[9] RFR (S): 8074548: Never-taken branches cause repeated deopts in MHs.GWT case (original) (raw)

Vladimir Ivanov vladimir.x.ivanov at oracle.com
Mon Mar 16 23:11:46 UTC 2015

Vladimir,

Thanks for the feedback!

Updated webrev in place: http://cr.openjdk.java.net/~vlivanov/8074548/webrev.00/

You already have 'result' variable for argument(0), why reread?:

CmpINode(argument(0) Good point. Fixed.

Usually IfTrue is the fast path. IGVN will revert that check to have that. But it is better to have it in code. Current code looks like double negation. Fixed.

There is no explanation in changes why falsecount never seen (== 0) is more important than truecount == 0. The comment says "one of the values". The code is the following: if (false_cnt == 0 || true_cnt == 0) { // According to profile, one value has been never seen. int expected_val = (false_cnt == 0) ? 1 : 0;

(false_cnt != 0) => (true_cnt == 0). Do you want me to add additional comment about that?

I chose (false_cnt == 0) because it refers to "always true" case.

Best regards, Vladimir Ivanov

Thanks, Vladimir On 3/16/15 11:26 AM, Vladimir Ivanov wrote: http://cr.openjdk.java.net/~vlivanov/8074548/webrev.00/ https://bugs.openjdk.java.net/browse/JDK-8074548

MethodHandleImpl::profileBoolean doesn't update never-taken branch count when hitting a deopt on it. As a result, for rarely taken branches consequent compilations consider them as never-taken and prune them again causing repeated deopts. It severely affects peak performance. The fix is to update MHI::profileBoolean intrinsic to insert a guard and uncommon trap w/ reexecute bit set for never-seen value. Once previously never seen value is encountered, the execution resumes after deopt in MHI::profileBoolean and corresponding count becomes non-zero. The guard doesn't add any additional overhead, since it dominates all value usages and all branches on the same value are eliminated. Testing: java/lang/invoke, nashorn, octane Best regards, Vladimir Ivanov

mlvm-dev mailing list mlvm-dev at openjdk.java.net http://mail.openjdk.java.net/mailman/listinfo/mlvm-dev

mlvm-dev mailing list mlvm-dev at openjdk.java.net http://mail.openjdk.java.net/mailman/listinfo/mlvm-dev

More information about the hotspot-compiler-dev mailing list