Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Filters

2011 - 20132

Settings

Subject: search.filters.subject.CPU

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    CSPR: Column only SPARSE matrix representation for performance improvement on GPU architecture
    (2011) Bayyapu, B.; Raghavendra, P.S.
    General purpose computation on graphics processing unit (GPU) is prominent in the high performance computing era of this time. Porting or accelerating the data parallel applications onto GPU gives the default performance improvement because of the increased computational units. Better performances can be seen if application specific fine tuning is done with respect to the architecture under consideration. One such very widely used computation intensive kernel is sparse matrix vector multiplication (SPMV) in sparse matrix based applications. Most of the existing data format representations of sparse matrix are developed with respect to the central processing unit (CPU) or multi cores. This paper gives a new format for sparse matrix representation with respect to graphics processor architecture that can give 2x to 5x performance improvement compared to CSR (compressed row format), 2x to 54x performance improvement with respect to COO (coordinate format) and 3x to 10 x improvement compared to CSR vector format for the class of application that fit for the proposed new format. It also gives 10% to 133% improvements in memory transfer (of only access information of sparse matrix) between CPU and GPU. This paper gives the details of the new format and its requirement with complete experimentation details and results of comparison. © 2011 Springer-Verlag.
  • No Thumbnail Available
    Item
    Replacement of heat sink fan by nanocoolants for enhancement of CPU efficiency
    (Institution of Engineering and Technology journals@theiet.org, 2013) Siddique, A.B.; Prabhu, K.N.
    The highest temperature under which a CPU can operate without interruption is 90°C. Heat sink fans generally provided for removal of heat produced by the processor are proved to be inadequate when CPU usage is 100%. The objective of this work is to exploit the enhanced thermal properties of nanofluid for dissipation of heat from the Intel (R) Core (TM) i5- 2310 CPU @ 2.9GHz quad-core processor for cooling it to a suitable operating temperature. Nanocoolants were prepared with two types of nanoparticles, titania and copper. The volume percentage of nanoparticles in nanocoolants were 0.01 and 0.1. It was observed that nanofluids are more efficient coolants than the base fluid and found to be significantly better than the traditional heat sink fan, as indicated by the CPU temperature, under the same loading condition. The average CPU temperatures were 90°C, 58°C, 56.6°C and 54.5°C with heat sink fan, deionized water, 0.1 vol% TiO2 and 0.1 vol% Cu nanofluids respectively at the flow rate of 700ml/min and CPU usage of 100%. The lowest CPU operating temperature (54.5°C) was obtained with 0.1 vol% Cu at the flow rate of 700ml/min. The cooling of CPU was also affected by the flow rate and the volume fraction of nanoparticles in the nanocoolant.