Options for Denormal Representation in Logarithmic Arithmetic

Mark Arnold 1 Sylvain Collange 2
2 ALF - Amdahl's Law is Forever
Inria Rennes – Bretagne Atlantique , IRISA-D3 - ARCHITECTURE
Abstract : Economical hardware often uses a FiXed-point Number System (FXNS), whose constant absolute precision is acceptable for many signal-processing algorithms. The almost-constant relative precision of the more expensive Floating-Point (FP) number system simplifies design, for example, by eliminating worries about FXNS overflow because the range of FP is much larger than FXNS for the same wordsize; however, primitive FP introduces another problem: underflow. The conventional Signed Logarithmic Number System (SLNS) offers similar range and precision as FP with much better performance (in terms of power, speed and area) for multiplication, division, powers and roots. Moderate-precision addition in SLNS uses table lookup with properties similar to FP (including underflow). This paper proposes a new number system, called the Denormal LNS (DLNS), which is a hybrid of the properties of FXNS and SLNS. The inspiration for DLNS comes from the denormal (aka subnormal) numbers found in IEEE-754 (that provide better, gradual underflow) and the μ-law often used for speech encoding; the novel DLNS circuit here allows arithmetic to be performed directly on such encoded data. The proposed approach allows customizing the range in which gradual underflow occurs. A wide gradual underflow range acts like FXNS; a narrow one acts like SLNS. The DLNS approach is most affordable for applications involving addition, subtraction and multiplication by constants, such as the Fast Fourier Transform (FFT). Simulation of an FFT application illustrates a moderate gradual underflow decreasing bit-switching activity 15% compared to underflow-free SLNS, at the cost of increasing application error by 30%. DLNS reduces switching activity 5% to 20% more than an abruptly-underflowing SLNS with one-half the error. Synthesis shows the novel circuit primarily consists of traditional SLNS addition and subtraction tables, with additional datapaths that allow the novel ALU to act on conventional SLNS as well as DLNS and mixed data, for a worst-case area overhead of 26%. For similar range and precision, simulation of Taylor-series computations suggest subnormal values in DLNS behave similarly to those in the IEEE-754 FP standard. Unlike SLNS, DLNS approach is quite costly for general (non-constant) multiplication, division and roots. To overcome this difficulty, this paper proposes two variation called Denormal Mitchell LNS (DMLNS) and Denormal Offset Mitchell LNS (DOMLNS), in which the well-known Mitchell's method makes the cost of general multiplication, division and roots closer to that of SLNS. Taylor-series computations suggest subnormal values in DMLNS and DOMLNS also behave similarly to those in the IEEE-754 FP standard. Synthesis shows that DMLNS and DOMLNS respectively have average area overheads of 25% and 17% compared to an equivalent SLNS 5-operation unit.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.inria.fr/hal-00909096
Contributor : Sylvain Collange <>
Submitted on : Monday, November 25, 2013 - 5:26:16 PM
Last modification on : Thursday, November 15, 2018 - 11:57:43 AM
Long-term archiving on : Monday, March 3, 2014 - 4:01:03 PM

File

arnold_denorm_tr.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00909096, version 1

Citation

Mark Arnold, Sylvain Collange. Options for Denormal Representation in Logarithmic Arithmetic. 2013. ⟨hal-00909096v1⟩

Share

Metrics

Record views

34

Files downloads

91