<html><body><p><font size="2" color="#2F2F2F">Dear all</font><font size="2" color="#2F2F2F">,</font><br><br><font size="2" color="#2F2F2F">Would you please review following change?</font><br><br><font size="2" color="#2F2F2F">Bug: </font><a href="https://bugs.openjdk.java.net/browse/JDK-8213754"><font size="2">https://bugs.openjdk.java.net/browse/JDK-8213754</font></a><br><font size="2" color="#2F2F2F">Webrev: </font><font size="2" color="#0000FF"><a href="http://cr.openjdk.java.net/~mhorie/8213754/webrev.00">http://cr.openjdk.java.net/~mhorie/8213754/webrev.00</a></font><br><br><font size="2" color="#2F2F2F">This change includes the intrinsics of Character isDigit</font><font size="2" color="#2F2F2F">,</font><font size="2" color="#2F2F2F"> isLowerCase</font><font size="2" color="#2F2F2F">,</font><font size="2" color="#2F2F2F"> isUpperCase</font><font size="2" color="#2F2F2F">,</font><font size="2" color="#2F2F2F"> and isWhitespace to support the Latin1 block using POWER9</font><font size="2" color="#2F2F2F">’</font><font size="2" color="#2F2F2F">s instructions cmprb</font><font size="2" color="#2F2F2F"> and</font><font size="2" color="#2F2F2F"> cmpeqb</font><font size="2" color="#2F2F2F">. The cmprb enables to compare a character with 1 or 2 ranged bytes, while the cmpeqb compares one with 1 to 8 values. Simple micro benchmark attached showed improvements by 20-40%. </font><br><br><i>(See attached file: Latin1Test.java)</i><br><br><br><font size="2">Best regards,</font><br><font size="2">--</font><br><font size="2">Michihiro,</font><br><font size="2">IBM Research - Tokyo</font><BR>
</body></html>