\boolfalse {citerequest}\boolfalse {citetracker}\boolfalse {pagetracker}\boolfalse {backtracker}\relax \defcounter {refsection}{0}\relax \select@language {english} \defcounter {refsection}{0}\relax \contentsline {section}{\numberline {1}Introduction}{2}{section.1} \defcounter {refsection}{0}\relax \contentsline {section}{\numberline {2}Roofline Model}{2}{section.2} \defcounter {refsection}{0}\relax \contentsline {subsection}{\numberline {2.1}Theoretical Peak Performance}{2}{subsection.2.1} \defcounter {refsection}{0}\relax \contentsline {subsection}{\numberline {2.2}Memory Bandwidth}{3}{subsection.2.2} \defcounter {refsection}{0}\relax \contentsline {subsection}{\numberline {2.3}Graph}{3}{subsection.2.3} \defcounter {refsection}{0}\relax \contentsline {section}{\numberline {3}Kernels}{4}{section.3} \defcounter {refsection}{0}\relax \contentsline {subsection}{\numberline {3.1}1/16 $\not =$ 1/16. Or: The Fancy Arithmetics of a Compiler}{5}{subsection.3.1} \defcounter {refsection}{0}\relax \contentsline {subsection}{\numberline {3.2}The 1/16 OI Kernel}{6}{subsection.3.2} \defcounter {refsection}{0}\relax \contentsline {subsection}{\numberline {3.3}The 8 OI Kernel}{6}{subsection.3.3} \defcounter {refsection}{0}\relax \contentsline {subsubsection}{\numberline {3.3.1}Some Further 8/1 Kernel}{8}{subsubsection.3.3.1} \defcounter {refsection}{0}\relax \contentsline {section}{\numberline {4}Results}{8}{section.4} \defcounter {refsection}{0}\relax \contentsline {section}{\numberline {5}Discussion}{12}{section.5}