Design and optimization for multiprocessor interactive GPU

Deng, Junyong; Li, Tao; Lin, Jenshan; Han, Jiawei; Shen, Xubang

doi:10.1016/s1005-8885(14)60305-8

Cited by 6 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the detailed circuit design, all operations are translated into fixed point operations [17], [18], which can reduce the difficulty of circuit implementation. And this design can be applied in our GPU [19] [20].…”

Section: Discussionmentioning

confidence: 99%

A Piecewise Cubic Polynomial Interpolation Algorithm for Approximating Elementary Function

Cao¹,

Du²,

Wang³

et al. 2015

2015 14th International Conference on Computer-Aided Design and Computer Graphics (CAD/Graphics)

View full text Add to dashboard Cite

The elementary function approximation using piecewise quadratic polynomial interpolation requires larger area of the look-up table (LUT) and circuit. To solve the problem, this paper presents an algorithm for elementary function approximation in single-precision floating-point format, which is based on minimax piecewise cubic polynomial approximation. The algorithm can efficiently achieve the approximation of reciprocal, square root, square root reciprocal, exponentials, logarithm, and trigonometric function in single-precision floating-point format. According to the algorithm the range of parameters is narrowed first, then we get the optimal truncated bit width of coefficients through errors analyzing and dividing the interval into subsections. Meanwhile Remes algorithm is used to perform the successive optimization, so as to reduce the area of LUT and circuit. At last the intermediate parameters of the circuit are optimally truncated, and the overall framework of hardware circuit is designed. The analysis and experimental results show that comparing with piecewise quadratic polynomial approximation the circuit delay is reduced by 17.25%, the area of LUT is decreased by 53.60% and total area of circuits is reduced by 19.73%. The comparisons with the polynomial approximation of degree-1, degree-2, degree-4 are also made, the results show that the piecewise cubic polynomial interpolation algorithm proposed by this paper can achieve optimal performance and minimized cost of hardware implementation.

show abstract

Section: Discussionmentioning

confidence: 99%

A Piecewise Cubic Polynomial Interpolation Algorithm for Approximating Elementary Function

Cao¹,

Du²,

Wang³

et al. 2015

2015 14th International Conference on Computer-Aided Design and Computer Graphics (CAD/Graphics)

View full text Add to dashboard Cite

show abstract

“…With the new transistor process and tri-gate fin design, a single chip will accommodate more computing resources [23] . So, the reconfiguration mechanism should facilitate this reality with minimal interconnection overheads increasing.…”

Section: Scalability Of Reconfiguration Mechanismmentioning

confidence: 99%

“…For example, the reconfigurable video processing system requires multiple PEs to execute the same task, such as intra-prediction (Intra), integer motion estimation (IME), fractional mo- tion estimation (FME), motion compensation (MC), DeBlocking filter (DB), etc. And in graphics processing field, the vertex shading, the plane-clip, projection, 3D-Clip, pixel shading, primitive assemble unit, back-face culling, viewport transformation, fragment operating unit and so on are also need several PEs to work together [24][25][26] . The associated PEs should also start simultaneously to process in parallel.…”

Section: Hrmmentioning

confidence: 99%

HRM: H-tree based reconfiguration mechanism in reconfigurable homogeneous PE array

Deng¹,

Lin²,

Zhu³

et al. 2020

J. Semicond.

Self Cite

View full text Add to dashboard Cite

In order to accommodate the variety of algorithms with different performance in specific application and improve power efficiency, reconfigurable architecture has become an effective methodology in academia and industry. However, existing architectures suffer from performance bottleneck due to slow updating of contexts and inadequate flexibility. This paper presents an H-tree based reconfiguration mechanism (HRM) with Huffman-coding-like and mask addressing method in a homogeneous processing element (PE) array, which supports both programmable and data-driven modes. The proposed HRM can transfer reconfiguration instructions/contexts to a particular PE or associated PEs simultaneously in one clock cycle in unicast, multicast and broadcast mode, and shut down the unnecessary PE/PEs according to the current configuration. To verify the correctness and efficiency, we implement it in RTL synthesis and FPGA prototype. Compared to prior works, the experiment results show that the HRM has improved the work frequency by an average of 23.4%, increased the updating speed by 2×, and reduced the area by 36.9%; HRM can also power off the unnecessary PEs which reduced 51% of dynamic power dissipation in certain application configuration. Furthermore, in the data-driven mode, the system frequency can reach 214 MHz, which is 1.68× higher compared with the programmable mode.

show abstract

“…We have designed a new type of GPU, Firefly2 [5]. It is designed for graphics rendering, image processing and machine vision applications.…”

Section: Introductionmentioning

confidence: 99%

Parallel Implementation of OpenVX on Firefly2 GPU

Guo

Han

Che

et al. 2015

2015 8th International Symposium on Computational Intelligence and Design (ISCID)

Self Cite

View full text Add to dashboard Cite

Given the fact that the traditional GPU mainly supports the parallel computing with SIMD (Single Instruction Multiple Data) and SIMT (Single Instruction Multiple Thread) mode, the Firefly2 GPU (Graphic Processing Unit) has special hardware configuration mechanism and can be used for paralleling computing on data-level, thread-level and operatedlevel. This paper presents parallel implementation of OpenVX kernels on Firefly2 GPU with the method by combing the operation level parallelism with data level parallelism. Experimental results indicate satisfactory speedup of the parallel implementation and show that the Firefly2 is suitable for graphics and image processing.

show abstract

Design and optimization for multiprocessor interactive GPU

Cited by 6 publications

References 4 publications

A Piecewise Cubic Polynomial Interpolation Algorithm for Approximating Elementary Function

A Piecewise Cubic Polynomial Interpolation Algorithm for Approximating Elementary Function

HRM: H-tree based reconfiguration mechanism in reconfigurable homogeneous PE array

Parallel Implementation of OpenVX on Firefly2 GPU

Contact Info

Product

Resources

About