Journalist Cap II

-> Multicores are bad for Super-Computers. More cores per chip slows downs data-intensive applications unless there is a big boost in memory bandwidth.

For more info : See the IEEE-Spectrum article here.

-> Intel on a shopping-spree. Acquires 3 multicore software companies listed below in the past few months.

1. Wind-River Systems.
2. Cilk.
3. RapidMind.

For more info : Check this out.

-> DNA May Help Build Next Generation of Chips.

For more info : Click here.

-> Malware Turns Software Compilers into Virus Breeders.

For more info : Check this article here.

-> Hardware Physics A Bad Idea. says Carmack.

Thermal Design Power

The links Phani pointed to has interesting links to look. Here is a wiki entry on what Thermal Design Point (TDP) means? And here is yet another link on Athlon 64 Processor.

20 years of PLDI (1979-1999)

Programming Language Design and Implementation is a top notch conference in programming languages and compilers. Here is a link to the most influential PLDI papers between 1979 to 1999. We shall try to study as many papers as possible from this list.

http://www.cs.utexas.edu/users/mckinley/20-years.html

You should also go through and pick any paper that sounds interesting for presenting in the class.

Journalist Cap I

Interesting Things for a Compilers guy.

• AMD launches its fastest ever CPU(Phe nom II 965) on August 13th. Some more technical details about the proc, here http://www.lifebump.com/?p=101

• Dally's Interesting comments about Intel's new Larrabee.

Bill Dally is the new Chief Scientist of Nvidia.

"I think also that the fact that they've adopted an x86-instruction set puts them at a disadvantage. It's a complex instruction set, it's got instruction prefixes, it only has eight registers and while they claim that this gives them code compatibility, it gives them code compatibility only if they want to run one core without the SIMD extension. To use taphe 32 cores or use the 16-wide SIMD extension , they have to write a parallel program, so they have to start over again anyway. And they might as well have started over with a clean instruction set and not carry the area and power cost of interpreting a very complicated instruction set - that puts them at a disadvantage as well."

Whole Interview here : http://www.pcgameshardware.com/aid,692145/Nvidias-Chief-Scientist-Bill-Dally-about-GPU-technology-DirectX-11-and-Intels-Larrabee/News/

• GCC-CCVM is a new language to represent Parallel applications. More about it here : http://gitorious.org/gcc-ccvm

• There exists a law similar to Moore's law about Compiler Advances.

Proebsting's Law : Compiler Advances Double Computing Power Every 18 years.
More about it here : http://research.microsoft.com/en-us/um/people/toddpro /papers/law.htm

• Intel Acquires Cilk++ Technology

http://www.ddj.com/cpp/218900367

• New Optimizing compiler for Multi-core

http://www.multicoreinfo.com/2009/03/optimizing-compiler-4-multicore/

• A different view on Multi-core programming. Interesting.

http://alarmingdevelopment.org/?p=117

Reading list for Lecture 2

The paper on data parallel algorithms is moved from optional reading list of Lecture 1 to required reading list of Lecture 2.

Required Reading

1. Hillis, W. D. and Steele, G. L. 1986. Data parallel algorithms. Commun. ACM 29, 12 (Dec. 1986), 1170-1183.
2. Blelloch, G. E. 1996. Programming parallel algorithms. Commun. ACM 39, 3 (Mar. 1996), 85-97.
3. Quammen, C. 2005. Introduction to programming shared-memory and distributed-memory parallel computers. Crossroads 12, 1 (Oct. 2005), 2-2.
4. What the $#@! is Parallelism, Anyhow?

Optional Reading

• None

Reading list for Lecture 1

I shall post the Reading List for every Lecture both on the Course Website which is not yet up and also on the blog.

Required Reading

1. Larus, J. 2009. Spending Moore's dividend. Commun. ACM 52, 5 (May. 2009), 62-69.
2. Agarwal, A. and Levy, M. 2007. The kill rule for multicore. In Proceedings of the 44th Annual Design Automation Conference (San Diego, California, June 04 - 08, 2007). DAC '07. ACM, New York, NY, 750-753.

Optional Reading

1. Smith, J. E., & Sohi, G. S. (1995). Microarchitecture Of Superscalar Processors. Proceedings Of The Ieee, 83(12), 1609-1624.
2. Chapter 7 on Multicores, Multiprocessors and Clusters from Patterson, D. A., & Hennessy, J. L. (2009). Computer organization and design: The hardware/software interface. Burlington, MA: Morgan Kaufmann.

Welcome Everyone

Welcome to the Advanced Compilers course blog for Monsoon 2009 at IIIT, Hyderabad! Hope we shall all have fun in this course.