Patents by Inventor NAVEEN K. MELLEMPUDI
NAVEEN K. MELLEMPUDI 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: 20240126544Abstract: Disclosed embodiments relate to instructions for fused multiply-add (FMA) operations with variable-precision inputs. In one example, a processor to execute an asymmetric FMA instruction includes fetch circuitry to fetch an FMA instruction having fields to specify an opcode, a destination, and first and second source vectors having first and second widths, respectively, decode circuitry to decode the fetched FMA instruction, and a single instruction multiple data (SIMD) execution circuit to process as many elements of the second source vector as fit into an SIMD lane width by multiplying each element by a corresponding element of the first source vector, and accumulating a resulting product with previous contents of the destination, wherein the SIMD lane width is one of 16 bits, 32 bits, and 64 bits, the first width is one of 4 bits and 8 bits, and the second width is one of 1 bit, 2 bits, and 4 bits.Type: ApplicationFiled: December 28, 2023Publication date: April 18, 2024Inventors: Dipankar DAS, Naveen K. MELLEMPUDI, Mrinmay DUTTA, Arun KUMAR, Dheevatsa MUDIGERE, Abhisek KUNDU
-
Patent number: 11900107Abstract: Disclosed embodiments relate to instructions for fused multiply-add (FMA) operations with variable-precision inputs. In one example, a processor to execute an asymmetric FMA instruction includes fetch circuitry to fetch an FMA instruction having fields to specify an opcode, a destination, and first and second source vectors having first and second widths, respectively, decode circuitry to decode the fetched FMA instruction, and a single instruction multiple data (SIMD) execution circuit to process as many elements of the second source vector as fit into an SIMD lane width by multiplying each element by a corresponding element of the first source vector, and accumulating a resulting product with previous contents of the destination, wherein the SIMD lane width is one of 16 bits, 32 bits, and 64 bits, the first width is one of 4 bits and 8 bits, and the second width is one of 1 bit, 2 bits, and 4 bits.Type: GrantFiled: March 25, 2022Date of Patent: February 13, 2024Assignee: Intel CorporationInventors: Dipankar Das, Naveen K. Mellempudi, Mrinmay Dutta, Arun Kumar, Dheevatsa Mudigere, Abhisek Kundu
-
Publication number: 20230351542Abstract: One embodiment provides for a graphics processing unit to perform computations associated with a neural network, the graphics processing unit comprising a hardware processing unit having a dynamic precision fixed-point unit that is configurable to convert elements of a floating-point tensor to convert the floating-point tensor into a fixed-point tensor.Type: ApplicationFiled: April 24, 2023Publication date: November 2, 2023Applicant: Intel CorporationInventors: Naveen K. MELLEMPUDI, DHEEVATSA MUDIGERE, DIPANKAR DAS, SRINIVAS SRIDHARAN
-
Patent number: 11669933Abstract: One embodiment provides for a graphics processing unit to perform computations associated with a neural network, the graphics processing unit comprising a hardware processing unit having a dynamic precision fixed-point unit that is configurable to quantize elements of a floating-point tensor to convert the floating-point tensor into a dynamic fixed-point tensor.Type: GrantFiled: April 27, 2022Date of Patent: June 6, 2023Assignee: Intel CorporationInventors: Naveen K. Mellempudi, Dheevatsa Mudigere, Dipankar Das, Srinivas Sridharan
-
Publication number: 20220343174Abstract: Described herein is a graphics processor including a processing resource including a multiplier configured to multiply input associated with the instruction at one of a first plurality of bit widths, an adder configured to add a product output from the multiplier with an accumulator value at one of a second plurality of bit widths, and circuitry to select a first bit width of the first plurality of bit widths for the multiplier and a second bit width of the second plurality of bit widths for the adder.Type: ApplicationFiled: May 12, 2022Publication date: October 27, 2022Applicant: Intel CorporationInventors: Dipankar Das, Roger Gramunt, Mikhail Smelyanskiy, Jesus Corbal, Dheevatsa Mudigere, Naveen K. Mellempudi, Alexander F. Heinecke
-
Publication number: 20220327656Abstract: One embodiment provides for a graphics processing unit to perform computations associated with a neural network, the graphics processing unit comprising a hardware processing unit having a dynamic precision fixed-point unit that is configurable to quantize elements of a floating-point tensor to convert the floating-point tensor into a dynamic fixed-point tensor.Type: ApplicationFiled: April 27, 2022Publication date: October 13, 2022Applicant: Intel CorporationInventors: Naveen K. MELLEMPUDI, DHEEVATSA MUDIGERE, DIPANKAR DAS, SRINIVAS SRIDHARAN
-
Publication number: 20220214877Abstract: Disclosed embodiments relate to instructions for fused multiply-add (FMA) operations with variable-precision inputs. In one example, a processor to execute an asymmetric FMA instruction includes fetch circuitry to fetch an FMA instruction having fields to specify an opcode, a destination, and first and second source vectors having first and second widths, respectively, decode circuitry to decode the fetched FMA instruction, and a single instruction multiple data (SIMD) execution circuit to process as many elements of the second source vector as fit into an SIMD lane width by multiplying each element by a corresponding element of the first source vector, and accumulating a resulting product with previous contents of the destination, wherein the SIMD lane width is one of 16 bits, 32 bits, and 64 bits, the first width is one of 4 bits and 8 bits, and the second width is one of 1 bit, 2 bits, and 4 bits.Type: ApplicationFiled: March 25, 2022Publication date: July 7, 2022Inventors: Dipankar DAS, Naveen K. MELLEMPUDI, Mrinmay DUTTA, Arun KUMAR, Dheevatsa MUDIGERE, Abhisek KUNDU
-
Patent number: 11334796Abstract: A processing cluster of a processing cluster array comprises a plurality of registers to store input values of vector input operands, the input values of at least some of the vector input operands having different bit lengths than those of other input values of other vector input operands, and a compute unit to execute a dot-product instruction with the vector input operands to perform a number of parallel multiply operations and an accumulate operation per 32-bit lane based on a bit length of the smallest-sized input value of a first vector input operand relative to the 32-bit lane.Type: GrantFiled: August 3, 2020Date of Patent: May 17, 2022Assignee: Intel CorporationInventors: Dipankar Das, Roger Gramunt, Mikhail Smelyanskiy, Jesus Corbal, Dheevatsa Mudigere, Naveen K. Mellempudi, Alexander F. Heinecke
-
Patent number: 11321086Abstract: Disclosed embodiments relate to instructions for fused multiply-add (FMA) operations with variable-precision inputs. In one example, a processor to execute an asymmetric FMA instruction includes fetch circuitry to fetch an FMA instruction having fields to specify an opcode, a destination, and first and second source vectors having first and second widths, respectively, decode circuitry to decode the fetched FMA instruction, and a single instruction multiple data (SIMD) execution circuit to process as many elements of the second source vector as fit into an SIMD lane width by multiplying each element by a corresponding element of the first source vector, and accumulating a resulting product with previous contents of the destination, wherein the SIMD lane width is one of 16 bits, 32 bits, and 64 bits, the first width is one of 4 bits and 8 bits, and the second width is one of 1 bit, 2 bits, and 4 bits.Type: GrantFiled: January 6, 2020Date of Patent: May 3, 2022Assignee: Intel CorporationInventors: Dipankar Das, Naveen K. Mellempudi, Mrinmay Dutta, Arun Kumar, Dheevatsa Mudigere, Abhisek Kundu
-
Publication number: 20210342692Abstract: Technologies for artificial neural network training include a computing node with a host fabric interface that sends a message that includes one or more artificial neural network training algorithm values to another computing node in response to receipt of a request to send the message. Prior to sending the message, the host fabric interface may receive a request to quantize the message and quantize the message based on a quantization level included in the request to generate a quantized message. The quantization message includes one or more quantized values such that each quantized value has a lower precision than a corresponding artificial neural network training algorithm value. The host fabric interface then transmits the quantized message, which includes metadata indicative of the quantization level, to another computing node in response to quantization of the message for artificial neural network training. Other embodiments are described and claimed.Type: ApplicationFiled: May 14, 2021Publication date: November 4, 2021Inventors: Naveen K. Mellempudi, Srinivas Sridharan, Dheevatsa Mudigere, Dipankar Das
-
Patent number: 11068780Abstract: Technologies for artificial neural network training include a computing node with a host fabric interface that sends a message that includes one or more artificial neural network training algorithm values to another computing node in response to receipt of a request to send the message. Prior to sending the message, the host fabric interface may receive a request to quantize the message and quantize the message based on a quantization level included in the request to generate a quantized message. The quantization message includes one or more quantized values such that each quantized value has a lower precision than a corresponding artificial neural network training algorithm value. The host fabric interface then transmits the quantized message, which includes metadata indicative of the quantization level, to another computing node in response to quantization of the message for artificial neural network training. Other embodiments are described and claimed.Type: GrantFiled: April 1, 2017Date of Patent: July 20, 2021Assignee: Intel CorporationInventors: Naveen K. Mellempudi, Srinivas Sridharan, Dheevatsa Mudigere, Dipankar Das
-
Publication number: 20210081201Abstract: An apparatus to facilitate utilizing structured sparsity in systolic arrays is disclosed. The apparatus includes a processor comprising a systolic array to receive data from a plurality of source registers, the data comprising unpacked source data, structured source data that is packed based on sparsity, and metadata corresponding to the structured source data; identify portions of the unpacked source data to multiply with the structured source data, the portions of the unpacked source data identified based on the metadata; and output, to a destination register, a result of multiplication of the portions of the unpacked source data and the structured source data.Type: ApplicationFiled: November 30, 2020Publication date: March 18, 2021Applicant: Intel CorporationInventors: Subramaniam Maiyuran, Jorge Parra, Ashutosh Garg, Chandra Gurram, Chunhui Mei, Durgesh Borkar, Shubra Marwaha, Supratim Pal, Varghese George, Wei Xiong, Yan Li, Yongsheng Liu, Dipankar Das, Sasikanth Avancha, Dharma Teja Vooturi, Naveen K. Mellempudi
-
Publication number: 20210019631Abstract: A processing cluster of a processing cluster array comprises a plurality of registers to store input values of vector input operands, the input values of at least some of the vector input operands having different bit lengths than those of other input values of other vector input operands, and a compute unit to execute a dot-product instruction with the vector input operands to perform a number of parallel multiply operations and an accumulate operation per 32-bit lane based on a bit length of the smallest-sized input value of a first vector input operand relative to the 32-bit lane.Type: ApplicationFiled: August 3, 2020Publication date: January 21, 2021Applicant: Intel CorporationInventors: Dipankar Das, Roger Gramunt, Mikhail Smelyanskiy, Jesus Corbal, Dheevatsa Mudigere, Naveen K. Mellempudi, Alexander F. Heinecke
-
Patent number: 10776699Abstract: One embodiment provides for a compute apparatus to perform machine learning operations, the compute apparatus comprising a fetch unit to fetch a single instruction having multiple input operands, wherein the multiple input operands have an unequal bit-length, a first input operand having a first bit-length and a second input operand having a second bit-length; a decode unit to decode the single instruction into a decoded instruction; an operand length unit to determine a smaller bit-length of the first bit-length and the second bit-length; and a compute unit to perform a matrix operation on the multiple input operands to generate an output value having a bit length of the smaller bit length.Type: GrantFiled: January 12, 2018Date of Patent: September 15, 2020Assignee: Intel CorporationInventors: Dipankar Das, Roger Gramunt, Mikhail Smelyanskiy, Jesus Corbal, Dheevatsa Mudigere, Naveen K. Mellempudi, Alexander F. Heinecke
-
Patent number: 10775873Abstract: In an embodiment, a processor includes: a plurality of first cores to independently execute instructions, each of the plurality of first cores including a plurality of counters to store performance information; at least one second core to perform memory operations; and a power controller to receive performance information from at least some of the plurality of counters, determine a workload type executed on the processor based at least in part on the performance information, and based on the workload type dynamically migrate one or more threads from one or more of the plurality of first cores to the at least one second core for execution during a next operation interval. Other embodiments are described and claimed.Type: GrantFiled: February 28, 2019Date of Patent: September 15, 2020Assignee: Intel CorporationInventors: Victor W. Lee, Edward T. Grochowski, Daehyun Kim, Yuxin Bai, Sheng Li, Naveen K. Mellempudi, Dhiraj D. Kalamkar
-
Publication number: 20200257527Abstract: Disclosed embodiments relate to instructions for fused multiply-add (FMA) operations with variable-precision inputs. In one example, a processor to execute an asymmetric FMA instruction includes fetch circuitry to fetch an FMA instruction having fields to specify an opcode, a destination, and first and second source vectors having first and second widths, respectively, decode circuitry to decode the fetched FMA instruction, and a single instruction multiple data (SIMD) execution circuit to process as many elements of the second source vector as fit into an SIMD lane width by multiplying each element by a corresponding element of the first source vector, and accumulating a resulting product with previous contents of the destination, wherein the SIMD lane width is one of 16 bits, 32 bits, and 64 bits, the first width is one of 4 bits and 8 bits, and the second width is one of 1 bit, 2 bits, and 4 bits.Type: ApplicationFiled: January 6, 2020Publication date: August 13, 2020Applicant: Intel CorporationInventors: Dipankar DAS, Naveen K. MELLEMPUDI, Mrinmay DUTTA, Arun KUMAR, Dheevatsa MUDIGERE, Abhisek KUNDU
-
Patent number: 10528346Abstract: Disclosed embodiments relate to instructions for fused multiply-add (FMA) operations with variable-precision inputs. In one example, a processor to execute an asymmetric FMA instruction includes fetch circuitry to fetch an FMA instruction having fields to specify an opcode, a destination, and first and second source vectors having first and second widths, respectively, decode circuitry to decode the fetched FMA instruction, and a single instruction multiple data (SIMD) execution circuit to process as many elements of the second source vector as fit into an SIMD lane width by multiplying each element by a corresponding element of the first source vector, and accumulating a resulting product with previous contents of the destination, wherein the SIMD lane width is one of 16 bits, 32 bits, and 64 bits, the first width is one of 4 bits and 8 bits, and the second width is one of 1 bit, 2 bits, and 4 bits.Type: GrantFiled: March 29, 2018Date of Patent: January 7, 2020Assignee: Intel CorporationInventors: Dipankar Das, Naveen K. Mellempudi, Mrinmay Dutta, Arun Kumar, Dheevatsa Mudigere, Abhisek Kundu
-
Publication number: 20190265777Abstract: In an embodiment, a processor includes: a plurality of first cores to independently execute instructions, each of the plurality of first cores including a plurality of counters to store performance information; at least one second core to perform memory operations; and a power controller to receive performance information from at least some of the plurality of counters, determine a workload type executed on the processor based at least in part on the performance information, and based on the workload type dynamically migrate one or more threads from one or more of the plurality of first cores to the at least one second core for execution during a next operation interval. Other embodiments are described and claimed.Type: ApplicationFiled: February 28, 2019Publication date: August 29, 2019Inventors: Victor W. Lee, Edward T. Grochowski, Daehyun Kim, Yuxin Bai, Sheng Li, Naveen K. Mellempudi, Dhiraj D. Kalamkar
-
Patent number: 10234930Abstract: In an embodiment, a processor includes: a plurality of first cores to independently execute instructions, each of the plurality of first cores including a plurality of counters to store performance information; at least one second core to perform memory operations; and a power controller to receive performance information from at least some of the plurality of counters, determine a workload type executed on the processor based at least in part on the performance information, and based on the workload type dynamically migrate one or more threads from one or more of the plurality of first cores to the at least one second core for execution during a next operation interval. Other embodiments are described and claimed.Type: GrantFiled: February 13, 2015Date of Patent: March 19, 2019Assignee: Intel CorporationInventors: Victor W. Lee, Edward T. Grochowski, Daehyun Kim, Yuxin Bai, Sheng Li, Naveen K. Mellempudi, Dhiraj D. Kalamkar
-
Publication number: 20180322390Abstract: One embodiment provides for a compute apparatus to perform machine learning operations, the compute apparatus comprising a fetch unit to fetch a single instruction having multiple input operands, wherein the multiple input operands have an unequal bit-length, a first input operand having a first bit-length and a second input operand having a second bit-length; a decode unit to decode the single instruction into a decoded instruction; an operand length unit to determine a smaller bit-length of the first bit-length and the second bit-length; and a compute unit to perform a matrix operation on the multiple input operands to generate an output value having a bit length of the smaller bit length.Type: ApplicationFiled: January 12, 2018Publication date: November 8, 2018Applicant: Intel CorporationInventors: Dipankar Das, Roger Gramunt, Mikhail Smelyanskiy, Jesus Corbal, Dheevatsa Mudigere, Naveen K. Mellempudi, Alexander F. Heinecke