Presentation is loading. Please wait.

Presentation is loading. Please wait.

Carnegie Mellon Program Generation with Spiral: Beyond Transforms This work was supported by DARPA DESA program, NSF-NGS/ITR, NSF-ACR, Mercury Inc., and.

Published byElvin Wright Modified over 9 years ago

Similar presentations

Presentation on theme: "Carnegie Mellon Program Generation with Spiral: Beyond Transforms This work was supported by DARPA DESA program, NSF-NGS/ITR, NSF-ACR, Mercury Inc., and."— Presentation transcript:

1 Carnegie Mellon Program Generation with Spiral: Beyond Transforms This work was supported by DARPA DESA program, NSF-NGS/ITR, NSF-ACR, Mercury Inc., and Intel Franz Franchetti, Daniel Mcfarlin, Frédéric de Mesmay, Hao Shen, Tomasz W. Włodarczyk, Srinivas Chellappa, Marek R. Telgarsky, Peter A. Milder, Yevgen Voronenko, Qian Yu, James C. Hoe, José M. F. Moura, Markus Püschel Electrical and Computer Engineering Carnegie Mellon University

2 Carnegie Mellon Vision Behind Spiral Numerical problem Computing platform algorithm selection compilation human effort automated implementation C program automated algorithm selection compilation implementation Numerical problem Computing platform Current Future C code a singularity: Compiler has no access to high level information Challenge: conquer the high abstraction level for complete automation

3 Carnegie Mellon Main Idea: Program Generation νpμνpμ Architectural parameter: Vector length, #processors, … rewriting defines Kernel: problem size, algorithm choice pick search abstraction Model: common abstraction = spaces of matching formulas architecture space algorithm space optimization

4 Carnegie Mellon Expressing Kernels as Operator Formulas Viterbi DecoderMatrix-Matrix Multiplication JPEG 2000 (Wavelet, EBCOT)Synthetic Aperture Radar (SAR) interpolation2D iFFT matched filtering preprocessing convolutional encoder Viterbi decoder Viterbi decoder 010001 11 10 00 01 10 01 11 00 010001 11 10 01 01 10 10 11 00 JPEG 2000 Compression DWT quantization entropy coding (EBCOT + MQ) entropy coding (EBCOT + MQ) = £

Download ppt "Carnegie Mellon Program Generation with Spiral: Beyond Transforms This work was supported by DARPA DESA program, NSF-NGS/ITR, NSF-ACR, Mercury Inc., and."

Similar presentations

Carnegie Mellon Performance Portable Tracking of Evolving Surfaces Wei Yu Citadel Investment Group Franz Franchetti, James C. Hoe, José M. F. Moura Carnegie.

Carnegie Mellon Performance Portable Tracking of Evolving Surfaces Wei Yu Citadel Investment Group Franz Franchetti, James C. Hoe, José M. F. Moura Carnegie.
ECE 734 VLSI Array Structures for Digital Signal Processing Topic: Implementation of JPEG 2000 component algorithm—DWT in TI TMS32060 Team Members: Peng.

ECE 734 VLSI Array Structures for Digital Signal Processing Topic: Implementation of JPEG 2000 component algorithm—DWT in TI TMS32060 Team Members: Peng.
Carnegie Mellon Automatic Generation of Vectorized Fast Fourier Transform Libraries for the Larrabee and AVX Instruction Set Extension Automatic Generation.

Carnegie Mellon Automatic Generation of Vectorized Fast Fourier Transform Libraries for the Larrabee and AVX Instruction Set Extension Automatic Generation.
MP3 Optimization Exploiting Processor Architecture and Using Better Algorithms Mancia Anguita Universidad de Granada J. Manuel Martinez – Lechado Vitelcom.

MP3 Optimization Exploiting Processor Architecture and Using Better Algorithms Mancia Anguita Universidad de Granada J. Manuel Martinez – Lechado Vitelcom.
Implementation of 2-D FFT on the Cell Broadband Engine Architecture William Lundgren Gedae), Kerry Barnes (Gedae), James Steed (Gedae)

Implementation of 2-D FFT on the Cell Broadband Engine Architecture William Lundgren Gedae), Kerry Barnes (Gedae), James Steed (Gedae)
Offline Adaptation Using Automatically Generated Heuristics Frédéric de Mesmay, Yevgen Voronenko, and Markus Püschel Department of Electrical and Computer.

Offline Adaptation Using Automatically Generated Heuristics Frédéric de Mesmay, Yevgen Voronenko, and Markus Püschel Department of Electrical and Computer.
Code Compaction of an Operating System Kernel Haifeng He, John Trimble, Somu Perianayagam, Saumya Debray, Gregory Andrews Computer Science Department.

Code Compaction of an Operating System Kernel Haifeng He, John Trimble, Somu Perianayagam, Saumya Debray, Gregory Andrews Computer Science Department.
Carnegie Mellon Spiral: Automatic Generation of Industry Strength Performance Libraries Franz Franchetti Carnegie Mellon University www.ece.cmu.edu/~franzf.

Carnegie Mellon Spiral: Automatic Generation of Industry Strength Performance Libraries Franz Franchetti Carnegie Mellon University
Carnegie Mellon Lessons From Building Spiral The C Of My Dreams Franz Franchetti Carnegie Mellon University Lessons From Building Spiral The C Of My Dreams.

Carnegie Mellon Lessons From Building Spiral The C Of My Dreams Franz Franchetti Carnegie Mellon University Lessons From Building Spiral The C Of My Dreams.
A Matlab Playground for JPEG Andy Pekarske Nikolay Kolev.

A Matlab Playground for JPEG Andy Pekarske Nikolay Kolev.
ECE 562 Computer Architecture and Design Project: Improving Feature Extraction Using SIFT on GPU Rodrigo Savage, Wo-Tak Wu.

ECE 562 Computer Architecture and Design Project: Improving Feature Extraction Using SIFT on GPU Rodrigo Savage, Wo-Tak Wu.
1 Outline  Introduction to JEPG2000  Why another image compression technique  Features  Discrete Wavelet Transform  Wavelet transform  Wavelet implementation.

1 Outline  Introduction to JEPG2000  Why another image compression technique  Features  Discrete Wavelet Transform  Wavelet transform  Wavelet implementation.
Carnegie Mellon 1 Optimal Scheduling “in a lifetime” for the SPIRAL compiler Frédéric de Mesmay Theodoros Strigkos based on Y. Voronenko’s idea.

Carnegie Mellon 1 Optimal Scheduling “in a lifetime” for the SPIRAL compiler Frédéric de Mesmay Theodoros Strigkos based on Y. Voronenko’s idea.
Application of Generalized Representations for Image Compression Application of Generalized Representations for Image Compression using Vector Quantization.

Application of Generalized Representations for Image Compression Application of Generalized Representations for Image Compression using Vector Quantization.
A Fast Fourier Transform Compiler Silvio D Carnevali.

A Fast Fourier Transform Compiler Silvio D Carnevali.
Carnegie Mellon μ-op Fission: Hyper-threading without the Hyper-headache Anthony Cartolano Robert Koutsoyannis Daniel S. McFarlin Carnegie Mellon University.

Carnegie Mellon μ-op Fission: Hyper-threading without the Hyper-headache Anthony Cartolano Robert Koutsoyannis Daniel S. McFarlin Carnegie Mellon University.
Zephyr By Shannon Poskus. What is Zephyr? Zephyr is one of two components of the National Compiler Infrastructure (NCI) project Co-funded by DARPA and.

Zephyr By Shannon Poskus. What is Zephyr? Zephyr is one of two components of the National Compiler Infrastructure (NCI) project Co-funded by DARPA and.
Carnegie Mellon Adaptive Mapping of Linear DSP Algorithms to Fixed-Point Arithmetic Lawrence J. Chang Inpyo Hong Yevgen Voronenko Markus Püschel Department.

Carnegie Mellon Adaptive Mapping of Linear DSP Algorithms to Fixed-Point Arithmetic Lawrence J. Chang Inpyo Hong Yevgen Voronenko Markus Püschel Department.
A Multiresolution Symbolic Representation of Time Series

A Multiresolution Symbolic Representation of Time Series
Automatic Generation of Customized Discrete Fourier Transform IPs Grace Nordin, Peter A. Milder, James C. Hoe, Markus Püschel Carnegie Mellon University.

Automatic Generation of Customized Discrete Fourier Transform IPs Grace Nordin, Peter A. Milder, James C. Hoe, Markus Püschel Carnegie Mellon University.

Similar presentations

Ads by Google