Edge Impulse on LinkedIn: Mark your calendars! In Arm's upcoming AI Tech Talk, Louis Moreau willā¦
Mark your calendars! In Arm's upcoming AI Tech Talk, Louis Moreau will show how to perform object detection on Cortex-M7 (and other) processors with Edgeā¦www.linkedin.com
Hmmmm could this be little chipper
Here's an ARM patent application from mid-2020 which converts CNN for matrix multiplication on a CPU!!!??? Plenty of scope to boost performance by incorporating a SNN. After all, they do envisage a hardware accelerator processing engine or specialized hardware, which may provide some hitherto unknown (to ARM) power/speed advantages.
US2021390367A1 Hardware Accelerator For IM2COL Operation
Applicants: ADVANCED RISC MACH LTD [GB]
Priorities: US202016901542AĀ·2020-06-15
one or more processors, coprocessors, processing engines (PEs), compute engines (CEs), etc., such as, for example, CPUs, GPUs, NPUs (e.g., the ARM ML Processor), DSPs, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), controllers, microcontrollers, matrix multiplier circuits, MAC arrays, etc.
[0002] Artificial neural networks (ANNs), such as deep neural networks (DNNs), convolutional neural networks (CNNs), etc., are a popular solution to a wide array of challenging classification, recognition and regression problems. However, many ANN models require a large number of calculations involving a large number of weights and activations, which presents a significant challenge with respect to access, storage and performance, particularly for mobile and other power or storage-constrained devices. An ANN hardware accelerator accelerates these calculations, such as, for example, convolution operations performed by CNNs.
[0003] Typically, native convolution operations are not performed by a CNN due to the complicated dataflow and expensive datapaths that are usually required. Instead, native convolution operations are converted into generic matrix multiplication (GEMM) operations, and then the GEMM operations are executed more efficiently by a central processing unit (CPU), specialized processor, hardware accelerator processing engine, etc., using optimized software libraries or specialized hardware. More particularly, an āIM2COLā software function is used to convert the filter (weight) matrix and the input feature map (IFM) matrix for each convolution operation into an expanded format that is compatible with a GEMM operation. The IM2COL versions of each filter (weight) matrix and each IFM matrix are generated and stored in memory, and then loaded from memory and processed by the GEMM operation.
https://iq.opengenus.org/im2col/
Im2col stands for Image to Column and is an implementation technique of computing Convolution operation (in Machine Learning) using GEMM operations. This is a preferred way of computing Convolution as GEMM operations from BLAS and BLIS libraries are optimized for specific hardware platforms and performs well in practice.