65954 2011-08-09 19:05:50 -0700 DFG JIT heap prediction causes regressions when combined with aggressive integer prediction 2011-08-10 00:07:17 -0700 1 1 1 Unclassified WebKit JavaScriptCore 528+ (Nightly build) All All RESOLVED FIXED P2 Normal --- 1 fpizlo webkit-unassigned barraclough fpizlo webkit.review.bot oldest_to_newest 448942 0 fpizlo 2011-08-09 19:05:50 -0700 Both of these patches produced speed-ups by themselves: https://bugs.webkit.org/show_bug.cgi?id=65883 https://bugs.webkit.org/show_bug.cgi?id=65949 But when combined, they produce slow-downs. Because the latter one was a bigger speed-up, the former should probably be disabled until the reasons behind the regressions are better understood. 448943 1 103430 fpizlo 2011-08-09 19:09:09 -0700 Created attachment 103430 the patch This improves performance on v8-crypto by 20%, bringing us back to where we were before we regressed. It does *not* remove the heap load prediction capability; it merely disables it, making it easier to reenable it if we figure out what is going wrong. 448977 2 103430 barraclough 2011-08-09 22:28:43 -0700 Comment on attachment 103430 the patch Seems like the smart move. Should probably revert properly if we don't get these working well together, but this seems a sensible step for now. 448993 3 103430 fpizlo 2011-08-09 23:09:32 -0700 Comment on attachment 103430 the patch Tests pass, ready to land. 449001 4 103430 webkit.review.bot 2011-08-10 00:07:12 -0700 Comment on attachment 103430 the patch Clearing flags on attachment: 103430 Committed r92750: <http://trac.webkit.org/changeset/92750> 449002 5 webkit.review.bot 2011-08-10 00:07:17 -0700 All reviewed patches have been landed. Closing bug. 103430 2011-08-09 19:09:09 -0700 2011-08-10 00:07:12 -0700 the patch disableheappred_patch_1.diff text/plain 1392 fpizlo SW5kZXg6IFNvdXJjZS9KYXZhU2NyaXB0Q29yZS9DaGFuZ2VMb2cKPT09PT09PT09PT09PT09PT09 PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PQotLS0gU291 cmNlL0phdmFTY3JpcHRDb3JlL0NoYW5nZUxvZwkocmV2aXNpb24gOTI3NDQpCisrKyBTb3VyY2Uv SmF2YVNjcmlwdENvcmUvQ2hhbmdlTG9nCSh3b3JraW5nIGNvcHkpCkBAIC0xLDMgKzEsMTcgQEAK KzIwMTEtMDgtMDkgIEZpbGlwIFBpemxvICA8ZnBpemxvQGFwcGxlLmNvbT4KKworICAgICAgICBE RkcgSklUIGhlYXAgcHJlZGljdGlvbiBjYXVzZXMgcmVncmVzc2lvbnMgd2hlbiBjb21iaW5lZCB3 aXRoCisgICAgICAgIGFnZ3Jlc3NpdmUgaW50ZWdlciBwcmVkaWN0aW9uCisgICAgICAgIGh0dHBz Oi8vYnVncy53ZWJraXQub3JnL3Nob3dfYnVnLmNnaT9pZD02NTk1NAorCisgICAgICAgIFJldmll d2VkIGJ5IE5PQk9EWSAoT09QUyEpLgorICAgICAgICAKKyAgICAgICAgRGlzYWJsZWQgaGVhcCBw cmVkaWN0aW9uLCBidXQgZGlkIG5vdCByZW1vdmUgdGhlIGNhcGFiaWxpdHkuCisgICAgICAgIFRo aXMgaW1wcm92ZXMgVjggY3J5cHRvIHBlcmZvcm1hbmNlIGJ5IDIwJS4KKworICAgICAgICAqIGRm Zy9ERkdHcmFwaC5oOgorICAgICAgICAoSlNDOjpERkc6OkdyYXBoOjpwcmVkaWN0KToKKwogMjAx MS0wOC0wOSAgRmlsaXAgUGl6bG8gIDxmcGl6bG9AYXBwbGUuY29tPgogCiAgICAgICAgIERGRyBK SVQgZG9lcyBub3Qgc3BlY3VsYXRpdmUgaW50ZWdlcnMgYXMgYWdncmVzc2l2ZWx5IGFzIGl0IHNo b3VsZApJbmRleDogU291cmNlL0phdmFTY3JpcHRDb3JlL2RmZy9ERkdHcmFwaC5oCj09PT09PT09 PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09 PT0KLS0tIFNvdXJjZS9KYXZhU2NyaXB0Q29yZS9kZmcvREZHR3JhcGguaAkocmV2aXNpb24gOTI3 MzkpCisrKyBTb3VyY2UvSmF2YVNjcmlwdENvcmUvZGZnL0RGR0dyYXBoLmgJKHdvcmtpbmcgY29w eSkKQEAgLTE2NCwxMyArMTY0LDYgQEAgcHVibGljOgogICAgICAgICBjYXNlIEdldEdsb2JhbFZh cjoKICAgICAgICAgICAgIHByZWRpY3RHbG9iYWxWYXIobm9kZS52YXJOdW1iZXIoKSwgcHJlZGlj dGlvbik7CiAgICAgICAgICAgICBicmVhazsKLSAgICAgICAgY2FzZSBHZXRCeUlkOgotICAgICAg ICBjYXNlIEdldE1ldGhvZDoKLSAgICAgICAgY2FzZSBHZXRCeVZhbDoKLSAgICAgICAgY2FzZSBD YWxsOgotICAgICAgICBjYXNlIENvbnN0cnVjdDoKLSAgICAgICAgICAgIG5vZGUucHJlZGljdChw cmVkaWN0aW9uKTsKLSAgICAgICAgICAgIGJyZWFrOwogICAgICAgICBkZWZhdWx0OgogICAgICAg ICAgICAgYnJlYWs7CiAgICAgICAgIH0K