scispace - formally typeset
C

Charles R. Yount

Researcher at Intel

Publications -  48
Citations -  777

Charles R. Yount is an academic researcher from Intel. The author has contributed to research in topics: Operand & Xeon Phi. The author has an hindex of 14, co-authored 48 publications receiving 721 citations.

Papers
More filters
Patent

Instruction and logic to provide vector horizontal compare functionality

TL;DR: In this article, an instruction specifying: a destination operand, a size of vector elements, a source operand and a mask corresponding to a portion of the vector element data fields in the source operands, corresponding to the mask and compare the values for equality.
Patent

Vector friendly instruction format and execution thereof

TL;DR: A vector friendly instruction format as mentioned in this paper has a plurality of fields including a base operation field, a modifier field, an augmentation operation field and a data element width field, wherein the first instruction format supports different versions of base operations and different augmentation operations through placement of different values in the base operator field, the modifier field and the alpha field.
Proceedings ArticleDOI

YASK-yet another stencil kernel: a framework for HPC stencil code-generation and tuning

TL;DR: The YASK (Yet Another Stencil Kernel) framework is described, including domain-specific-languages (DSLs), code generators for stencil-equation and loop code, and a genetic-algorithm-based automated tuning tool.
Journal ArticleDOI

Architecture and Performance of Devito, a System for Automated Stencil Computation

TL;DR: The architecture of the Devito compiler, as well as the performance optimizations that are applied when generating code, are presented and the effectiveness of such performance optimizations is demonstrated using operators drawn from seismic imaging applications.
Proceedings ArticleDOI

Using Model Trees for Computer Architecture Performance Analysis of Software Applications

TL;DR: A model-tree based approach based on the M5' algorithm is implemented and validated that accounts for event interactions and workload characteristics, attesting it as a sound approach for performance analysis of modern superscalar machines.