Deploying convolution-based algorithms into SRAM computing-in-memory (CIM) systems faces various challenges, such as operator incompatibility and intrinsic non-ideal error. This paper proposes a compilation framework to address this issue. Efficient weight mapping strategies are introduced to improve the utilization of SRAM-CIM macro. The intrinsic non-ideal errors of SRAM-CIM macro are also taken into consideration, and two efficient error correction schemes are proposed, which include calibration of computation voltage linear error (CCVLE) and the mitigation of analog-to-digital quantization error (MAQE). In addition, bit-width flexibility and signed-unsigned reconfigurability are also supported to facilitate the deployment of various convolution-based algorithms. ResNet18, finite impulse response (FIR) filtering, and Gaussian image filtering are deployed into a multi-macro SRAM-CIM system. These algorithms serve as deployment representatives of convolutional neural network (CNN), digital signal processing (DSP), and digital image processing (DIP), respectively. The results show that the introduced weight mapping strategies improve the macro utilization by 63.29% and 21.10% for two types of frequently used convolution layers compared to the traditional strategy. Moreover, the proposed error correction schemes achieve similar algorithm accuracy to the floating-point results, and the deployment result of ResNet18 achieves 66.3%~70.1% top-1 classification accuracy evaluated on the ImageNet dataset with different throughput tradeoffs.

Mixed-precision Neural Networks achieve high energy efficiency and throughput for hardware deployment. The most common mixed-precision methods adopt layer-wise granularity. However, the layer-wise method does not quantize the model to its limit because the optimal bit precision that preserves accuracy for different kernels can be different. To address this issue, this paper presents GroupQ, a group-wise quantization method with multi-objective optimization for CNN accelerators. Group-wise divides the convolutional kernels in a layer into several groups by clustering, and each group shares the same bit precision. The multi-objective optimization algorithm is used to optimize the quantization policy automatically based on the selected quantization objectives, such as model accuracy, model size, or computation cost. The experiments show that GroupQ significantly outperforms the existing layer-wise retraining-free methods, even better than some training-based methods. Specifically, GroupQ achieves a 0.49% higher accuracy with up to 28.1% smaller Bit Operations (BOPs) on ResNet-18 compared to HAWQ-V3 and can quantize MobileNetV2 to 1.65MB model size with 71.75% top-1 accuracy. This paper shows that GroupQ is friendly for hardware deployment by a lookup table (LUT)-based mixed-precision processing element (LMPE) proposed for CNN accelerators. LMPE provides power reduction of up to 3.6%, up to 3.9% lower area, compared to conventional implementation.

This paper proposes an efficient way of using edge based redundant information for improving the error resilience of IDR frames. The proposed method generates spatial error concealment mode and edge direction data at the encoder which are sent to the decoder to guide the concealment process. Results show that the method offers very good performance with only a very small increase in complexity at the decoder and the introduction of negligible overhead to the coded stream.