{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":45717250,"defaultBranch":"master","name":"tensorflow","ownerLogin":"tensorflow","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2015-11-07T01:19:20.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/15658638?v=4","public":true,"private":false,"isOrgOwned":true},"refInfo":{"name":"","listCacheKey":"v0:1716281757.0","currentOid":""},"activityList":{"items":[{"before":null,"after":"1bfa9c851af5efb4a192592655edc8ed4cbe1cf4","ref":"refs/heads/exported_pr_635706553","pushedAt":"2024-05-21T08:55:57.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"Automated Code Change\n\nPiperOrigin-RevId: 635706553","shortMessageHtmlLink":"Automated Code Change"}},{"before":"8c8867ce348b41aac0d99cdd93f7043c1e6462f8","after":"4cca3247676c74b8abe157402076f48b5c726374","ref":"refs/heads/exported_pr_635707877","pushedAt":"2024-05-21T08:52:49.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"This change is to help the developers implement custom scatter ops that emulates the behavior on GPU.\n\nPiperOrigin-RevId: 635707877","shortMessageHtmlLink":"This change is to help the developers implement custom scatter ops th…"}},{"before":"aa8bb6a0db6bf51e44a60936c5de4eccd603e287","after":null,"ref":"refs/heads/exported_pr_635137854","pushedAt":"2024-05-21T08:52:19.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"}},{"before":"ea5adb0f08787c01697a4142d1cd2f2ec6361db2","after":"aa8bb6a0db6bf51e44a60936c5de4eccd603e287","ref":"refs/heads/master","pushedAt":"2024-05-21T08:52:17.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"Automated Code Change\n\nPiperOrigin-RevId: 635716090","shortMessageHtmlLink":"Automated Code Change"}},{"before":"f601b723ca9dfa33a65f3385147cf7def3777fe0","after":"aa8bb6a0db6bf51e44a60936c5de4eccd603e287","ref":"refs/heads/exported_pr_635137854","pushedAt":"2024-05-21T08:52:16.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"Automated Code Change\n\nPiperOrigin-RevId: 635716090","shortMessageHtmlLink":"Automated Code Change"}},{"before":"ea5adb0f08787c01697a4142d1cd2f2ec6361db2","after":null,"ref":"refs/heads/exported_pr_634683280","pushedAt":"2024-05-21T08:43:58.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"}},{"before":"f53aae362873d6df132d08b63b495adf644d67d9","after":"ea5adb0f08787c01697a4142d1cd2f2ec6361db2","ref":"refs/heads/master","pushedAt":"2024-05-21T08:43:56.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"MLIR emitters: Vectorize transposes with small element types.\n\nSpecial thanks to github user lingzhi98, who proposed and benchmarked\nthis optimization and implemented it in https://github.com/openxla/xla/pull/12552.\nIt turned out that the Tiling abstraction made this harder than it needs to be.\nThis is an independent reimplementation that removes the Tiling abstraction, but\nreuses lingzhi98's tests and most of their heuristic for enabling vectorization.\n\nThe differences in the heuristic are:\n- respect the shared memory budget\n- enable vectorization if the dimensions are divisible by 2, not just when\n  they are divisible by 64.\n\nPiperOrigin-RevId: 635715722","shortMessageHtmlLink":"MLIR emitters: Vectorize transposes with small element types."}},{"before":"19c3823720cb56d110464adb4163f962cfd709eb","after":"ea5adb0f08787c01697a4142d1cd2f2ec6361db2","ref":"refs/heads/exported_pr_634683280","pushedAt":"2024-05-21T08:43:55.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"MLIR emitters: Vectorize transposes with small element types.\n\nSpecial thanks to github user lingzhi98, who proposed and benchmarked\nthis optimization and implemented it in https://github.com/openxla/xla/pull/12552.\nIt turned out that the Tiling abstraction made this harder than it needs to be.\nThis is an independent reimplementation that removes the Tiling abstraction, but\nreuses lingzhi98's tests and most of their heuristic for enabling vectorization.\n\nThe differences in the heuristic are:\n- respect the shared memory budget\n- enable vectorization if the dimensions are divisible by 2, not just when\n  they are divisible by 64.\n\nPiperOrigin-RevId: 635715722","shortMessageHtmlLink":"MLIR emitters: Vectorize transposes with small element types."}},{"before":null,"after":"3ea74bf0f0d1859e7be3338931cba4d43a40254a","ref":"refs/heads/exported_pr_635633441","pushedAt":"2024-05-21T08:36:59.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"Automated Code Change\n\nPiperOrigin-RevId: 635633441","shortMessageHtmlLink":"Automated Code Change"}},{"before":"2a8e48400e1bb9a701cf9e55ad8513d403ac0cef","after":"8c8867ce348b41aac0d99cdd93f7043c1e6462f8","ref":"refs/heads/exported_pr_635707877","pushedAt":"2024-05-21T08:32:44.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"This change is to help the developers implement custom scatter ops that emulates the behavior on GPU.\n\nPiperOrigin-RevId: 635707877","shortMessageHtmlLink":"This change is to help the developers implement custom scatter ops th…"}},{"before":null,"after":"ecc4b4f65f66f7604dcc0cc646f1556bb7e8e730","ref":"refs/heads/exported_pr_635632602","pushedAt":"2024-05-21T08:28:14.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"Automated Code Change\n\nPiperOrigin-RevId: 635632602","shortMessageHtmlLink":"Automated Code Change"}},{"before":"f53aae362873d6df132d08b63b495adf644d67d9","after":null,"ref":"refs/heads/exported_pr_634373712","pushedAt":"2024-05-21T08:26:18.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"}},{"before":"fde16c701672a992c75c9ee19e6cd2da4bc420f7","after":"f53aae362873d6df132d08b63b495adf644d67d9","ref":"refs/heads/master","pushedAt":"2024-05-21T08:26:16.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"Automated Code Change\n\nPiperOrigin-RevId: 635712904","shortMessageHtmlLink":"Automated Code Change"}},{"before":"3a76740af1dbe10a4df10fee1559616fbae203ff","after":"f53aae362873d6df132d08b63b495adf644d67d9","ref":"refs/heads/exported_pr_634373712","pushedAt":"2024-05-21T08:26:15.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"Automated Code Change\n\nPiperOrigin-RevId: 635712904","shortMessageHtmlLink":"Automated Code Change"}},{"before":"f8fdb2893edf38cc5ad041952bc4134482756c69","after":"58530b1688b94c84bc9e6568200c600b39742917","ref":"refs/heads/exported_pr_635672553","pushedAt":"2024-05-21T08:24:51.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"Automated Code Change\n\nPiperOrigin-RevId: 635672553","shortMessageHtmlLink":"Automated Code Change"}},{"before":"f187dc9ca0b7f83229cd3c472a2a2103a7724800","after":"2a8e48400e1bb9a701cf9e55ad8513d403ac0cef","ref":"refs/heads/exported_pr_635707877","pushedAt":"2024-05-21T08:19:41.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"This change is to help the developers implement custom scatter ops that emulates the behavior on GPU.\n\nPiperOrigin-RevId: 635707877","shortMessageHtmlLink":"This change is to help the developers implement custom scatter ops th…"}},{"before":null,"after":"f187dc9ca0b7f83229cd3c472a2a2103a7724800","ref":"refs/heads/exported_pr_635707877","pushedAt":"2024-05-21T08:07:55.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"This change is to help the developers implement custom scatter ops that emulates the behavior on GPU.\n\nPiperOrigin-RevId: 635707877","shortMessageHtmlLink":"This change is to help the developers implement custom scatter ops th…"}},{"before":"876786525b06339940778d894d559b7c1b248fb8","after":"b2e76451f967dab68050086893afff106f82531a","ref":"refs/heads/exported_pr_635704096","pushedAt":"2024-05-21T08:07:30.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"Automated Code Change\n\nFix header includes\n\nPiperOrigin-RevId: 635704096","shortMessageHtmlLink":"Automated Code Change"}},{"before":"fde16c701672a992c75c9ee19e6cd2da4bc420f7","after":null,"ref":"refs/heads/exported_pr_635692974","pushedAt":"2024-05-21T08:05:14.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"}},{"before":"a51ee7da2ff54d595bf568ec5976f86899a68eca","after":"fde16c701672a992c75c9ee19e6cd2da4bc420f7","ref":"refs/heads/master","pushedAt":"2024-05-21T08:05:12.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"Rename Buffer to GetBuffer.\n\nInterpreterValue::Buffer having the same name as Buffer is considered\ninvalid by GCC.\n\nsed \"s/\\.Buffer/.GetBuffer/g\" -i `find . -name '*.cc'`\n\nPiperOrigin-RevId: 635710161","shortMessageHtmlLink":"Rename Buffer to GetBuffer."}},{"before":"42426722b4e5df4257a7936c426c1c47edb58671","after":"fde16c701672a992c75c9ee19e6cd2da4bc420f7","ref":"refs/heads/exported_pr_635692974","pushedAt":"2024-05-21T08:05:11.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"Rename Buffer to GetBuffer.\n\nInterpreterValue::Buffer having the same name as Buffer is considered\ninvalid by GCC.\n\nsed \"s/\\.Buffer/.GetBuffer/g\" -i `find . -name '*.cc'`\n\nPiperOrigin-RevId: 635710161","shortMessageHtmlLink":"Rename Buffer to GetBuffer."}},{"before":"665bf7fe473c8117e2e496f1237be946a73b158f","after":"19c3823720cb56d110464adb4163f962cfd709eb","ref":"refs/heads/exported_pr_634683280","pushedAt":"2024-05-21T08:03:35.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"MLIR emitters: Vectorize transposes with small element types.\n\nSpecial thanks to github user lingzhi98, who proposed and benchmarked\nthis optimization and implemented it in https://github.com/openxla/xla/pull/12552.\nIt turned out that the Tiling abstraction made this harder than it needs to be.\nThis is an independent reimplementation that removes the Tiling abstraction, but\nreuses lingzhi98's tests and most of their heuristic for enabling vectorization.\n\nThe differences in the heuristic are:\n- respect the shared memory budget\n- enable vectorization if the dimensions are divisible by 2, not just when\n  they are divisible by 64.\n\nPiperOrigin-RevId: 634683280","shortMessageHtmlLink":"MLIR emitters: Vectorize transposes with small element types."}},{"before":null,"after":"68ed7fa0ee8dab80e1257a2d7548cddb22a00f92","ref":"refs/heads/exported_pr_635695083","pushedAt":"2024-05-21T08:01:08.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"Automated Code Change\n\nPiperOrigin-RevId: 635695083","shortMessageHtmlLink":"Automated Code Change"}},{"before":"b6ee9980e023c89e5c1d84913bca3db1876e2b46","after":"3a76740af1dbe10a4df10fee1559616fbae203ff","ref":"refs/heads/exported_pr_634373712","pushedAt":"2024-05-21T07:50:21.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"Automated Code Change\n\nPiperOrigin-RevId: 634373712","shortMessageHtmlLink":"Automated Code Change"}},{"before":null,"after":"a28ed2e4d09cccd8628b7d69fd2353e08e011932","ref":"refs/heads/exported_pr_635442144","pushedAt":"2024-05-21T07:49:27.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"[XLA:FFI] Add helper macro to register enum attributes decoding.\n\nPiperOrigin-RevId: 635442144","shortMessageHtmlLink":"[XLA:FFI] Add helper macro to register enum attributes decoding."}},{"before":"3aca0deccb06f8d7de144a1b4a67e639d43a4d09","after":"f4a5cf7747ffa118359da91b3bf128ad3edf16d7","ref":"refs/heads/exported_pr_634601611","pushedAt":"2024-05-21T07:46:46.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"Add unbounded dynamism test for FftOp.\n\nPiperOrigin-RevId: 634601611","shortMessageHtmlLink":"Add unbounded dynamism test for FftOp."}},{"before":"3abf6c284b6e952d771b197be81b30ee0ad9cdfd","after":"42426722b4e5df4257a7936c426c1c47edb58671","ref":"refs/heads/exported_pr_635692974","pushedAt":"2024-05-21T07:46:43.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"Rename Buffer to GetBuffer.\n\nInterpreterValue::Buffer having the same name as Buffer is considered\ninvalid by GCC.\n\nsed \"s/\\.Buffer/.GetBuffer/g\" -i `find . -name '*.cc'`\n\nPiperOrigin-RevId: 635692974","shortMessageHtmlLink":"Rename Buffer to GetBuffer."}},{"before":null,"after":"876786525b06339940778d894d559b7c1b248fb8","ref":"refs/heads/exported_pr_635704096","pushedAt":"2024-05-21T07:44:29.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"Automated Code Change\n\nFix header includes\n\nPiperOrigin-RevId: 635704096","shortMessageHtmlLink":"Automated Code Change"}},{"before":"59168a073c54faea56dc9adf8c5a4de335e7c360","after":"665bf7fe473c8117e2e496f1237be946a73b158f","ref":"refs/heads/exported_pr_634683280","pushedAt":"2024-05-21T07:43:42.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"},"commit":{"message":"MLIR emitters: Vectorize transposes with small element types.\n\nSpecial thanks to github user lingzhi98, who proposed and benchmarked\nthis optimization and implemented it in https://github.com/openxla/xla/pull/12552.\nIt turned out that the Tiling abstraction made this harder than it needs to be.\nThis is an independent reimplementation that removes the Tiling abstraction, but\nreuses lingzhi98's tests and most of their heuristic for enabling vectorization.\n\nThe differences in the heuristic are:\n- respect the shared memory budget\n- enable vectorization if the dimensions are divisible by 2, not just when\n  they are divisible by 64.\n\nPiperOrigin-RevId: 634683280","shortMessageHtmlLink":"MLIR emitters: Vectorize transposes with small element types."}},{"before":"15a8bacf288892e3f6e1084ddaaa72149dcc25da","after":null,"ref":"refs/heads/exported_pr_634385781","pushedAt":"2024-05-21T07:42:13.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"copybara-service[bot]","name":null,"path":"/apps/copybara-service","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/44061?s=80&v=4"}}],"hasNextPage":true,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAAET5-bQQA","startCursor":null,"endCursor":null}},"title":"Activity · tensorflow/tensorflow"}