Dharmendra S. Modha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Dharmendra S. Modha has a total of 100 co-authors. Here are the top co-authors by number of shared publications:
Rathinakumar Appuswamy
IBM Research IBM Software
6 shared publicationsBryan L. Jackson
IBM Research, Almaden Research Center, San Jose, CA
5 shared publications- John V. Arthur
IBM Research Almaden 95120 San Jose CA
5 shared publications - Andrew S. Cassidy
IBM Research Almaden 95120 San Jose CA
4 shared publications John V. Arthur
IBM Research IBM Software
4 shared publicationsMyron D. Flickner
IBM Research IBM Software
4 shared publications
Latest Publications
- Open Access
A Scalable NorthPole System with End-to-End Vertical Integration for Low-Latency and Energy-Efficient LLM Inference
A vertically integrated, end-to-end, research prototype system combines 288 NorthPole neural inference accelerator cards, offline training algorithms, a high-performance runtime stack, and a containerized inference pipeline to deliver a scalable and efficient cloud inference service. The system delivers 115 peta-ops at 4-bit integer precision and 3.7 PB/s of memory bandwidth across 18 2U servers, while consuming only 30 kW of power and weighing 730 kg in a 0.67 m^2 42U rack footprint. The system can run 3 simultaneous instances of the 8-billion-parameter open-source IBM Granite-3.3-8b-instruct model at 2,048 context length with 28 simultaneous users and a per-user inter-token latency of 2.8 ms. The system is scalable, modular, and reconfigurable, supporting various model sizes and context lengths, and is ideal for deploying agentic workflows for enterprise AI applications in existing data center (cloud, on-prem) environments. For example, the system can support 18 instances of a 3-billion-parameter model or a single instance of a 70-billion-parameter model.
Open AccessA Scalable NorthPole System with End-to-End Vertical Integration for Low-Latency and Energy-Efficient LLM Inference
A vertically integrated, end-to-end, research prototype system combines 288 NorthPole neural inference accelerator cards, offline training algorithms, a high-performance runtime stack, and a containerized inference pipeline to deliver a scalable and efficient cloud inference service. The system delivers 115 peta-ops at 4-bit integer precision and 3.7 PB/s of memory bandwidth across 18 2U servers, while consuming only 30 kW of power and weighing 730 kg in a 0.67 m^2 42U rack footprint. The system can run 3 simultaneous instances of the 8-billion-parameter open-source IBM Granite-3.3-8b-instruct model at 2,048 context length with 28 simultaneous users and a per-user inter-token latency of 2.8 ms. The system is scalable, modular, and reconfigurable, supporting various model sizes and context lengths, and is ideal for deploying agentic workflows for enterprise AI applications in existing data center (cloud, on-prem) environments. For example, the system can support 18 instances of a 3-billion-parameter model or a single instance of a 70-billion-parameter model.
- 20 October 2023
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 382 (6668) , 329-335
Neural inference at the frontier of energy, space, and time
Computing, since its inception, has been processor-centric, with memory separated from compute. Inspired by the organic brain and optimized for inorganic silicon, NorthPole is a neural inference architecture that blurs this boundary by eliminating off-chip memory, intertwining compute with memory on-chip, and appearing externally as an active memory chip. NorthPole is a low-precision, massively parallel, densely interconnected, energy-efficient, and spatial computing architecture with a co-optimized, high-utilization programming model. On the ResNet50 benchmark image classification network, relative to a graphics processing unit (GPU) that uses a comparable 12-nanometer technology process, NorthPole achieves a 25 times higher energy metric of frames per second (FPS) per watt, a 5 times higher space metric of FPS per transistor, and a 22 times lower time metric of latency. Similar results are reported for the Yolo-v4 detection network. NorthPole outperforms all prevalent architectures, even those that use more-advanced technology processes.
- 20 October 2023
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 382 (6668) , 329-335
Neural inference at the frontier of energy, space, and time
Computing, since its inception, has been processor-centric, with memory separated from compute. Inspired by the organic brain and optimized for inorganic silicon, NorthPole is a neural inference architecture that blurs this boundary by eliminating off-chip memory, intertwining compute with memory on-chip, and appearing externally as an active memory chip. NorthPole is a low-precision, massively parallel, densely interconnected, energy-efficient, and spatial computing architecture with a co-optimized, high-utilization programming model. On the ResNet50 benchmark image classification network, relative to a graphics processing unit (GPU) that uses a comparable 12-nanometer technology process, NorthPole achieves a 25 times higher energy metric of frames per second (FPS) per watt, a 5 times higher space metric of FPS per transistor, and a 22 times lower time metric of latency. Similar results are reported for the Yolo-v4 detection network. NorthPole outperforms all prevalent architectures, even those that use more-advanced technology processes.
- Open Access
Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference
To realize the promise of ubiquitous embedded deep network inference, it is essential to seek limits of energy and area efficiency. To this end, low-precision networks offer tremendous promise because both energy and area scale down quadratically with the reduction in precision. Here we demonstrate ResNet-18, -34, -50, -152, Inception-v3, Densenet-161, and VGG-16bn networks on the ImageNet classification benchmark that, at 8-bit precision exceed the accuracy of the full-precision baseline networks after one epoch of finetuning, thereby leveraging the availability of pretrained models. We also demonstrate ResNet-18, -34, -50, -152, Densenet-161, and VGG-16bn 4-bit models that match the accuracy of the full-precision baseline networks -- the highest scores to date. Surprisingly, the weights of the low-precision networks are very close (in cosine similarity) to the weights of the corresponding baseline networks, making training from scratch unnecessary. We find that gradient noise due to quantization during training increases with reduced precision, and seek ways to overcome this noise. The number of iterations required by SGD to achieve a given training error is related to the square of (a) the distance of the initial solution from the final plus (b) the maximum variance of the gradient estimates. Therefore, we (a) reduce solution distance by starting with pretrained fp32 precision baseline networks and fine-tuning, and (b) combat gradient noise introduced by quantization by training longer and reducing learning rates. Sensitivity analysis indicates that these simple techniques, coupled with proper activation function range calibration to take full advantage of the limited precision, are sufficient to discover low-precision networks, if they exist, close to fp32 precision baseline networks. The results herein provide evidence that 4-bits suffice for classification.
Open AccessDiscovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference
To realize the promise of ubiquitous embedded deep network inference, it is essential to seek limits of energy and area efficiency. To this end, low-precision networks offer tremendous promise because both energy and area scale down quadratically with the reduction in precision. Here we demonstrate ResNet-18, -34, -50, -152, Inception-v3, Densenet-161, and VGG-16bn networks on the ImageNet classification benchmark that, at 8-bit precision exceed the accuracy of the full-precision baseline networks after one epoch of finetuning, thereby leveraging the availability of pretrained models. We also demonstrate ResNet-18, -34, -50, -152, Densenet-161, and VGG-16bn 4-bit models that match the accuracy of the full-precision baseline networks -- the highest scores to date. Surprisingly, the weights of the low-precision networks are very close (in cosine similarity) to the weights of the corresponding baseline networks, making training from scratch unnecessary. We find that gradient noise due to quantization during training increases with reduced precision, and seek ways to overcome this noise. The number of iterations required by SGD to achieve a given training error is related to the square of (a) the distance of the initial solution from the final plus (b) the maximum variance of the gradient estimates. Therefore, we (a) reduce solution distance by starting with pretrained fp32 precision baseline networks and fine-tuning, and (b) combat gradient noise introduced by quantization by training longer and reducing learning rates. Sensitivity analysis indicates that these simple techniques, coupled with proper activation function range calibration to take full advantage of the limited precision, are sufficient to discover low-precision networks, if they exist, close to fp32 precision baseline networks. The results herein provide evidence that 4-bits suffice for classification.
- Open Access
- 21 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 66 (6) , 996-1007
Always-On Speech Recognition Using TrueNorth, a Reconfigurable, Neurosynaptic Processor
Deep neural networks (DNN) have been shown to be very effective at solving challenging problems in several areas of computing, including vision, speech, and natural language processing. However, traditional platforms for implementing these DNNs are often very power hungry, which has lead to significant efforts in the development of configurable platforms capable of implementing these DNNs efficiently. One of these platforms, the IBM TrueNorth processor, has demonstrated very low operating power in performing visual computing and neural network classification tasks in real-time. The neuron computation, synaptic memory, and communication fabrics are all configurable, so that a wide range of network types and topologies can be mapped to TrueNorth. This reconfigurability translates into the capability to support a wide range of low-power functions in addition to feed-forward DNN classifiers, including for example, the audio processing functions presented here.In this work, we propose an end-to-end audio processing pipeline that is implemented entirely on a TrueNorth processor and designed to specifically leverage the highly-parallel, low-precision computing primitives TrueNorth offers. As part of this pipeline, we develop an audio feature extractor (LATTE) designed for implementation on TrueNorth, and explore the tradeoffs among several design variants in terms of accuracy, power, and performance. We customize the energy-efficient deep neuromorphic networks structures that our design utilizes as the classifier and show how classifier parameters can trade between power and accuracy. In addition to enabling a wide range of diverse functions, the reconfigurability of TrueNorth enables re-training and re-programming the system to satisfy varying energy, speed, area, and accuracy requirements. The resulting system's end-to-end power consumption can be as low as 14:43 mW, which would give up to 100 hours of continuous usage with button cell batteries (CR3023 1:5 Whr) or 450 hours with cellphone batteries (iPhone 6s 6:55 Whr).
- 21 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 66 (6) , 996-1007
Open AccessAlways-On Speech Recognition Using TrueNorth, a Reconfigurable, Neurosynaptic Processor
Deep neural networks (DNN) have been shown to be very effective at solving challenging problems in several areas of computing, including vision, speech, and natural language processing. However, traditional platforms for implementing these DNNs are often very power hungry, which has lead to significant efforts in the development of configurable platforms capable of implementing these DNNs efficiently. One of these platforms, the IBM TrueNorth processor, has demonstrated very low operating power in performing visual computing and neural network classification tasks in real-time. The neuron computation, synaptic memory, and communication fabrics are all configurable, so that a wide range of network types and topologies can be mapped to TrueNorth. This reconfigurability translates into the capability to support a wide range of low-power functions in addition to feed-forward DNN classifiers, including for example, the audio processing functions presented here.In this work, we propose an end-to-end audio processing pipeline that is implemented entirely on a TrueNorth processor and designed to specifically leverage the highly-parallel, low-precision computing primitives TrueNorth offers. As part of this pipeline, we develop an audio feature extractor (LATTE) designed for implementation on TrueNorth, and explore the tradeoffs among several design variants in terms of accuracy, power, and performance. We customize the energy-efficient deep neuromorphic networks structures that our design utilizes as the classifier and show how classifier parameters can trade between power and accuracy. In addition to enabling a wide range of diverse functions, the reconfigurability of TrueNorth enables re-training and re-programming the system to satisfy varying energy, speed, area, and accuracy requirements. The resulting system's end-to-end power consumption can be as low as 14:43 mW, which would give up to 100 hours of continuous usage with button cell batteries (CR3023 1:5 Whr) or 450 hours with cellphone batteries (iPhone 6s 6:55 Whr).
- Open Access
Structured Convolution Matrices for Energy-efficient Deep learning
We derive a relationship between network representation in energy-efficient neuromorphic architectures and block Toplitz convolutional matrices. Inspired by this connection, we develop deep convolutional networks using a family of structured convolutional matrices and achieve state-of-the-art trade-off between energy efficiency and classification accuracy for well-known image recognition tasks. We also put forward a novel method to train binary convolutional networks by utilising an existing connection between noisy-rectified linear units and binary activations.
Open AccessStructured Convolution Matrices for Energy-efficient Deep learning
We derive a relationship between network representation in energy-efficient neuromorphic architectures and block Toplitz convolutional matrices. Inspired by this connection, we develop deep convolutional networks using a family of structured convolutional matrices and achieve state-of-the-art trade-off between energy efficiency and classification accuracy for well-known image recognition tasks. We also put forward a novel method to train binary convolutional networks by utilising an existing connection between noisy-rectified linear units and binary activations.
- Open Access
Deep neural networks are robust to weight binarization and other non-linear distortions
Recent results show that deep neural networks achieve excellent performance even when, during training, weights are quantized and projected to a binary representation. Here, we show that this is just the tip of the iceberg: these same networks, during testing, also exhibit a remarkable robustness to distortions beyond quantization, including additive and multiplicative noise, and a class of non-linear projections where binarization is just a special case. To quantify this robustness, we show that one such network achieves 11% test error on CIFAR-10 even with 0.68 effective bits per weight. Furthermore, we find that a common training heuristic--namely, projecting quantized weights during backpropagation--can be altered (or even removed) and networks still achieve a base level of robustness during testing. Specifically, training with weight projections other than quantization also works, as does simply clipping the weights, both of which have never been reported before. We confirm our results for CIFAR-10 and ImageNet datasets. Finally, drawing from these ideas, we propose a stochastic projection rule that leads to a new state of the art network with 7.64% test error on CIFAR-10 using no data augmentation.
Open AccessDeep neural networks are robust to weight binarization and other non-linear distortions
Recent results show that deep neural networks achieve excellent performance even when, during training, weights are quantized and projected to a binary representation. Here, we show that this is just the tip of the iceberg: these same networks, during testing, also exhibit a remarkable robustness to distortions beyond quantization, including additive and multiplicative noise, and a class of non-linear projections where binarization is just a special case. To quantify this robustness, we show that one such network achieves 11% test error on CIFAR-10 even with 0.68 effective bits per weight. Furthermore, we find that a common training heuristic--namely, projecting quantized weights during backpropagation--can be altered (or even removed) and networks still achieve a base level of robustness during testing. Specifically, training with weight projections other than quantization also works, as does simply clipping the weights, both of which have never been reported before. We confirm our results for CIFAR-10 and ImageNet datasets. Finally, drawing from these ideas, we propose a stochastic projection rule that leads to a new state of the art network with 7.64% test error on CIFAR-10 using no data augmentation.
- Open Access
Mapping Generative Models onto a Network of Digital Spiking Neurons
Stochastic neural networks such as Restricted Boltzmann Machines (RBMs) have been successfully used in applications ranging from speech recognition to image classification. Inference and learning in these algorithms use a Markov Chain Monte Carlo procedure called Gibbs sampling, where a logistic function forms the kernel of this sampler. On the other side of the spectrum, neuromorphic systems have shown great promise for low-power and parallelized cognitive computing, but lack well-suited applications and automation procedures. In this work, we propose a systematic method for bridging the RBM algorithm and digital neuromorphic systems, with a generative pattern completion task as proof of concept. For this, we first propose a method of producing the Gibbs sampler using bio-inspired digital noisy integrate-and-fire neurons. Next, we describe the process of mapping generative RBMs trained offline onto the IBM TrueNorth neurosynaptic processor -- a low-power digital neuromorphic VLSI substrate. Mapping these algorithms onto neuromorphic hardware presents unique challenges in network connectivity and weight and bias quantization, which, in turn, require architectural and design strategies for the physical realization. Generative performance metrics are analyzed to validate the neuromorphic requirements and to best select the neuron parameters for the model. Lastly, we describe a design automation procedure which achieves optimal resource usage, accounting for the novel hardware adaptations. This work represents the first implementation of generative RBM inference on a neuromorphic VLSI substrate.
Open AccessMapping Generative Models onto a Network of Digital Spiking Neurons
Stochastic neural networks such as Restricted Boltzmann Machines (RBMs) have been successfully used in applications ranging from speech recognition to image classification. Inference and learning in these algorithms use a Markov Chain Monte Carlo procedure called Gibbs sampling, where a logistic function forms the kernel of this sampler. On the other side of the spectrum, neuromorphic systems have shown great promise for low-power and parallelized cognitive computing, but lack well-suited applications and automation procedures. In this work, we propose a systematic method for bridging the RBM algorithm and digital neuromorphic systems, with a generative pattern completion task as proof of concept. For this, we first propose a method of producing the Gibbs sampler using bio-inspired digital noisy integrate-and-fire neurons. Next, we describe the process of mapping generative RBMs trained offline onto the IBM TrueNorth neurosynaptic processor -- a low-power digital neuromorphic VLSI substrate. Mapping these algorithms onto neuromorphic hardware presents unique challenges in network connectivity and weight and bias quantization, which, in turn, require architectural and design strategies for the physical realization. Generative performance metrics are analyzed to validate the neuromorphic requirements and to best select the neuron parameters for the model. Lastly, we describe a design automation procedure which achieves optimal resource usage, accounting for the novel hardware adaptations. This work represents the first implementation of generative RBM inference on a neuromorphic VLSI substrate.
- Open Access
- 1 May 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 02714302,p. 2704-2707
Gibbs sampling with low-power spiking digital neurons
Restricted Boltzmann Machines and Deep Belief Networks have been successfully used in a wide variety of applications including image classification and speech recognition. Inference and learning in these algorithms uses a Markov Chain Monte Carlo procedure called Gibbs sampling. A sigmoidal function forms the kernel of this sampler which can be realized from the firing statistics of noisy integrate-and-fire neurons on a neuromorphic VLSI substrate. This paper demonstrates such an implementation on an array of digital spiking neurons with stochastic leak and threshold properties for inference tasks and presents some key performance metrics for such a hardware-based sampler in both the generative and discriminative contexts.
- 1 May 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 02714302,p. 2704-2707
Open AccessGibbs sampling with low-power spiking digital neurons
Restricted Boltzmann Machines and Deep Belief Networks have been successfully used in a wide variety of applications including image classification and speech recognition. Inference and learning in these algorithms uses a Markov Chain Monte Carlo procedure called Gibbs sampling. A sigmoidal function forms the kernel of this sampler which can be realized from the firing statistics of noisy integrate-and-fire neurons on a neuromorphic VLSI substrate. This paper demonstrates such an implementation on an array of digital spiking neurons with stochastic leak and threshold properties for inference tasks and presents some key performance metrics for such a hardware-based sampler in both the generative and discriminative contexts.
- Open Access
Gibbs Sampling with Low-Power Spiking Digital Neurons
Restricted Boltzmann Machines and Deep Belief Networks have been successfully used in a wide variety of applications including image classification and speech recognition. Inference and learning in these algorithms uses a Markov Chain Monte Carlo procedure called Gibbs sampling. A sigmoidal function forms the kernel of this sampler which can be realized from the firing statistics of noisy integrate-and-fire neurons on a neuromorphic VLSI substrate. This paper demonstrates such an implementation on an array of digital spiking neurons with stochastic leak and threshold properties for inference tasks and presents some key performance metrics for such a hardware-based sampler in both the generative and discriminative contexts.
Open AccessGibbs Sampling with Low-Power Spiking Digital Neurons
Restricted Boltzmann Machines and Deep Belief Networks have been successfully used in a wide variety of applications including image classification and speech recognition. Inference and learning in these algorithms uses a Markov Chain Monte Carlo procedure called Gibbs sampling. A sigmoidal function forms the kernel of this sampler which can be realized from the firing statistics of noisy integrate-and-fire neurons on a neuromorphic VLSI substrate. This paper demonstrates such an implementation on an array of digital spiking neurons with stochastic leak and threshold properties for inference tasks and presents some key performance metrics for such a hardware-based sampler in both the generative and discriminative contexts.
- Top Cited Papers
- 8 August 2014
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 345 (6197) , 668-673
A million spiking-neuron integrated circuit with a scalable communication network and interface
Modeling computer chips on real brains: Computers are nowhere near as versatile as our own brains. Merollaet al.applied our present knowledge of the structure and function of the brain to design a new computer chip that uses the same wiring rules and architecture. The flexible, scalable chip operated efficiently in real time, while using very little power.Science, this issue p.668
- 8 August 2014
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 345 (6197) , 668-673
Top Cited PapersA million spiking-neuron integrated circuit with a scalable communication network and interface
Modeling computer chips on real brains: Computers are nowhere near as versatile as our own brains. Merollaet al.applied our present knowledge of the structure and function of the brain to design a new computer chip that uses the same wiring rules and architecture. The flexible, scalable chip operated efficiently in real time, while using very little power.Science, this issue p.668