ixed precision is an approximate computing technique that can be used to trade-off computation accuracy for performance and/or energy. It can be applied to many error-tolerant applications, but manual precision tuning is both tedious and error-prone. Furthermore, the effectiveness of the technique heavily depends on hardware characteristics. Therefore, a hardware/software co-design approach is necessary for an effective exploitation of precision tuning opportunities offered by the applications. In this paper, we propose, based on the state of the art of precision tuning software and mixed precision hardware, a roadmap for the evolution of hardware designs and compiler-based precision tuning support, which is ongoing in the context of the Eu...
International audienceFull-precision Floating-Point Units (FPUs) can be a source of extensive hardwa...
Approximate Computing trades off computation accuracy against performance or energy efficiency. It i...
In recent years approximate computing has been extensively explored as a paradigm to design hardware...
ixed precision is an approximate computing technique that can be used to trade-off computation accur...
Mixed precision is an approximate computing technique that can be used to trade-off computation accu...
International audienceError-tolerating applications are increasingly common in the emerging field of...
The use of reduced precision to improve performance metrics such as computation latency and power co...
The precision used in an algorithm affects the error and performance of individual computations, the...
Writing mixed-precision kernels allows to achieve higher throughput together with outputs whose prec...
Precision tuning consists of finding the least floating-point formats enabling a program to compute ...
Abstract—This paper introduces a novel mixed precision methodology for mathematical optimisation. It...
This thesis introduces a novel methodology to realize accuracy-aware systems, which will help design...
We present taffo, a framework that automatically performs precision tuning to exploit the performanc...
With the ever-increasing energy-efficiency requirements for the computing platforms at the edge, pre...
The growing demands of the worldwide IT infrastructure stress the need for reduced power consumption...
International audienceFull-precision Floating-Point Units (FPUs) can be a source of extensive hardwa...
Approximate Computing trades off computation accuracy against performance or energy efficiency. It i...
In recent years approximate computing has been extensively explored as a paradigm to design hardware...
ixed precision is an approximate computing technique that can be used to trade-off computation accur...
Mixed precision is an approximate computing technique that can be used to trade-off computation accu...
International audienceError-tolerating applications are increasingly common in the emerging field of...
The use of reduced precision to improve performance metrics such as computation latency and power co...
The precision used in an algorithm affects the error and performance of individual computations, the...
Writing mixed-precision kernels allows to achieve higher throughput together with outputs whose prec...
Precision tuning consists of finding the least floating-point formats enabling a program to compute ...
Abstract—This paper introduces a novel mixed precision methodology for mathematical optimisation. It...
This thesis introduces a novel methodology to realize accuracy-aware systems, which will help design...
We present taffo, a framework that automatically performs precision tuning to exploit the performanc...
With the ever-increasing energy-efficiency requirements for the computing platforms at the edge, pre...
The growing demands of the worldwide IT infrastructure stress the need for reduced power consumption...
International audienceFull-precision Floating-Point Units (FPUs) can be a source of extensive hardwa...
Approximate Computing trades off computation accuracy against performance or energy efficiency. It i...
In recent years approximate computing has been extensively explored as a paradigm to design hardware...