Constant propagation with conditional branches
ACM Transactions on Programming Languages and Systems (TOPLAS)
Efficiently computing static single assignment form and the control dependence graph
ACM Transactions on Programming Languages and Systems (TOPLAS)
Improvements to graph coloring register allocation
ACM Transactions on Programming Languages and Systems (TOPLAS)
ACM Transactions on Programming Languages and Systems (TOPLAS)
Concurrent programming in ERLANG (2nd ed.)
Concurrent programming in ERLANG (2nd ed.)
Generational stack collection and profile-driven pretenuring
PLDI '98 Proceedings of the ACM SIGPLAN 1998 conference on Programming language design and implementation
Advanced compiler design and implementation
Advanced compiler design and implementation
Linear scan register allocation
ACM Transactions on Programming Languages and Systems (TOPLAS)
A high performance Erlang system
Proceedings of the 2nd ACM SIGPLAN international conference on Principles and practice of declarative programming
Assembling code for machines with span-dependent instructions
Communications of the ACM
Native code compilation of Erlang's bit syntax
Proceedings of the 2002 ACM SIGPLAN workshop on Erlang
The HiPE/x86 Erlang Compiler: System Description and Performance Evaluation
FLOPS '02 Proceedings of the 6th International Symposium on Functional and Logic Programming
Unboxed compilation of floating point arithmetic in a dynamically typed language environment
IFL'02 Proceedings of the 14th international conference on Implementation of functional languages
TinyMT pseudo random number generator for Erlang
Proceedings of the eleventh ACM SIGPLAN workshop on Erlang workshop
| Hi-index | 0.00 |
Erlang is a concurrent functional language designed for developing large-scale, distributed, fault-tolerant systems. The primary implementation of the language is the Erlang/OTP system from Ericsson. Even though Erlang/OTP is by default based on a virtual machine interpreter, it nowadays also includes the HiPE (High Performance Erlang) native code compiler as a fully integrated component. This paper describes the recently developed port of HiPE to the AMD64 architecture. We discuss technical issues that had to be addressed when developing the port, decisions we took and why, and report on the speedups (compared with BEAM) which HiPE/AMD64 achieves across a range of Erlang programs and how these compare with speedups for the more mature SPARC and x86 back-ends.