scispace - formally typeset
M

Mircea Namolaru

Researcher at IBM

Publications -  8
Citations -  453

Mircea Namolaru is an academic researcher from IBM. The author has contributed to research in topics: Compiler & Optimizing compiler. The author has an hindex of 6, co-authored 8 publications receiving 407 citations. Previous affiliations of Mircea Namolaru include University of Haifa.

Papers
More filters
Journal ArticleDOI

Milepost GCC: Machine Learning Enabled Self-tuning Compiler

TL;DR: Milepost GCC is described, the first publicly-available open-source machine learning-based compiler that automatically adapts the internal optimization heuristic at function-level granularity to improve execution time, code size and compilation time of a new program on a given architecture.

MILEPOST GCC: machine learning based research compiler

TL;DR: MILEPOST 1 GCC is described, a machine-learning-based compiler that automatically adjusts its optimization heuristics to improve the execution time, code size, or compilation time of specific programs on different architectures.
Proceedings ArticleDOI

Practical aggregation of semantical program properties for machine learning based optimization

TL;DR: A general method for systematically generating numerical features from a program, which puts no restrictions on how to logically and algebraically aggregate semantical properties into numerical features is proposed.
Patent

Method and apparatus for improving colorability of constrained nodes in an interference graph within a computer system

TL;DR: In this paper, a method and apparatus for coloring an interference graph yields a higher number of colored nodes by taking into consideration the colors of neighbors of a node's uncolored constrained neighbors.
Proceedings ArticleDOI

Compiling for an indirect vector register architecture

TL;DR: This paper modified an existing register allocator to target all available registers and added a post-pass to rename live-ranges considering spatial locality and interaction among operand types, and presents several compilation approaches to deal with the mapping mechanism and an outer-loop vectorization transformation developed to promote the use of many vector registers.