195898 2019-03-18 11:18:14 -0700 Remove the inline capacity of Operands 2019-03-18 12:04:16 -0700 1 1 1 Unclassified WebKit JavaScriptCore WebKit Nightly Build Unspecified Unspecified RESOLVED FIXED InRadar P2 Normal --- 1 rmorisset rmorisset commit-queue ews-watchlist keith_miller mark.lam msaboff saam webkit-bug-importer ysuzuki oldest_to_newest 1517800 0 rmorisset 2019-03-18 11:18:14 -0700 Operands currently has a vector with an inline capacity of 24. I tested on JetStream2, and only 4776 functions out of 12035 (that reach the DFG tier) have 24 or fewer elements in it. This is a major problem, because we have 5 Operands in every DFG::BasicBlock, resulting in 2688 bytes of inline capacity per basic block. Still on JetStream 2, functions have an average of 18 BB, but those functions whose operands overflow have an average of 27 BB (so we are wasting 72kB on average when compiling them), and the largest function has 1241 BB (!), for a total of 3.3MB being wasted while it is compiled. So I removed the inline capacity of the vector in Operands, and here are the results: Baseline Jetstream2: 159.741 159.746 159.989 Baseline RAMification on grouped and jit tests: (end/peak/score) 89.288/89.763/89.526 90.166/90.761/90.418 89.560/90.014/89.787 After optimization Jetstream2: 159.342 161.812 162.037 After optimization RAMification: 89.147/89.644/89.395 89.102.89.585/89.343 88.953/89.536/89.2444 So it looks like a roughly 1% improvement on RAMification (at least the tests where the JIT is enabled), and more surprisingly also a 1% progression on Jetstream2 (although I have more doubts about this one considering the variability in my numbers). I hope to land this, and get more accurate results from the bots. 1517803 1 365035 rmorisset 2019-03-18 11:21:29 -0700 Created attachment 365035 Patch 1517807 2 365035 ysuzuki 2019-03-18 11:25:15 -0700 Comment on attachment 365035 Patch View in context: https://bugs.webkit.org/attachment.cgi?id=365035&action=review r=me > Source/JavaScriptCore/ChangeLog:11 > + Still on JetStream 2, functions have an average of 18 BB, but those functions whose operands overflow have an average of 27 BB (so we are wasting 72kB on average when compiling them), and the largest function has 1241 BB (!), for a total of 3.3MB being wasted while it is compiled. I think FTL::OSRExitDescriptor also includes Operands, and it is kept alive during the code is live :) 1517830 3 365035 commit-queue 2019-03-18 12:03:38 -0700 Comment on attachment 365035 Patch Clearing flags on attachment: 365035 Committed r243088: <https://trac.webkit.org/changeset/243088> 1517831 4 commit-queue 2019-03-18 12:03:40 -0700 All reviewed patches have been landed. Closing bug. 1517833 5 webkit-bug-importer 2019-03-18 12:04:16 -0700 <rdar://problem/48987979> 365035 2019-03-18 11:21:29 -0700 2019-03-18 12:03:38 -0700 Patch bug-195898-20190318112129.patch text/plain 2658 rmorisset SW5kZXg6IFNvdXJjZS9KYXZhU2NyaXB0Q29yZS9DaGFuZ2VMb2cKPT09PT09PT09PT09PT09PT09 PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PQotLS0gU291 cmNlL0phdmFTY3JpcHRDb3JlL0NoYW5nZUxvZwkocmV2aXNpb24gMjQzMDg0KQorKysgU291cmNl L0phdmFTY3JpcHRDb3JlL0NoYW5nZUxvZwkod29ya2luZyBjb3B5KQpAQCAtMSwzICsxLDM4IEBA CisyMDE5LTAzLTE4ICBSb2JpbiBNb3Jpc3NldCAgPHJtb3Jpc3NldEBhcHBsZS5jb20+CisKKyAg ICAgICAgUmVtb3ZlIHRoZSBpbmxpbmUgY2FwYWNpdHkgb2YgT3BlcmFuZHMKKyAgICAgICAgaHR0 cHM6Ly9idWdzLndlYmtpdC5vcmcvc2hvd19idWcuY2dpP2lkPTE5NTg5OAorCisgICAgICAgIFJl dmlld2VkIGJ5IE5PQk9EWSAoT09QUyEpLgorCisgICAgICAgIE9wZXJhbmRzIGN1cnJlbnRseSBo YXMgYSB2ZWN0b3Igd2l0aCBhbiBpbmxpbmUgY2FwYWNpdHkgb2YgMjQuCisgICAgICAgIEkgdGVz dGVkIG9uIEpldFN0cmVhbTIsIGFuZCBvbmx5IDQ3NzYgZnVuY3Rpb25zIG91dCBvZiAxMjAzNSAo dGhhdCByZWFjaCB0aGUgREZHIHRpZXIpIGhhdmUgMjQgb3IgZmV3ZXIgZWxlbWVudHMgaW4gaXQu CisgICAgICAgIFRoaXMgaXMgYSBtYWpvciBwcm9ibGVtLCBiZWNhdXNlIHdlIGhhdmUgNSBPcGVy YW5kcyBpbiBldmVyeSBERkc6OkJhc2ljQmxvY2ssIHJlc3VsdGluZyBpbiAyNjg4IGJ5dGVzIG9m IGlubGluZSBjYXBhY2l0eSBwZXIgYmFzaWMgYmxvY2suCisgICAgICAgIFN0aWxsIG9uIEpldFN0 cmVhbSAyLCBmdW5jdGlvbnMgaGF2ZSBhbiBhdmVyYWdlIG9mIDE4IEJCLCBidXQgdGhvc2UgZnVu Y3Rpb25zIHdob3NlIG9wZXJhbmRzIG92ZXJmbG93IGhhdmUgYW4gYXZlcmFnZSBvZiAyNyBCQiAo c28gd2UgYXJlIHdhc3RpbmcgNzJrQiBvbiBhdmVyYWdlIHdoZW4gY29tcGlsaW5nIHRoZW0pLCBh bmQgdGhlIGxhcmdlc3QgZnVuY3Rpb24gaGFzIDEyNDEgQkIgKCEpLCBmb3IgYSB0b3RhbCBvZiAz LjNNQiBiZWluZyB3YXN0ZWQgd2hpbGUgaXQgaXMgY29tcGlsZWQuCisgICAgICAgIAorICAgICAg ICBTbyBJIHJlbW92ZWQgdGhlIGlubGluZSBjYXBhY2l0eSBvZiB0aGUgdmVjdG9yIGluIE9wZXJh bmRzLCBhbmQgaGVyZSBhcmUgdGhlIHJlc3VsdHM6CisgICAgICAgIEJhc2VsaW5lIEpldHN0cmVh bTI6CisgICAgICAgIDE1OS43NDEKKyAgICAgICAgMTU5Ljc0NgorICAgICAgICAxNTkuOTg5Cisg ICAgICAgIEJhc2VsaW5lIFJBTWlmaWNhdGlvbiBvbiBncm91cGVkIGFuZCBqaXQgdGVzdHM6IChl bmQvcGVhay9zY29yZSkKKyAgICAgICAgODkuMjg4Lzg5Ljc2My84OS41MjYKKyAgICAgICAgOTAu MTY2LzkwLjc2MS85MC40MTgKKyAgICAgICAgODkuNTYwLzkwLjAxNC84OS43ODcKKyAgICAgICAg QWZ0ZXIgb3B0aW1pemF0aW9uIEpldHN0cmVhbTI6CisgICAgICAgIDE1OS4zNDIKKyAgICAgICAg MTYxLjgxMgorICAgICAgICAxNjIuMDM3CisgICAgICAgIEFmdGVyIG9wdGltaXphdGlvbiBSQU1p ZmljYXRpb246CisgICAgICAgIDg5LjE0Ny84OS42NDQvODkuMzk1CisgICAgICAgIDg5LjEwMi44 OS41ODUvODkuMzQzCisgICAgICAgIDg4Ljk1My84OS41MzYvODkuMjQ0NAorICAgICAgICAKKyAg ICAgICAgU28gaXQgbG9va3MgbGlrZSBhIHJvdWdobHkgMSUgaW1wcm92ZW1lbnQgb24gUkFNaWZp Y2F0aW9uIChhdCBsZWFzdCB0aGUgdGVzdHMgd2hlcmUgdGhlIEpJVCBpcyBlbmFibGVkKSwgYW5k IG1vcmUgc3VycHJpc2luZ2x5IGFsc28gYSAxJSBwcm9ncmVzc2lvbiBvbiBKZXRzdHJlYW0yIChh bHRob3VnaCBJIGhhdmUgbW9yZSBkb3VidHMgYWJvdXQgdGhpcyBvbmUgY29uc2lkZXJpbmcgdGhl IHZhcmlhYmlsaXR5IGluIG15IG51bWJlcnMpLgorICAgICAgICBJIGhvcGUgdG8gbGFuZCB0aGlz LCBhbmQgZ2V0IG1vcmUgYWNjdXJhdGUgcmVzdWx0cyBmcm9tIHRoZSBib3RzLgorCisgICAgICAg ICogYnl0ZWNvZGUvT3BlcmFuZHMuaDoKKwogMjAxOS0wMy0xOCAgWXVzdWtlIFN1enVraSAgPHlz dXp1a2lAYXBwbGUuY29tPgogCiAgICAgICAgIFtKU0NdIGpzU3Vic3RyaW5nIHNob3VsZCByZXNv bHZlIHJvcGUgYmVmb3JlIGNhbGxpbmcgSlNSb3BlU3RyaW5nOjpjcmVhdGUKSW5kZXg6IFNvdXJj ZS9KYXZhU2NyaXB0Q29yZS9ieXRlY29kZS9PcGVyYW5kcy5oCj09PT09PT09PT09PT09PT09PT09 PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT0KLS0tIFNvdXJj ZS9KYXZhU2NyaXB0Q29yZS9ieXRlY29kZS9PcGVyYW5kcy5oCShyZXZpc2lvbiAyNDI3NjEpCisr KyBTb3VyY2UvSmF2YVNjcmlwdENvcmUvYnl0ZWNvZGUvT3BlcmFuZHMuaAkod29ya2luZyBjb3B5 KQpAQCAtMjY2LDcgKzI2Niw3IEBAIHB1YmxpYzoKICAgICAKIHByaXZhdGU6CiAgICAgLy8gVGhl IGZpcnN0IG1fbnVtQXJndW1lbnRzIG9mIG1fdmFsdWVzIGFyZSBhcmd1bWVudHMsIHRoZSByZXN0 IGFyZSBsb2NhbHMuCi0gICAgVmVjdG9yPFQsIDI0LCBVbnNhZmVWZWN0b3JPdmVyZmxvdz4gbV92 YWx1ZXM7CisgICAgVmVjdG9yPFQsIDAsIFVuc2FmZVZlY3Rvck92ZXJmbG93PiBtX3ZhbHVlczsK ICAgICB1bnNpZ25lZCBtX251bUFyZ3VtZW50czsKIH07CiAK