Add to ORKGInternational audienceWe propose a new systematic approach for minimal-precisioncomputations. This approach is reliable, general, comprehensive,high-performance, and realistic. Although the proposed systemis still in development, this presentation shows that the systemcould be constructed by combining already available (developed)in-house technologies as well as extending them
For many scientific calculations, particularly those involving empirical data, IEEE 32-bit floating-...
Many algorithms feature an iterative loop that converges to the result of interest. The numerical op...
This paper proposes a unique hardware-software collaborative strategy to remove useless work at 16-b...
International audienceWe propose a new systematic approach for minimal-precisioncomputations. This a...
International audienceWe proposed a new concept of weak numerical reproducibilityand a systematic ap...
The present paper is a continuation of research in parallel information processing based on the tabu...
For many years, computing systems rely on guaranteed numerical precision of each step in complex com...
International audienceA number of features of today’s high-performance computers make it ...
Mixed precision is an approximate computing technique that can be used to trade-off computation accu...
International audienceA new design paradigm, Approximate Computing (AxC), has been established to in...
Proceedings of: First International Workshop on Sustainable Ultrascale Computing Systems (NESUS 2014...
In this paper, hardware and software techniques are presented for improving the Throughput (defined ...
Today's computer architectures and semiconductor technologies are facing major challenges making the...
Abstract—For many scientific calculations, particularly those involving empirical data, IEEE 32-bit ...
Abstract — Approximate computing has recently emerged as a promising approach to energy-efficient de...
For many scientific calculations, particularly those involving empirical data, IEEE 32-bit floating-...
Many algorithms feature an iterative loop that converges to the result of interest. The numerical op...
This paper proposes a unique hardware-software collaborative strategy to remove useless work at 16-b...
International audienceWe propose a new systematic approach for minimal-precisioncomputations. This a...
International audienceWe proposed a new concept of weak numerical reproducibilityand a systematic ap...
The present paper is a continuation of research in parallel information processing based on the tabu...
For many years, computing systems rely on guaranteed numerical precision of each step in complex com...
International audienceA number of features of today’s high-performance computers make it ...
Mixed precision is an approximate computing technique that can be used to trade-off computation accu...
International audienceA new design paradigm, Approximate Computing (AxC), has been established to in...
Proceedings of: First International Workshop on Sustainable Ultrascale Computing Systems (NESUS 2014...
In this paper, hardware and software techniques are presented for improving the Throughput (defined ...
Today's computer architectures and semiconductor technologies are facing major challenges making the...
Abstract—For many scientific calculations, particularly those involving empirical data, IEEE 32-bit ...
Abstract — Approximate computing has recently emerged as a promising approach to energy-efficient de...
For many scientific calculations, particularly those involving empirical data, IEEE 32-bit floating-...
Many algorithms feature an iterative loop that converges to the result of interest. The numerical op...
This paper proposes a unique hardware-software collaborative strategy to remove useless work at 16-b...