Copyright © 2000-2007, Intel Corporation.
Function Trunc
The Trunc function computes a rounded towards zero integer value for each vector element.
Performance:
| Intel(R) Xeon(R) processor 5100 Series | 45nm
Intel(R) Core(TM)2 Duo processor |
Intel(R) Itanium(R) 2 processor | ||
| single | HA | 2.22 | 1.04 | 2.05 |
| LA | 2.22 | 1.04 | 2.05 | |
| EP | 2.22 | 1.04 | 2.05 | |
| double | HA | 4.27 | 1.92 | 2.06 |
| LA | 4.27 | 1.92 | 2.06 | |
| EP | 4.27 | 1.92 | 2.06 | |
Notes:
1) Units - CPE (Clocks per Element)
2) Performance was measured on "working" interval (double precision: [-5.0, 25.0]; single precision: [-3.0, 9.0])
3) Data - vectors of 1000 elements with random generated numbers.
Accuracy:
| Intel(R) Xeon(R) processor 5100 Series |
45nm Intel(R) Core(TM)2 Duo processor |
Intel(R) Itanium(R) 2 processor | ||
| single | HA | 0.00 | 0.00 | 0.00 |
| LA | 0.00 | 0.00 | 0.00 | |
| EP | 0.00 | 0.00 | 0.00 | |
| double | HA | 0.00 | 0.00 | 0.00 |
| LA | 0.00 | 0.00 | 0.00 | |
| EP | 0.00 | 0.00 | 0.00 | |
Performance Graphs:
Copyright © 2000-2007, Intel Corporation.