DocumentCode :
188166
Title :
Harmonica: An FPGA-Based Data Parallel Soft Core
Author :
Kersey, Chad ; Yalamanchili, Sudhakar ; Hyojong Kim ; Nigania, Nimit ; Hyesoon Kim
Author_Institution :
Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
fYear :
2014
fDate :
11-13 May 2014
Firstpage :
171
Lastpage :
171
Abstract :
General-purpose GPUs or GPGPUs have taken their place in the market, being present in 38 of the Top 500 supercomputers [5]. In the same way that the emergence of FPGAs in the 1980s led to a demand for soft cores with instruction sets similar to the CPUs of the day, we anticipate a similar demand in the 2010s for soft cores with GPGPU instruction sets. These architectures are distinguished by their SIMT, single-instruction-multiple-thread, execution model, acheiving throughput by running multiple threads of execution simultaneously across multiple functional units, keeping separate register values for each lane of execution.
Keywords :
field programmable gate arrays; graphics processing units; instruction sets; multiprocessing systems; parallel processing; FPGA; GPGPU; GPGPU instruction sets; SIMT; data parallel soft core; execution model; general purpose GPU; single instruction multiple thread; soft cores; Computer architecture; Educational institutions; Field programmable gate arrays; Hardware; Instruction sets; Prototypes; Registers; C++; FPGA; GPGPU; SIMT; data parallel; processor near memory;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Field-Programmable Custom Computing Machines (FCCM), 2014 IEEE 22nd Annual International Symposium on
Conference_Location :
Boston, MA
Print_ISBN :
978-1-4799-5110-9
Type :
conf
DOI :
10.1109/FCCM.2014.53
Filename :
6861615
Link To Document :
بازگشت