{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":23496542,"defaultBranch":"main","name":"triton","ownerLogin":"triton-lang","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2014-08-30T17:07:16.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/169110177?v=4","public":true,"private":false,"isOrgOwned":true},"refInfo":{"name":"","listCacheKey":"v0:1726931562.0","currentOid":""},"activityList":{"items":[{"before":"910fc6586205b5b4ff92d6e19c7d339dbc32574e","after":"3ea8b575d0a851675a550a5135733dfbf8ef9aa2","ref":"refs/heads/gh-pages","pushedAt":"2024-09-22T00:09:57.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"ptillet","name":"Philippe Tillet","path":"/ptillet","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/614788?s=80&v=4"},"commit":{"message":"[GH-PAGES] Updated website","shortMessageHtmlLink":"[GH-PAGES] Updated website"}},{"before":"3a647f01c16530e9ec644b034d0b07f09a78e913","after":"576426bccfb9a2c90f2abaa405995738d4a79403","ref":"refs/heads/main","pushedAt":"2024-09-21T16:35:59.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"ThomasRaoux","name":"Thomas Raoux","path":"/ThomasRaoux","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/24322263?s=80&v=4"},"commit":{"message":"[BACKEND] Switch back to use llvm.load for shared memory load (#4776)\n\nWhen we don't have predicates we can use llvm.load. Using inline asm for\r\ni8 types can cause inefficient code generation in llvm due to the\r\ninteraction with DAG legalizer.","shortMessageHtmlLink":"[BACKEND] Switch back to use llvm.load for shared memory load (#4776)"}},{"before":"93c2027f0631878284005bf94261464967452052","after":"3a647f01c16530e9ec644b034d0b07f09a78e913","ref":"refs/heads/main","pushedAt":"2024-09-21T15:47:06.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"ThomasRaoux","name":"Thomas Raoux","path":"/ThomasRaoux","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/24322263?s=80&v=4"},"commit":{"message":"Revert \"Use fast math function for tl.math.log as exp (#4723)\" (#4779)\n\nThis reverts commit 84fe9dadad9633421d020b3fa5dea14367b19ea8.","shortMessageHtmlLink":"Revert \"Use fast math function for tl.math.log as exp (#4723)\" (#4779)"}},{"before":null,"after":"382c778cee361a1d32c436f335e98db63da95dd6","ref":"refs/heads/revert6","pushedAt":"2024-09-21T15:12:42.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"ThomasRaoux","name":"Thomas Raoux","path":"/ThomasRaoux","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/24322263?s=80&v=4"},"commit":{"message":"Revert \"Use fast math function for tl.math.log as exp (#4723)\"\n\nThis reverts commit 84fe9dadad9633421d020b3fa5dea14367b19ea8.","shortMessageHtmlLink":"Revert \"Use fast math function for tl.math.log as exp (#4723)\""}},{"before":"46c6dd635cd2ca97853debb0a03d356b92db0126","after":null,"ref":"refs/heads/keren/proton-cmd","pushedAt":"2024-09-21T03:03:41.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"}},{"before":"20f4b4112b673a4e7121a07e10aa18d5c4be7e3e","after":"93c2027f0631878284005bf94261464967452052","ref":"refs/heads/main","pushedAt":"2024-09-21T03:03:40.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"[PROTON] Fix option conflict with subcommands (#4775)\n\nPreviously, if both the subcommand (e.g., pytest) and proton had the\r\nsame option (e.g., -k), proton would fail due to an option conflict. By\r\nusing argparse.REMAINDER—though its behavior is not well documented in\r\nthe Python documentation—we now allow proton to parse the -k option only\r\nbefore the subcommand.","shortMessageHtmlLink":"[PROTON] Fix option conflict with subcommands (#4775)"}},{"before":"1e06252a8ebad23648edb4d14ad37e4d74683c99","after":"20f4b4112b673a4e7121a07e10aa18d5c4be7e3e","ref":"refs/heads/main","pushedAt":"2024-09-21T02:18:01.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"ThomasRaoux","name":"Thomas Raoux","path":"/ThomasRaoux","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/24322263?s=80&v=4"},"commit":{"message":"Turn off fast log (#4777)\n\nTemporarily turn off log for now to deal with precision problem.","shortMessageHtmlLink":"Turn off fast log (#4777)"}},{"before":null,"after":"46c6dd635cd2ca97853debb0a03d356b92db0126","ref":"refs/heads/keren/proton-cmd","pushedAt":"2024-09-21T01:25:57.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Update","shortMessageHtmlLink":"Update"}},{"before":"35a8a00ef97d12edd14cacf35e6602618ec8547e","after":"1e06252a8ebad23648edb4d14ad37e4d74683c99","ref":"refs/heads/main","pushedAt":"2024-09-21T00:49:10.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"antiagainst","name":"Lei Zhang","path":"/antiagainst","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/487928?s=80&v=4"},"commit":{"message":"[AMD] Enable the loop unroller (#4773)","shortMessageHtmlLink":"[AMD] Enable the loop unroller (#4773)"}},{"before":"0f14676cd2608a143ed46fe88456a6ab1b86e550","after":"35a8a00ef97d12edd14cacf35e6602618ec8547e","ref":"refs/heads/main","pushedAt":"2024-09-21T00:16:25.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"htyu","name":"Hongtao Yu","path":"/htyu","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/15899383?s=80&v=4"},"commit":{"message":"[FRONTEND] Adding unroll loops count to tl.range for scf for (#4662)\n\nThis change exposes the scf For Loop attribute used in PR #4645 the\r\nfrontend. It does this by adding a field to tl.range (the same `as\r\nnum_stages`), this will allow setting loop unrolling factors like so:\r\n\r\n```\r\n@triton.jit\r\ndef _kernel(dst, v):\r\n pid = tl.program_id(axis=0)\r\n for i in tl.range(0, 10, loop_unroll_factor=2):\r\n tl.atomic_add(dst + pid, i + pid)\r\n```\r\n\r\nUnroll factors of less than 2 do nothing, but 2 or more results in the\r\nloop body being replicated that number of times (similar to a clang\r\n`#pragma unroll`).","shortMessageHtmlLink":"[FRONTEND] Adding unroll loops count to tl.range for scf for (#4662)"}},{"before":"4025ee41b7f3186bc883534c508496bd72db7ca7","after":"910fc6586205b5b4ff92d6e19c7d339dbc32574e","ref":"refs/heads/gh-pages","pushedAt":"2024-09-21T00:09:32.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"ptillet","name":"Philippe Tillet","path":"/ptillet","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/614788?s=80&v=4"},"commit":{"message":"[GH-PAGES] Updated website","shortMessageHtmlLink":"[GH-PAGES] Updated website"}},{"before":"556a62a445a2de41625e75acb281dd60defd48e9","after":null,"ref":"refs/heads/h_asm_sass","pushedAt":"2024-09-20T23:44:39.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"apgoucher","name":null,"path":"/apgoucher","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/17485158?s=80&v=4"}},{"before":"d6a11a4636b20eecb285d980441d3912ed960d23","after":"0f14676cd2608a143ed46fe88456a6ab1b86e550","ref":"refs/heads/main","pushedAt":"2024-09-20T23:44:38.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"apgoucher","name":null,"path":"/apgoucher","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/17485158?s=80&v=4"},"commit":{"message":"Allow h.asm[\"sass\"] to work (#4772)\n\nThis is less tedious than having to manually import `get_sass` and call\r\n`get_sass(h.asm[\"cubin\"])`. Moreover, this is done lazily the first time\r\nthat we want the SASS, so there is no overhead.","shortMessageHtmlLink":"Allow h.asm[\"sass\"] to work (#4772)"}},{"before":"b36cf6c99399f048a03d163dddf397a431ce55f5","after":"556a62a445a2de41625e75acb281dd60defd48e9","ref":"refs/heads/h_asm_sass","pushedAt":"2024-09-20T20:57:41.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"apgoucher","name":null,"path":"/apgoucher","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/17485158?s=80&v=4"},"commit":{"message":"Update compiler.py","shortMessageHtmlLink":"Update compiler.py"}},{"before":"42f4adb7146a70e76e6ad337e341dc9678349d95","after":"b36cf6c99399f048a03d163dddf397a431ce55f5","ref":"refs/heads/h_asm_sass","pushedAt":"2024-09-20T20:45:29.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"apgoucher","name":null,"path":"/apgoucher","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/17485158?s=80&v=4"},"commit":{"message":"Update test_disasm.py","shortMessageHtmlLink":"Update test_disasm.py"}},{"before":null,"after":"42f4adb7146a70e76e6ad337e341dc9678349d95","ref":"refs/heads/h_asm_sass","pushedAt":"2024-09-20T20:43:54.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"apgoucher","name":null,"path":"/apgoucher","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/17485158?s=80&v=4"},"commit":{"message":"Update compiler.py","shortMessageHtmlLink":"Update compiler.py"}},{"before":"7527dbe4cfed681ecbfddee0ddf6031a6ac89aed","after":"d2f5de26737e5b37ea7f8590b4dd4fc6b996fbc9","ref":"refs/heads/keren/local-alloc","pushedAt":"2024-09-20T20:26:31.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Update","shortMessageHtmlLink":"Update"}},{"before":"3ae95a858eac26088102075500e3860864432106","after":"d6a11a4636b20eecb285d980441d3912ed960d23","ref":"refs/heads/main","pushedAt":"2024-09-20T17:29:52.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"antiagainst","name":"Lei Zhang","path":"/antiagainst","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/487928?s=80&v=4"},"commit":{"message":"[AMD] Add TritonAMDGPU dialect scaffolding (#4685)\n\nThis PR adds an TritonAMDGPU dialect to host future\r\nAMD specific ops to help with AMD backend CodeGen.\r\n\r\n---------\r\n\r\nCo-authored-by: Ognjen Plavsic \r\nCo-authored-by: Lei Zhang ","shortMessageHtmlLink":"[AMD] Add TritonAMDGPU dialect scaffolding (#4685)"}},{"before":"41a69050967bb5fb94053c7cfc071cb3dcea754a","after":"7527dbe4cfed681ecbfddee0ddf6031a6ac89aed","ref":"refs/heads/keren/local-alloc","pushedAt":"2024-09-20T15:38:15.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Update","shortMessageHtmlLink":"Update"}},{"before":"b22b0f36aeaa1767c642fea0395fb18e63693dea","after":"4025ee41b7f3186bc883534c508496bd72db7ca7","ref":"refs/heads/gh-pages","pushedAt":"2024-09-20T00:09:27.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"ptillet","name":"Philippe Tillet","path":"/ptillet","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/614788?s=80&v=4"},"commit":{"message":"[GH-PAGES] Updated website","shortMessageHtmlLink":"[GH-PAGES] Updated website"}},{"before":null,"after":"b435f8c838b720922cbdb33cd837915cb90def92","ref":"refs/heads/rand_precision","pushedAt":"2024-09-19T22:39:20.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"ThomasRaoux","name":"Thomas Raoux","path":"/ThomasRaoux","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/24322263?s=80&v=4"},"commit":{"message":"Use higher precision for Box-Muller transform","shortMessageHtmlLink":"Use higher precision for Box-Muller transform"}},{"before":"54b3f67771f4175ff6d64d23e97a4ef17c231c25","after":"41a69050967bb5fb94053c7cfc071cb3dcea754a","ref":"refs/heads/keren/local-alloc","pushedAt":"2024-09-19T19:07:37.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Update","shortMessageHtmlLink":"Update"}},{"before":"ad0cdfbb0dac92bdd019817780675e70c8c261e8","after":"3ae95a858eac26088102075500e3860864432106","ref":"refs/heads/main","pushedAt":"2024-09-19T18:23:39.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"antiagainst","name":"Lei Zhang","path":"/antiagainst","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/487928?s=80&v=4"},"commit":{"message":"[AMD][CanonicalizePtr] Add a series of fixes for the new pipeliner (#4743)\n\nThis PR is fixing some issues with the `CanonicalizePointer` pass and\r\nthe new pipeliner:\r\n- Don't traverse twice the same nodes\r\n- Don't assume the operation to delete are in the correct order, but\r\n force dropping the reference of the ops before we delete them\r\n- Add support for select operation (+test), which is used when dealing\r\nwith multiple buffer (this part has been coauthored with @sjw36)","shortMessageHtmlLink":"[AMD][CanonicalizePtr] Add a series of fixes for the new pipeliner (#…"}},{"before":"fad49b2ab90f3db9b1ab0967d4efd8bdc07d5fd3","after":"ad0cdfbb0dac92bdd019817780675e70c8c261e8","ref":"refs/heads/main","pushedAt":"2024-09-19T17:34:59.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"antiagainst","name":"Lei Zhang","path":"/antiagainst","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/487928?s=80&v=4"},"commit":{"message":"Attach the datalayout before optimizing the LLVM module (#4761)\n\nWe should always set the `datalayout` when we run the optimization\r\npipeline on the LLVM IR module.","shortMessageHtmlLink":"Attach the datalayout before optimizing the LLVM module (#4761)"}},{"before":"98ab9c8c66e0c1186c96afe7116be9e0f2b08e68","after":"54b3f67771f4175ff6d64d23e97a4ef17c231c25","ref":"refs/heads/keren/local-alloc","pushedAt":"2024-09-19T17:34:46.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Update","shortMessageHtmlLink":"Update"}},{"before":"f483507483792d55540d4af0e3e3e1d77180127d","after":null,"ref":"refs/heads/llvm-abi-breaking-checks-issue","pushedAt":"2024-09-19T10:12:28.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"karupayun","name":"Pablo Zimmermann","path":"/karupayun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/8610429?s=80&v=4"}},{"before":null,"after":"f483507483792d55540d4af0e3e3e1d77180127d","ref":"refs/heads/llvm-abi-breaking-checks-issue","pushedAt":"2024-09-19T09:14:40.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"karupayun","name":"Pablo Zimmermann","path":"/karupayun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/8610429?s=80&v=4"},"commit":{"message":"Fix llvm abi breaking checks issue","shortMessageHtmlLink":"Fix llvm abi breaking checks issue"}},{"before":"b4550e4634b028459933dfbc71b95407157ead93","after":"b0a9ee9bd50ab31cb94db6ac598197f86932d37d","ref":"refs/heads/llvm-head","pushedAt":"2024-09-19T08:45:37.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"karupayun","name":"Pablo Zimmermann","path":"/karupayun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/8610429?s=80&v=4"},"commit":{"message":"Testing clang-12 to solve the LLVM_ABI_BREAKING_CHECKS issue","shortMessageHtmlLink":"Testing clang-12 to solve the LLVM_ABI_BREAKING_CHECKS issue"}},{"before":"f29a7255193e15af22e5fe00e82f9052dccdb744","after":"b22b0f36aeaa1767c642fea0395fb18e63693dea","ref":"refs/heads/gh-pages","pushedAt":"2024-09-19T00:09:40.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"ptillet","name":"Philippe Tillet","path":"/ptillet","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/614788?s=80&v=4"},"commit":{"message":"[GH-PAGES] Updated website","shortMessageHtmlLink":"[GH-PAGES] Updated website"}},{"before":"5083988ce3984470e8a15cc878150f0eb63bcde3","after":"fad49b2ab90f3db9b1ab0967d4efd8bdc07d5fd3","ref":"refs/heads/main","pushedAt":"2024-09-18T23:36:56.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"antiagainst","name":"Lei Zhang","path":"/antiagainst","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/487928?s=80&v=4"},"commit":{"message":"[Pipeliner] Fixed the epilogue predicate (#4754)\n\nThis mirrors upstream patch\r\nhttps://github.com/llvm/llvm-project/pull/108964","shortMessageHtmlLink":"[Pipeliner] Fixed the epilogue predicate (#4754)"}}],"hasNextPage":true,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"Y3Vyc29yOnYyOpK7MjAyNC0wOS0yMlQwMDowOTo1Ny4wMDAwMDBazwAAAAS874eQ","startCursor":"Y3Vyc29yOnYyOpK7MjAyNC0wOS0yMlQwMDowOTo1Ny4wMDAwMDBazwAAAAS874eQ","endCursor":"Y3Vyc29yOnYyOpK7MjAyNC0wOS0xOFQyMzozNjo1Ni4wMDAwMDBazwAAAAS6QL-Y"}},"title":"Activity · triton-lang/triton"}