International audienceGrowing interest in graphics processing units has brought renewed attention to the Single Instruction Multiple Data (SIMD) execution model. SIMD machines give application developers tremendous computational power; however, programming them is still challenging. In particular, developers must deal with memory and control-flow divergences. These phenomena stem from a condition that we call data divergence, which occurs whenever two processing elements (PEs) see the same variable name holding different values. This article introduces divergence analysis, a static analysis that discovers data divergences. This analysis, currently deployed in an industrial quality compiler, is useful in several ways: it improves the transla...
International audienceSingle-Instruction Multiple-Thread (SIMT) micro-architectures implemented in G...
International audienceUsing SIMD instructions is essential in modern processor architecture for high...
Increasing single instruction multiple data (SIMD) capabilities in modern hardware allows for compil...
International audienceGrowing interest in graphics processing units has brought renewed attention to...
The rise of graphics processing units in high-performance computing is bringing renewed interest in ...
The rising popularity of graphics processing units is bringing renewed interest in code optimization...
Graphic processing units (GPUs) are composed of a group of single-instruction multiple data (SIMD) s...
We propose a compiler analysis pass for programs expressed in the Single Program, Multiple Data (SPM...
National audienceParallel architectures following the SIMT model such as GPUs benefit from applicati...
Parallel architectures following the SIMT model such as GPUs benefit from application regularity by ...
Abstract—Data-parallel architectures must provide efficient support for complex control-flow constru...
International audienceThe increasing popularity of Graphics Processing Units (GPUs), has brought ren...
Vectorizing compilers employ divergence analysis to detect at which program point a specific variabl...
Parallel architectures following the SIMT model such as GPUs benefit from application regularity by ...
The energy costs of data movement are limiting the performance scaling of future generations of high...
International audienceSingle-Instruction Multiple-Thread (SIMT) micro-architectures implemented in G...
International audienceUsing SIMD instructions is essential in modern processor architecture for high...
Increasing single instruction multiple data (SIMD) capabilities in modern hardware allows for compil...
International audienceGrowing interest in graphics processing units has brought renewed attention to...
The rise of graphics processing units in high-performance computing is bringing renewed interest in ...
The rising popularity of graphics processing units is bringing renewed interest in code optimization...
Graphic processing units (GPUs) are composed of a group of single-instruction multiple data (SIMD) s...
We propose a compiler analysis pass for programs expressed in the Single Program, Multiple Data (SPM...
National audienceParallel architectures following the SIMT model such as GPUs benefit from applicati...
Parallel architectures following the SIMT model such as GPUs benefit from application regularity by ...
Abstract—Data-parallel architectures must provide efficient support for complex control-flow constru...
International audienceThe increasing popularity of Graphics Processing Units (GPUs), has brought ren...
Vectorizing compilers employ divergence analysis to detect at which program point a specific variabl...
Parallel architectures following the SIMT model such as GPUs benefit from application regularity by ...
The energy costs of data movement are limiting the performance scaling of future generations of high...
International audienceSingle-Instruction Multiple-Thread (SIMT) micro-architectures implemented in G...
International audienceUsing SIMD instructions is essential in modern processor architecture for high...
Increasing single instruction multiple data (SIMD) capabilities in modern hardware allows for compil...