2 Hits in 4.0 sec


Tao B. Schardl, William S. Moses, Charles E. Leiserson
2017 Proceedings of the 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming - PPoPP '17  
This paper explores how fork-join parallelism, as supported by concurrency platforms such as Cilk and OpenMP, can be embedded into a compiler's intermediate representation (IR).  ...  Tapir enables LLVM's existing compiler optimizations for serial code -including loop-invariant-code motion, commonsubexpression elimination, and tail-recursion eliminationto work with parallel control  ...  Ease of implementation Tapir's asymmetric representation of logically parallel tasks makes it relatively simple to integrate Tapir into an existing compiler's intermediate representation such as LLVM IR  ... 
doi:10.1145/3018743.3018758 fatcat:tonvhhd76fbvtmcvza522hc7ua

TapirXLA: Embedding Fork-Join Parallelism into the XLA Compiler in TensorFlow Using Tapir [article]

Tao B. Schardl, Siddharth Samsi
2019 arXiv   pre-print
This work introduces TapirXLA, a replacement for TensorFlow's XLA compiler that embeds recursive fork-join parallelism into XLA's low-level representation of code.  ...  This work studies how Tapir, a compiler intermediate representation (IR) that embeds parallelism into a mainstream compiler IR, can be incorporated into a compiler for machine learning to remedy this problem  ...  Tapir/LLVM [16] embeds fork-join parallelism into the intermediate representation of the LLVM compiler.  ... 
arXiv:1908.11338v1 fatcat:fpe4tmadwnbd3adplv4gfjbrpe