Highly optimized programs are prone to bit rot, where performance quickly becomes suboptimal in the face of new hardware and com-piler techniques. In this paper we show how to automatically lift performance-critical stencil kernels from a stripped x86 binary and generate the corresponding code in the high-level domain-specific language Halide. Using Halide’s state-of-the-art optimizations tar-geting current hardware, we show that new optimized versions of these kernels can replace the originals to rejuvenate the application for newer hardware. The original optimized code for kernels in stripped binaries is nearly impossible to analyze statically. Instead, we rely on dynamic traces to regenerate the kernels. We perform buffer structure recon...
Hardware-Software Partitioning and decompilation is a key issue in the Codesign of embedded systems....
\u3cp\u3eEfficient code generation for image processing applications continues to pose a challenge i...
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Comput...
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Comput...
Our aim is to apply program transformations to stencil codes, in order to yield highest possible per...
Many image processing tasks are naturally expressed as a pipeline of small computational kernels kno...
Earth system modeling computations use stencils extensively while running many kernels. Optimal codi...
Communicated by Guest Editors Our aim is to apply program transformations to stencil codes in order ...
There are many security tools and techniques for finding bugs, but many of them assume access to sou...
Specialized Digital Signal Processors (DSPs) play an important role in power-efficient, high-perform...
International audienceStencil kernels arise in many scientific codes as the result from dis-cretizin...
Automatic library generators, such as ATLAS [11], Spi-ral [8] and FFTW [2], are promising technologi...
Image processing applications typically involve data-oriented kernels with limited control divergenc...
The growth of data to be processed in the Oil & Gas industry matches the requirements imposed by evo...
This work introduces a generalized framework for automatically tuning stencil computations to achiev...
Hardware-Software Partitioning and decompilation is a key issue in the Codesign of embedded systems....
\u3cp\u3eEfficient code generation for image processing applications continues to pose a challenge i...
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Comput...
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Comput...
Our aim is to apply program transformations to stencil codes, in order to yield highest possible per...
Many image processing tasks are naturally expressed as a pipeline of small computational kernels kno...
Earth system modeling computations use stencils extensively while running many kernels. Optimal codi...
Communicated by Guest Editors Our aim is to apply program transformations to stencil codes in order ...
There are many security tools and techniques for finding bugs, but many of them assume access to sou...
Specialized Digital Signal Processors (DSPs) play an important role in power-efficient, high-perform...
International audienceStencil kernels arise in many scientific codes as the result from dis-cretizin...
Automatic library generators, such as ATLAS [11], Spi-ral [8] and FFTW [2], are promising technologi...
Image processing applications typically involve data-oriented kernels with limited control divergenc...
The growth of data to be processed in the Oil & Gas industry matches the requirements imposed by evo...
This work introduces a generalized framework for automatically tuning stencil computations to achiev...
Hardware-Software Partitioning and decompilation is a key issue in the Codesign of embedded systems....
\u3cp\u3eEfficient code generation for image processing applications continues to pose a challenge i...
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Comput...