Electronic Design

Vector Floating-Point Unit Speeds ARM9

VECTOR FLOATING-POINT UNIT SPEEDS ARM9 NXP’s 90-nm, 208-MHz LPC32x0 is based on ARM’s ARM926EJ-S core plus a vector floating-point (VFP) coprocessor. The chip has 256 kbytes of SRAM plus 32-kbyte ...
EDN

…and adds floating point unit to TriCore processor

Munich, Germany — Infineon Technologies AG has added a floating-point maths unit (FPU) to its library of system design blocks supporting the TriCore processor core. The addition of an FPU will improve ...
EDN

ARM adds floating-point unit to processor cores

SAN JOSE, Calif. — ARM Holdings plc will describe the addition of floating-point math capabilities to its ARM9 and ARM10 RISC processor cores at this week's Embedded Processor Forum. “Optional ...
Semiconductor Engineering

AI Chips Must Get The Floating-Point Math Right

Most AI chips and hardware accelerators that power machine learning (ML) and deep learning (DL) applications include floating-point units (FPUs). Algorithms used in neural networks today are often ...
Semiconductor Engineering

Achieving Numerical Precision And Design Customization With Flexible Floating-Point IP

As defined by the IEEE 754 standard, floating-point values are represented in three fields: a significand or mantissa, a sign bit for the significand and an exponent field. The exponent is a biased ...