3.2.3. Performance goals

Most applications require tuning to gain the best performance from vectorization. There is always some overhead so the theoretical maximum performance cannot be reached. For example, the NEON unit can process four single-precision floats at one time. This means that the theoretical maximum performance for a floating-point application, is a factor of four over the original scalar non vectorized code. Given typical overheads, a reasonable goal for a whole floating-point application is to aim for a 50% improvement on performance over the scalar code. For large applications that are not completely vectorizable, achieving a 25% improvement on performance over the scalar code is a reasonable goal.

See Improving performance for more information.

Copyright © 2007 ARM Limited. All rights reserved.ARM DUI 0350A
Non-Confidential