Code Overlay: Difference between revisions

From esoterum.org
Jump to navigationJump to search
No edit summary
 
(7 intermediate revisions by the same user not shown)
Line 1: Line 1:
*[[Overlay generator]] technical details and instructions
=== Literature ===
*(10.16)Cytron, R. and Loewner, P. G. [http://portal.acm.org/citation.cfm?id=9931.9935&dl=GUIDE&dl=GUIDE&CFID=62477417&CFTOKEN=40689096 An automatic overlay generator]. IBM J. Res. Dev. 30, 6 (Nov. 1986), 603-608.
*(10.17)Spacek, T. R. 1972. [http://portal.acm.org/citation.cfm?id=361407# A proposal to establish a pseudo virtual memory via writable overlays]. Commun. ACM 15, 6 (Jun. 1972), 421-426.
*(10.15) Amit Pabalkar,  Aviral Shrivastava, Arun Kannan and Jongeun Lee. [http://www.springerlink.com/content/98qu566lq563008p/ SDRM: Simultaneous Determination of Regions and Function-to-Region Mapping for Scratchpad Memories]. High Performance Computing - HiPC 2008. Springer Berlin / Heidelberg. Volume Volume 5374/2008. Wednesday, December 17, 2008  
*(10.15) Amit Pabalkar,  Aviral Shrivastava, Arun Kannan and Jongeun Lee. [http://www.springerlink.com/content/98qu566lq563008p/ SDRM: Simultaneous Determination of Regions and Function-to-Region Mapping for Scratchpad Memories]. High Performance Computing - HiPC 2008. Springer Berlin / Heidelberg. Volume Volume 5374/2008. Wednesday, December 17, 2008  


Line 47: Line 54:
*(10.10) Manish Verma and Lars Wehmeyer and Peter Marwedel. [http://portal.acm.org/citation.cfm?id=1016748 Dynamic overlay of scratchpad memory for energy minimization]. International Conference on Hardware Software Codesign. Pages: 104 - 109. 2004.
*(10.10) Manish Verma and Lars Wehmeyer and Peter Marwedel. [http://portal.acm.org/citation.cfm?id=1016748 Dynamic overlay of scratchpad memory for energy minimization]. International Conference on Hardware Software Codesign. Pages: 104 - 109. 2004.
:-University of Dortmund, Dortmund, Germany
:-University of Dortmund, Dortmund, Germany
=== Segment Prefetching ===
*[http://en.wikipedia.org/wiki/Branch_target_predictor Branch target prediction], should be similar to what we want to accomplish as opposed to branch prediction


=== IBM CBE Compilers (xlc/gcc) ===
=== IBM CBE Compilers (xlc/gcc) ===
*Overlay manager source code <<code>ovl_spu.S</code>> is located in <<code>spu-binutils-2.18.50-21.src.rpm: ld/emultempl/spu_ovl.S</code>>
*[http://publib.boulder.ibm.com/infocenter/systems/scope/syssw/index.jsp?topic=/eicct/prg/overlaycompileroption.html switches for automatic overlay generation]
*[http://publib.boulder.ibm.com/infocenter/systems/scope/syssw/index.jsp?topic=/eicct/prg/overlaycompileroption.html switches for automatic overlay generation]
:<code>--auto-overlay=link.script</code> outputs the generated overlay as a linker script and halts
:<code>--auto-overlay=link.script</code> outputs the generated overlay as a linker script and halts
Line 54: Line 65:
*[http://www.loongson.cn/svn/toolchain-gs/branches/auto-vectorization/binutils-2.18/ld/emultempl/spu_ovl.S Overlay manager source code]
*[http://www.loongson.cn/svn/toolchain-gs/branches/auto-vectorization/binutils-2.18/ld/emultempl/spu_ovl.S Overlay manager source code]
*[http://www.williamstein.org/home/kirkby/binutils-2.19.1/ld/emultempl/spu_ovl.S Overlay manager source code], different comments
*[http://www.williamstein.org/home/kirkby/binutils-2.19.1/ld/emultempl/spu_ovl.S Overlay manager source code], different comments
*[http://cvs.opensolaris.org/source/xref/sfw/usr/src/cmd/binutils/binutils-2.19/ld/emultempl/spu_ovl.S Overlay manager source codee], another version
*[http://cvs.opensolaris.org/source/xref/sfw/usr/src/cmd/binutils/binutils-2.19/ld/emultempl/spu_ovl.S Overlay manager source code], another version
*[http://binutils.sourcearchive.com/documentation/2.18.93.20081009/elf32-spu_8c-source.html elf32-spu.c]




<code>Last printed: 10.15</code>
<code>Last printed: 10.17</code>

Latest revision as of 09:21, 19 November 2009


Literature

-"Call-graph partitioning faces challenges with very large single functions. Such functions are generally the result of aggressive optimizations, particularly function inlining and loop unrolling."


-University of Dortmund, Computer Science 12, 44221 Dortmund, Germany
-University of Maryland, College Park, MD
-Seoul National University, Seoul, Korea
  • (10.3) Federico Angiolini and Francesco Menichelli and Alberto Ferrero and Luca Benini and Mauro Olivieri. A post-compiler approach to scratchpad mapping of code. International Conference on Compilers, Architecture and Synthesis for Embedded Systems. Pages: 259 - 267. 2004.
-Università di Bologna, Bologna, Italy
-University of Bologna, Bologna, Bologna, Italy
-University of Dortmund, Computer Science 12, 44221 Dortmund, Germany
-University of Dortmund, Computer Science 12, 44221 Dortmund, Germany
-University of Maryland, College Park, MD
-Microsyst. Design Lab., Pennsylvania State Univ., University Park, PA, USA;
-Sch. of Comput. Sci. & Eng., New South Wales Univ., Sydney, NSW, Australia;

Dynamic Code Mapping

-Seoul National University, Korea
-The University of New South Wales, Sydney, Australia
-University of Dortmund, 44221 Dortmund, Germany
-University of Dortmund, Dortmund, Germany

Segment Prefetching

IBM CBE Compilers (xlc/gcc)

--auto-overlay=link.script outputs the generated overlay as a linker script and halts


Last printed: 10.17