-
公开(公告)号:US20230273832A1
公开(公告)日:2023-08-31
申请号:US18133616
申请日:2023-04-12
Applicant: Intel Corporation
Inventor: Somnath Paul , Muhammad M. Khellah , Linda Zeng , Mohamed Elmalaki
IPC: G06F9/50 , G06F1/3228 , G06F1/3296
CPC classification number: G06F9/505 , G06F1/3228 , G06F1/3296
Abstract: A system for autonomous and proactive power management for energy efficient execution of machine learning workloads may include an apparatus such as system-on-chip (SoC) comprising an accelerator configurable to load and execute a neural network and circuitry to receive a profile of the neural network. The profile may be received from a compiler and include information regarding a plurality of layers of the neural network. Responsive to the profile and the information regarding the plurality of layers, circuitry may adjust, using a local power management unit (PMU) included the apparatus, a power level to the accelerator while the accelerator executes the neural network. The power level adjustment may be based on whether the particular layer is a compute-intensive layer or a memory-intensive layer.
-
公开(公告)号:US11176994B2
公开(公告)日:2021-11-16
申请号:US17001432
申请日:2020-08-24
Applicant: Intel Corporation
Inventor: Muhammad M. Khellah , Somnath Paul , Charles Augustine , Turbo Majumder , Suyoung Bang
IPC: G11C11/00 , G11C13/00 , G11C11/419 , G11C11/412 , G11C7/12 , G11C7/10 , G11C11/418 , G11C7/22
Abstract: Embodiments include apparatuses, methods, and systems to implement a multi-read and/or multi-write process with a set of memory cells. The set of memory cells may be multiplexed with a same sense amplifier. As part of a multi-read process, a memory controller coupled to a memory circuit may precharge the bit lines associated with the set of memory cells, provide a single assertion of a word line signal on the word line, and then sequentially read data from the set of memory cells (using the sense amplifier) based on the precharge and the single assertion of the word line signal. Additionally, or alternatively, a multi-write process may be performed to sequentially write data to the set of memory cells based on one precharge of the associated bit lines. Other embodiments may be described and claimed.
-
公开(公告)号:US10748060B2
公开(公告)日:2020-08-18
申请号:US15294666
申请日:2016-10-14
Applicant: Intel Corporation
Inventor: Somnath Paul , Charles Augustine , Muhammad M. Khellah
Abstract: A processor or integrated circuit includes a memory to store weight values for a plurality neuromorphic states and a circuitry coupled to the memory. The circuitry is to detect an incoming data signal for a pre-synaptic neuromorphic state and initiate a time window for the pre-synaptic neuromorphic state in response to detecting the incoming data signal. The circuitry is further to, responsive to detecting an end of the time window: retrieve, from the memory, a weight value for a post-synaptic neuromorphic state for which an outgoing data signal is generated during the time window, the post-synaptic neuromorphic state being a fan-out connection of the pre-synaptic neuromorphic state; perform a causal update to the weight value, according to a learning function, to generate an updated weight value; and store the updated weight value back to the memory.
-
公开(公告)号:US20180322384A1
公开(公告)日:2018-11-08
申请号:US15584510
申请日:2017-05-02
Applicant: Intel Corporation
Inventor: Charles Augustine , Somnath Paul , Sadique Ul Ameen Sheik , Muhammad M. Khellah
Abstract: A spike sent from a first artificial neuron in a spiking neural network (SNN) to a second artificial neuron in the SNN is identified, with the spike sent over a particular artificial synapse in the SNN. The membrane potential of the second artificial neuron at a particular time step, corresponding to sending of the spike, is compared to a threshold potential, where the threshold potential is set lower than a firing potential of the second artificial neuron. A change to the synaptic weight of the particular artificial synapse is determined based on the spike, where the synaptic weight is to be decreased if the membrane potential of the second artificial neuron is lower than the threshold potential at the particular time step and the synaptic weight is to be increased if the membrane potential of the second artificial neuron is higher than the threshold potential at the particular time step.
-
5.
公开(公告)号:US09734880B1
公开(公告)日:2017-08-15
申请号:US15088419
申请日:2016-04-01
Applicant: Intel Corporation
Inventor: Charles Augustine , Somnath Paul , Sadique Ul Ameen Sheik , Muhammad M. Khellah
CPC classification number: G11C11/161 , G06N3/049 , G06N3/0635 , G06N3/088 , G06N5/025 , G11C11/1653 , G11C11/1657 , G11C11/1659 , G11C11/1675 , G11C11/54 , G11C13/0002
Abstract: Embodiments include apparatuses, systems, and methods including a memory apparatus including a plurality of bit cells, wherein each of the plurality of bit cells correspond to a respective weight value and include a switch device that has a magnetic tunnel junction (MTJ) or other suitable resistive memory element to produce stochastic switching. In embodiments, the switch device may produce a switching output according to a stochastic switching probability of the switch device. In embodiments, a bit line or a source line passes a current across the MTJ for a switching time associated with the stochastic switching probability to produce the switching output which enables a determination of whether the respective weight value is to be updated. Other embodiments may also be described and claimed.
-
公开(公告)号:US08990662B2
公开(公告)日:2015-03-24
申请号:US13631937
申请日:2012-09-29
Applicant: Intel Corporation
Inventor: Somnath Paul , Sriram R. Vangal , Michael D. Abbott , Eugene M. Kishinevsky
CPC classification number: G06F11/1443 , H04L1/20 , H04L1/242
Abstract: Techniques for resilient communication. A data path stores data to be transmitted over a link to a receiving node. An output stage is coupled between the data path and the link. The output stage includes double sampling mechanisms to preserve a copy of data transmitted over the link to the receiving node. Error detection circuitry is coupled with the output stage to detect transient timing errors in the data path or output stage. The error detection circuitry causes the output stage to send the copy of the data transmitted over the link in response to detecting an error.
Abstract translation: 弹性沟通技巧。 数据路径存储要通过链接发送到接收节点的数据。 输出级耦合在数据路径和链路之间。 输出级包括双重采样机制,以保留通过链路传送到接收节点的数据副本。 错误检测电路与输出级耦合以检测数据通路或输出级中的瞬态定时误差。 响应于检测到错误,错误检测电路使得输出级发送通过链路发送的数据的副本。
-
公开(公告)号:US12197601B2
公开(公告)日:2025-01-14
申请号:US17560193
申请日:2021-12-22
Applicant: Intel Corporation
Inventor: Ren Wang , Sameh Gobriel , Somnath Paul , Yipeng Wang , Priya Autee , Abhirupa Layek , Shaman Narayana , Edwin Verplanke , Mrittika Ganguli , Jr-Shian Tsai , Anton Sorokin , Suvadeep Banerjee , Abhijit Davare , Desmond Kirkpatrick , Rajesh M. Sankaran , Jaykant B. Timbadiya , Sriram Kabisthalam Muthukumar , Narayan Ranganathan , Nalini Murari , Brinda Ganesh , Nilesh Jain
Abstract: Examples described herein relate to offload circuitry comprising one or more compute engines that are configurable to perform a workload offloaded from a process executed by a processor based on a descriptor particular to the workload. In some examples, the offload circuitry is configurable to perform the workload, among multiple different workloads. In some examples, the multiple different workloads include one or more of: data transformation (DT) for data format conversion, Locality Sensitive Hashing (LSH) for neural network (NN), similarity search, sparse general matrix-matrix multiplication (SpGEMM) acceleration of hash based sparse matrix multiplication, data encode, data decode, or embedding lookup.
-
公开(公告)号:US11908542B2
公开(公告)日:2024-02-20
申请号:US16725747
申请日:2019-12-23
Applicant: Intel Corporation
Inventor: Charles Augustine , Somnath Paul , Turbo Majumder , Iqbal Rajwani , Andrew Lines , Altug Koker , Lakshminarayanan Striramassarma , Muhammad Khellah
CPC classification number: G11C7/1048 , G11C7/1006 , G11C7/12 , G11C7/22
Abstract: Prior knowledge of access pattern is leveraged to improve energy dissipation for general matrix operations. This improves memory access energy for a multitude of applications such as image processing, deep neural networks, and scientific computing workloads, for example. In some embodiments, prior knowledge of access pattern allows for burst read and/or write operations. As such, burst mode solution can provide energy savings in both READ (RD) and WRITE (WR) operations. For machine learning or inference, the weight values are known ahead in time (e.g., inference operation), and so the unused bytes in the cache line are exploited to store a sparsity map that is used for disabling read from either upper or lower half of the cache line, thus saving dynamic capacitance.
-
公开(公告)号:US20210043251A1
公开(公告)日:2021-02-11
申请号:US17001432
申请日:2020-08-24
Applicant: Intel Corporation
Inventor: Muhammad M. Khellah , Somnath Paul , Charles Augustine , Turbo Majumder , Suyoung Bang
IPC: G11C11/419 , G11C11/412 , G11C7/12 , G11C7/10 , G11C11/418
Abstract: Embodiments include apparatuses, methods, and systems to implement a multi-read and/or multi-write process with a set of memory cells. The set of memory cells may be multiplexed with a same sense amplifier. As part of a multi-read process, a memory controller coupled to a memory circuit may precharge the bit lines associated with the set of memory cells, provide a single assertion of a word line signal on the word line, and then sequentially read data from the set of memory cells (using the sense amplifier) based on the precharge and the single assertion of the word line signal. Additionally, or alternatively, a multi-write process may be performed to sequentially write data to the set of memory cells based on one precharge of the associated bit lines. Other embodiments may be described and claimed.
-
公开(公告)号:US10755771B2
公开(公告)日:2020-08-25
申请号:US16226385
申请日:2018-12-19
Applicant: Intel Corporation
Inventor: Muhammad M. Khellah , Somnath Paul , Charles Augustine , Turbo Majumder , Suyoung Bang
IPC: G11C11/00 , G11C13/00 , G11C11/419 , G11C11/412 , G11C7/12 , G11C7/10 , G11C11/418 , G11C7/22
Abstract: Embodiments include apparatuses, methods, and systems to implement a multi-read and/or multi-write process with a set of memory cells. The set of memory cells may be multiplexed with a same sense amplifier. As part of a multi-read process, a memory controller coupled to a memory circuit may precharge the bit lines associated with the set of memory cells, provide a single assertion of a word line signal on the word line, and then sequentially read data from the set of memory cells (using the sense amplifier) based on the precharge and the single assertion of the word line signal. Additionally, or alternatively, a multi-write process may be performed to sequentially write data to the set of memory cells based on one precharge of the associated bit lines. Other embodiments may be described and claimed.
-
-
-
-
-
-
-
-
-