1 citations · 1 across the 10 of their papers we have counts for
11 papers
Bandwidth, Not FLOPS: FFT Kernels, Matrix Units and SAR Imaging on Apple M6
Mohamed Amine Bergach
The fast Fourier transform (FFT) underlies radar, imaging and scientific computing. A classic rule for fast GPU FFTs is to compute the largest block that fits on chip and compose l…
The Price of Remembering: A Calibrated Energy Law for Computation
Mohamed Amine Bergach
Where does a computer's energy go? Mostly into keeping, not into computing. A bit held in fast storage draws power for every second it stays there, and it costs energy again each t…
MADAR: An Address-Free Processor
Mohamed Amine Bergach
In a modern processor, computing is the cheap part. Most of its area and energy go to \emph{addressing} -- moving operands to and from a register file and cache, and running the ta…
Range, Not Precision: Block-Floating-Point Half-Precision FFT and SAR Imaging on Apple Silicon
Mohamed Amine Bergach
Half precision (FP16) promises to double FFT throughput on GPUs, but the prevailing view is that its 10-bit mantissa makes it unsuitable for radar-grade signal processing. We show…
When Quantization Is Free: An int4 KV Cache That Outruns fp16 on Apple Silicon
Mohamed Amine Bergach
KV-cache quantization is framed as a quality--latency trade-off. We show it is \emph{inverted} on Apple Silicon's unified memory: a single fused Metal kernel (sign-randomized FFT $…
Training Transformers in Cosine Coefficient Space
Mohamed Amine Bergach
Linear layers hold most of a transformer's parameters. We replace each linear layer with one that stores out of two-dimensional DCT coefficients per weight matrix and reco…
Shortest-Path FFT: Optimal SIMD Instruction Scheduling via Graph Search
Mohamed Amine Bergach
An -point FFT admits many valid implementations that differ in radix choice, stage ordering, and register-blocking strategy. These alternatives use different SIMD instruction mi…
From 8 Seconds to 370ms: Kernel-Fused SAR Imaging on Apple Silicon via Single-Dispatch FFT Pipelines
Mohamed Amine Bergach
We present the first kernel-fused SAR Range Doppler pipeline on any GPU platform. By fusing FFT, matched-filter multiply, and IFFT into a single Metal compute dispatch -- keeping a…
Dual-Select FMA Butterfly for FFT: Eliminating Twiddle Factor Singularities with Bounded Precomputed Ratios
Mohamed Amine Bergach
The fused multiply-add (FMA) instruction enables the radix-2 FFT butterfly to be computed in 6~FMA operations -- the proven minimum. The classical factorization by Linzer and Feig~…
Beating vDSP: A 138 GFLOPS Radix-8 Stockham FFT on Apple Silicon via Two-Tier Register-Threadgroup Memory Decomposition
Mohamed Amine Bergach
We present an optimized Fast Fourier Transform (FFT) implementation for Apple Silicon GPUs, achieving 138.45~GFLOPS for complex single-precision transforms -- a 29\% i…
Efficient FFT mapping on GPU for radar processing application: modeling and implementation
Mohamed Amine Bergach, Emilien Kofman, Robert de Simone +2
General-purpose multiprocessors (as, in our case, Intel IvyBridge and Intel Haswell) increasingly add GPU computing power to the former multicore architectures. When used for embed…