S2CBench : Synthesizable SystemC Benchmark Suite for · PDF fileS2CBench : Synthesizable SystemC Benchmark Suite for High-Level ... –TB sends stimuli data stored in files (test vectors)

S2CBench : Synthesizable SystemC Benchmark Suite for High-Level

SynthesisBenjamin Carrion Schafer1, Ansuhree Mahapatra2

The Hong Kong Polytechnic UniversityDepartment of Electronic and Information Engineering

[email protected], [email protected]

@DARC_lab

2

Outline

• Motivation for a Synthesizable SystemC Benchmark Suite• Requirements for S2CBench• A review of past HLS benchmarks• S2CBench overview

– 12 synthesizable design– 1 non synthesizable (tests floating point and trigonometric functions)

• Benchmark composition overview• Detail benchmark characteristics

– Size– Complexity– Arithmetic operations

• How to download• Conclusions

Motivation for S2CBench

3

Vendor Tool Name Supported Languages

Cadence (Forte) Cynthesizer SystemC

Cadence C-to-Silicon C, C++, SystemC

Calypto CatapultC C++, SystemC

NEC CyberWorkBench C, SystemC

Xilinx Vivado HLS C, C++, SystemC

• Not evaluation standards

• Not enough HLS models for RTL designs to compare QoR

HLS tool evaluation

times

• Different HLS tools support different input languages

• One common language supported by all HLS tools: SystemC

HLS tool input languages

Requirements for a HLS Benchmark

Must cover different domains of applications

Test specific optimization techniques of HLS tools

Avoid re-writing descriptions for tool evaluations

4

S2CBench enables the direct comparison of commercial HLS tools

HLS Benchmarks: A Review

5

CHStone

HLS benchmark based on ANSI-C

ANSI-C not supported by all

HLS tools

C does not support fixed-

point operations

HLS92,95

Written in behavioral VHDL

Targets various optimization

options

Currently not supported by any HLS tool

MiBench, MediaBench

Written in C

Do not support fixed point operations

Do not test specific HLS

features

S2CBench: An Overview

• Covers different domains:

Automotive

Security

Telecommunication

Consumer

• Contains Control dominant and Data dominant designs

6

12+1 SystemC Benchmarks which comply with latest SystemC synthesizable subset draft

12 Synthesizable1 non

synthesizable

• Contains trigonometric & floating-point operations

• Helps check the ability of tools to support them

S2CBench: Features

7

Synthesis optimizations(e.g. loop unrolling, pipelining, function inlining, array synthesis)

Tool language support(e.g. templates, structures, fixed point data types)

Tool performance(e.g. synthesis run-time, accuracy of synthesis report)

Every application features a testbench along with associated test vectors

HLS optimizations

Synthesizer language support

Synthesizer performance

S2CBench model

• Testbench functions:– TB sends stimuli data stored in files

(test vectors) to UUT

– TB receives the data and compares it against golden output (stored in file)

– TB reports if results match or not

• Option to dump VCD file

• Test vectors are modifiable

8

S2CBench : 12+1 designs

9

Design Type Domain Optimizations Tested

qsort dd Auto/Ind Loops, arrays, functions pointers

sobel dd Auto/Ind Loops, functions, IO array expansion, multi-dimensional arrays expansion, fixed arrays (ROM, logic)

aes cipher dd Security IO array expansion, multi-dimensional arrays expansion , large fixed arrays

kasumi dd Security Multi-processes, delay report accuracy

md5c dd Security #define macros, delay report accuracy

snow3G dd Security Templates, delay report accuracy, function synthesis

adpcm cd Telecom Structure synthesis

FFT dd Telecom Floating point, trigonometric functions

FIR dd Consumer IO array expansion, arrays, loops, functions, sum of products

Decimation dd Consumer Resource sharing across loops, fixed point data types

Interp dd Consumer Polynomial decomposition, fixed point data types, sum or products

IDCT dd Consumer #include statement to initialize arrays, loops, functions,

Disparity cd/dd Consumer Hierarchical design, multi-dimensional array expansion, synthesis running time

Detail Benchmark Contents for each Design

• Top module including UUT and TB(Main.cpp)

• Design description( <benchmark>.cpp/.h)

• Testbench module(tb_<benchmark>.cpp/.h)

SystemC files

• Test vector( input.txt)

• Golden output(outputs_golden.txt)

• Image files(some applications)Stimuli data

• Allows different make options•Make: generates executable binary(default)

•Make ‘wave’: binary having VCD file

•Make ‘debug’: binary with debug version

Makefile

10

Quick – Quick Sort

• Description

sort design sorts data in ascending order using the well-known quick sort algorithm

• Optimization options to be tested

loop unrolling

array synthesis (register or memory)

function synthesis with pointer argument support

11

Sobel

• Descriptionedge-detection algorithm that takes a bitmap image

directly as the input and returns a new bitmap image solely consisting of the edges of the original image.

• Optimization options to be tested nested loop unrolling and pipelining optimizations I/O ports expansion (expand inputs specified as arrays

to individual ports)multi-dimensional arrays expansionfixed arrays synthesized as logic or ROMspointer arguments to functions

12

AES - Advanced Encryption Standard Cipher

• DescriptionAdvanced Encryption Standard Cipher encryption

algorithm performs AES encryption

• Optimization options to be tested Contains a large number of small for loops having

inter-loop data dependencies.

Input port expansion

Array synthesis (memory or registers)

Function synthesis (inline, goto)

Large fixed arrays synthesized as logic or ROMs.

13

Kasumi

• Descriptionblock cipher algorithm used in mobile

communication systems

Composed of two sc_threads and multiple functions

• Optimization options to be tested Ability to synthesize large logic operations

Accuracy of estimating the critical path

Multi-process systems verification

14

MD5C - Message Digest Algorithm

• Description

generates hash functions and check data integrity.


functions synthesis

arrays of different bit widths

different levels of loop nesting

extensive use of define macros (language support)

15

Snow3G

• Description

stream cipher that produces a key stream that consists of 32-bit blocks using a 128-bit key

Contains a variable length multiplication operation


Support of templates.

Loops, functions and array synthesis

16

ADPCM -Adaptive Differential Pulse-Code modulation (encoder part only)

• Description

accepts 16-bit Pulse Code Modulation (PCM) samples as input and converts them into 4-bit samples


loop unrolling, function synthesis, array synthesis

support for structures synthesis

17

FFT – Fast Fourier Transform

• Description

– Converts time/space to frequency and vice versa

– Not synthesizable as per latest synthesis draft


– Support for floating point operations and trigonometric functions

18

Why is it included

Most HLS vendors do support floating-point, trigonometric operations

Helps evaluation engineers analyze the extent of support of these operations

FIR – Finite Impulse Response Filter

• Description

– 10- tap FIR filter algorithm designed for 8- bit integer operations.


– loop unrolling and pipelining

– automatic array expansion of the I/O ports

– pointers to functions

19

Decimation Filter

• Description– 5-stage decimation filter. Consists of 5 FIR filters

cascaded together where the output of one stage is the input to the next stage.

• Optimization options to be tested – resource sharing of the Multiply Accumulate

(MAC) operations across loops

– fixed-point data types and its different rounding and saturation modes.

– Ability to preserve the SoP constructs

20

Interpolation Filter

• Description

– 4-stage interpolation filter


– automatic polynomial decompositions(Mathematical optimization of HLS tool)

– fixed- point data types and its different rounding and saturation modes

21

IDCT - Inverse Discrete Cosine Transform

• Description

– Describes a finite sequence of data points as a sum of cosine functions of different frequencies


– initialization of an array using #include statement

– loops, functions, array synthesis

22

Disparity – Stereoscopic Disparity Estimator

• Description

– estimates the disparity in a stereoscopic image.

– It is the largest of all the designs and consists of 4 processes executed in parallel


– Synthesis running time of the HLS tool

– Verification of Multi-process (threads) systems

23

Detailed Benchmark Characteristics

Variety of operations

24

Distribution of Number of Program Lines

25Note: Only lines of code of synthesizable description (not including testbench)

Complexity distribution of designs

26

0

5

10

15

20

25

qsort sobel aescipher

kasumi md5c snow3G adpcm fft fir decim interp idct disparity

NU

MB

ER

APPLICATIONS

Processes

Function

No. of arrays

if statement

for loop

while loop

Publicly Available for download

• www.s2cbench.org• http://sourceforge.net/projects/s2cbench/

27

More Information

B. Carrion Schafer and A.Mahapatra, "S2CBench:Synthesizable SystemC Benchmark Suite for High-Level Synthesis “IEEE Embedded Systems Letters, Accepted for publication

YouTube Channel: DARClabify

28

Summary and Conclusions

• A benchmark suite in a common language supported by all major HLS vendors

• Each benchmark tests unique HLS features1. Tool language support

2. Synthesis optimizations

3. Tool performance

• Benchmarks include testbench with inputs, golden outputs and option to generate VCD file

• Publicly available at www.s2cbench.org or sourceforge.net

29

Documents

S2CBench : Synthesizable SystemC Benchmark Suite for · PDF fileS2CBench : Synthesizable SystemC Benchmark Suite for High-Level ... –TB sends stimuli data stored in files (test vectors)