Patents by Inventor Stephen Junkins
Stephen Junkins 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).
-
Publication number: 20230297373Abstract: Embodiments described herein provided for an instruction and associated logic to enable GPGPU program code to access special purpose hardware logic to accelerate dot product operations. One embodiment provides for a graphics processing unit comprising a fetch unit to fetch a single instruction for execution, a decode unit to decode the single instruction into a decoded instruction, wherein the decoded instruction is to cause the graphics processing unit to perform a set of parallel dot product operations on elements of input matrices, and a systolic dot product unit to execute the decoded instruction across one or more parallel processor lanes using multiple systolic layers associated with multiple pipeline stages. The multiple pipeline stages include one or more sets of interconnected multipliers and adders to compute multiple concurrent dot products.Type: ApplicationFiled: April 26, 2023Publication date: September 21, 2023Applicant: Intel CorporationInventors: SUBRAMANIAM MAIYURAN, GUEI-YUAN LUEH, SUPRATIM PAL, ASHUTOSH GARG, CHANDRA S. GURRAM, JORGE E. PARRA, JUNJIE GU, KONRAD TRIFUNOVIC, HONG BIN LIAO, MIKE B. MACPHERSON, SHUBH B. SHAH, SHUBRA MARWAHA, STEPHEN JUNKINS, TIMOTHY R. BAUER, VARGHESE GEORGE, WEIYU CHEN
-
Patent number: 11640297Abstract: Embodiments described herein provided for an instruction and associated logic to enable GPGPU program code to access special purpose hardware logic to accelerate dot product operations. One embodiment provides for a graphics processing unit comprising a fetch unit to fetch an instruction for execution and a decode unit to decode the instruction into a decoded instruction. The decoded instruction is a matrix instruction to cause the graphics processing unit to perform a parallel dot product operation. The GPGPU also includes systolic dot product circuitry to execute the decoded instruction across one or more SIMD lanes using multiple systolic layers, wherein to execute the decoded instruction, a dot product computed at a first systolic layer is to be output to a second systolic layer, wherein each systolic layer includes one or more sets of interconnected multipliers and adders, each set of multipliers and adders to generate a dot product.Type: GrantFiled: June 15, 2021Date of Patent: May 2, 2023Assignee: Intel CorporationInventors: Subramaniam Maiyuran, Guei-Yuan Lueh, Supratim Pal, Ashutosh Garg, Chandra S. Gurram, Jorge E. Parra, Junjie Gu, Konrad Trifunovic, Hong Bin Liao, Mike B. MacPherson, Shubh B. Shah, Shubra Marwaha, Stephen Junkins, Timothy R. Bauer, Varghese George, Weiyu Chen
-
Publication number: 20230057492Abstract: Interleaving of variable bitrate streams for GPU implementations is described. An example of an apparatus includes one or more processors including a graphic processor, the graphics processor including a super-compression encoder pipeline to provide variable width interleaved coding; and memory for storage of data, wherein the graphics processor is to perform parallel dictionary encoding on a bitstream of symbols one of multiple workgroups, the workgroup to employ a plurality of encoders to generate a plurality of token-streams of variable lengths; create a histogram including at least tokens from the plurality of token-streams for the workgroup to generate an optimized entropy code; entropy code each of the plurality of token-streams for the workgroup into an encoded bitstream; and variably interleave the encoded bitstreams to generate an interleaved bitstream and bookkeep a size of the interleaved bitstream.Type: ApplicationFiled: June 30, 2022Publication date: February 23, 2023Applicant: Intel CorporationInventors: Sreenivas Kothandaraman, Stephen Junkins, Srihari Pratapa, Prasoonkumar Surti
-
Publication number: 20220414053Abstract: A processing apparatus includes a processing resource including a general-purpose parallel processing engine and a matrix accelerator. The matrix accelerator includes first circuitry to receive a command to perform operations associated with an instruction, second circuitry to configure the matrix accelerator according to a physical depth of a systolic array within the matrix accelerator and a logical depth associated with the instruction, third circuitry to read operands for the instruction from a register file associated with the systolic array, fourth circuitry to perform operations for the instruction via one or more passes through one or more physical pipeline stages of the systolic array based on a configuration performed by the second circuitry, and fifth circuitry to write output of the operations to the register file associated with the systolic array.Type: ApplicationFiled: June 24, 2021Publication date: December 29, 2022Applicant: Intel CorporationInventors: Jorge Parra, Wei-yu Chen, Kaiyu Chen, Varghese George, Junjie Gu, Chandra Gurram, Guei-Yuan Lueh, Stephen Junkins, Subramaniam Maiyuran, Supratim Pal
-
Publication number: 20220301228Abstract: Variable width interleaved coding for graphics processing is described. An example of an apparatus includes one or more processors including a graphic processor; and memory for storage of data including data for graphics processing, wherein the graphics processor includes an encoder pipeline to provide variable width interleaved coding and a decoder pipeline to decode the variable width interleaved coding, and wherein the encoder pipeline is to receive a plurality of bitstreams from workgroups; perform parallel entropy encoding on the bitstreams to generate a plurality of encoded bitstreams for each of the workgroups; perform variable interleaving of the bitstreams for each workgroup based at least in part on data requirements for decoding received from the decoder pipeline; and compact outputs for each of the workgroups into a contiguous stream of interleaved data.Type: ApplicationFiled: June 24, 2021Publication date: September 22, 2022Applicant: Intel CorporationInventors: Stephen Junkins, Sreenivas Kothandaraman, Prasoonkumar Surti, Srihari Pratapa, William Hux, John Feit
-
Patent number: 11436695Abstract: One embodiment provides for a general-purpose graphics processing device comprising a general-purpose graphics processing compute block to process a workload including graphics or compute operations, a first cache memory, and a coherency module enable the first cache memory to coherently cache data for the workload, the data stored in memory within a virtual address space, wherein the virtual address space shared with a separate general-purpose processor including a second cache memory that is coherent with the first cache memory.Type: GrantFiled: March 12, 2021Date of Patent: September 6, 2022Assignee: Intel CorporationInventors: Joydeep Ray, Altug Koker, James A. Valerio, David Puffer, Abhishek R. Appu, Stephen Junkins
-
Publication number: 20220051467Abstract: Apparatus and method for efficient graphics processing including ray tracing. For example, one embodiment of a graphics processor comprises: execution hardware logic to execute graphics commands and render images; an interface to couple functional units of the execution hardware logic to a tiled resource; and a tiled resource manager to manage access by the functional units to the tiled resource, a functional unit of the execution hardware logic to generate a request with a hash identifier (ID) to request access to a portion of the tiled resource, wherein the tiled resource manager is to determine whether a portion of the tiled resource identified by the hash ID exists, and if not, to allocate a new portion of the tiled resource and associate the new portion with the hash ID.Type: ApplicationFiled: December 23, 2020Publication date: February 17, 2022Inventors: Sven Woop, Michael J. Doyle, Sreenivas Kothandaraman, Karthik Vaidyanathan, Abhishek R. Appu, Carsten Benthin, Prasoonkumar Surti, Holger GRUEN, Stephen Junkins, Adam Lake, Bret G. Alfieri, Gabor Liktor, Joshua Barczak, Won-Jong Lee
-
Publication number: 20220051476Abstract: Apparatus and method for efficient graphics processing including ray tracing. For example, one embodiment of a graphics processor comprises: execution hardware logic to execute graphics commands and render images; an interface to couple functional units of the execution hardware logic to a tiled resource; and a tiled resource manager to manage access by the functional units to the tiled resource, a functional unit of the execution hardware logic to generate a request with a hash identifier (ID) to request access to a portion of the tiled resource, wherein the tiled resource manager is to determine whether a portion of the tiled resource identified by the hash ID exists, and if not, to allocate a new portion of the tiled resource and associate the new portion with the hash ID.Type: ApplicationFiled: December 23, 2020Publication date: February 17, 2022Inventors: Sven Woop, Michael J. Doyle, Sreenivas Kothandaraman, Karthik Vaidyanathan, Abhishek R. Appu, Carsten Benthin, Prasoonkumar Surti, Holger GRUEN, Stephen Junkins, Adam Lake, Bret G. Alfieri, Gabor Liktor, Joshua Barczak, Won-Jong Lee
-
Publication number: 20210303299Abstract: Embodiments described herein provided for an instruction and associated logic to enable GPGPU program code to access special purpose hardware logic to accelerate dot product operations. One embodiment provides for a graphics processing unit comprising a fetch unit to fetch an instruction for execution and a decode unit to decode the instruction into a decoded instruction. The decoded instruction is a matrix instruction to cause the graphics processing unit to perform a parallel dot product operation. The GPGPU also includes systolic dot product circuitry to execute the decoded instruction across one or more SIMD lanes using multiple systolic layers, wherein to execute the decoded instruction, a dot product computed at a first systolic layer is to be output to a second systolic layer, wherein each systolic layer includes one or more sets of interconnected multipliers and adders, each set of multipliers and adders to generate a dot product.Type: ApplicationFiled: June 15, 2021Publication date: September 30, 2021Applicant: Intel CorporationInventors: SUBRAMANIAM MAIYURAN, GUEI-YUAN LUEH, SUPRATIM PAL, ASHUTOSH GARG, CHANDRA S. GURRAM, JORGE E. PARRA, JUNJIE GU, KONRAD TRIFUNOVIC, HONG BIN LIAO, MIKE B. MACPHERSON, SHUBH B. SHAH, SHUBRA MARWAHA, STEPHEN JUNKINS, TIMOTHY R. BAUER, VARGHESE GEORGE, WEIYU CHEN
-
Publication number: 20210272231Abstract: One embodiment provides for a general-purpose graphics processing device comprising a general-purpose graphics processing compute block to process a workload including graphics or compute operations, a first cache memory, and a coherency module enable the first cache memory to coherently cache data for the workload, the data stored in memory within a virtual address space, wherein the virtual address space shared with a separate general-purpose processor including a second cache memory that is coherent with the first cache memory.Type: ApplicationFiled: March 12, 2021Publication date: September 2, 2021Applicant: Intel CorporationInventors: Joydeep Ray, Altug Koker, James A. Valerio, David Puffer, Abhishek R. Appu, Stephen Junkins
-
Patent number: 11042370Abstract: Embodiments described herein provided for an instruction and associated logic to enable GPGPU program code to access special purpose hardware logic to accelerate dot product operations. One embodiment provides for a graphics processing unit comprising a fetch unit to fetch an instruction for execution and a decode unit to decode the instruction into a decoded instruction. The decoded instruction is a matrix instruction to cause the graphics processing unit to perform a parallel dot product operation. The GPGPU also includes a systolic dot product unit to execute the decoded instruction across one or more SIMD lanes using multiple systolic layers, wherein to execute the decoded instruction, a dot product computed at a first systolic layer is to be output to a second systolic layer, wherein each systolic layer includes one or more sets of interconnected multipliers and adders, each set of multipliers and adders to generate a dot product.Type: GrantFiled: April 19, 2018Date of Patent: June 22, 2021Assignee: Intel CorporationInventors: Subramaniam Maiyuran, Guei-Yuan Lueh, Supratim Pal, Ashutosh Garg, Chandra S. Gurram, Jorge E. Parra, Junjie Gu, Konrad Trifunovic, Hong Bin Liao, Mike B. Macpherson, Shubh B. Shah, Shubra Marwaha, Stephen Junkins, Timothy R. Bauer, Varghese George, Weiyu Chen
-
Patent number: 10949945Abstract: One embodiment provides for a general-purpose graphics processing device comprising a general-purpose graphics processing compute block to process a workload including graphics or compute operations, a first cache memory, and a coherency module enable the first cache memory to coherently cache data for the workload, the data stored in memory within a virtual address space, wherein the virtual address space shared with a separate general-purpose processor including a second cache memory that is coherent with the first cache memory.Type: GrantFiled: May 11, 2020Date of Patent: March 16, 2021Assignee: Intel CorporationInventors: Joydeep Ray, Altug Koker, James A. Valerio, David Puffer, Abhishek R. Appu, Stephen Junkins
-
Publication number: 20200342564Abstract: One embodiment provides for a general-purpose graphics processing device comprising a general-purpose graphics processing compute block to process a workload including graphics or compute operations, a first cache memory, and a coherency module enable the first cache memory to coherently cache data for the workload, the data stored in memory within a virtual address space, wherein the virtual address space shared with a separate general-purpose processor including a second cache memory that is coherent with the first cache memory.Type: ApplicationFiled: May 11, 2020Publication date: October 29, 2020Applicant: Intel CorporationInventors: Joydeep Ray, Altug Koker, James A. Valerio, David Puffer, Abhishek R. Appu, Stephen Junkins
-
Patent number: 10657618Abstract: One embodiment provides for a general-purpose graphics processing device comprising a general-purpose graphics processing compute block to process a workload including graphics or compute operations, a first cache memory, and a coherency module enable the first cache memory to coherently cache data for the workload, the data stored in memory within a virtual address space, wherein the virtual address space shared with a separate general-purpose processor including a second cache memory that is coherent with the first cache memory.Type: GrantFiled: June 14, 2019Date of Patent: May 19, 2020Assignee: Intel CorporationInventors: Joydeep Ray, Altug Koker, James A. Valerio, David Puffer, Abhishek R. Appu, Stephen Junkins
-
Publication number: 20190324746Abstract: Embodiments described herein provided for an instruction and associated logic to enable GPGPU program code to access special purpose hardware logic to accelerate dot product operations. One embodiment provides for a graphics processing unit comprising a fetch unit to fetch an instruction for execution and a decode unit to decode the instruction into a decoded instruction. The decoded instruction is a matrix instruction to cause the graphics processing unit to perform a parallel dot product operation. The GPGPU also includes a systolic dot product unit to execute the decoded instruction across one or more SIMD lanes using multiple systolic layers, wherein to execute the decoded instruction, a dot product computed at a first systolic layer is to be output to a second systolic layer, wherein each systolic layer includes one or more sets of interconnected multipliers and adders, each set of multipliers and adders to generate a dot product.Type: ApplicationFiled: April 19, 2018Publication date: October 24, 2019Applicant: Intel CorporationInventors: SUBRAMANIAM MAIYURAN, GUEI-YUAN LUEH, SUPRATIM PAL, ASHUTOSH GARG, CHANDRA S. GURRAM, JORGE E. PARRA, JUNJIE GU, KONRAD TRIFUNOVIC, HONG BIN LIAO, MIKE B. MACPHERSON, SHUBH B. SHAH, SHUBRA MARWAHA, STEPHEN JUNKINS, TIMOTHY R. BAUER, VARGHESE GEORGE, WEIYU CHEN
-
Publication number: 20190304052Abstract: One embodiment provides for a general-purpose graphics processing device comprising a general-purpose graphics processing compute block to process a workload including graphics or compute operations, a first cache memory, and a coherency module enable the first cache memory to coherently cache data for the workload, the data stored in memory within a virtual address space, wherein the virtual address space shared with a separate general-purpose processor including a second cache memory that is coherent with the first cache memory.Type: ApplicationFiled: June 14, 2019Publication date: October 3, 2019Applicant: Intel CorporationInventors: Joydeep Ray, Altug Koker, James A. Valerio, David Puffer, Abhishek R. Appu, Stephen Junkins
-
Patent number: 10373285Abstract: One embodiment provides for a general-purpose graphics processing device comprising a general-purpose graphics processing compute block to process a workload including graphics or compute operations, a first cache memory, and a coherency module enable the first cache memory to coherently cache data for the workload, the data stored in memory within a virtual address space, wherein the virtual address space shared with a separate general-purpose processor including a second cache memory that is coherent with the first cache memory.Type: GrantFiled: April 9, 2017Date of Patent: August 6, 2019Assignee: Intel CorporationInventors: Joydeep Ray, Altug Koker, James A. Valerio, David Puffer, Abhishek R. Appu, Stephen Junkins
-
Publication number: 20180293693Abstract: One embodiment provides for a general-purpose graphics processing device comprising a general-purpose graphics processing compute block to process a workload including graphics or compute operations, a first cache memory, and a coherency module enable the first cache memory to coherently cache data for the workload, the data stored in memory within a virtual address space, wherein the virtual address space shared with a separate general-purpose processor including a second cache memory that is coherent with the first cache memory.Type: ApplicationFiled: April 9, 2017Publication date: October 11, 2018Applicant: Intel CorporationInventors: Joydeep Ray, Altug Koker, James A. Valerio, David Puffer, Abhishek R. Appu, Stephen Junkins
-
Publication number: 20180285262Abstract: Various embodiments described herein include an input/output memory management unit (IOMMU) that can restrict write accesses originating from a shared virtual memory (SVM) device towards a CPU's code page, so that the SVM device cannot be used to attack and manipulate the CPU's behavior. In some embodiments, the IOMMU may perform a security check so that whenever a write request arrives from an SVM device, if the page requested is present and is executable, an access violation fault is generated and the request is terminated. In some such embodiments, this may prevent a malicious or vulnerable device from corrupting the CPU's process memory and causing an arbitrary code execution with the CPU process's privileges.Type: ApplicationFiled: March 31, 2017Publication date: October 4, 2018Applicant: INTEL CORPORATIONInventors: ANNA TRIKALINOU, RAJESH M. SANKARAN, STEPHEN JUNKINS
-
Patent number: 8823720Abstract: Methods, systems and data structures produce a rasterizer. A graphical state is detected on a machine architecture. The graphical state is used for assembling a shell rasterizer. The machine architecture is used for selecting replacement logic that replaces portions of shell logic in the shell rasterizer. The machine architecture is used for selectively inserting memory management logic into portions of the shell logic to produce.Type: GrantFiled: April 17, 2013Date of Patent: September 2, 2014Assignee: Intel CorporationInventors: William A. Hux, Stephen Junkins