FPU implementations with denormalized numbers

@article{Schwarz2005FPUIW,
  title={FPU implementations with denormalized numbers},
  author={E. Schwarz and M. Schmookler and S. D. Trong},
  journal={IEEE Transactions on Computers},
  year={2005},
  volume={54},
  pages={825-836}
}
Denormalized numbers are the most difficult type of numbers to implement in floating-point units. They are so complex that certain designs have elected to handle them in software rather than in hardware. Traps to software can result in long execution times, which renders denormalized numbers useless to programmers. This does not have to happen. With a small amount of additional hardware, denormalized numbers and underflows can be handled close to the speed of normalized numbers. This paper… Expand
41 Citations
P6 Binary Floating-Point Unit
  • 36
  • PDF
Advanced Clockgating Schemes for Fused-Multiply-Add-Type Floating-Point Units
  • 17
  • PDF
Binary Floating-Point Unit Design
  • 15
Testing of floating point unit using BIST with parallelism
Floating-Point Computer Arithmetic
A Novel Rounding Algorithm for a High Performance IEEE 754 Double-Precision Floating-Point Multiplier
4GHz+ low-latency fixed-point and binary floating-point execution units for the POWER6 processor
  • B. Curran, B. McCredie, +6 authors A. Goyal
  • Computer Science
  • 2006 IEEE International Solid State Circuits Conference - Digest of Technical Papers
  • 2006
  • 19
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 25 REFERENCES
Hardware implementations of denormalized numbers
  • 24
167 MHz radix-4 floating point multiplier
  • R. Yu, Gregory B. Zyner
  • Computer Science, Mathematics
  • Proceedings of the 12th Symposium on Computer Arithmetic
  • 1995
  • 75
High performance floating-point unit with 116 bit wide divider
  • 23
Floating-point fused multiply-add with reduced latency
  • T. Lang, J.D. Bruguera
  • Computer Science
  • Proceedings. IEEE International Conference on Computer Design: VLSI in Computers and Processors
  • 2002
  • 44
  • PDF
Design of the IBM RISC System/6000 Floating-Point Execution Unit
  • 210
A General Proof for Overlapped Multiple-Bit Scanning Multiplications
  • 53
Second-generation RISC floating point with multiply-add fused
  • 119
  • PDF
A low-power, high-speed implementation of a PowerPC/sup TM/ microprocessor vector extension
  • 45
IA-64 and elementary functions - speed and precision
  • 167
1 GHz HAL SPARC64/sup R/ Dual Floating Point Unit with RAS features
  • 35
...
1
2
3
...