.5555/1863086.1863099 · DOI
- Dieter Wendel, Ronald Kalla, Joshua Friedrich, James Kahle, Jens Leenstra, Cedric Lichtenau, Balaram Sinharoy, William Starke, and Victor Zyuban. 2010. The POWER7 processor SoC. In Proceedings of the International Conference on IC Design and Technology (ICICDT’10). 71--73.
Cited by
Sorted by citations
Artificial intelligence: a survey on evolution, models, applications and future trends
Lu, Y. (2019) · Journal of Management Analytics · doi:10.1080/23270012.2019.1570365 · Cited by 641
Accelerating A uto D ock 4 with GPUs and Gradient-Based Local Search
Santos‐Martins, D., Solis-Vasquez, L., Tillack, A. F., Sanner, M. F., Koch, A., & Forli, S. (2021) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.0c01006 · Cited by 480
A survey of FPGA-based accelerators for convolutional neural networks
Mittal, S. (2018) · Neural Computing and Applications · doi:10.1007/s00521-018-3761-1 · Cited by 454
Self-citationComputer vision algorithms and hardware implementations: A survey
Feng, X., Jiang, Y., Yang, X., Du, M., & Li, X. S. (2019) · Integration · doi:10.1016/j.vlsi.2019.07.005 · Cited by 380
A Survey on optimized implementation of deep learning models on the NVIDIA Jetson platform
Mittal, S. (2019) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2019.01.011 · Cited by 319
Self-citation
Metadata
- Authors
- Mittal, S., & Vetter, J. S.
- Affiliations
- Oak Ridge National Laboratory (US)
- Venue
- ACM Computing Surveys
- Published
- 2015-07-21
- Volume
- 47
- Issue
- 4
- Pages
- 1-35
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W1864199185
- Semantic Scholar
- a14bb15298961545b83e7c7cefff0e7af79828f7
- Cited by
- 568
- References
- 197
- Citations by year
- 2026: 43 · 2025: 51 · 2024: 57 · 2023: 46 · 2022: 45 · 2021: 58 · 2020: 61 · 2019: 67 · 2018: 68 · 2017: 35 · 2016: 35 · 2015: 2
- FWCI
- 71.01
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM Computing Surveys (publishedVersion, public-domain)
- OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion)
- Funders
- U.S. Department of Energy
- Office of Science
- Advanced Scientific Computing Research
- Topics
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Physical Sciences › Computer Science › Computer Networks and Communications › Distributed and Parallel Computing Systems
- Physical Sciences › Computer Science › Hardware and Architecture › Embedded Systems Design Techniques
- Keywords
- CPU-GPU heterogeneous computing, workload partitioning, heterogeneous supercomputers, energy efficiency, benchmark suite, exascale computing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-11-08, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-08 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
