This problem is related to the use of high-end x86 processors in HPC system cons

Question

This problem is related to the use of high-end x86 processors in HPC system construction. Answer the following questions: a. Referring to the latest Top 500 list of supercomputing systems, list all systems that have used x86 processors. Identify the processor models and key processor characteristics such as number of cores, clock frequency, and projected performance. b. Some have used GPUs to complement the x86 CPUs. Identify those systems that have procured substantial GPUs. Discuss the roles of GPUs to provide peak or sustained flops per dollar.

Explanation / Answer

Some systems that used x86 processors are AMD and Intel processors are few examples.

AMD Phenom

The AMD Athlon, Opteron, and Phenom processors are clones with respect to Intel’s x86 Instruction Set Architecture, and especially the dual-core Opteron has been (and is) quite popular for use in clusters. In addition, the Opteron and Phenom are used in Cray and the Liquid Computer systems that are presented later.

The Phenom is a quad core chip.

The clock frequency is in the range of 2.2–2.5 GHz

The decoding in the Phenom core has become more efficient than in the earlier processors: SSE instructions decode now into 1 micro-operation (µop) as are most integer and floating-point instructions. In addition, a new piece of hardware, called the sideband stack optimiser, has been added (not shown in the figure) that takes care of the stack manipulations in the instruction stream thus making instruction reordering more efficient thereby increasing the effective number of instructions per cycle.

IBM POWER6

Recently, in the systems that feature as IBM’s supercomputer line, the p575 series, the nodes contain the POWER6 chip as the computational engine. There are quite some changes with respect to its predecessor, the POWER5+, both in the chip lay-out and in the two cores that reside on a chip. The layout of the cores, caches, and controllers on the chip. Already here are significnant changes: instead of a 1.875 MB shared L2 cache now each core has its own 4 MB 8-way set-associative L2 cache that operates at half the core frequency. In addition, there are 2 memory controllers that via buffer chips connect to the memory and, depending on the amount of buffer chips and data widths (both are variable) can have a data read speed.

The clock frequency has increased from 1.9 GHz in the POWER5+ to 4.7 GHz for the POWER6 (water cooled version), an increase of almost a factor 2.5 while the power consumption stayed in the same range of that of the POWER5+. This has partly come about by a technology shrink from a 90 nm to a 65 nm feature size. It meant also that some features of the POWER5+ have disappeared.

Some other processor models are : IBM PowerPC 970 processor

IBM BlueGene processors

Intel Itanium 2.

b. Graphical Processing Units: Graphics processing is characterised by doing the same (floating-point) operation on massive amounts of data. To accommodate for this way of processing Graphical Processing Units (GPUs) consist of a large amount of relatively simple processors, fast but limited local memory, and fast internal buses to transport the operands and results.

HPC users often have similar computational demands as those in the graphical world: the same operation on very many data items. So, it was natural to look into GPUs with their many integrated parallel processors and fast memory. The first adopters of GPUs from the HPC community therefore disguised their numerical program fragments as graphical code (e.g., by using the graphical language OpenGL) to get fast results, often with remarkable speedups. Another advantage is that GPUs are relatively cheap because of the enormous amounts that are sold for graphical use in virtually every PC.

Related Questions

Navigate

• Browse (All)
• Browse T
• Subjects

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.