Patents by Inventor Raphael C. Polig
Raphael C. Polig has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 10685082Abstract: According to some embodiments, a computer-implemented method for performing sparse matrix dense matrix (SpMM) multiplication on a single field programmable gate array (FPGA) module comprising a k-stage pipeline is described. The method may include interleaving k-stage threads on the k-stage pipeline comprising a plurality of threads t0 to tk-1, wherein a first result of thread t0 is ready one cycle after the first input of thread tk-1 is fed into the pipeline, and outputting a result matrix Y.Type: GrantFiled: October 31, 2016Date of Patent: June 16, 2020Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Costas Bekas, Alessandro Curioni, Heiner Giefers, Christoph Hagleitner, Raphael C. Polig, Peter W. J. Staar
-
Patent number: 9779061Abstract: An iterative refinement apparatus configured to generate data defining a solution vector x for a linear system represented by Ax=b, where A is a predetermined matrix and b is a predetermined vector. An outer solver processes input data, defining the matrix A and vector b, in accordance with an outer loop of an iterative refinement method to generate said data defining the solution vector x. An inner solver processes data items in accordance with an inner loop of the iterative refinement method. The inner solver is configured to process said data items having variable bit-width and data format. A precision controller determines the bit-widths and data formats of the data items adaptively in dependence on the results of the processing steps of the iterative refinement method; the precision controller configured to control operation of the inner solver for processing said data items with the bit-widths and data formats.Type: GrantFiled: February 16, 2015Date of Patent: October 3, 2017Assignee: International Business Machines CorporationInventors: Christoph M. Angerer, Konstantinos Bekas, Alessandro Curioni, Silvio Dragone, Heiner Giefers, Christoph Hagleitner, Raphael C. Polig
-
Publication number: 20170147531Abstract: According to some embodiments, a computer-implemented method for performing sparse matrix dense matrix (SpMM) multiplication on a single field programmable gate array (FPGA) module comprising a k-stage pipeline is described. The method may include interleaving k-stage threads on the k-stage pipeline comprising a plurality of threads t0 to tk-1, wherein a first result of thread t0 is ready one cycle after the first input of thread tk-1 is fed into the pipeline, and outputting a result matrix Y.Type: ApplicationFiled: October 31, 2016Publication date: May 25, 2017Inventors: Costas Bekas, Alessandro Curioni, Heiner Giefers, Christoph Hagleitner, Raphael C. Polig, Peter W. J. Staar
-
Patent number: 9582472Abstract: A conjugate gradient solver apparatus is provided for generating data defining a solution vector x for a linear system represented by Ax=b where A is a predetermined matrix and b is a predetermined vector. The apparatus includes solver circuitry and a precision controller. The solver circuitry processes input data, defining said matrix A and vector b, in accordance with an iterative conjugate gradient method to generate said data defining the solution vector x. The solver circuitry is adapted to process data items, corresponding to vectors used in said conjugate gradient method, having a variable fixed-point data format. The precision controller determines the fixed-point data formats of respective said data items adaptively during progress of the conjugate gradient method in the solver circuitry.Type: GrantFiled: February 11, 2015Date of Patent: February 28, 2017Assignee: International Business Machines CorporationInventors: Christoph M. Angerer, Konstantinos Bekas, Alessandro Curioni, Silvio Dragone, Christoph Hagleitner, Raphael C. Polig
-
Patent number: 9575930Abstract: A conjugate gradient solver apparatus is provided for generating data defining a solution vector x for a linear system represented by Ax=b where A is a predetermined matrix and b is a predetermined vector. The apparatus includes solver circuitry and a precision controller. The solver circuitry processes input data, defining said matrix A and vector b, in accordance with an iterative conjugate gradient method to generate said data defining the solution vector x. The solver circuitry is adapted to process data items, corresponding to vectors used in said conjugate gradient method, having a variable fixed-point data format. The precision controller determines the fixed-point data formats of respective said data items adaptively during progress of the conjugate gradient method in the solver circuitry.Type: GrantFiled: June 23, 2015Date of Patent: February 21, 2017Assignee: International Business Machines CorporationInventors: Christoph M. Angerer, Konstantinos Bekas, Alessandro Curioni, Silvio Dragone, Christoph Hagleitner, Raphael C. Polig
-
Patent number: 9558156Abstract: According to some embodiments, a computer-implemented method for performing sparse matrix dense matrix (SpMM) multiplication on a single field programmable gate array (FPGA) module comprising a k-stage pipeline is described. The method may include interleaving k-stage threads on the k-stage pipeline comprising a plurality of threads t0 to tk-1, wherein a first result of thread t0 is ready one cycle after the first input of thread tk-1 is fed into the pipeline, and outputting a result matrix Y.Type: GrantFiled: November 24, 2015Date of Patent: January 31, 2017Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Costas Bekas, Alessandro Curioni, Heiner Giefers, Christoph Hagleitner, Raphael C. Polig, Peter W. J. Staar
-
Publication number: 20150293882Abstract: A conjugate gradient solver apparatus is provided for generating data defining a solution vector x for a linear system represented by Ax=b where A is a predetermined matrix and b is a predetermined vector. The apparatus includes solver circuitry and a precision controller. The solver circuitry processes input data, defining said matrix A and vector b, in accordance with an iterative conjugate gradient method to generate said data defining the solution vector x. The solver circuitry is adapted to process data items, corresponding to vectors used in said conjugate gradient method, having a variable fixed-point data format. The precision controller determines the fixed-point data formats of respective said data items adaptively during progress of the conjugate gradient method in the solver circuitry.Type: ApplicationFiled: June 23, 2015Publication date: October 15, 2015Inventors: Christoph M. Angerer, Konstantinos Bekas, Alessandro Curioni, Silvio Dragone, Christoph Hagleitner, Raphael C. Polig
-
Publication number: 20150234781Abstract: A conjugate gradient solver apparatus is provided for generating data defining a solution vector x for a linear system represented by Ax=b where A is a predetermined matrix and b is a predetermined vector. The apparatus includes solver circuitry and a precision controller. The solver circuitry processes input data, defining said matrix A and vector b, in accordance with an iterative conjugate gradient method to generate said data defining the solution vector x. The solver circuitry is adapted to process data items, corresponding to vectors used in said conjugate gradient method, having a variable fixed-point data format. The precision controller determines the fixed-point data formats of respective said data items adaptively during progress of the conjugate gradient method in the solver circuitry.Type: ApplicationFiled: February 11, 2015Publication date: August 20, 2015Inventors: Christoph M. Angerer, Konstantinos Bekas, Alessandro Curioni, Silvio Dragone, Christoph Hagleitner, Raphael C. Polig
-
Publication number: 20150234783Abstract: An iterative refinement apparatus configured to generate data defining a solution vector x for a linear system represented by Ax=b, where A is a predetermined matrix and b is a predetermined vector. An outer solver processes input data, defining the matrix A and vector b, in accordance with an outer loop of an iterative refinement method to generate said data defining the solution vector x. An inner solver processes data items in accordance with an inner loop of the iterative refinement method. The inner solver is configured to process said data items having variable bit-width and data format. A precision controller determines the bit-widths and data formats of the data items adaptively in dependence on the results of the processing steps of the iterative refinement method; the precision controller configured to control operation of the inner solver for processing said data items with the bit-widths and data formats.Type: ApplicationFiled: February 16, 2015Publication date: August 20, 2015Inventors: Christoph M. Angerer, Konstantinos Bekas, Alessandro Curioni, Silvio Dragone, Heiner Giefers, Christoph Hagleitner, Raphael C. Polig