BROADCAST CACHE COHERENCE ON PARTIALLY-ORDERED NETWORK

申请公布号:
US2014281237(A1)
申请号:
US201313830967
申请日期:
2013.03.14
申请公布日期:
2014.09.18
申请人:
ORACLE INTERNATIONAL CORPORATION
发明人:
Loewenstein Paul N.;Phillips Stephen E.;Smentek David Richard;Cheung Connie Wai Mun;Leung Serena Wing Yee;Walker Damien;Sivaramakrishnan Ramaswamy
分类号:
G06F12/08
主分类号:
G06F12/08
地址:
Redwood Shores CA US
摘要:
A method for cache coherence, including: broadcasting, by a requester cache (RC) over a partially-ordered request network (RN), a peer-to-peer (P2P) request for a cacheline to a plurality of slave caches; receiving, by the RC and over the RN while the P2P request is pending, a forwarded request for the cacheline from a gateway; receiving, by the RC and after receiving the forwarded request, a plurality of responses to the P2P request from the plurality of slave caches; setting an intra-processor state of the cacheline in the RC, wherein the intra-processor state also specifies an inter-processor state of the cacheline; and issuing, by the RC, a response to the forwarded request after setting the intra-processor state and after the P2P request is complete; and modifying, by the RC, the intra-processor state in response to issuing the response to the forwarded request.
主权项:
1. A method for cache coherence, comprising: broadcasting, by a cache agent of a first requester cache (RC) over a partially-ordered request network of a local processor, a first peer-to-peer (P2P) request for a cacheline to a plurality of cache agents of a plurality of slave caches on the local processor; receiving, by the cache agent of the first RC and over the partially-ordered request network while the first P2P request is pending, a forwarded request associated with the cacheline from a local gateway on the local processor, wherein the local gateway is operatively connected to a foreign gateway on a foreign processor, wherein the cache agent of the first RC delays responding to the forwarded request because the first P2P request is pending; receiving, by the cache agent of the first RC and after receiving the forwarded request, a plurality of responses to the first P2P request from the plurality of cache agents of the plurality of slave caches; setting, by the cache agent of the first RC and after receiving the plurality of responses, an intra-processor state of the cacheline in the first RC, wherein the intra-processor state also specifies an inter-processor state of the cacheline associated with the local processor and the foreign processor; and issuing, by the cache agent of the first RC, a response to the forwarded request after setting the intra-processor state and after the first P2P request is complete; and modifying, by the cache agent of the first RC, the intra-processor state in response to issuing the response to the forwarded request.
专利推荐
移动版 | 电脑版 | 返回顶部