Implementing and Evaluating an Heterogeneous, Scalable, Tridiagonal Linear System Solver with OpenCL to Target FPGAs, GPUs, and CPUs

<table class="table-group" id="tab4"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">Component</td><td class="align_center">Specification</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">CPU</td><td class="align_center">Intel Xeon E5-1620 v4 @ 3.50 GHz</td></tr><tr><td class="align_left">GPU</td><td class="align_center">NVIDIA M4000 8 GB GDDR5<br/>PCIe G3 x16</td></tr><tr><td class="align_left">FPGA</td><td class="align_center">Bittware A10PL4 w/<br/>Intel Arria 10 GX 8 GB DDR4<br/>PCIe G3 x8</td></tr><tr><td class="align_left">RAM</td><td class="align_center">64 GB DDR4 @ 2400 MHz</td></tr><tr><td class="align_left">OS</td><td class="align_center">CentOS 7.4</td></tr><tr><td class="align_left">Software</td><td class="align_center">ICC 18.0.3<br/>CUDA 9.0<br/>Intel Quartus Pro 17.0<br/>Intel OpenCL SDK 7.0.0.2568</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Specifications for Dell T5000 desktop PC.</div>

International Journal of Reconfigurable Computing

tab4

Table 4

Table 4: Implementing and Evaluating an Heterogeneous, Scalable, Tridiagonal Linear System Solver with OpenCL to Target FPGAs, GPUs, and CPUs 