User time measures the time spent by the processor executing code. This doesn`t count anything else that might be running, or the CPU time spent in the kernel (for example, for file I/O). The time of the wall clock is exactly what it says, the elapsed time measured by the clock on your wall (or wristwatch) The term wall clock has also been widely used in computer simulation to distinguish between (1) simulation time (often compressed or extended) and (2) time as it passes for the user of the simulation tool.    CPU time measures the total time spent by the CPU executing your code or the elements requested by your code. This includes kernel time. Wall time is therefore different from CPU time, which only measures the time that the processor is actively working on a particular task. The difference between the two may be due to factors dependent on architecture and execution, such as scheduled delays or waiting for system resources to become available. Let`s take the example of a mathematical program that reports that it used “CPU time 0m0.04s, wall time 6m6.01s”. This means that while the program was active for six minutes and one second, the computer`s processor spent only 4/100 of a second performing calculations for the program during that time. Another definition of “wall time” is the measurement of time via a separate, independent clock as opposed to the internal time of the local system, i.e.
in terms of the difference between the two.  Wall clock time is the time you would get if you measured the running time with a stopwatch. User time is the time it takes for the processor to execute only the code on your behalf (this does not include system calls that your task can perform). CPU time is the time it takes for the CPU to actively execute your code and include possible system calls. If the wall clock time is the processor time, wait for the hard disk, network, or other devices. Real-time elapsed time, real-time time, wall clock, wall time, or wall time is the actual time it takes between the beginning and end of a computer program. In other words, it is the difference between when a task is completed and when the task was started. The term “CPU user time” can be a bit misleading at first. To be clear, total time (actual CPU time) is the combination of the time the CPU spends performing an action on a program and the time the CPU spends making system calls to the kernel on behalf of the program.
When a program traverses a matrix, it accumulates the user`s CPU time. Conversely, when a program makes a system call such as exec or fork, it accumulates system CPU time. Conversely, programs running in parallel on more than one processing unit can consume CPU time several times over their elapsed time. Since the definition of elapsed time is not trivial in simultaneous calculation, conceptualizing elapsed time measured on a separate, independent wall clock is convenient. (also wall clock time) 1. “Real” time (what the clock shows on the wall), as opposed to the idea of system clock time. 2. The actual execution of a program, as opposed to the number of ticks required to run it (on a timeshare system, these are always different, because no one program receives all ticks, and on multiprocessor systems with good thread support, you can get more CPU time than real time). We perform IT tasks with GridEngine. Each task returns 3 different times: System CPU time is the time spent in the kernel, usually the time spent handling system calls. Detailed man page: linux.die.net/man/1/time “real-time” in the sense of “wall time” should not be confused with real-time computing.
The “user time” measure is probably better suited for measuring the performance of different tasks, as it is less affected by other things happening on the system. Wall time, also known as real-time or wall clock, refers to the elapsed time determined by a stopwatch such as a wristwatch or wall clock. (The reference to a wall clock is how the term originally got its name.) Wall clock time is the actual time it takes for a computer to complete a task. This is the sum of three terms: CPU time, I/O time, and communication channel delay (for example, when data is scattered across multiple machines). Unlike CPU time, which only measures the time the processor is actively working on a particular task, wall time measures the total time it takes to complete the process. The difference between the two is the time that passes due to scheduled delays or waiting for resources to become available. In practical computing, wall time is the actual time, usually measured in seconds, that it takes for a program to perform or perform the tasks assigned to it. When the computer is multitasking, the wall time is determined separately for each program and depends on how the microprocessor distributes resources among the programs.