Usable assembly language for GPUs: a success story

Daniel J.  Bernstein; Hsieh-Chung Chen; Chen-Mou Cheng; Tanja Lange; Ruben Niederhagen; Peter Schwabe; Bo-Yin Yang

Paper 2012/137

Usable assembly language for GPUs: a success story

Daniel J. Bernstein, Hsieh-Chung Chen, Chen-Mou Cheng, Tanja Lange, Ruben Niederhagen, Peter Schwabe, and Bo-Yin Yang

Abstract

The NVIDIA compilers nvcc and ptxas leave the programmer with only very limited control over register allocation, register spills, instruction selection, and instruction scheduling. In theory a programmer can gain control by writing an entire kernel in van der Laan's cudasm assembly language, but this requires tedious, error-prone tracking of register assignments. This paper introduces a higher-level assembly language, qhasm-cudasm, that allows much faster programming while providing the same amount of control over the GPU. This language has been used successfully to build a 90000-machine-instruction kernel for a computation described in detail in the paper, the largest public cryptanalytic project in history. The best GTX 295 speed that has been obtained for this computation with nvcc and ptxas is 25 million iterations per second; the best GTX 295 speed that has been obtained with qhasm-cudasm is 63 million iterations per second.

Metadata

Available format(s): PDF
Category: Implementation
Publication info: Published elsewhere. Unknown where it was published
Keywords: GPUs assembly language ECC2K-130 Pollard rho register allocation.
Contact author(s): tanja @ hyperelliptic org
History: 2012-03-22: received
Short URL: https://ia.cr/2012/137
License: CC BY

BibTeX

@misc{cryptoeprint:2012/137,
      author = {Daniel J.  Bernstein and Hsieh-Chung Chen and Chen-Mou Cheng and Tanja Lange and Ruben Niederhagen and Peter Schwabe and Bo-Yin Yang},
      title = {Usable assembly language for {GPUs}: a success story},
      howpublished = {Cryptology {ePrint} Archive, Paper 2012/137},
      year = {2012},
      url = {https://eprint.iacr.org/2012/137}
}