{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":809916233,"defaultBranch":"stable","name":"gap-gem5","ownerLogin":"hal-uw","currentUserCanPush":false,"isFork":true,"isEmpty":false,"createdAt":"2024-06-03T17:41:41.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/52299604?v=4","public":true,"private":false,"isOrgOwned":true},"refInfo":{"name":"","listCacheKey":"v0:1722557501.0","currentOid":""},"activityList":{"items":[{"before":null,"after":"29b1a85459e53492d5c6c2f84eaf474039f08c0e","ref":"refs/heads/gap-iter8-gpufs","pushedAt":"2024-08-02T00:11:41.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"Nagendra-KJ","name":"Nagendra Kumar Jamadagni","path":"/Nagendra-KJ","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/45456076?s=80&v=4"},"commit":{"message":"gpu-compute: Changed debug message to include WG info\n\nChange-Id: I5b44cdb68a975a56b8a7f03b61517e861689adda","shortMessageHtmlLink":"gpu-compute: Changed debug message to include WG info"}},{"before":"de61d0be43cfc09682999c7f90bb765905782334","after":"5c5afdd97279f14ae2bfdd5087fe5819e2ec42a5","ref":"refs/heads/feature-memtime","pushedAt":"2024-07-19T03:25:47.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"mjkpolo","name":"Marco Kurzynski","path":"/mjkpolo","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/70489411?s=80&v=4"},"commit":{"message":"arch-vega: Pass s_memtime through smem pipe\n\nPreviously, the cycle count was written with no latency.\nNow, the cycle count is written when the scalar memory pipeline executes s_memtime, because a s_memtime should be treated like a s_load_dwordx2.\nThrough microbenchmarks, the s_memtime latency has been set to 41 clock cycles.\nMemtimes are marked hasNoAddr so that they can pass through to the VIPERSequencer,\nif other instructions are added that use hasNoAddr their behavior should be added to hitCallback\n\nChange-Id: I39a8c56990fdc0054be00a1effe16f06a3da4836","shortMessageHtmlLink":"arch-vega: Pass s_memtime through smem pipe"}},{"before":"10fd2dc94a56f25d36da60c59dee0d61bb32a219","after":"de61d0be43cfc09682999c7f90bb765905782334","ref":"refs/heads/feature-memtime","pushedAt":"2024-07-14T23:49:51.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"mjkpolo","name":"Marco Kurzynski","path":"/mjkpolo","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/70489411?s=80&v=4"},"commit":{"message":"arch-vega: Pass s_memtime through smem pipe\n\nPreviously, the cycle count was written with no latency.\nNow, the cycle count is written when the scalar memory pipeline executes s_memtime, because a s_memtime should be treated like a s_load_dwordx2.\nThrough microbenchmarks, the s_memtime latency has been set to 41 clock cycles.\n\nChange-Id: I5e251dde28c06fe1c492aea4abf9f34f05784420","shortMessageHtmlLink":"arch-vega: Pass s_memtime through smem pipe"}},{"before":"dad5c7b6f7434ec7668192edffad83bc31a1d5f7","after":"ce8db858677d8e66f46ba76f0637aee67f550c22","ref":"refs/heads/develop","pushedAt":"2024-07-10T14:11:13.000Z","pushType":"push","commitsCount":155,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"cpu: Add cpuIdlePins to indicate the threadContext of CPU is idle (#1285)\n\nIf the threacContext of CPU enters the suspend mode, raise the threadID\r\nof threadContext cpu_idle_pins with the high signal to target. If the\r\nthreadContext of CPU enters the activate mode, lower the threadID of\r\nthread cpu_idle_pins with low signal to target.","shortMessageHtmlLink":"cpu: Add cpuIdlePins to indicate the threadContext of CPU is idle (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2372030370\" data-permission-text=\"Title is private\" data-url=\"https://github.com/gem5/gem5/issues/1285\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/gem5/gem5/pull/1285/hovercard\" href=\"https://github.com/gem5/gem5/pull/1285\">ge…</a>"}},{"before":"fd0e6acc94885aa1ef868363eebd32504c96693e","after":"bb418d41eb6d87c0a0591869097005c16420c6aa","ref":"refs/heads/stable","pushedAt":"2024-07-10T14:11:04.000Z","pushType":"push","commitsCount":623,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"misc: Add scheduler.yaml (#1308)","shortMessageHtmlLink":"misc: Add scheduler.yaml (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2384601681\" data-permission-text=\"Title is private\" data-url=\"https://github.com/gem5/gem5/issues/1308\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/gem5/gem5/pull/1308/hovercard\" href=\"https://github.com/gem5/gem5/pull/1308\">gem5#1308</a>)"}},{"before":"942b71bf3a5a37ba0be515f37ca16715d960e000","after":"f0ca52dbfefb787f185e290ef394b5353cacd5b6","ref":"refs/heads/gap-iter3-coalescer-params","pushedAt":"2024-06-18T01:48:20.000Z","pushType":"push","commitsCount":3,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"configs, gpu-compute: Add configurable L1 scalar latencies\n\nPreviously the scalar cache path used the same latency parameter as the\nvector cache path for memory requests. This commit adds new parameters\nfor the scalar cache path latencies. This commit also modifies the model\nto use the new latency parameter to set the memory request latency in\nthe scalar cache. The new paramters are '--scalar-mem-req-latency' and\n'--scalar-mem-resp-latency' and are set to default values of 50 and 0\nrespectively\n\nChange-Id: I7483f780f2fc0cfbc320ed1fd0c2ee3e2dfc7af2\nReviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/65511\nReviewed-by: Matt Sinclair <mattdsinclair@gmail.com>\nMaintainer: Jason Lowe-Power <power.jg@gmail.com>\nReviewed-by: Jason Lowe-Power <power.jg@gmail.com>\nTested-by: kokoro <noreply+kokoro@google.com>\nMaintainer: Matt Sinclair <mattdsinclair@gmail.com>","shortMessageHtmlLink":"configs, gpu-compute: Add configurable L1 scalar latencies"}},{"before":"942b71bf3a5a37ba0be515f37ca16715d960e000","after":"6ff9cbb525db08ae4f585abb3af6582927cc609d","ref":"refs/heads/gap-iter2-clock-1801MHz","pushedAt":"2024-06-18T01:47:55.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"configs,gpu-compute: Add configurable LDS bus latency\n\nPreviously the LDS bus latency was not configurable in the GPU config\nscripts. As a result, the simulations would use the default value from\nGPU.py. This commit adds support to change this value as an input\noption. The option to use is \"--vrf_lm_bus_latency\".\n\nChange-Id: I8d8852e6d7b9d03ebec1fe8b392968f396dd3526\nReviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/63652\nMaintainer: Matthew Poremba <matthew.poremba@amd.com>\nTested-by: kokoro <noreply+kokoro@google.com>\nReviewed-by: Matt Sinclair <mattdsinclair.wisc@gmail.com>","shortMessageHtmlLink":"configs,gpu-compute: Add configurable LDS bus latency"}},{"before":"942b71bf3a5a37ba0be515f37ca16715d960e000","after":"63aa17fdb1ae4146e7307caae26e27ee34b9e371","ref":"refs/heads/gap-iter1-clock-domain","pushedAt":"2024-06-18T01:04:10.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"configs,gpu-compute: Add configurable LDS bus latency\n\nPreviously the LDS bus latency was not configurable in the GPU config\nscripts. As a result, the simulations would use the default value from\nGPU.py. This commit adds support to change this value as an input\noption. The option to use is \"--vrf_lm_bus_latency\".\n\nChange-Id: I8d8852e6d7b9d03ebec1fe8b392968f396dd3526\nReviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/63652\nMaintainer: Matthew Poremba <matthew.poremba@amd.com>\nTested-by: kokoro <noreply+kokoro@google.com>\nReviewed-by: Matt Sinclair <mattdsinclair.wisc@gmail.com>","shortMessageHtmlLink":"configs,gpu-compute: Add configurable LDS bus latency"}},{"before":"bea84d35a3407ab2be5c21afa54a86d2ad06a533","after":"7255919c9913e009bb5a0ca3a8f08c9b9fbfddc8","ref":"refs/heads/gap-iter5-atomics","pushedAt":"2024-06-17T13:27:21.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"configs: Add configurable GPU L1,L2 num banks and L2 latencies\n\nPreviously, the L1, L2 number of banks and L2 latencies were not\nconfigurable through command line arguments. This commit adds support to\nconfigure them through tthe arguments '--tcp-num-banks' for number of\nbanks in L1, '--tcc-num-banks' for number of banks in L2, and\n'--tcc-tag-access-latency', and '--tcc-data-access-latency'\n\nChange-Id: Ie3b713ead16865fd7120e2d809ebfa56b69bc4a1","shortMessageHtmlLink":"configs: Add configurable GPU L1,L2 num banks and L2 latencies"}},{"before":"355825a621555792b738e262b514c1ab549cf3ba","after":"bea84d35a3407ab2be5c21afa54a86d2ad06a533","ref":"refs/heads/gap-iter5-atomics","pushedAt":"2024-06-12T17:16:32.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"mem-ruby: Add instSeqNum to atomic responses from GPU L2 caches\n\nThis commit adds instSeqNum to the atomic responses in\nGPU_VIPER-TCC.sm. This will be useful when debugging issues related to\nGPU atomic transactions\n\nChange-Id: Ic05c8e1a1cb230abfca2759b51e5603304aadaa3","shortMessageHtmlLink":"mem-ruby: Add instSeqNum to atomic responses from GPU L2 caches"}},{"before":"d834e8bf4e48731d5e51f925ba06c0268822b558","after":"670dac1f83bbcff8180a74cbc3767dd0a11cda91","ref":"refs/heads/gap-iter7-pre-gpufs","pushedAt":"2024-06-12T17:13:40.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"mem-ruby: Add instSeqNum to atomic responses from GPU L2 caches\n\nThis commit adds instSeqNum to the atomic responses in\nGPU_VIPER-TCC.sm. This will be useful when debugging issues related to\nGPU atomic transactions\n\nChange-Id: Ic05c8e1a1cb230abfca2759b51e5603304aadaa3","shortMessageHtmlLink":"mem-ruby: Add instSeqNum to atomic responses from GPU L2 caches"}},{"before":"d834e8bf4e48731d5e51f925ba06c0268822b558","after":"86d28b74191f93afe0d24d4c2ac8303862f219a5","ref":"refs/heads/gap-iter6-mshr-fix","pushedAt":"2024-06-12T17:13:10.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"mem-ruby: Add instSeqNum to atomic responses from GPU L2 caches\n\nThis commit adds instSeqNum to the atomic responses in\nGPU_VIPER-TCC.sm. This will be useful when debugging issues related to\nGPU atomic transactions\n\nChange-Id: Ic05c8e1a1cb230abfca2759b51e5603304aadaa3","shortMessageHtmlLink":"mem-ruby: Add instSeqNum to atomic responses from GPU L2 caches"}},{"before":"485c148b4d9468c4446fd9010318d882aa1d4a69","after":"355825a621555792b738e262b514c1ab549cf3ba","ref":"refs/heads/gap-iter5-atomics","pushedAt":"2024-06-11T03:43:03.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"mem-ruby: Create log entries on atomic no return requests\n\nAugmenting Datablock and WriteMask to support optional arg to\ndistinguish between return and no return. In the case of atomic no\nreturn requests, log entries should not be created when performing the\natomic.\n\nChange-Id: Ic3112834742f4058a7aa155d25ccc4c014b60199a","shortMessageHtmlLink":"mem-ruby: Create log entries on atomic no return requests"}},{"before":null,"after":"10fd2dc94a56f25d36da60c59dee0d61bb32a219","ref":"refs/heads/feature-memtime","pushedAt":"2024-06-08T18:27:03.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"mjkpolo","name":"Marco Kurzynski","path":"/mjkpolo","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/70489411?s=80&v=4"},"commit":{"message":"gpu-compute: memtime attempt\n\nChange-Id: I614b0e993b9a898134697366e0ea846075b433b9","shortMessageHtmlLink":"gpu-compute: memtime attempt"}},{"before":null,"after":"d834e8bf4e48731d5e51f925ba06c0268822b558","ref":"refs/heads/gap-iter7-pre-gpufs","pushedAt":"2024-06-03T17:53:05.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"misc: bump mypy from 1.9.0 to 1.10.0 (#1092)\n\nBumps [mypy](https://github.com/python/mypy) from 1.9.0 to 1.10.0.\r\n\r\nSigned-off-by: dependabot[bot] <support@github.com>\r\nCo-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>","shortMessageHtmlLink":"misc: bump mypy from 1.9.0 to 1.10.0 (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2274241298\" data-permission-text=\"Title is private\" data-url=\"https://github.com/gem5/gem5/issues/1092\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/gem5/gem5/pull/1092/hovercard\" href=\"https://github.com/gem5/gem5/pull/1092\">gem5#1092</a>)"}},{"before":null,"after":"d834e8bf4e48731d5e51f925ba06c0268822b558","ref":"refs/heads/gap-iter6-mshr-fix","pushedAt":"2024-06-03T17:53:01.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"misc: bump mypy from 1.9.0 to 1.10.0 (#1092)\n\nBumps [mypy](https://github.com/python/mypy) from 1.9.0 to 1.10.0.\r\n\r\nSigned-off-by: dependabot[bot] <support@github.com>\r\nCo-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>","shortMessageHtmlLink":"misc: bump mypy from 1.9.0 to 1.10.0 (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2274241298\" data-permission-text=\"Title is private\" data-url=\"https://github.com/gem5/gem5/issues/1092\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/gem5/gem5/pull/1092/hovercard\" href=\"https://github.com/gem5/gem5/pull/1092\">gem5#1092</a>)"}},{"before":null,"after":"485c148b4d9468c4446fd9010318d882aa1d4a69","ref":"refs/heads/gap-iter5-atomics","pushedAt":"2024-06-03T17:52:50.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"arch-vega: Fix vop2Helper scalar support\n\nA previous change added a vop2Helper to remove 100s of lines of common\ncode from VOP2 instructions related to processing SDWA and DPP support.\nThat change inadvertently changed the type of operand source 0 from\nconst to non-const. The vector container operator[] does not allow\nreading a scalar value such as a constant, a dword literal, etc. The\nerror shows up in the form of: assert(!scalar) in operand.hh.\n\nSince the SDWA and DPP cases need to modify the source vector and\nnon-SDWA/DPP cases might require const, we make a non-const copy of the\nconst source 0 vector and place it in a tempoary non-const vector. This\nnon-const vector is passed to the lambda function implementation of the\ninstruction. This prevents needing a const and non-const version of the\nlambda and avoids needing to propagate the template parameters through\nthe various SDWA/DPP helper methods which seems like it will not work\nanyways as they need to modify the vector.\n\nAs a result of this, as more VOP2 instructions are implemented using\nthis helper,they will need to specify the const and non-const template\nparameters of the vector container needed for the instruction.\n\nChange-Id: Ia0b3c550d7de32b830040007a110f4821e3385aa","shortMessageHtmlLink":"arch-vega: Fix vop2Helper scalar support"}},{"before":null,"after":"28dea9afd4e2c58b2f2fc4b5504f0180b0f41b4b","ref":"refs/heads/gap-iter4-L2","pushedAt":"2024-06-03T17:52:47.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"configs: Add configurable GPU L1,L2 num banks and L2 latencies\n\nPreviously, the L1, L2 number of banks and L2 latencies were not\nconfigurable through command line arguments. This commit adds support to\nconfigure them through the arguments '--tcp-num-banks' for number of\nbanks in L1, '--tcc-num-banks' for number of banks in L2, and\n'--tcc-tag-access-latency', and '--tcc-data-access-latency'\n\nChange-Id: Ie3b713ead16865fd7120e2d809ebfa56b69bc4a1","shortMessageHtmlLink":"configs: Add configurable GPU L1,L2 num banks and L2 latencies"}},{"before":null,"after":"942b71bf3a5a37ba0be515f37ca16715d960e000","ref":"refs/heads/gap-iter3-coalescer-params","pushedAt":"2024-06-03T17:52:42.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"gpu-compute: Move GPU caches to GPU clock domain\n\nGPU caches TCP/TCC need to be in the GPU clock domain instead\nof ruby clock domain. This patch moves them to GPU clock domain\nby creating a clock domain for each cache separately.\n\nChange-Id: Iab6382233b75862e21b028186691a35d92d9a0f9\nReviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/61589\nMaintainer: Jason Lowe-Power <power.jg@gmail.com>\nReviewed-by: Matt Sinclair <mattdsinclair@gmail.com>\nReviewed-by: Jason Lowe-Power <power.jg@gmail.com>\nMaintainer: Matt Sinclair <mattdsinclair@gmail.com>\nTested-by: kokoro <noreply+kokoro@google.com>","shortMessageHtmlLink":"gpu-compute: Move GPU caches to GPU clock domain"}},{"before":null,"after":"942b71bf3a5a37ba0be515f37ca16715d960e000","ref":"refs/heads/gap-iter2-clock-1801MHz","pushedAt":"2024-06-03T17:52:39.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"gpu-compute: Move GPU caches to GPU clock domain\n\nGPU caches TCP/TCC need to be in the GPU clock domain instead\nof ruby clock domain. This patch moves them to GPU clock domain\nby creating a clock domain for each cache separately.\n\nChange-Id: Iab6382233b75862e21b028186691a35d92d9a0f9\nReviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/61589\nMaintainer: Jason Lowe-Power <power.jg@gmail.com>\nReviewed-by: Matt Sinclair <mattdsinclair@gmail.com>\nReviewed-by: Jason Lowe-Power <power.jg@gmail.com>\nMaintainer: Matt Sinclair <mattdsinclair@gmail.com>\nTested-by: kokoro <noreply+kokoro@google.com>","shortMessageHtmlLink":"gpu-compute: Move GPU caches to GPU clock domain"}},{"before":null,"after":"942b71bf3a5a37ba0be515f37ca16715d960e000","ref":"refs/heads/gap-iter1-clock-domain","pushedAt":"2024-06-03T17:52:35.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"gpu-compute: Move GPU caches to GPU clock domain\n\nGPU caches TCP/TCC need to be in the GPU clock domain instead\nof ruby clock domain. This patch moves them to GPU clock domain\nby creating a clock domain for each cache separately.\n\nChange-Id: Iab6382233b75862e21b028186691a35d92d9a0f9\nReviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/61589\nMaintainer: Jason Lowe-Power <power.jg@gmail.com>\nReviewed-by: Matt Sinclair <mattdsinclair@gmail.com>\nReviewed-by: Jason Lowe-Power <power.jg@gmail.com>\nMaintainer: Matt Sinclair <mattdsinclair@gmail.com>\nTested-by: kokoro <noreply+kokoro@google.com>","shortMessageHtmlLink":"gpu-compute: Move GPU caches to GPU clock domain"}},{"before":null,"after":"9c1af09605a9a8584bba19bfc2c43d614f62bd14","ref":"refs/heads/gap-iter0-initial","pushedAt":"2024-06-03T17:51:51.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"v-ramadas","name":"Vishnu Ramadas","path":"/v-ramadas","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/22855050?s=80&v=4"},"commit":{"message":"mem-ruby, gpu-compute: update TCP,SQC to pass hit/miss\n\nPreviously, the GPU SQC and TCP Ruby protocols always told the Sequencer\nthat the externalHit field was false.  This impacts the statistics and\nprofiling, because the Sequencer uses this hit/miss information both for\nprofiling and the coalescer's statistics.\n\nTo resolve this, this commit updates the GPU SQC and TCP Ruby protocols\nto pass the appropriate hit/miss information into the Sequencer's\nreadCallback and hitCallback functions.\n\nChange-Id: Ib74af09b66fa8866eee72d3a9ab0e8a8f2196c03\nReviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/60652\nReviewed-by: Matthew Poremba <matthew.poremba@amd.com>\nMaintainer: Matthew Poremba <matthew.poremba@amd.com>\nTested-by: kokoro <noreply+kokoro@google.com>","shortMessageHtmlLink":"mem-ruby, gpu-compute: update TCP,SQC to pass hit/miss"}}],"hasNextPage":false,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"Y3Vyc29yOnYyOpK7MjAyNC0wOC0wMlQwMDoxMTo0MS4wMDAwMDBazwAAAASPqsNG","startCursor":"Y3Vyc29yOnYyOpK7MjAyNC0wOC0wMlQwMDoxMTo0MS4wMDAwMDBazwAAAASPqsNG","endCursor":"Y3Vyc29yOnYyOpK7MjAyNC0wNi0wM1QxNzo1MTo1MS4wMDAwMDBazwAAAARbOqU7"}},"title":"Activity · hal-uw/gap-gem5"}