Corpus ID: 28848620

Analyzing CUDA’s Compiler through the Visualization of Decoded GPU Binaries

@inproceedings{Nugteren2012AnalyzingCC,
  title={Analyzing CUDA’s Compiler through the Visualization of Decoded GPU Binaries},
  author={C. Nugteren and B. Mesman and H. Corporaal},
  year={2012}
}
  • C. Nugteren, B. Mesman, H. Corporaal
  • Published 2012
  • Computer Science
  • With GPU architectures becoming increasingly important due to their large number of parallel processors, NVIDIA’s CUDA environment is becoming widely used to support general purpose applications. To efficiently use the parallel processing power, programmers need to efficiently parallelize and map their algorithms. The difficulty of this task leads to the idea to investigate CUDA’s compiler. Part of the compiler in the CUDA tool-chain is entirely undocumented, as is its output. To draw… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 17 REFERENCES
    An analytical model for a GPU architecture with memory-level and thread-level parallelism awareness
    • 630
    • PDF
    Dynamic Warp Formation and Scheduling for Efficient GPU Control Flow
    • 456
    • PDF
    GPGPU: general purpose computation on graphics hardware
    • 238
    Translating GPU Binaries to Tiered SIMD Architectures with Ocelot
    • 44
    • PDF
    Mapping computational concepts to GPUs
    • 217
    Register allocation via graph coloring
    • 209
    Many-Core vs. Many-Thread Machines: Stay Away From the Valley
    • 101
    • PDF
    NVIDIA Tesla: A Unified Graphics and Computing Architecture
    • 1,334
    • Highly Influential
    • PDF