Will C. Meilander

Importance of SIMD computation reconsidered

In this paper, SIMD and MIMD solutions for the real-time database management problem of air traffic control are compared. A real-time database system is highly constrained in a multiprocessor and access to the common database must be made to a limited number of data elements at a time. This MIMD database access is contrasted with the comparable SIMD common database access, which can be several hundred times greater. This is true because the SIMD can simultaneously access thousands of pertinent records instead of the limited number in the MIMD. A relatively simple example is given of a problem that has a polynomial time solution using a SIMD but for which a polynomial time solution using a MIMD is normally impossible. The fact that SIMD can support a polynomial time solution for the air traffic control problem but this problem is normally considered to be intractable for multiprocessors argues against the common belief that MIMD have greater power than SIMD. SIMD are more efficient and powerful for some critically important application areas.

Comparisons of air traffic control implementations on an associative processor with a MIMD and consequences for parallel computing

This paper has two complementary focuses. The first is the system design and algorithmic development for air traffic control (ATC) using an associative SIMD processor (AP). The second is the comparison of this implementation with a multiprocessor implementation and the implications of these comparisons. This paper demonstrates how one application, ATC, can more easily, more simply, and more efficiently be implemented on an AP than is generally possible on other types of traditional hardware. The AP implementation of ATC will take advantage of its deterministic hardware to use static scheduling. The software will be dramatically smaller and cheaper to create and maintain. Likewise, a large AP system will be considerably simpler and cheaper than the MIMD hardware currently used. While APs were used for ATC-type applications earlier, these are no longer available. We use a ClearSpeed CSX600 accelerator to emulate the AP solutions of ATC on an ATC prototype consisting of eight data-intensive ATC real-time tasks. Its performance is compared with an 8-core multiprocessor (MP) using OpenMP. Our extensive experiments show that the AP implementation meets all deadlines while the MP will regularly miss a large number of deadlines. The AP code will be similar in size to sequential code for the same tasks and will avoid all of the additional support software needed with an MP to handle dynamic scheduling, load balancing, shared resource management, race conditions, false sharing, etc. At this point, essentially only MIMD systems are built. Many of the advantages of using an AP to solve an ATC problem would carry over to other applications. AP solutions for a wide variety of applications will be cited in this paper. Applications that involve a high degree of data parallelism such as database management, text processing, image processing, graph processing, bioinformatics, weather modeling, managing UAS (Unmanned Aircraft Systems or drones) etc., are good candidates for AP solutions. This raises the issue of whether we should routinely consider using non-multiprocessor hardware like the AP for applications where substantially simpler software solutions will normally exist. It also raises the question of whether the use of both AP and MIMD hardware in a single hetergeneous system could provide more versatility and efficiency. Either the AP or MIMD could serve as the primary system, but could hand off jobs it could not handle efficiently to the other system.

Overview of air traffic control using an SIMD COTS system

Air traffic control is an important application with demanding real-time database processing requirements. Systems that have been implemented using current approaches have typically been expensive, late, over-budget and have not performed up to specification. In part this is because, in attempting to meet the real-time requirements, developers have been driven to use complex algorithms and software for what are inherently relatively simple requirements. Our analysis indicates that the use of modern SIMD COTS systems enables guaranteed real-time performance to be achieved with simpler algorithms on modest amounts of hardware. This paper covers the system, the approach to the application and some of the solution details.

Scalable and Efficient Associative Processor Solution to Guarantee Real-Time Requirements for Air Traffic Control Systems

This paper proposes a solution to air traffic control (ATC) using an enhanced SIMD machine model called an Associative Processor (AP). Our solution differs from previous ATC systems that are designed for MIMD computers and have a great deal of difficulty meeting the predictability requirements for ATC, which are critical for meeting the strict certification standards required for safety critical software components. The proposed AP solution supports accurate predictions of worst case execution times and guarantees all deadlines are met. Furthermore, the software developed based on the AP model is much simpler and smaller in size than the current corresponding ATC software. As the associative processor is built from SIMD hardware, it is considerably cheaper and simpler than the MIMD hardware currently used to support ATC. We have designed a prototype for eight ATC real-time tasks on Clear Speed CSX600 accelerator that is used to emulate AP. Performance is evaluated in terms of execution time and predictability and is compared to the fastest host-only version implemented using OpenMP on an 8-core multiprocessor (MIMD). Our extensive experiments show that the AP implementation meets all deadlines that can be statically scheduled. To the contrary, some tasks miss their deadlines when implemented on MIMD. It is shown that the proposed AP solution will support accurate and meaningful predictions of worst case execution times and will guarantee that all deadlines are met.

An efficient Associative Processor solution to an Air Traffic Control problem

This paper proposes a SIMD solution to air traffic control (ATC) using an enhanced SIMD machine model called an Associative Processor (AP). This differs from previous ATC systems that are designed for MIMD computers and have a great deal of difficulty meeting the predictability requirements for ATC, which are critical for meeting the strict certification standards required for safety critical software components. The proposed SIMD solution will support accurate and meaningful predictions of worst case execution times and will guarantee all deadlines are met. Also, the software will be much simpler and smaller in size than the current corresponding ATC software. An important consequence of these features is that the V&V (Validation and Verification) process will be considerably simpler than for current ATC software. Additionally, the associative processor is enhanced SIMD hardware and is considerably cheaper and simpler than the MIMD hardware currently used to support ATC. The ClearSpeed CSX600 accelerator is used to emulate the AP model. A preliminary implementation of the proposed method has been developed and experimental results comparing MIMD and CSX600 approaches are presented. The performance of CSX600 has better scalability, efficiency, and predictability than that of MIMD.

The power of SIMDs vs. MIMDs in real-time scheduling

SIMDs and MIMDs are the most important categories of computer systems for parallel computing in Flynn’s classification scheme. Due to their higher flexibility in allowing processors to execute independently and their ability to use off-the-shelf microprocessors, the MIMD systems are generally favored and considered to be more powerful. In comparison, the SIMD systems are considered outdated. However, we observe that many intrinsic weaknesses of the MIMD systems are not fully recognized until they are compared while solving realtime scheduling problems. The SIMD systems have inherent advantages that MIMDs lack. In this paper, we compare SIMDs and MIMDs in real-time scheduling, e.g., scheduling for air traffic control. Two abstract parallel computation models, the ASC and BSP models that represent SIMDs and MIMDs respectively, are used in our discussion and analysis. We argue that the common belief that MIMDs have greater power than SIMDs is false. Our research shows that SIMDs are not outdated, as they offer tractable solutions for problems considered intractable with MIMDs. Rather, SIMDs are more efficient and powerful in some important application fields. They deserve more attention and considerations than they currently receive.

Real-time database scheduling simplicity

A different paradigm for the field of real-time data processing for command and control (C&C) is needed. Using multiprocessors (MP) all past approaches for real-time database computing have proven intractable whenever the problem requirements have exceeded simple cases. We review reasons why the MP architecture is considered intractable, and then show a simpler architecture where these reasons for intractability are non-existent. We present a solution in terms of a static, non-preemptive schedule using a processor; we designate an associative processor (AP). The AP, a set processor, uses a single thread instruction stream that can operate on an entire set of data with each instruction. The AP eliminates concurrent processes, the nemesis of multiprocessing, and a real-time C&C problem is shown to be schedulable in polynomial time.

3-D real-time database

Summary form only given. A SIMD architecture consists of one instruction processor (IP) with a separate memory for instructions, and a set of processing elements (PEs), each with its own separate memory. The instructions issued by the IP are sent to every PE simultaneously. When memory is addressed, the value in memory for each PE is simultaneously sent to its PE. Thus, thousands of data elements may be sent to their respective PEs simultaneously through execution of a single instruction. Whats a MIMD? The MIMD architecture consists of a collection of SISD (single instruction single data) machines coupled together in some way to act on the RTDB problem. The MIMD architecture connects SISD processors to work on the RTDB problem. The MP spends most of its time passing data back and forth between the SISDs. Then the MP executes concurrent processes, and resynchronizes the system.