[go: up one dir, main page]

PL3812883T3 - Procesor komputerowy do obliczeń o wyższej precyzji z zastosowaniem dekompozycji operacji o mieszanej precyzji - Google Patents

Procesor komputerowy do obliczeń o wyższej precyzji z zastosowaniem dekompozycji operacji o mieszanej precyzji

Info

Publication number
PL3812883T3
PL3812883T3 PL20215256T PL20215256T PL3812883T3 PL 3812883 T3 PL3812883 T3 PL 3812883T3 PL 20215256 T PL20215256 T PL 20215256T PL 20215256 T PL20215256 T PL 20215256T PL 3812883 T3 PL3812883 T3 PL 3812883T3
Authority
PL
Poland
Prior art keywords
precision
operations
mixed
computer processor
decomposition
Prior art date
Application number
PL20215256T
Other languages
English (en)
Inventor
Gregory Henry
Alexander Heinecke
Original Assignee
Intel Corporation
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Intel Corporation filed Critical Intel Corporation
Publication of PL3812883T3 publication Critical patent/PL3812883T3/pl

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F7/00Methods or arrangements for processing data by operating upon the order or content of the data handled
    • G06F7/38Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation
    • G06F7/48Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation using non-contact-making devices, e.g. tube, solid state device; using unspecified devices
    • G06F7/483Computations with numbers represented by a non-linear combination of denominational numbers, e.g. rational numbers, logarithmic number system or floating-point numbers
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/16Constructional details or arrangements
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/16Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F7/00Methods or arrangements for processing data by operating upon the order or content of the data handled
    • G06F7/38Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation
    • G06F7/48Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation using non-contact-making devices, e.g. tube, solid state device; using unspecified devices
    • G06F7/483Computations with numbers represented by a non-linear combination of denominational numbers, e.g. rational numbers, logarithmic number system or floating-point numbers
    • G06F7/485Adding; Subtracting
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F7/00Methods or arrangements for processing data by operating upon the order or content of the data handled
    • G06F7/38Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation
    • G06F7/48Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation using non-contact-making devices, e.g. tube, solid state device; using unspecified devices
    • G06F7/483Computations with numbers represented by a non-linear combination of denominational numbers, e.g. rational numbers, logarithmic number system or floating-point numbers
    • G06F7/487Multiplying; Dividing
    • G06F7/4876Multiplying
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F7/00Methods or arrangements for processing data by operating upon the order or content of the data handled
    • G06F7/38Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation
    • G06F7/48Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation using non-contact-making devices, e.g. tube, solid state device; using unspecified devices
    • G06F7/52Multiplying; Dividing
    • G06F7/523Multiplying only
    • G06F7/53Multiplying only in parallel-parallel fashion, i.e. both operands being entered in parallel
    • G06F7/5324Multiplying only in parallel-parallel fashion, i.e. both operands being entered in parallel partitioned, i.e. using repetitively a smaller parallel parallel multiplier or using an array of such smaller multipliers
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F7/00Methods or arrangements for processing data by operating upon the order or content of the data handled
    • G06F7/38Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation
    • G06F7/48Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation using non-contact-making devices, e.g. tube, solid state device; using unspecified devices
    • G06F7/544Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation using non-contact-making devices, e.g. tube, solid state device; using unspecified devices for evaluating functions by calculation
    • G06F7/5443Sum of products
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/30003Arrangements for executing specific machine instructions
    • G06F9/30007Arrangements for executing specific machine instructions to perform operations on data operands
    • G06F9/3001Arithmetic instructions
    • G06F9/30014Arithmetic instructions with variable precision
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/30003Arrangements for executing specific machine instructions
    • G06F9/30007Arrangements for executing specific machine instructions to perform operations on data operands
    • G06F9/30025Format conversion instructions, e.g. Floating-Point to Integer, decimal conversion
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/30145Instruction analysis, e.g. decoding, instruction word fields

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Nonlinear Science (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Human Computer Interaction (AREA)
  • Databases & Information Systems (AREA)
  • Algebra (AREA)
  • Complex Calculations (AREA)
  • Advance Control (AREA)
PL20215256T 2018-09-27 2019-06-25 Procesor komputerowy do obliczeń o wyższej precyzji z zastosowaniem dekompozycji operacji o mieszanej precyzji PL3812883T3 (pl)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US16/144,964 US10853067B2 (en) 2018-09-27 2018-09-27 Computer processor for higher precision computations using a mixed-precision decomposition of operations
EP20215256.7A EP3812883B1 (en) 2018-09-27 2019-06-25 A computer processor for higher precision computations using a mixed-precision decomposition of operations
EP19182449.9A EP3629147B1 (en) 2018-09-27 2019-06-25 Computer processor for higher precision computations using a mixed-precision decomposition of operations

Publications (1)

Publication Number Publication Date
PL3812883T3 true PL3812883T3 (pl) 2022-06-06

Family

ID=65229962

Family Applications (3)

Application Number Title Priority Date Filing Date
PL19182449.9T PL3629147T3 (pl) 2018-09-27 2019-06-25 Procesor komputerowy do obliczeń o większej precyzji wykorzystujący dekompozycję operacji do mieszanej precyzji
PL24152035.2T PL4328744T3 (pl) 2018-09-27 2019-06-25 Procesor komputerowy do obliczeń o większej precyzji wykorzystujący dekompozycję operacji do mieszanej precyzji
PL20215256T PL3812883T3 (pl) 2018-09-27 2019-06-25 Procesor komputerowy do obliczeń o wyższej precyzji z zastosowaniem dekompozycji operacji o mieszanej precyzji

Family Applications Before (2)

Application Number Title Priority Date Filing Date
PL19182449.9T PL3629147T3 (pl) 2018-09-27 2019-06-25 Procesor komputerowy do obliczeń o większej precyzji wykorzystujący dekompozycję operacji do mieszanej precyzji
PL24152035.2T PL4328744T3 (pl) 2018-09-27 2019-06-25 Procesor komputerowy do obliczeń o większej precyzji wykorzystujący dekompozycję operacji do mieszanej precyzji

Country Status (7)

Country Link
US (5) US10853067B2 (pl)
EP (4) EP4328744B1 (pl)
CN (3) CN117931121A (pl)
DK (1) DK4328744T3 (pl)
ES (3) ES2914605T3 (pl)
FI (1) FI4328744T3 (pl)
PL (3) PL3629147T3 (pl)

Families Citing this family (81)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10409614B2 (en) 2017-04-24 2019-09-10 Intel Corporation Instructions having support for floating point and integer data types in the same register
US10474458B2 (en) 2017-04-28 2019-11-12 Intel Corporation Instructions and logic to perform floating-point and integer operations for machine learning
US11789729B2 (en) 2017-12-29 2023-10-17 Intel Corporation Systems and methods for computing dot products of nibbles in two tile operands
US11816483B2 (en) * 2017-12-29 2023-11-14 Intel Corporation Systems, methods, and apparatuses for matrix operations
US11809869B2 (en) * 2017-12-29 2023-11-07 Intel Corporation Systems and methods to store a tile register pair to memory
US11093247B2 (en) 2017-12-29 2021-08-17 Intel Corporation Systems and methods to load a tile register pair
US11893470B2 (en) * 2018-12-06 2024-02-06 MIPS Tech, LLC Neural network processing using specialized data representation
US20200202195A1 (en) * 2018-12-06 2020-06-25 MIPS Tech, LLC Neural network processing using mixed-precision data representation
EP3974968B1 (en) 2019-03-15 2024-09-04 Intel Corporation Graphics processors and graphics processing units having dot product accumulate instruction for hybrid floating point format
JP7408671B2 (ja) 2019-03-15 2024-01-05 インテル コーポレイション シストリックアレイに対するブロックスパース演算のためのアーキテクチャ
US11934342B2 (en) 2019-03-15 2024-03-19 Intel Corporation Assistance for hardware prefetch in cache access
US12182035B2 (en) 2019-03-15 2024-12-31 Intel Corporation Systems and methods for cache optimization
US11194585B2 (en) 2019-03-25 2021-12-07 Flex Logix Technologies, Inc. Multiplier-accumulator circuitry having processing pipelines and methods of operating same
US20190220278A1 (en) * 2019-03-27 2019-07-18 Menachem Adelman Apparatus and method for down-converting and interleaving multiple floating point values
US11314504B2 (en) * 2019-04-09 2022-04-26 Flex Logix Technologies, Inc. Multiplier-accumulator processing pipelines and processing component, and methods of operating same
US10990389B2 (en) * 2019-04-29 2021-04-27 Micron Technology, Inc. Bit string operations using a computing tile
US11016765B2 (en) * 2019-04-29 2021-05-25 Micron Technology, Inc. Bit string operations using a computing tile
CN112394990A (zh) * 2019-08-13 2021-02-23 上海寒武纪信息科技有限公司 浮点转半精度浮点指令处理装置、方法及相关产品
US11169776B2 (en) 2019-06-28 2021-11-09 Intel Corporation Decomposed floating point multiplication
CN112394997A (zh) * 2019-08-13 2021-02-23 上海寒武纪信息科技有限公司 八位整形转半精度浮点指令处理装置、方法及相关产品
US11327923B2 (en) 2019-09-04 2022-05-10 SambaNova Systems, Inc. Sigmoid function in hardware and a reconfigurable data processor including same
US11886377B2 (en) 2019-09-10 2024-01-30 Cornami, Inc. Reconfigurable arithmetic engine circuit
US11288076B2 (en) 2019-09-13 2022-03-29 Flex Logix Technologies, Inc. IC including logic tile, having reconfigurable MAC pipeline, and reconfigurable memory
US11327713B2 (en) 2019-10-01 2022-05-10 SambaNova Systems, Inc. Computation units for functions based on lookup tables
US11455368B2 (en) 2019-10-02 2022-09-27 Flex Logix Technologies, Inc. MAC processing pipeline having conversion circuitry, and methods of operating same
US11188303B2 (en) 2019-10-02 2021-11-30 Facebook, Inc. Floating point multiply hardware using decomposed component numbers
WO2021073511A1 (zh) * 2019-10-14 2021-04-22 安徽寒武纪信息科技有限公司 用于浮点运算的乘法器、方法、集成电路芯片和计算装置
US12015428B2 (en) 2019-11-05 2024-06-18 Flex Logix Technologies, Inc. MAC processing pipeline using filter weights having enhanced dynamic range, and methods of operating same
US11836490B2 (en) * 2019-11-14 2023-12-05 Nvidia Corporation Kernel coefficient quantization
US11861761B2 (en) 2019-11-15 2024-01-02 Intel Corporation Graphics processing unit processing and caching improvements
US11663746B2 (en) 2019-11-15 2023-05-30 Intel Corporation Systolic arithmetic on sparse data
US11327717B2 (en) 2019-11-19 2022-05-10 SambaNova Systems, Inc. Look-up table with input offsetting
CN111008230B (zh) 2019-11-22 2023-08-04 远景智能国际私人投资有限公司 数据存储方法、装置、计算机设备及存储介质
US11328038B2 (en) 2019-11-25 2022-05-10 SambaNova Systems, Inc. Computational units for batch normalization
CN116594589B (zh) * 2019-12-31 2024-03-26 华为技术有限公司 浮点数乘法计算的方法、装置和算术逻辑单元
US11663000B2 (en) * 2020-01-07 2023-05-30 SK Hynix Inc. Multiplication and accumulation(MAC) operator and processing-in-memory (PIM) device including the MAC operator
US11314483B2 (en) 2020-01-08 2022-04-26 International Business Machines Corporation Bit-serial computation with dynamic frequency modulation for error resiliency in neural network
US11836629B2 (en) 2020-01-15 2023-12-05 SambaNova Systems, Inc. Computationally efficient softmax loss gradient backpropagation
US11960856B1 (en) 2020-01-15 2024-04-16 Flex Logix Technologies, Inc. Multiplier-accumulator processing pipeline using filter weights having gaussian floating point data format
CN115934030B (zh) * 2020-01-20 2024-01-16 华为技术有限公司 算数逻辑单元、浮点数乘法计算的方法及设备
US12197887B2 (en) 2020-03-13 2025-01-14 Altera Corporation Floating-point decomposition circuitry with dynamic precision
CN113408717B (zh) * 2020-03-17 2025-09-09 安徽寒武纪信息科技有限公司 计算装置、方法、板卡和计算机可读存储介质
CN113408716B (zh) * 2020-03-17 2025-06-24 安徽寒武纪信息科技有限公司 计算装置、方法、板卡和计算机可读存储介质
US11442881B2 (en) 2020-04-18 2022-09-13 Flex Logix Technologies, Inc. MAC processing pipelines, circuitry to control and configure same, and methods of operating same
US11775298B2 (en) * 2020-04-24 2023-10-03 Intel Corporation Frequency scaling for per-core accelerator assignments
US11551148B2 (en) * 2020-04-29 2023-01-10 Marvell Asia Pte Ltd System and method for INT9 quantization
US11714998B2 (en) * 2020-05-05 2023-08-01 Intel Corporation Accelerating neural networks with low precision-based multiplication and exploiting sparsity in higher order bits
US12282748B1 (en) 2020-05-26 2025-04-22 Analog Devices, Inc. Coarse floating point accumulator circuit, and MAC processing pipelines including same
CN113867792A (zh) * 2020-06-30 2021-12-31 上海寒武纪信息科技有限公司 计算装置、集成电路芯片、板卡、电子设备和计算方法
US12282749B2 (en) 2020-08-20 2025-04-22 Analog Devices, Inc. Configurable MAC pipelines for finite-impulse-response filtering, and methods of operating same
CN114186186B (zh) * 2020-09-15 2023-08-04 华为技术有限公司 矩阵计算方法及相关设备
CN112148249B (zh) * 2020-09-18 2023-08-18 北京百度网讯科技有限公司 点积运算实现方法、装置、电子设备及存储介质
CN114327360B (zh) * 2020-09-29 2023-07-18 华为技术有限公司 运算装置、浮点数计算的方法、装置、芯片和计算设备
CN112416295B (zh) * 2020-12-09 2024-02-02 厦门壹普智慧科技有限公司 用于浮点数据、张量数据运算的运算器
US12020028B2 (en) * 2020-12-26 2024-06-25 Intel Corporation Apparatuses, methods, and systems for 8-bit floating-point matrix dot product instructions
WO2022150058A1 (en) * 2021-01-07 2022-07-14 Groq, Inc. Numerical precision in digital multiplier circuitry
US12455723B2 (en) 2021-02-02 2025-10-28 Analog Devices, Inc. MAC processing pipeline having activation circuitry, and methods of operating same
CN112860218B (zh) * 2021-02-07 2023-07-11 厦门壹普智慧科技有限公司 用于fp16浮点数据和int8整型数据运算的混合精度运算器
US12461713B2 (en) 2021-03-03 2025-11-04 Analog Devices, Inc. MAC processing pipelines, circuitry to configure same, and methods of operating same
CN113076083B (zh) * 2021-06-04 2021-08-31 南京后摩智能科技有限公司 数据乘加运算电路
US20210326135A1 (en) * 2021-06-25 2021-10-21 Dheeraj Subbareddy Programmable Fabric-Based Instruction Set Architecture for a Processor
US12353878B2 (en) * 2021-06-26 2025-07-08 Intel Corporation Apparatuses, methods, and systems for instructions for matrix multiplication instructions
US20230050279A1 (en) * 2021-08-12 2023-02-16 Taiwan Semiconductor Manufacturing Company, Ltd. Integrated circuit and method of operating same
KR102653107B1 (ko) * 2021-08-23 2024-04-01 삼성전자주식회사 연산 방법 및 장치
US20230069000A1 (en) * 2021-08-31 2023-03-02 Intel Corporation Bfloat16 arithmetic instructions
US20230133360A1 (en) * 2021-10-28 2023-05-04 Taiwan Semiconductor Manufacturing Company, Ltd. Compute-In-Memory-Based Floating-Point Processor
CN114169498B (zh) * 2021-11-24 2025-07-15 北京大觥科技有限公司 基于神经网络的特征数据处理方法及装置
CN114141086A (zh) * 2021-12-13 2022-03-04 湖南文理学院 一种内置模拟物理力学实验场景的电子装置
US20230205527A1 (en) * 2021-12-23 2023-06-29 Intel Corporation Conversion instructions
GB202202905D0 (en) 2022-03-02 2022-04-13 Graphcore Ltd Processing device for intermediate value scaling
US20230289138A1 (en) * 2022-03-08 2023-09-14 International Business Machines Corporation Hardware device to execute instruction to convert input value from one data format to another data format
US20230289139A1 (en) * 2022-03-08 2023-09-14 International Business Machines Corporation Hardware device to execute instruction to convert input value from one data format to another data format
CN114847914A (zh) * 2022-05-18 2022-08-05 上海交通大学 一种基于混合精度神经网络的电阻抗成像方法及系统
US12399713B2 (en) * 2022-09-29 2025-08-26 Tenstorrent Ai Ulc Multiplication hardware block with adaptive fidelity control system
CN115718586B (zh) * 2022-11-29 2024-01-19 格兰菲智能科技有限公司 像素颜色混合操作方法、图形绘制方法、装置和设备
EP4481554A1 (en) * 2023-06-20 2024-12-25 Huawei Technologies Co., Ltd. Methods for decomposition of high-precision matrix multiplications into multiple matrix multiplications of different data types
US20250004661A1 (en) * 2023-06-27 2025-01-02 Western Digital Technologies, Inc. Computational storage device with computation precision-defined fixed point data grouping and storage management
US20250130794A1 (en) * 2023-10-20 2025-04-24 Advanced Micro Devices, Inc. Multi-format operand circuit
US12405786B1 (en) 2024-02-27 2025-09-02 Apple Inc. Hardware support for conversion between integer and floating-point data
US20250307133A1 (en) * 2024-03-28 2025-10-02 Advanced Micro Devices, Inc. Offloading Quantization of Directional Blocked Data Formats to Near-Memory Units
CN120631450B (zh) * 2025-08-15 2025-10-24 上海壁仞科技股份有限公司 数据处理方法、装置、芯片和计算机设备

Family Cites Families (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3389379A (en) * 1965-10-05 1968-06-18 Sperry Rand Corp Floating point system: single and double precision conversions
JP3178746B2 (ja) 1991-09-25 2001-06-25 松下電器産業株式会社 浮動小数点数のためのフォーマット変換装置
US6108772A (en) * 1996-06-28 2000-08-22 Intel Corporation Method and apparatus for supporting multiple floating point processing models
US6029243A (en) * 1997-09-19 2000-02-22 Vlsi Technology, Inc. Floating-point processor with operand-format precision greater than execution precision
US6230257B1 (en) * 1998-03-31 2001-05-08 Intel Corporation Method and apparatus for staggering execution of a single packed data instruction using the same circuit
US5995122A (en) * 1998-04-30 1999-11-30 Intel Corporation Method and apparatus for parallel conversion of color values from a single precision floating point format to an integer format
US6714197B1 (en) * 1999-07-30 2004-03-30 Mips Technologies, Inc. Processor having an arithmetic extension of an instruction set architecture
US8280941B2 (en) * 2007-12-19 2012-10-02 HGST Netherlands B.V. Method and system for performing calculations using fixed point microprocessor hardware
US20100180100A1 (en) 2009-01-13 2010-07-15 Mavrix Technology, Inc. Matrix microprocessor and method of operation
US8655937B1 (en) 2009-04-29 2014-02-18 Nvidia Corporation High precision integer division using low precision hardware operations and rounding techniques
US8745111B2 (en) * 2010-11-16 2014-06-03 Apple Inc. Methods and apparatuses for converting floating point representations
US8838664B2 (en) 2011-06-29 2014-09-16 Advanced Micro Devices, Inc. Methods and apparatus for compressing partial products during a fused multiply-and-accumulate (FMAC) operation on operands having a packed-single-precision format
US9128697B1 (en) 2011-07-18 2015-09-08 Apple Inc. Computer numerical storage format with precision type indicator
US9104474B2 (en) * 2012-12-28 2015-08-11 Intel Corporation Variable precision floating point multiply-add circuit
US10445092B2 (en) * 2014-12-27 2019-10-15 Intel Corporation Method and apparatus for performing a vector permute with an index and an immediate
US9870341B2 (en) * 2016-03-18 2018-01-16 Qualcomm Incorporated Memory reduction method for fixed point matrix multiply
US10282169B2 (en) 2016-04-06 2019-05-07 Apple Inc. Floating-point multiply-add with down-conversion
EP4053695B1 (en) 2017-03-20 2025-09-24 INTEL Corporation Systems, methods, and apparatuses for dot production operations
US10474458B2 (en) 2017-04-28 2019-11-12 Intel Corporation Instructions and logic to perform floating-point and integer operations for machine learning
GB2563878B (en) 2017-06-28 2019-11-20 Advanced Risc Mach Ltd Register-based matrix multiplication
GB2568083B (en) * 2017-11-03 2021-06-02 Imagination Tech Ltd Histogram-based per-layer data format selection for hardware implementation of deep neutral network
US11216250B2 (en) * 2017-12-06 2022-01-04 Advanced Micro Devices, Inc. Dynamic, variable bit-width numerical precision on field-programmable gate arrays for machine learning tasks
US10678508B2 (en) * 2018-03-23 2020-06-09 Amazon Technologies, Inc. Accelerated quantized multiply-and-add operations
US20190340499A1 (en) * 2018-05-04 2019-11-07 Microsoft Technology Licensing, Llc Quantization for dnn accelerators
US10963246B2 (en) 2018-11-09 2021-03-30 Intel Corporation Systems and methods for performing 16-bit floating-point matrix dot product instructions

Also Published As

Publication number Publication date
EP3629147A1 (en) 2020-04-01
US20240211252A1 (en) 2024-06-27
CN112506467B (zh) 2024-08-30
US11868770B2 (en) 2024-01-09
US20230214215A1 (en) 2023-07-06
US11544057B2 (en) 2023-01-03
US11126428B2 (en) 2021-09-21
ES2927546T3 (es) 2022-11-08
EP3812883B1 (en) 2022-03-16
US12346692B2 (en) 2025-07-01
EP3812883A1 (en) 2021-04-28
FI4328744T3 (fi) 2025-09-03
CN112506467A (zh) 2021-03-16
US10853067B2 (en) 2020-12-01
EP4328744A2 (en) 2024-02-28
EP4044020A1 (en) 2022-08-17
CN110955404A (zh) 2020-04-03
ES2914605T3 (es) 2022-06-14
CN117931121A (zh) 2024-04-26
DK4328744T3 (da) 2025-09-08
PL4328744T3 (pl) 2025-10-06
US20190042244A1 (en) 2019-02-07
EP4044020B1 (en) 2025-07-30
US20210103444A1 (en) 2021-04-08
US20210089303A1 (en) 2021-03-25
ES3040290T3 (en) 2025-10-29
EP4328744A3 (en) 2024-04-17
EP3629147B1 (en) 2022-07-06
PL3629147T3 (pl) 2022-09-26
EP4328744B1 (en) 2025-06-18

Similar Documents

Publication Publication Date Title
PL3812883T3 (pl) Procesor komputerowy do obliczeń o wyższej precyzji z zastosowaniem dekompozycji operacji o mieszanej precyzji
CA203150S (en) Computer
EP3870075A4 (en) SHIELD FOR WRIST INSTRUMENTS
AU201716311S (en) Adapter for Computer Mouse
GB2580406B (en) A client-server computer system
SG11202111817SA (en) Cooling a computer processing unit
CA198228S (en) Portable computer
IL266360B (en) An accessory for providing hands-free computer input
CA186932S (en) Portable computer
CA186928S (en) Portable computer
EP3776213A4 (en) PROCEDURE FOR TROUBLESHOOTING A PROCESSOR
GB201818997D0 (en) Providing external access to a prcoessing platform
GB2597884B (en) Executing multiple data requests of multiple-core processors
CA214706S (en) Computer
EP3957081A4 (en) COMPUTER PERIPHERALS
CA206284S (en) Computer
JP1725953S (ja) コンピュータ用カバー
GB201615796D0 (en) User interface for searching a large data set
GB201815424D0 (en) Chemical computer
GB201910847D0 (en) A System for configuring an environment to provide mobile computing
CA225768S (en) Computer
CA205831S (en) Case for portable computer
GB201904517D0 (en) Heptane computer processor architecture
IL254295A0 (en) Optical band for a multi-core processor
GB202016127D0 (en) Zero instruction set computer