BISMO: A Scalable Bit-Serial Matrix Multiplication Overlay for Reconfigurable Computing

06/22/2018
by   Yaman Umuroglu, et al.
0

Matrix-matrix multiplication is a key computational kernel for numerous applications in science and engineering, with ample parallelism and data locality that lends itself well to high-performance implementations. Many matrix multiplication-dependent applications can use reduced-precision integer or fixed-point representations to increase their performance and energy efficiency while still offering adequate quality of results. However, precision requirements may vary between different application phases or depend on input data, rendering constant-precision solutions ineffective. We present BISMO, a vectorized bit-serial matrix multiplication overlay for reconfigurable computing. BISMO utilizes the excellent binary-operation performance of FPGAs to offer a matrix multiplication performance that scales with required precision and parallelism. We characterize the resource usage and performance of BISMO across a range of parameters to build a hardware cost model, and demonstrate a peak performance of 6.5 TOPS on the Xilinx PYNQ-Z1 board.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/02/2019

Optimizing Bit-Serial Matrix Multiplication for Reconfigurable Computing

Matrix-matrix multiplication is a key computational kernel for numerous ...
research
06/21/2023

DGEMM on Integer Matrix Multiplication Unit

Deep learning hardware achieves high throughput and low power consumptio...
research
08/15/2022

LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale

Large language models have been widely adopted but require significant G...
research
12/17/2019

Defects Mitigation in Resistive Crossbars for Analog Vector Matrix Multiplication

With storage and computation happening at the same place, computing in r...
research
09/21/2023

AIM: Accelerating Arbitrary-precision Integer Multiplication on Heterogeneous Reconfigurable Computing Platform Versal ACAP

Arbitrary-precision integer multiplication is the core kernel of many ap...
research
09/21/2022

POAS: A high-performance scheduling framework for exploiting Accelerator Level Parallelism

Heterogeneous computing is becoming mainstream in all scopes. This new e...
research
07/22/2019

Reconfigurable multiplier architecture based on memristor-cmos with higher flexibility

Multiplication is an indispensable operation in most of digital signal p...

Please sign up or login with your details

Forgot password? Click here to reset