Changeset 900 for docs/EuroPar2011

Ignore:
Timestamp:
Feb 6, 2011, 1:48:32 PM (8 years ago)
Message:

Fred's latest changes.

Location:
docs/EuroPar2011
Files:
2 edited

Legend:

Unmodified
 r898 hardest of the 13 dwarves'' to parallelize \cite{Asanovic:EECS-2006-183}, parallel bitstream technology shows considerable promise for these types of applications\cite{PPoPP08,CameronHerdyLin2008,Green2009}. %types of applications\cite{PPoPP08,CameronHerdyLin2008,Green2009}. types of applications \cite{PPoPP08,CameronHerdyLin2008,Green2009}. In this approach, character streams are processed $N$ positions at a time using the $N$-bit SIMD registers commonly found on commodity instructions also available on commodity processors, the Parabix 1 XML parser was shown to considerably accelerate XML parsing in comparison with conventional byte-at-a-time parser % parsing in comparison with conventional byte-at-a-time parser parsing in comparison with conventional byte-at-a-time parsers in applications such as statistics gathering \cite{CameronHerdyLin2008} and as GML to SVG conversion \cite{Herdy2008}. The starting point for bitstream methods are \emph{basis} bitstreams and their use in determining \emph{character-class} bitstreams. The $k$th basis bitstream $B_k$ consists of the $k$th bit (0-based, starting at the LSB) The $k$th basis bitstream $B_k$ consists of the $k$th bit (0-based, starting at the the least significant bit) of each character in the source data stream; thus each $B_k$ is dependent on the encoding of the source characters (ASCII, UTF-8, UTF-16, etc.). the middle of a span. The parallel parsing task is to move each of the four markers forward through the corresponding spans of of the four markers forward (to the left) through the corresponding spans of digits to the immediately following positions. \begin{tabular}{cr}\\ source data $\vartriangleleft$ & \verb----173942---654----1----49731----321--\\ $M_0 =$ & \verb.........1.....1....1......1...........\\ $M_0$ & \verb.........1.....1....1......1...........\\ $D =$\verb:[0-9]: & \verb....111111...111....1....11111....111..\\ $M_0 + D$ & \verb...1........1......1....1...11....111..\\ After these operations, there are no more attributes in the first tag, so its corresponding marker becomes zeroed out. However, $M_{1, 8}$ is not all $0$s, as the second tags still has an unparsed attribute-value pair. However, $M_{1, 8}$ is not all $0$s, as the second tag still has an unparsed attribute-value pair. Thus, the parsing continues. %\subsection{Summary} Overall, parallel bitstream techniques are quite well-suited to Overall, parallel bitstream techniques are well-suited to verification problems such as XML well-formedness checking. Many of the character validation and syntax checking requirements In this section, we compare the performance of our \verb:xmlwf: implementation using the Parabix2 technology described above with several implementation using the Parabix 2 technology described above with several other implementations. These include the original \verb:xmlwf: