> Quoting Roland Dreier <[EMAIL PROTECTED]>: > Subject: Re: libmlx4 wc flash > > > > memcpy(ctx->bf_page + ctx->bf_offset, ctrl, align(size > > * 16, 64)); > > By the way, if we have an SQ with 32-byte WQEs, and we do blueflame > from a WQE at the end of the buffer, we might end up reading off the > end of the buffer. Not very likely, I guess.
Hmm, is 32-byte SQ wqe shift actually possible? Which parameters give this? > I wonder if memset(,0,) for the remaining bytes might be faster anyway? In some early testing it seemed much slower. Try it :) -- MST _______________________________________________ general mailing list [email protected] http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
