SIMD architecture
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.
Improved SIMD Architecture for High Performance Video Processors
Single instruction multiple data (SIMD) execution is in no doubt an efficient
way to exploit the data level parallelism in image and video applications.
However, SIMD execution bottlenecks must be tackled in order to achieve high
execution efficiency. We first analyze in this paper the implementation of two
major kernel functions of H.264/AVC namely, SATD and subpel interpolation, in
conventional SIMD architectures to identify the bottlenecks in traditional
approaches. Based on the analysis results, we propose a new SIMD architecture
with two novel features: 1) parallel memory structure with variable block size
and word length support, and 2) configurable SIMD structure. The proposed
parallel memory structure allows great flexibility for programmers to perform
data access of different block sizes and different word lengths. The
configurable SIMD structure allows almost “random” register file access and
slightly different operations in ALUs inside SIMD. The new features greatly
benefit the realization of H.264/AVC kernel functions. For instance, the
fractional motion estimation, particularly the half to quarter pixel
interpolation, can now be executed with minimal or no additional memory access.
When comparing with the conventional SIMD systems, the proposed SIMD
architecture can have a further speedup of 2.1X to 4.6X when implementing
H.264/AVC kernel functions. Based on Amdahl's law, the overall speedup of
H.264/AVC encoding application can be projected to be 2.46X. We expect
significant improvement can also be achieved when applying the proposed
architecture to other image and video processing applications.
