NDLI: Soft vector processors vs FPGA custom hardware: measuring and reducing the gap

Please wait, while we are loading the content...

Towards automated ECOs in FPGAs

Architectural enhancements in Stratix-III™ and Stratix-IV™

A comparison of CPUs, GPUs, FPGAs, and massively parallel processor arrays for random number generation

FPGA-based front-end electronics for positron emission tomography

CMOS vs Nano: comrades or rivals?

Making good points: application-specific pareto-point generation for design space exploration using statistical methods

FPCNA: a field programmable carbon nanotube array

SPR: an architecture-adaptive CGRA mapping tool

Large-scale wire-speed packet classification on FPGAs

SmartOpt: an industrial strength framework for logic synthesis

A high performance fpga-based implementation of position specific iterated blast

HW/SW methodologies for synchronization in FPGA multiprocessors

Soft vector processors vs FPGA custom hardware: measuring and reducing the gap

Simultaneous multi-channel data acquisition with variable sampling frequencies using a scalable adaptive synchronous controller

A parallel/vectorized double-precision exponential core to accelerate computational science applications

Emerging application domains: research challenges and opportunities for FPGAs

Clock power reduction for virtex-5 FPGAs

Towards reliable 5Gbps wave-pipelined and 3Gbps surfing interconnect in 65nm FPGAs

A high-performance FPGA architecture for restricted boltzmann machines

Fpga-based face detection system using Haar classifiers

VPR 5.0: FPGA cad and architecture exploration tools with single-driver routing, heterogeneity and process scaling

Flexible multi-mode embedded floating-point unit for field programmable gate arrays

Synthesis of reconfigurable high-performance multicore systems

Fast and scalable packet classification using perfect hash functions

Cholesky decomposition using fused datapath synthesis

A communication architecture for complex runtime reconfigurable systems and its implementation on spartan-3 FPGAs

Automatic bus macro placement for partially reconfigurable FPGA designs

Data streaming and simd support for the microblaze architecture

Performance and power of cache-based reconfigurable computing

FPGAs with time-division multiplexed wiring: an architectural exploration and area analysis

Choose-your-own-adventure routing: lightweight load-time defect avoidance

A comparison of via-programmable gate array logic cell circuits

A multi-fpga 10x-real-time high-speed search engine for a 5000-word vocabulary speech recognizer

A 17ps time-to-digital converter implemented in 65nm FPGA technology

FPGA technology mapping with encoded libraries andstaged priority cuts

Wirelength modeling for homogeneous and heterogeneous FPGA architectural development

Intel® atom™ processor core made FPGA-synthesizable

Diagonal tracks in FPGAs: a performance evaluation

PERG-Rx: a hardware pattern-matching engine supporting limited regular expressions

Bus mastering PCI express in an FPGA

Small scale multiprocessor soft IP (SSM IP): single FPGA chip area and performance evaluation

Computation reuse in domain-specific optimization of signal recognition

A novel BIST approach for testing input/output buffers in FPGAs

Scalable don't-care-based logic optimization and resynthesis

High-performance, energy-efficient platforms using in-socket FPGA accelerators

Customizable bit-width in an OpenMP-based circuit design tool

The input-aware dynamic adaptation of area and performance for reconfigurable accelerator

Impact and compensation of correlated process variation on ring oscillator based puf

Revisiting bitwidth optimizations

Implementation of the reconfiguration port scheduling on the erlangen slot machine

A novel minloop SB design to improve FPGA routability

A clustering framework for task partitioning based on function-level data usage analysis

HMMer acceleration using systolic array based reconfigurable architecture

High-performance, cost-effective heterogeneous 3D FPGA architectures

An intermediate hardware model with load/store unit for C to FPGA

FPGA implementation of real-time skin color detection with mean-based surface flattening

Measuring and modeling variabilityusing low-cost FPGAs

N-port memory mapping for LUT-based FPGAs

Streaming implementation of a sequential decompression algorithm on an FPGA

3D configuration caching for 2D FPGAs

Parallel placement for FPGAs revisited

32-bit floating-point FPGA gaussian elimination

Implementation of a genetic algorithm on a virtex-ii pro FPGA

Closed-loop modeling of power and temperature profiles of FPGAs

Soft vector processors vs FPGA custom hardware: measuring and reducing the gap

Content Provider	ACM Digital Library
Author	Yiannacouras, Peter Steffan, J. Gregory Rose, Jonathan
Abstract	Soft processors are often used in FPGA-based systems because of their ease-of-use, but for a given computation there is a significant gap in area/performance between a C code implementation executing on a soft processor and a custom FPGA hardware implementation. Recent research has demonstrated that soft processors augmented with support for vector instructions provide significant improvements in performance and scalability for data-parallel workloads. In this work, using an FPGA platform equipped with DDR memory executing data-parallel benchmarks from the industry-standard EEMBC suite, we measure the area/performance gaps between (i) C programs executing on a scalar soft processor, (ii) hand-vectorized programs executing on a soft vector processor, and (iii) custom FPGA hardware. We demonstrate that the wall clock performance gap between scalar executed C and custom hardware can be drastically reduced using our improved soft vector processors, even though they are still clocked 3x slower than custom hardware. We identify loop overhead, data delivery, and exact resource usage as three key advantages of custom hardware that we propose to mitigate in our soft vector processor respectively by decoupling pipelines, tuning cache design, supporting prefetching, and automatically eliminating unused instructions and datapath width. We show that together these improvements increase performance by 3x and reduce the area of the fastest soft vector processor by 2x, significantly reducing the need for designers to resort to more challenging custom hardware implementations.
Starting Page	277
Ending Page	277
Page Count	1
ISBN	9781605584102
DOI	10.1145/1508128.1508178
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2009-02-24
Publisher Place	New York
Access Restriction	Subscribed
Subject Keyword	Processor Eembc Fpga Viram Simd Adaptable Soft Vector Data parallel
Content Type	Text
Resource Type	Article

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in