NDLI: Exploiting mixed SIMD parallelism by reducing data reorganization overhead

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

Cheetah: detecting false sharing efficiently and effectively

StructSlim: a lightweight profiler to guide structure splitting

A black-box approach to energy-aware scheduling on integrated CPU-GPU systems

A basic linear algebra compiler for structured matrices

Inference of peak density of indirect branches to detect ROP attacks

Towards automatic significance analysis for approximate computing

Validating optimizations of concurrent C/C++ programs

Flexible on-stack replacement in LLVM

AutoFDO: automatic feedback-directed optimization for warehouse-scale applications

Exploiting recent SIMD architectural advances for irregular applications

Portable and transparent software managed scheduling on accelerators for fair resource sharing

Opening polyhedral compiler's black box

Sparse flow-sensitive pointer analysis for multithreaded programs

Have abstraction and eat performance, too: optimized heterogeneous computing with parallel patterns

IPAS: intelligent protection against silent output corruption in scientific applications

BlackBox: lightweight security monitoring for COTS binaries

Portable performance on asymmetric multicore processors

Exploiting mixed SIMD parallelism by reducing data reorganization overhead

Communication-aware mapping of stream graphs for multi-GPU platforms

Trace-based affine reconstruction of codes

Symbolic range analysis of pointers

NRG-loops: adjusting power from within applications

Atomicity violation checker for task parallel programs

Re-constructing high-level information for language-specific binary re-optimization

gpucc: an open-source GPGPU compiler

Exploiting mixed SIMD parallelism by reducing data reorganization overhead

Content Provider	ACM Digital Library
Author	Xue, Jingling Zhou, Hao
Abstract	Existing loop vectorization techniques can exploit either intra- or inter-iteration SIMD parallelism alone in a code region if one part of the region vectorized for one type of parallelism has data dependences (called mixed-parallelism-inhibiting dependences) on the other part of the region vectorized for the other type of parallelism. In this paper, we consider a class of loops that exhibit both types of parallelism (i.e., mixed SIMD parallelism) in its code regions that contain mixed-parallelism-inhibiting data dependences. We present a new compiler approach for exploiting such mixed SIMD parallelism effectively by reducing the data reorganization overhead incurred when one type of parallelism is switched to the other. Our auto-vectorizer is simple and has been implemented in LLVM (3.5.0). We evaluate it on seven benchmarks with mixed SIMD parallelism selected from SPEC and NAS benchmark suites and demonstrate its performance advantages over the state-of-the-art. .
Starting Page	59
Ending Page	69
Page Count	11
File Format	PDF
ISBN	9781450337786
DOI	10.1145/2854038.2854054
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2016-02-29
Publisher Place	New York
Access Restriction	Subscribed
Subject Keyword	Slp Loop vectorization Mixed simd parallelism Data reorganization optimization
Content Type	Text
Resource Type	Article

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

A Compiler Approach for Exploiting Partial SIMD Parallelism

Outer-loop vectorization: revisited for short SIMD architectures

Auto-vectorization of interleaved data for SIMD

SIMD Defragmenter: Efficient ILP Realization on Data-parallel Architectures

Retargetable code optimization with SIMD instructions

A New Algorithm to Exploit Superword Level Parallelism

Exploiting Hyper-Loop Parallelism in Vectorization to Improve Memory Performance on CUDA GPGPU

Energy aware compilation for DSPs with SIMD instructions

Exploiting Pure Superword Level Parallelism for Array Indirections

Exploiting mixed SIMD parallelism by reducing data reorganization overhead

Similar Documents

A Compiler Approach for Exploiting Partial SIMD Parallelism

Outer-loop vectorization: revisited for short SIMD architectures

Auto-vectorization of interleaved data for SIMD

SIMD Defragmenter: Efficient ILP Realization on Data-parallel Architectures

Retargetable code optimization with SIMD instructions

A New Algorithm to Exploit Superword Level Parallelism

Exploiting Hyper-Loop Parallelism in Vectorization to Improve Memory Performance on CUDA GPGPU

Energy aware compilation for DSPs with SIMD instructions

Exploiting Pure Superword Level Parallelism for Array Indirections

Exploiting mixed SIMD parallelism by reducing data reorganization overhead