Out-of-order Execution - History

History

Out-of-order execution is a restricted form of data flow computation, which was a major research area in computer architecture in the 1970s and early 1980s. Important academic research in this subject was led by Yale Patt and his HPSm simulator. A paper by James E. Smith and A.R. Pleszkun, published in 1985 completed the scheme by describing how the precise behavior of exceptions could be maintained in out-of-order machines.

Arguably the first machine to use out-of-order execution was the CDC 6600 (1964), which used a scoreboard to resolve conflicts. In modern usage, such scoreboarding is considered to be in-order execution, not out-of-order execution, since such machines stall on the first RAW (Read After Write) conflict. Strictly speaking, such machines initiate execution in-order, although they may complete execution out-of-order.

About three years later, the IBM 360/91 (1966) introduced Tomasulo's algorithm, supporting full out-of-order execution.

In 1990, IBM introduced the first out-of-order microprocessor, the POWER1, although out-of-order execution was limited to floating point instructions only.

Throughout the 1990s out-of-order execution became more common, and was featured in the IBM/Motorola PowerPC 601 (1993), Fujitsu/HAL SPARC64 (1995), Intel Pentium Pro (1995), MIPS R10000 (1996), HP PA-8000 (1996), AMD K5 (1996) and DEC Alpha 21264 (1998). Notable exceptions to this trend include the Sun UltraSPARC, HP/Intel Itanium, Transmeta Crusoe, Intel Atom, and the IBM POWER6.

The logical complexity of the out-of-order schemes was the reason that this technique did not reach mainstream machines until the mid-1990s. Many low-end processors meant for cost-sensitive markets still do not use this paradigm due to the large silicon area that is required to build this class of machine. Low power usage is another design goal that's harder to achieve with an OoOE design.