Rewriting History: Repurposing Domain-Specific CGRAs

09/16/2023
by   Jackson Woodruff, et al.
0

Coarse-grained reconfigurable arrays (CGRAs) are domain-specific devices promising both the flexibility of FPGAs and the performance of ASICs. However, with restricted domains comes a danger: designing chips that cannot accelerate enough current and future software to justify the hardware cost. We introduce FlexC, the first flexible CGRA compiler, which allows CGRAs to be adapted to operations they do not natively support. FlexC uses dataflow rewriting, replacing unsupported regions of code with equivalent operations that are supported by the CGRA. We use equality saturation, a technique enabling efficient exploration of a large space of rewrite rules, to effectively search through the program-space for supported programs. We applied FlexC to over 2,000 loop kernels, compiling to four different research CGRAs and 300 generated CGRAs and demonstrate a 2.2× increase in the number of loop kernels accelerated leading to 3× speedup compared to an Arm A5 CPU on kernels that would otherwise be unsupported by the accelerator.

READ FULL TEXT

page 2

page 7

page 8

page 9

research
11/30/2022

Canal: A Flexible Interconnect Generator for Coarse-Grained Reconfigurable Arrays

The architecture of a coarse-grained reconfigurable array (CGRA) interco...
research
01/21/2022

Trireme: Exploring Hierarchical Multi-Level Parallelism for Domain Specific Hardware Acceleration

The design of heterogeneous systems that include domain specific acceler...
research
01/02/2023

Hardware Abstractions and Hardware Mechanisms to Support Multi-Task Execution on Coarse-Grained Reconfigurable Arrays

Domain-specific accelerators are used in various computing systems rangi...
research
10/12/2018

ISA Mapper: A Compute and Hardware Agnostic Deep Learning Compiler

Domain specific accelerators present new challenges and opportunities fo...
research
05/06/2019

An optimizing multi-platform source-to-source compiler framework for the NEURON MODeling Language

Domain-specific languages (DSLs) play an increasingly important role in ...
research
11/13/2017

Domain-Specific Acceleration and Auto-Parallelization of Legacy Scientific Code in FORTRAN 77 using Source-to-Source Compilation

Massively parallel accelerators such as GPGPUs, manycores and FPGAs repr...
research
02/25/2019

Mitigating Power Side Channels during Compilation

The code generation modules inside modern compilers such as GCC and LLVM...

Please sign up or login with your details

Forgot password? Click here to reset