\DeclareAcronym{pim}{ short = PIM, long = processing-in-memory, } \DeclareAcronym{dnn}{ short = DNN, long = deep neural network, } \DeclareAcronym{cnn}{ short = CNN, long = convolutional neural network, } \DeclareAcronym{mlp}{ short = MLP, long = multilayer perceptron, } \DeclareAcronym{rnn}{ short = RNN, long = recurrent neural network, } \DeclareAcronym{blas}{ short = BLAS, long = Basic Linear Algebra Subprograms, } \DeclareAcronym{gemv}{ short = GEMV, long = matrix-vector multiplication, } \DeclareAcronym{dram}{ short = DRAM, long = Dynamic Random Access Memory, } \DeclareAcronym{fimdram}{ short = PIM-HBM, alt = FIMDRAM, long = Fun\-ction-In-Memory DRAM, } \DeclareAcronym{hbm2}{ short = HBM2, long = High Bandwidth Memory 2, } \DeclareAcronym{simd}{ short = SIMD, long = single-instruction multiple-data, } \DeclareAcronym{pch}{ short = pCH, long = pseudo channel, } \DeclareAcronym{fpu}{ short = FPU, long = floating-point unit, } \DeclareAcronym{fp}{ short = FP, long = floating-point, } \DeclareAcronym{crf}{ short = CRF, long = command register file, } \DeclareAcronym{grf}{ short = GRF, long = general register file, } \DeclareAcronym{srf}{ short = SRF, long = scalar register file, } \DeclareAcronym{fp16}{ short = FP16, long = 16-bit floating-point, } \DeclareAcronym{ssa}{ short = SSA, long = secondary sense amplifier, } \DeclareAcronym{pu}{ short = PU, long = processing unit, } \DeclareAcronym{sb}{ short = SB, long = Single-Bank, } \DeclareAcronym{ab}{ short = AB, long = All-Bank, } \DeclareAcronym{abp}{ short = AB-PIM, long = All-Bank-PIM, } \DeclareAcronym{act}{ short = ACT, long = activate, } \DeclareAcronym{pre}{ short = PRE, long = precharge, } \DeclareAcronym{rd}{ short = RD, long = read, } \DeclareAcronym{wr}{ short = WR, long = write, } \DeclareAcronym{risc}{ short = RISC, long = reduced instruction set computer, } \DeclareAcronym{ld}{ short = LD, long = load, } \DeclareAcronym{st}{ short = ST, long = store, } \DeclareAcronym{aam}{ short = AAM, long = address aligned mode, } \DeclareAcronym{mac}{ short = MAC, long = multiply-accumulate, } \DeclareAcronym{haxpy}{ short = HAXPY, long = half precision $a \cdot x + y$, } \DeclareAcronym{relu}{ short = ReLU, long = rectified linear unit, } \DeclareAcronym{gpu}{ short = GPU, long = graphics processing unit, } \DeclareAcronym{fpga}{ short = FPGA, long = field-programmable gate array, } \DeclareAcronym{edp}{ short = EDP, long = energy-delay product, }