• What exactly is a full implementation of ARMv8.2-A?
    The technical spec for ARM Cortex A-75 claims that it supports a full implementation of ARMv8.2-A. The documents I have been able to reference only point to ARMv8A. Specifically I'm looking for what ARMv8...
  • Is Advanced-SIMD supported in Cortex-R5F?
    Hi, I have a Cortex-R5F core in which integration register value CPACR.ASEDIS = 1 and CPACR.D32DIS = 1m which says Advanced SIMD is not available. However, in ARM Cortex-R5F Technical Reference Manual...
  • How to get absolute value of a 32-bit signed integer as fast as possible?
    Hi. I wonder how to calculate absolute value of a 32-bit signed integer in C as fast as possible. I saw that there is a FPU instruction VABS.F32, which do that in one cycle (above the floats). I thought...
  • Coding for Neon - Part 3: Matrix Multiplication
    In part 1 of this series we dealt with how to load and store data with NEON, and part 2 involved how to handle the leftovers resulting from vector processing . Let us move on to doing some useful data...
  • Coding for Neon - Part 1: Load and Stores
    Arm's Neon technology is a 64/128-bit hybrid SIMD architecture designed to accelerate the performance of multimedia and signal processing applications, including video encoding and decoding, audio encoding...