4 papers
Fair and Square: Replacing One Real Multiplication with a Single Square and One Complex Multiplication with Three Squares When Performing Matrix Multiplication and Convolutions
Vincenzo Liguori
This paper shows that, for matrix multiplications and convolutions, it is possible to asymptotically replace each real multiplication with a single squaring operation. Similarly, a…
Procrastination Is All You Need: Exponent Indexed Accumulators for Floating Point, Posits and Logarithmic Numbers
Vincenzo Liguori
This paper discusses a simple and effective method for the summation of long sequences of floating point numbers. The method comprises two phases: an accumulation phase where the m…
From a Lossless (~1.5:1) Compression Algorithm for Llama2 7B Weights to Variable Precision, Variable Range, Compressed Numeric Data Types for CNNs and LLMs
Vincenzo Liguori
This paper starts with a simple lossless ~1.5:1 compression algorithm for the weights of the Large Language Model (LLM) Llama2 7B [1] that can be implemented in ~200 LUTs in AMD FP…
Efficient FIR filtering with Bit Layer Multiply Accumulator
Vincenzo Liguori
Bit Layer Multiplier Accumulator (BLMAC) is an efficient method to perform dot products without multiplications that exploits the bit level sparsity of the weights. A total of 1,98…