发明名称 Systems and methods for generating reference results using parallel-processing computer system
摘要 A method for debugging an application includes obtaining first and second fusible operation requests; if there is a break point between the first and the second operation request, generating a first set of compute kernels including programs corresponding to the first operation request, but not to the second operation request; and generating a second set of compute kernels including programs corresponding the second operation request, but not to the first operation request; if there is no break point between the first and the second operation request, generating a third set of compute kernels which include programs corresponding to a merge of the first and second operation requests; and arranging for execution of either the first and second, or the third set of compute kernels, further including debugging the first or second set of compute kernels when there is a break point set between the first and second operation requests.
申请公布号 US8972943(B2) 申请公布日期 2015.03.03
申请号 US201213603361 申请日期 2012.09.04
申请人 Google Inc. 发明人 Papakipos Matthew N.;Grant Brian K.;Demetriou Christopher G
分类号 G06F9/44;G06F11/00;G06F9/50 主分类号 G06F9/44
代理机构 Morgan, Lewis & Bockius LLP 代理人 Morgan, Lewis & Bockius LLP
主权项 1. A computer-implemented method, comprising: at a computer having memory and a plurality of processing elements: obtaining a plurality of operation requests from an application, the plurality of operation requests including a first operation request and a second operation request, wherein the first operation request and the second operation request are fusible;in accordance with a determination that there is a break point set between the first operation request and the second operation request, generating a first set of compute kernels, the first set of compute kernels including programs corresponding to the first operation request, but not to the second operation request;generating a second set of compute kernels, the second set of compute kernels including programs corresponding the second operation request, but not to the first operation request; andin accordance with a determination that there is no break point set between the first operation request and the second operation request, generating a third set of compute kernels, the third set of compute kernels including programs corresponding to a merge of the first and second operation requests; andarranging for execution of either the first and the second sets of compute kernels, or the third set of compute kernels, on the plurality of processing elements, further including debugging the first or the second set of compute kernels during the execution, when there is a break point set between the first operation request and the second operation request.
地址 Mountain View CA US