Mixed-precision is a paradigm that tries to combine computations with different levels of precision to compose results. This approach has been used extensively to optimize scientific applications and has shown speed and energy gains, without causing any relevant precision loss. However, to exploit mixed precision opportunities most applications need to be recompiled to use different instructions and types. Thus, in this work, we present a new floating-point unit design, able to automatically decide when an instruction should be executed using less precision, without recompilation or user direct intervention. Our proposal takes advantage of ad-hoc polymorphism to perform computations with different data types, dynamically selecting a proper ...
International audienceFloating-Point (FP) units in processors are generally limited to supporting a ...
International audienceThe popularity and community-driven development model of RISCV have opened man...
International audienceThis paper presents a multiple-precision binary floating-point library, writte...
Mixed precision is an approximate computing technique that can be used to trade-off computation accu...
Precision tuning consists of finding the least floating-point formats enabling a program to compute ...
International audienceFull-precision Floating-Point Units (FPUs) can be a source of extensive hardwa...
Full-precision Floating-Point Units (FPUs) can be a source of extensive hardware overhead in general...
<p>In this thesis, we design frameworks for efficient and accurate floating point computation. The p...
Abstract. Most mathematical formulae are defined in terms of operations on real numbers, but compute...
This paper presents the design and the implementation of a fully combinatorial floating point unit (...
Traditional optimization methods rely on the use of single-precision floating point arithmetic, whic...
As scientific computation continues to scale, it is crucial to use floating-point arithmetic process...
International audienceOptimizing compilers for high performance computing only support IEEE 754 floa...
In recent years approximate computing has been extensively explored as a paradigm to design hardware...
Reduced-precision floating-point (FP) arithmetic is being widely adopted to reduce memory footprint ...
International audienceFloating-Point (FP) units in processors are generally limited to supporting a ...
International audienceThe popularity and community-driven development model of RISCV have opened man...
International audienceThis paper presents a multiple-precision binary floating-point library, writte...
Mixed precision is an approximate computing technique that can be used to trade-off computation accu...
Precision tuning consists of finding the least floating-point formats enabling a program to compute ...
International audienceFull-precision Floating-Point Units (FPUs) can be a source of extensive hardwa...
Full-precision Floating-Point Units (FPUs) can be a source of extensive hardware overhead in general...
<p>In this thesis, we design frameworks for efficient and accurate floating point computation. The p...
Abstract. Most mathematical formulae are defined in terms of operations on real numbers, but compute...
This paper presents the design and the implementation of a fully combinatorial floating point unit (...
Traditional optimization methods rely on the use of single-precision floating point arithmetic, whic...
As scientific computation continues to scale, it is crucial to use floating-point arithmetic process...
International audienceOptimizing compilers for high performance computing only support IEEE 754 floa...
In recent years approximate computing has been extensively explored as a paradigm to design hardware...
Reduced-precision floating-point (FP) arithmetic is being widely adopted to reduce memory footprint ...
International audienceFloating-Point (FP) units in processors are generally limited to supporting a ...
International audienceThe popularity and community-driven development model of RISCV have opened man...
International audienceThis paper presents a multiple-precision binary floating-point library, writte...